{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "01000000",
   "metadata": {},
   "source": [
    "# Statystyka opisowa i wizualizacja rozkładów\n",
    "\n",
    "Statystyka opisowa ma prosty cel: **uporządkować dane i opisać je tak, aby można było je sensownie interpretować**.\n",
    "\n",
    "W praktyce zwykle zaczynamy od **wykresu** albo jakiejś innej formy wizualizacji, a dopiero potem liczymy (np. średnią, medianę lub odchylenie standardowe). Wykres szybko ujawnia **kształt rozkładu** i **potencjalne problemy** (np. obserwacje odstające).\n",
    "\n",
    "W tym notatniku skupimy się na opisie rozkładu zmiennej ilościowej: **centrum**, **rozproszenie**, **kształt** oraz **obserwacje odstające**. To fundament, zanim przejdziemy do wnioskowania statystycznego.\n",
    "\n",
    "Na wykresach konsekwentnie opisujemy osie i jednostki — to drobny nawyk, który bardzo ułatwia interpretację."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000001",
   "metadata": {},
   "source": [
    "## Cele\n",
    "\n",
    "Po tym wykładzie:\n",
    "\n",
    "- Umiesz zaimplementować podstawowe sposoby prezentacji rozkładu (tabela częstości, histogram, wygładzenie, wykres pudełkowy).\n",
    "- Umiesz opisać rozkład: tendencja centralna, rozproszenie, kształt, obserwacje odstające.\n",
    "- Umiesz policzyć miary tendencji centralnej (np. średnia, mediana, średnia obcięta).\n",
    "- Umiesz policzyć miary zmienności (np. wariancja, odchylenie standardowe, IQR, MAD).\n",
    "- Umiesz liczyć i interpretować percentyle / kwartyle / decyle.\n",
    "- Rozumiesz, jak proste transformacje liniowe wpływają na średnią i odchylenie standardowe.\n",
    "- Rozróżniasz podstawowe skale pomiarowe (nominalną, porządkową, przedziałową, ilorazową) i dobierasz do nich sensowne podsumowania oraz wykresy.\n",
    "- Rozumiesz różnicę między populacją i próbą oraz między statystyką opisową a wnioskowaniem statystycznym."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000045",
   "metadata": {},
   "source": [
    "## Podstawowe pojęcia: populacja, próba i losowość\n",
    "\n",
    "W statystyce prawie zawsze interesuje nas pewna **populacja** (np. wszyscy studenci pierwszego roku), ale w praktyce obserwujemy tylko **próbę** (np. 60 studentów, którzy wypełnili ankietę).\n",
    "\n",
    "- Populacja to zbiór wszystkich wyników/obiektów, o których chcemy coś powiedzieć.\n",
    "- Próba to część populacji, którą rzeczywiście mierzymy.\n",
    "\n",
    "Z próby liczymy **statystyki** (np. średnią z próby $\\bar{x}$), a populację opisują **parametry** (np. średnia $\\mu$). Parametry zwykle są nieznane, ale usiłujemy je estymować ze statystyk z próby.\n",
    "\n",
    "Z reguły parametry populacji oznaczane są literami greckimi, takimi jak $\\sigma$, $\\mu$ lub $\\theta$, a statystyki z próby oznaczane są łacińskimi literami np. $s$ czy $\\bar{x}$\n",
    "\n",
    "Dwa słowa, które łatwo pomylić:\n",
    "\n",
    "- *Losowy dobór próby* dotyczy tego, **kogo** badamy (reprezentatywność).\n",
    "- *Losowy przydział do warunków* dotyczy tego, **co** komu robimy w eksperymencie (wnioskowanie przyczynowe).\n",
    "\n",
    "W tym notatniku będziemy głównie porządkować i opisywać dane, ale te pojęcia wrócą, gdy przejdziemy do wnioskowania."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000046",
   "metadata": {},
   "source": [
    "## Statystyka opisowa a wnioskowanie statystyczne\n",
    "\n",
    "- **Statystyka opisowa** porządkuje dane: wykresy, tabele, miary tendencji centralnej i rozproszenia.\n",
    "- **Wnioskowanie statystyczne** odpowiada na pytanie: co wyniki z próby mówią o populacji i jak duża jest niepewność tej odpowiedzi? Tutaj pojawiają się m.in. przedziały ufności i testy."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000047",
   "metadata": {},
   "source": [
    "## Skale pomiarowe i typy danych\n",
    "\n",
    "To, co wolno zrobić z danymi, zależy od tego, co one znaczą. Szczególnie ważna jest **skala pomiarowa**.\n",
    "\n",
    "Praktyczny podział:\n",
    "\n",
    "- **Dane kategorialne (zmienne nominalne, jakościowe)**: wartości to etykiety, np. typ bodźca (twarz / dom), poprawność odpowiedzi (poprawna / niepoprawna), grupa eksperymentalna (terapia X i grupa kontrolna). Duża część danych demograficznych (płeć, kierunek studiów, itp.) też jest zmiennymi kategorialnymi. \n",
    "- **Dane ilościowe**: wartości to liczby z jednostką, np. czas reakcji [ms], czas fiksacji [ms], wynik testu [pkt].\n",
    "\n",
    "### Klasyczny podział skal pomiarowych:\n",
    "\n",
    "1) **Skala nominalna**\n",
    "\n",
    "- Kategorie bez naturalnego porządku (np. typ bodźca, płeć, specjalizacja lekarska).\n",
    "- Sensowne są zliczenia, odsetki i moda (najczęstsza wartość, inaczej: dominanta); typowy wykres to słupki (częstości lub odsetki).\n",
    "- Średnia z kategorii nie ma interpretacji (nawet jeśli w zbiorze danych mamy zakodowną np. płeć jako liczbę, to nie wyciągajmy z niej średniej!).\n",
    "\n",
    "2) **Skala porządkowa**\n",
    "\n",
    "- Kategorie mają porządek, ale odstępy między nimi nie muszą być równe (np. ocena pewności 1–7).\n",
    "- Sensowne są mediany, kwartyle/percentyle i rankingi.\n",
    "- Używanie średniej jest możlie wyłącznie przy dodatkowych założeniach (traktujemy kategorie jak równomiernie rozstawione punkty na osi liczbowej).\n",
    "\n",
    "3) **Skala przedziałowa**\n",
    "\n",
    "- Równe odstępy, brak absolutnego zera (np. temperatura w °C; także niektóre skale standaryzowane w testach).\n",
    "- Różnice mają sens (o 10 jednostek więcej), ilorazy już nie (na przykład dla temperatury 20 stopni nie jest „dwa razy” 10 stopni!).\n",
    "- Średnia i odchylenie standardowe są interpretowalne; typowe wykresy to histogram i krzywa gęstości.\n",
    "\n",
    "4) **Skala ilorazowa**\n",
    "\n",
    "- Jak przedziałowa, ale z naturalnym zerem (np. czas reakcji, czas trwania, liczba poprawnych odpowiedzi).\n",
    "- Różnice i ilorazy mają sens; możemy stosować standardowe miary i wykresy dla danych ilościowych.\n",
    "\n",
    "W dalszej części notatnika będziemy pracować głównie na zmiennych ilościowych (czas reakcji), dlatego pojawią się histogramy, miary tendencji centralnej i miary rozproszenia."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000048",
   "metadata": {},
   "source": [
    "## Komputery i odtwarzalność\n",
    "\n",
    "W praktyce większość obliczeń wykonuje się w programie statystycznym. To zmniejsza ryzyko błędów rachunkowych, ale nie zwalnia z myślenia: trzeba umieć dobrać miarę do skali pomiarowej i sprawdzić, czy wynik ma sens."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000003",
   "metadata": {},
   "source": [
    "## Dane przykładowe: czasy reakcji\n",
    "\n",
    "Zaczniemy od klasycznego przykładu z psychologii poznawczej: **zadania Sternberga** (przeszukiwanie pamięci krótkotrwałej).\n",
    "\n",
    "W każdej próbie badany:\n",
    "\n",
    "1. zapamiętuje krótki zestaw elementów (np. cyfr),\n",
    "2. widzi bodziec testowy,\n",
    "3. odpowiada, czy bodziec testowy był w zestawie (**odpowiedź pozytywna**) czy nie (**odpowiedź negatywna**).\n",
    "\n",
    "Jedna z prostych, opisowych hipotez (na razie bez testów) brzmi: **im większy zestaw do przeszukania, tym dłuższy czas reakcji**.\n",
    "\n",
    "Dla celów dydaktycznych stworzymy mały, **syntetyczny** zbiór danych o podobnej strukturze. To nie są rzeczywiste dane, ale stanowią dobrą ilustrację. \n",
    "\n",
    "Ustawiamy też stałe ziarno generatora liczb losowych (`SEED`), aby wyniki były w pełni odtwarzalne.\n",
    "\n",
    "Zmienne w zbiorze danych:\n",
    "\n",
    "- `set_size` — liczba elementów w zestawie (1, 3, 5),\n",
    "- `response` — odpowiedź „pozytywna” lub „negatywna”,\n",
    "- `reaction_time_ms` — czas reakcji w milisekundach."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "01000004",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from scipy import stats\n",
    "\n",
    "SEED = 20250116\n",
    "\n",
    "sns.set_theme(style='whitegrid')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "01000005",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>set_size</th>\n",
       "      <th>response</th>\n",
       "      <th>reaction_time_ms</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>464.181809</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>467.250173</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>435.774221</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>502.307484</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>384.992766</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>433.714471</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>1</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>478.412992</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>468.062968</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>461.661262</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>1</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>472.196529</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   set_size   response  reaction_time_ms\n",
       "0         1  pozytywna        464.181809\n",
       "1         1  pozytywna        467.250173\n",
       "2         1  pozytywna        435.774221\n",
       "3         1  pozytywna        502.307484\n",
       "4         1  pozytywna        384.992766\n",
       "5         1  pozytywna        433.714471\n",
       "6         1  pozytywna        478.412992\n",
       "7         1  pozytywna        468.062968\n",
       "8         1  pozytywna        461.661262\n",
       "9         1  pozytywna        472.196529"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rng = np.random.default_rng(SEED)\n",
    "\n",
    "set_sizes = [1, 3, 5]\n",
    "response_types = ['pozytywna', 'negatywna']\n",
    "\n",
    "trials_per_condition = 25\n",
    "\n",
    "rows = []\n",
    "\n",
    "for set_size in set_sizes:\n",
    "    for response in response_types:\n",
    "        if response == 'pozytywna':\n",
    "            mean_ms = 420 + 35 * set_size\n",
    "        else:\n",
    "            # trochę dłuższy czas dla odpowiedzi negatywnej\n",
    "            mean_ms = 450 + 35 * set_size \n",
    "\n",
    "        sd_ms = 45\n",
    "\n",
    "        reaction_times = rng.normal(\n",
    "            loc=mean_ms,\n",
    "            scale=sd_ms,\n",
    "            size=trials_per_condition,\n",
    "        )\n",
    "        reaction_times = np.clip(reaction_times, a_min=200, a_max=None)\n",
    "\n",
    "        for rt in reaction_times:\n",
    "            rows.append(\n",
    "                {\n",
    "                    'set_size': int(set_size),\n",
    "                    'response': response,\n",
    "                    'reaction_time_ms': float(rt),\n",
    "                }\n",
    "            )\n",
    "\n",
    "df = pd.DataFrame(rows)\n",
    "df.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "01000006",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>reaction_time_ms</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>150.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>540.077187</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>68.842267</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>384.992766</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>489.291144</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>526.826779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>585.478804</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>723.659793</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       reaction_time_ms\n",
       "count        150.000000\n",
       "mean         540.077187\n",
       "std           68.842267\n",
       "min          384.992766\n",
       "25%          489.291144\n",
       "50%          526.826779\n",
       "75%          585.478804\n",
       "max          723.659793"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[['reaction_time_ms']].describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000007",
   "metadata": {},
   "source": [
    "## Organizacja danych: tabela częstości i proste wykresy\n",
    "\n",
    "Surowe dane (lista liczb) zwykle trudno interpretować. Pierwszy krok to ich uporządkowanie: zliczamy, jak często pojawiają się poszczególne wartości (tabela częstości) albo przedziały wartości.\n",
    "\n",
    "Ponieważ czasy reakcji są mierzone w milisekundach i mają część ułamkową, na potrzeby tabeli częstości zaokrąglimy je do **10 ms**, czyli do **setnych części sekundy (0.01 s)**. Dzięki temu wiele obserwacji trafi do tych samych kategorii.\n",
    "\n",
    "Uwaga: takie zaokrąglenie jest tylko narzędziem opisu i wizualizacji — nie zmienia sensu danych, o ile nie jest zbyt agresywne.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "01000008",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>reaction_time_cs</th>\n",
       "      <th>frequency</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>41.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>43.0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>44.0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>45.0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>46.0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>47.0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>48.0</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>49.0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>50.0</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>51.0</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>52.0</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>53.0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>54.0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>55.0</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    reaction_time_cs  frequency\n",
       "0               38.0          1\n",
       "1               41.0          2\n",
       "2               43.0          3\n",
       "3               44.0          5\n",
       "4               45.0          6\n",
       "5               46.0          4\n",
       "6               47.0          6\n",
       "7               48.0          7\n",
       "8               49.0          6\n",
       "9               50.0         12\n",
       "10              51.0          8\n",
       "11              52.0         13\n",
       "12              53.0          5\n",
       "13              54.0          5\n",
       "14              55.0         10"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['reaction_time_cs'] = (df['reaction_time_ms'] / 10).round()  # 1 cs = 10 ms\n",
    "freq = df['reaction_time_cs'].value_counts().sort_index()\n",
    "freq_df = freq.rename_axis('reaction_time_cs').reset_index(name='frequency')\n",
    "freq_df.head(15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "01000009",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10, 4))\n",
    "plt.plot(\n",
    "    freq_df['reaction_time_cs'],\n",
    "    freq_df['frequency'],\n",
    "    marker='o',\n",
    "    linewidth=2,\n",
    ")\n",
    "plt.title('Wielokąt częstości (z tabeli częstości)')\n",
    "plt.xlabel('Czas reakcji [0.01 s]')\n",
    "plt.ylabel('Częstość')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000010",
   "metadata": {},
   "source": [
    "### Zależność między zmiennymi: wykres punktowy i średnie\n",
    "\n",
    "Opis rozkładu jednej zmiennej to początek. Często chcemy też zobaczyć zależność między zmiennymi: czy średni czas reakcji rośnie, gdy rośnie `set_size`?\n",
    "\n",
    "Najpierw pokażemy wszystkie obserwacje (wykres punktowy), a potem podsumujemy dane średnią i miarą zmienności w każdej grupie.\n",
    "\n",
    "Uwaga: na wykresie ze średnimi pokażemy **błąd standardowy średniej** (SEM). To nie jest \"rozrzut danych\" (tym jest odchylenie standardowe), tylko niepewność oszacowania średniej — maleje, gdy rośnie liczebność próby. Będziemy o tym mówić w dalszej części kursu!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "01000011",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(8, 4))\n",
    "sns.scatterplot(\n",
    "    data=df,\n",
    "    x='set_size',\n",
    "    y='reaction_time_ms',\n",
    "    hue='response',\n",
    "    alpha=0.6,\n",
    "    \n",
    ")\n",
    "plt.title('Czas reakcji a wielkość zestawu')\n",
    "plt.xlabel('Wielkość zestawu')\n",
    "plt.ylabel('Czas reakcji [ms]')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "01000012",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>set_size</th>\n",
       "      <th>response</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>n</th>\n",
       "      <th>sem</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>negatywna</td>\n",
       "      <td>497.988482</td>\n",
       "      <td>36.156116</td>\n",
       "      <td>25</td>\n",
       "      <td>7.231223</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>462.511320</td>\n",
       "      <td>40.804257</td>\n",
       "      <td>25</td>\n",
       "      <td>8.160851</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>negatywna</td>\n",
       "      <td>551.866683</td>\n",
       "      <td>52.523925</td>\n",
       "      <td>25</td>\n",
       "      <td>10.504785</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>519.294686</td>\n",
       "      <td>33.033775</td>\n",
       "      <td>25</td>\n",
       "      <td>6.606755</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>negatywna</td>\n",
       "      <td>619.311082</td>\n",
       "      <td>45.288042</td>\n",
       "      <td>25</td>\n",
       "      <td>9.057608</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5</td>\n",
       "      <td>pozytywna</td>\n",
       "      <td>589.490867</td>\n",
       "      <td>52.530791</td>\n",
       "      <td>25</td>\n",
       "      <td>10.506158</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   set_size   response        mean        std   n        sem\n",
       "0         1  negatywna  497.988482  36.156116  25   7.231223\n",
       "1         1  pozytywna  462.511320  40.804257  25   8.160851\n",
       "2         3  negatywna  551.866683  52.523925  25  10.504785\n",
       "3         3  pozytywna  519.294686  33.033775  25   6.606755\n",
       "4         5  negatywna  619.311082  45.288042  25   9.057608\n",
       "5         5  pozytywna  589.490867  52.530791  25  10.506158"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grouped = df.groupby(['set_size', 'response'])['reaction_time_ms']\n",
    "summary = grouped.agg(mean='mean', std='std', n='count').reset_index()\n",
    "summary['sem'] = summary['std'] / np.sqrt(summary['n'])\n",
    "summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "01000013",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(8, 4))\n",
    "for response in response_types:\n",
    "    subset = summary[summary['response'] == response]\n",
    "    plt.errorbar(\n",
    "        subset['set_size'],\n",
    "        subset['mean'],\n",
    "        yerr=subset['sem'],\n",
    "        marker='o',\n",
    "        capsize=4,\n",
    "        linewidth=2,\n",
    "        label=response,\n",
    "    )\n",
    "\n",
    "plt.title('Średni czas reakcji (z błędem standardowym średniej)')\n",
    "plt.xlabel('Wielkość zestawu')\n",
    "plt.ylabel('Średni czas reakcji [ms]')\n",
    "plt.legend(title='Odpowiedź')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "0fe595cf-37f7-44d5-91d3-6cf3ba6cdf13",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.lineplot(data=df, x='set_size', y='reaction_time_ms',\n",
    "             hue='response', marker='o',\n",
    "             errorbar='se')  # automatycznie SEM\n",
    "plt.title('Średni czas reakcji (SEM)')\n",
    "plt.xlabel('Wielkość zestawu')\n",
    "plt.ylabel('Średni czas reakcji [ms]')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "681b977e",
   "metadata": {},
   "source": [
    "### Co na razie widzimy (opis, bez wnioskowania)\n",
    "\n",
    "Na wykresach możemy opisać kilka rzeczy:\n",
    "\n",
    "- W każdej grupie czasy reakcji są rozproszone: pojedyncze obserwacje różnią się od siebie nawet przy tej samej wielkości zestawu.\n",
    "- Średni czas reakcji rośnie wraz z wielkością zestawu (`set_size`), co jest zgodne z intuicją „więcej do przeszukania = wolniejsza odpowiedź”.\n",
    "- Różnice między odpowiedzią pozytywną i negatywną mogą się pojawiać, ale na tym etapie **nie rozstrzygamy**, czy są „prawdziwe w populacji” — do tego potrzebujemy wnioskowania statystycznego.\n",
    "\n",
    "Ważne: słupki błędu na wykresie średnich pokazują **błąd standardowy średniej** (SEM), czyli miarę niepewności oszacowania średniej, a nie miarę rozproszenia danych."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000014",
   "metadata": {},
   "source": [
    "## Histogramy\n",
    "\n",
    "Histogram pokazuje, jak dane rozkładają się wzdłuż osi liczbowej. Oś X dzielimy na **przedziały** o stałej szerokości, a następnie zliczamy, ile obserwacji wpada do każdego przedziału.\n",
    "\n",
    "Histogram pomaga odpowiedzieć na pytania: czy rozkład jest symetryczny, czy ma długi ogon, czy jest jedno- lub wielomodalny (ma jeden lub kilka „szczytów”).\n",
    "\n",
    "Praktyczna uwaga: wygląd histogramu zależy od doboru przedziałów (ich szerokości i położenia granic). Dlatego warto sprawdzić kilka sensownych ustawień.\n",
    "\n",
    "Na osi Y możemy pokazać liczbę obserwacji (częstość) albo gęstość (tak, aby pole pod słupkami było równe 1). Poniżej użyjemy gęstości.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "01000015",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10, 4))\n",
    "sns.histplot(\n",
    "    data=df,\n",
    "    x='reaction_time_ms',\n",
    "    bins=14,\n",
    "    stat='density',\n",
    "    color='lightgrey',\n",
    "    edgecolor='white',\n",
    ")\n",
    "\n",
    "plt.title('Histogram czasów reakcji (14 koszyków)')\n",
    "plt.xlabel('Czas reakcji [ms]')\n",
    "plt.ylabel('Gęstość')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "01000016",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "reaction_times = df['reaction_time_ms']\n",
    "\n",
    "bin_width = 30\n",
    "start_a = 300\n",
    "start_b = 315\n",
    "\n",
    "bins_a = np.arange(start_a, reaction_times.max() + bin_width, bin_width)\n",
    "bins_b = np.arange(start_b, reaction_times.max() + bin_width, bin_width)\n",
    "\n",
    "plt.figure(figsize=(12, 4))\n",
    "\n",
    "plt.subplot(1, 2, 1)\n",
    "plt.hist(\n",
    "    reaction_times,\n",
    "    bins=bins_a,\n",
    "    density=True,\n",
    "    color='lightgrey',\n",
    "    edgecolor='white',\n",
    ")\n",
    "plt.title('Histogram: początek=300, szerokość=30')\n",
    "plt.xlabel('Czas reakcji [ms]')\n",
    "plt.ylabel('Gęstość')\n",
    "\n",
    "plt.subplot(1, 2, 2)\n",
    "plt.hist(\n",
    "    reaction_times,\n",
    "    bins=bins_b,\n",
    "    density=True,\n",
    "    color='lightgrey',\n",
    "    edgecolor='white',\n",
    ")\n",
    "plt.title('Histogram: początek=315, szerokość=30')\n",
    "plt.xlabel('Czas reakcji [ms]')\n",
    "plt.ylabel('Gęstość')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a724e035",
   "metadata": {},
   "source": [
    "## Interaktywny histogram: szerokość i początek przedziałów\n",
    "\n",
    "Poniższy widget pozwala zmieniać **szerokość przedziałów** oraz ich **punkt startowy** i od razu obserwować, jak wpływa to na wygląd histogramu.\n",
    "\n",
    "Cel ćwiczenia jest prosty: zobaczyć, że histogram jest użytecznym opisem rozkładu, ale jego szczegóły zależą od sensownego doboru parametrów."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "0173729a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b53e7a933e18445ca8155f60d80bc92e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntSlider(value=30, continuous_update=False, description='Szerokość [ms]:', max=80, min=10, ste…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b928116121444d56bb83578f9dcc88b1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import os\n",
    "if os.environ.get('JPY_SESSION_NAME') is None:\n",
    "    print('Ta sekcja korzysta z widgetów Jupyter i wymaga uruchomienia w notatniku. W trybie wsadowym (np. nbconvert) jest pomijana.')\n",
    "else:\n",
    "    import ipywidgets as widgets\n",
    "    from IPython.display import display\n",
    "\n",
    "    bin_width_ms_slider = widgets.IntSlider(\n",
    "        value=30,\n",
    "        min=10,\n",
    "        max=80,\n",
    "        step=5,\n",
    "        description='Szerokość [ms]:',\n",
    "        continuous_update=False,\n",
    "    )\n",
    "\n",
    "    start_ms_slider = widgets.IntSlider(\n",
    "        value=300,\n",
    "        min=300,\n",
    "        max=520,\n",
    "        step=5,\n",
    "        description='Początek [ms]:',\n",
    "        continuous_update=False,\n",
    "    )\n",
    "\n",
    "    y_axis_scale_toggle = widgets.ToggleButtons(\n",
    "        options=['Gęstość', 'Częstość'],\n",
    "        value='Gęstość',\n",
    "        description='Oś Y:',\n",
    "    )\n",
    "\n",
    "    histogram_out = widgets.Output()\n",
    "\n",
    "    def draw_histogram(_=None):\n",
    "        bin_width_ms = bin_width_ms_slider.value\n",
    "        start_ms = start_ms_slider.value\n",
    "        y_scale = y_axis_scale_toggle.value\n",
    "\n",
    "        bins = np.arange(start_ms, reaction_times.max() + bin_width_ms, bin_width_ms)\n",
    "\n",
    "        with histogram_out:\n",
    "            histogram_out.clear_output(wait=True)\n",
    "\n",
    "            fig, ax = plt.subplots(figsize=(10, 4))\n",
    "\n",
    "            if y_scale == 'Gęstość':\n",
    "                ax.hist(\n",
    "                    reaction_times,\n",
    "                    bins=bins,\n",
    "                    density=True,\n",
    "                    color='lightgrey',\n",
    "                    edgecolor='white',\n",
    "                )\n",
    "                ax.set_ylabel('Gęstość')\n",
    "            else:\n",
    "                ax.hist(\n",
    "                    reaction_times,\n",
    "                    bins=bins,\n",
    "                    density=False,\n",
    "                    color='lightgrey',\n",
    "                    edgecolor='white',\n",
    "                )\n",
    "                ax.set_ylabel('Częstość')\n",
    "\n",
    "            ax.set_title('Histogram czasów reakcji: wpływ wyboru przedziałów')\n",
    "            ax.set_xlabel('Czas reakcji [ms]')\n",
    "            fig.tight_layout()\n",
    "            plt.show()\n",
    "\n",
    "    for control in [bin_width_ms_slider, start_ms_slider, y_axis_scale_toggle]:\n",
    "        control.observe(draw_histogram, names='value')\n",
    "\n",
    "    controls = widgets.HBox([bin_width_ms_slider, start_ms_slider, y_axis_scale_toggle])\n",
    "    display(controls, histogram_out)\n",
    "\n",
    "    draw_histogram()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000017",
   "metadata": {},
   "source": [
    "## Wygładzanie rozkładu: krzywa normalna i estymacja jądrowa gęstości (KDE)\n",
    "\n",
    "Histogram jest wykresem „schodkowym” i to, jak wygląda, zależy od doboru przedziałów. Innym sposobem jest narysowanie krzywej, która **wygładza** rozkład.\n",
    "\n",
    "Dwie popularne strategie:\n",
    "\n",
    "1. Dopasować krzywą rozkładu normalnego o parametrach oszacowanych z danych (podejście parametryczne).\n",
    "2. Zastosować **estymację jądrową gęstości** (KDE) — wygładzanie bez przyjmowania konkretnej rodziny rozkładów.\n",
    "\n",
    "To są narzędzia **opisowe**: nie „dowodzą normalności” i nie zastępują interpretacji merytorycznej. Estymacja jądrowa również ma parametr wygładzania (analogicznie do tego, że histogram ma szerokość przedziałów)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "01000018",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "mu_hat = reaction_times.mean()\n",
    "sd_hat = reaction_times.std(ddof=1)\n",
    "\n",
    "x_grid = np.linspace(reaction_times.min(), reaction_times.max(), 400)\n",
    "normal_pdf = stats.norm.pdf(x_grid, loc=mu_hat, scale=sd_hat)\n",
    "\n",
    "plt.figure(figsize=(10, 4))\n",
    "plt.hist(\n",
    "    reaction_times,\n",
    "    bins=15,\n",
    "    density=True,\n",
    "    color='lightgrey',\n",
    "    edgecolor='white',\n",
    ")\n",
    "plt.plot(x_grid, normal_pdf, color='black', linewidth=2, label='Dopasowana normalna')\n",
    "\n",
    "plt.title('Histogram + dopasowana krzywa normalna')\n",
    "plt.xlabel('Czas reakcji [ms]')\n",
    "plt.ylabel('Gęstość')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "01000019",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA2MAAAGMCAYAAABXvHp3AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjgsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvwVt1zgAAAAlwSFlzAAAPYQAAD2EBqD+naQAA44tJREFUeJzs3XdYFNfXwPHv0nsHQewNRUVQAVFU7L1GE1tssSWWxILlp7HFromxlyiWRE2MPZbYewFbYsUuAlJUQEA67PsHL5MQMFEEF/V8nsdHnZ25c2buLszZ21RqtVqNEEIIIYQQQoi3SkvTAQghhBBCCCHEh0iSMSGEEEIIIYTQAEnGhBBCCCGEEEIDJBkTQgghhBBCCA2QZEwIIYQQQgghNECSMSGEEEIIIYTQAEnGhBBCCCGEEEIDJBkTQgghhBBCCA2QZEwIIQqYWq3WdAjvPbnHoiDJ+0sIUVAkGRNCfNDGjh1Lw4YNX/p6w4YNGTt27Ev//18OHz7MmDFj3ihG8XLh4eEMGDCA0NBQTYfyypycnFi0aNEblbFt2zacnJwICQl543he9z39IcmP91e3bt2oX78+kZGRr3xMSEgITk5ObNu2Lc/nFUK8G3Q0HYAQQrxLFi9ejImJySvvv3bt2oILRnDmzBmOHz+u6TBeyy+//IK9vf0bleHj48Mvv/yCnZ1dPkUlcvOm768zZ85w48YNNmzY8Fp1ZWdnxy+//EKJEiXyfG4hxLtBkjEhhHgNzs7Omg6h0PL396dnz54cPnyYYsWKaTqcQsvV1fWNy7CyssLKyurNgxEFysnJif3791OkSJHXOk5PTy9f3idCiMJPuikKIcRr+GeXrt27d9O2bVtcXFyoVasWo0aNIiIiAoBPP/2UgIAAAgICcHJywt/fH4DIyEjGjRtH/fr1cXFxoVOnThw+fDjbeeLj45k4cSJeXl64ubkxfPhw1q5di5OTk7LPp59+yqhRoxg2bBiurq706dMHyOziNHr0aLy9valcuTJeXl6MHj2a6OjobNexePFiZsyYgaenJ25ubowcOZIXL16wcuVK6tWrR40aNRg6dGi24/JTRkYGK1eupEmTJlSpUoVmzZrx448/Ztvn0aNHDBo0CE9PT6pVq8Ynn3yitFRs27aNcePGAdCoUSPGjh3L7NmzcXFxIS4uLls5S5cupUaNGiQmJrJo0SKaN2/OwYMHad26NVWrVqVdu3ZcvnyZP/74g86dO+Pi4kLr1q05e/ZstnIOHTpEt27dcHNzo0qVKjRv3pwNGzZk2ycyMpIxY8YoddejRw8uX76svP7PboqBgYEMGTKEWrVqUblyZerWrcu0adNISkp66b3LrZvir7/+SseOHXF1dcXFxYV27dqxb9++bMcFBgbSp08f3NzcaNCgAbt27cpRtpOTE4sXL6Zjx464uLiwePFiAB4+fMiwYcOoU6cOrq6ufPrpp1y8eBGAmJgYnJ2ds7UEh4WF4eTkhK+vr7ItIyMDT09PVqxYAbzaezU39+7do3///lSvXp3atWszf/58xo0bx6effprtXH9/fzVo0IC5c+dmu6+v+/4CSE9PZ8OGDbRp0wYXFxd8fHyYN28eycnJSrlRUVGMHDmStm3b0rhxY9q1a8eOHTuyXcP9+/cZMmQIHh4euLu7M3DgQO7du6fcF+mmKMSHQVrGhBACSEtLe+1jLl68yOjRo/niiy9wd3cnPDycuXPnMnLkSH766ScmTZqkPIhOmjSJcuXK8fTpUzp16oS+vj7Dhw/H0tKSbdu2MXjwYObMmUPbtm0B+OKLL7h58ybDhw+naNGibNy4kW+//TZHDPv27aNt27YsW7aMjIwMEhMT6dmzJ5aWlkyaNAlTU1MuX77M4sWLMTAwYOrUqcqxfn5+1KlTh/nz53Pt2jW+/fZbrl+/jp2dHd988w0hISFMnz4dGxsbJk2alOs9yMjIICMjQ/l31t9Z91NbWxuVSpXrsZMnT2bbtm0MHDgQNzc3zp8/z4wZM4iNjWXw4MFkZGQwcOBA7OzsmDNnDjo6Oqxfv57PP/+cffv24ePjw+eff86yZctYvHgxTk5OpKam4ufnx++//07nzp2Vc+3cuZOWLVtiaGgIZI4FmjVrFsOHD8fIyIhvvvmGYcOGoaury6BBg3BwcFBeP3bsGAYGBhw7dozBgwfTs2dPhg4dSlJSEhs3bmTq1KlUqVKFatWq8eLFC7p27Up6ejq+vr4UKVIEPz8/+vbty/bt2ylVqlS2exAZGUn37t1xdXVl1qxZ6OnpceLECdasWYOdnR0DBgz4z/chwIYNG5g2bRpDhw6lRo0aPH/+nB9++IFRo0bh5uaGvb09ERER9OjRg1KlSjF37lzi4+OZN28ez549y1He8uXLGTlyJKVLl8bR0ZG7d+/y8ccfU6pUKSZMmICuri7r16+nV69e+Pn54eHhgaurK2fOnKF3794ASiJ74cIFpdw///yTmJgYfHx8Xuu9+ndRUVH06NEDa2trZs6cSXp6OgsWLODx48fZWpMmT57MqVOnGDhwICVLluTBgwcsW7aMwMBAVq9enaf3F8DEiRPZuXMn/fv3p2bNmty4cYMlS5Zw8+ZNVq1ahUqlwtfXl2fPnjFlyhRMTEzYuXMnY8aMwd7enlq1ahEREcEnn3xCkSJFmDx5MkZGRixatIhevXqxe/fuV6pzIcT7QZIxIcQHLzQ0lMqVK7/2cRcvXsTAwIABAwagp6cHgIWFBVevXkWtVlOuXDllfFnWQ+KyZcuIiopi//79ODo6AlC/fn169+7NnDlzaN26Nf7+/vj7+7No0SKaNm0KQL169WjdurXyzXkWXV1dpkyZopz/5s2b2NvbM3v2bIoXLw5ArVq1+PPPPwkICMh2rImJCfPnz0dHR4fatWuzfft2IiIi+PXXXzE1NQXg5MmTXLp06aX3YMmSJUrLSZYmTZoo/545cyYdO3bMcdyDBw/YvHkzI0aMUBIOb29vVCoVK1asoFu3bqSlpXH//n2++OIL6tevD6C01KSkpGBlZaWMqalUqZLSNdLNzY2dO3cqydilS5d4+PAhs2bNUs6fmJjIpEmTqFevHgB3797l22+/Zfr06XTq1AmAhIQEhg0bxoMHD6hUqRJ3796lQ4cOjB8/XinHzc0NT09P/P39qVatGtu3byc0NJTt27dTqVIlAKpXr0779u05f/58jmTs9u3bVKpUiQULFijvldq1a3P69Gn8/f1fORkLDg7ms88+44svvlC2OTo60rFjRy5evEirVq1Yu3Yt6enprFy5UuniWLp0aT7++OMc5dWsWVNpaQX46quv0NPTY/369UqcPj4+tG7dmjlz5rBlyxZ8fHxYtmwZqamp6OrqcvbsWSpXrsz169cJCQmhWLFinDx5EkdHR5ycnF7rvfp3P/74Iy9evGDHjh1K979q1arRrFkzZZ+s99eGDRuoVq2ack2lS5emV69eXLp0ieLFi7/2++vu3bts2bKFkSNHKnVTp04d7OzsGD16NCdOnKB+/foEBAQwePBgGjduDICHhwcWFhbK53Tt2rWkpKSwZs0abG1tAahYsSJdu3blzz//pGzZsq9U70KId58kY0KID56trS3Lli3L9bXPP//8pce5u7szf/58WrduTbNmzahfvz7e3t7Kg11uAgICcHNzUxKxLG3btmXcuHHcv3+fc+fOoaurqzzIAWhpadGyZcscs/CVKVNGecCDzIfGjRs3kpGRwcOHDwkKCuLu3bvcv38/R+ufi4sLOjp//RqwsbHByMhIScQgM7m8ffv2S6/n448/xsfHB4Dr168zadIkli1bpjxgvmzs2Llz51Cr1TRs2DBbXA0bNmTZsmVcvHiRRo0aUa5cOb7++mtOnTqFt7c39erVU7qOvcxHH33E119/TWhoKI6Ojmzfvp3SpUvj5uaWbb/q1atnu3ZAeXDPunaA2NhYAPr16wfAixcvePDgAY8ePeLq1asApKSkAJkJerFixZREDMDQ0JD9+/fnGqu3tzfe3t6kpqZy9+5dgoKCuH37NlFRUcr5X0VWF7rY2Fju379PUFCQ0i3277G5urpmG2tWrVo1ihYtmqO8v8cPme/bBg0aZJu8RkdHh1atWrFkyRJevHhB/fr1+fbbb/nzzz+pWbMm586dY9SoUUyaNInz589TrFgxTpw4obxfXue9+nfnzp3Dzc0t2zgsR0fHbPWb9f7q1q1brmXcunULNze3135/ZSWJrVq1yra9VatWjBs3Dn9/f+rXr4+npyeLFi3ixo0b1K1bl/r162ebVTWrLrI+JwD29vYcPXoUIF9myRRCvBskGRNCfPD09PSoWrXqS197GTc3N1auXMnatWtZs2YNK1euxMbGhkGDBmUbu/J3z58/V1oB/i4rGYiNjSU6OhoLCwu0tLIP67W2ts5xnLGxcY5ta9asYfny5cTExGBjY0OVKlUwNDTMMY4qt1khjYyMXnq9uSlSpIjyUJyQkABAhQoV/nMCj5iYGCDnQ22WiIgIVCoVfn5+LFu2jIMHD7Jjxw4lSZ0yZQrm5ua5HtuyZUtmzJjBzp07+eyzz9i3b1+uLUy5XX9WN8bcREVFMWnSJA4dOoRKpaJkyZLUrFkT+GsdqpiYmFzr6WUyMjL47rvv2LBhAwkJCTg4OODi4oK+vv4rlwGZY58mTpzI2bNn0dXVpUyZMlSsWDFbbM+fP8+1Xv6eEGT55/vg+fPnynv072xsbFCr1cTHx+Pk5ISDgwNnzpzB0tKSyMhIateuTfXq1QkICKB+/fpcv36dL7/8Ujn+Vd+rfxcVFZVrS7aNjQ1Pnz4F/np/bdiwIdd7WbRo0Ty9v54/f57rPdPR0cHS0lKJe/78+Sxfvpx9+/axf/9+tLS0qF27NlOnTsXR0ZGYmBiZ5EYIAUgyJoQQb6Ru3brUrVuXxMREzp07x/r165k2bRrVqlXDxcUlx/7m5uY8efIkx/asbZaWlhQpUoTo6GgyMjKyJWS5je35p99++41Zs2bh6+tLx44dlVaQL7/8UmnFKQzMzMwAWLduXa4JZVZrTdaYmkmTJhEYGMjvv//ODz/8oIwzyo2xsTHNmzdn3759VKhQgYSEBNq1a/fGMY8aNYr79++zdu1a3Nzc0NPTIzExkc2bNyv7mJqa5tqqcenSJczNzXN0P8tK5qdMmULTpk2VVsmsrpKvIiMjgwEDBqCrq8uWLVuoVKkSOjo63L17l507dyr7WVpaKsnK32UlLv/G3Nw812P//r6FzC63Z8+exdramtKlS2Nra4unpyebN2/m1KlTGBgY4OnpCeT9vWpvb59rLH//fGS9vywsLChXrly2a7158ya6urrA67+/shK0J0+eZGvdTk1NJTo6WrkPpqam+Pr64uvry/379zl8+DBLly5lypQprFy5ElNTU6KionKUf/bsWYoVK/bScZZCiPePzKYohBB5NHv2bD766CPUajWGhoY0aNBA6Yr0+PFjgBytW+7u7ly+fDnHIrK7du3C1taWkiVL4uHhQVpaGkeOHFFeV6vVHDp06D9junjxImZmZvTr1095uH3x4gUXL15UJtgoDLJalKKjo6lataryJyoqigULFhATE8Ply5epXbs2V65cQaVSUalSJYYPH06FChVeen+zdOrUidu3b7Nu3Tpq16792lOL5+bixYs0bdoUT09PpcX0xIkTwF+Tl9SsWZPg4GDu3LmjHJecnMzQoUPZsmVLrmWWK1eOjz76SEnEIiIiuH379ivXV3R0NA8ePKBTp05UrVpV6Xr6z9hq1arF5cuXldk+IXOsXHBw8H+ew93dnaNHjxIfH69sS09PZ8+ePVStWlW5Hz4+Ply9epUTJ07g4eGhnDckJISff/6ZOnXqKPvm9b3q7u7OH3/8ke1LjcjISP744w/l/1nvr19//TXbsWvWrKF3795ER0fn6f2VdU179uzJtn3Pnj2kp6dTo0YNQkNDqV+/Pr///juQ2ZW4f//+1K5dWym3Zs2a/Pnnn9kSsmfPntGvX793bt08IcSbkZYxIYTIo1q1arFmzRrGjh1L27ZtSU1NZdWqVVhYWFCrVi0g8xv6y5cvc/bsWZydnenTpw+7du2id+/eDBkyBAsLC3bs2MG5c+eYMWMGWlpauLu7U6dOHcaPH8/Tp08pWrQoW7Zs4datW//5jbmLiwubNm1i1qxZNGjQgMjISFavXs3Tp09f2q0vv3h6enLr1q1X2tfJyYm2bdsqY7uqVKnCgwcPmD9/PsWKFaNUqVKkpaVhYGDA6NGjGTp0KDY2Npw5c4abN2/Ss2dP4K8WkIMHD1KvXj2l5alGjRqULl2agIAA5s+fny/X5+Liwm+//UblypWxt7fn0qVLrFy5EpVKRWJiIgAdO3bkxx9/5PPPP2fYsGFYWlqyfv16UlNTcx2/5OLiwtKlS1m5ciWurq4EBQWxYsUKUlJSlDL/i7W1NY6OjmzYsAF7e3vMzMw4efIk69evBzKnmAfo1asXW7Zs4bPPPmPo0KGkp6czf/58pZXo3wwZMoQTJ07Qs2dPpRXup59+Ijg4mFWrVin71apVCy0tLY4dO8Z3330HQOXKlTE2NubixYtMnz4927Xn5b3as2dPNmzYwGeffcbgwYOBzKULUlNTlc9H1vtr3bp1aGlp4e3tzZUrV1i1ahUfffQRJUuWxN7e/rXfX+XKlaNDhw4sXLiQxMRE3N3duXnzJosXL8bT05O6deuipaWFvb0906ZNIz4+nhIlSnDt2jWOHz/OwIEDAejduzc7duygX79+DBw4EF1dXZYtW4a9vT1t2rT5126aQoj3iyRjQgiRR/Xr12fevHn4+fkxZMgQVCoVNWrUYP369crkC927d+fatWv079+fmTNn0qZNGzZt2sS3337LtGnTSE1NpWLFiixdupRGjRopZc+fP59Zs2bx7bffkpaWRqNGjejatWuOtYr+qUOHDoSEhLB161Y2btxIkSJFqF+/Pt26dePrr7/m3r17hWamtpkzZ7JixQp+/vlnwsPDsba2pmXLlnz11Vdoa2ujra2Nn5+fMsthbGwspUqVYurUqcoMjZ6entSuXZtvv/2Ws2fPsnLlSqV8Hx8foqKisk2E8iZmzZrFN998wzfffANAqVKlmDJlCrt27VKmbzcxMeGnn35izpw5fPPNN2RkZODq6sr69etzHSs4cOBAoqOjWb9+PUuWLMHBwYF27dops0rGxsYqCcG/yVozbuzYsejp6VG+fHlWrFhB3759OXLkCEOHDsXS0pJNmzYxffp0xo4di7GxMf369WPv3r3/WX758uXZuHEj3333HePGjUOlUuHi4sL69euVVijIHHPn6emZrWVMR0eHmjVrZpu8A/L+XjUzM2P9+vVMnz6d0aNHY2xsTLdu3TA0NMw21m3mzJmUKlWK7du34+fnh5GREYMGDVISIn19/Ty9v6ZPn07JkiXZunUrP/zwA3Z2dvTs2ZMvvvhCaUlbvHgx3333HQsWLCA6OhoHBweGDBmijF10cHBg48aNzJ07V6kzT09P5s+fj7m5uSRjQnxAVOqskb1CCCEKhdDQUP744w8aNWqEgYGBsn3YsGEEBwezfft2DUb3blCr1bRq1Qpvb2/+97//aTocRXJyMi4uLvj6+iqzM+bFpk2bmDx5MmfPns02O+I/VatWjXPnzv3rxCTvmqy1yv4+a2laWho+Pj7KrIb/5OPjw549e3IdnyiEEJokLWNCCFHIaGlpMXbsWBo1akSnTp3Q1tbm5MmTHDhwgJkzZ2o6vEItPj6etWvXcvXqVYKDg186q6UmXLhwgTNnzgBQsmTJPJWhVqv57bff2LNnD+bm5v85/b2JiQnff/89Pj4+ZGRkUKdOnTydtzB5/Pgxw4cPZ/DgwXh4eJCYmMgvv/xCXFxcrmumQeYsiBs2bKBKlSoYGBhkW9ZACCE0SVrGhBCiEDp37hxLlizh5s2bpKWlUbZsWfr06UPr1q01HVqhltVCkpGRwbhx42jTpo2mQ1J88cUXnDt3jgYNGjBz5sx/XTbhZUJDQ2nfvj2GhoaMHDnyP2eJ3LZtGzNnzsTCwoLhw4fTsmXLvIZfqGzatImNGzcSHByMrq4u1apV48svv3zpEhUrV65k+fLlFClShHHjximLfQshhKZJMiaEEEIIIYQQGiBT2wshhBBCCCGEBkgyJoQQQgghhBAaIMmYEEIIIYQQQmiAzKaYDy5fvoxarX6lhTOFEEIIIYQQ76+sRejd3Nz+c19pGcsHarUamQclk1qtJiUlRe5HISX1U7hJ/RRuUj+Fm9RP4Sb1U7hJ/eSv18kNpGUsH2S1iL1sSt0PSUJCAjdv3qRcuXIYGRlpOhzxD1I/hZvUT+Em9VO4Sf0UblI/hZvUT/66evXqK+8rLWNCCCGEEEIIoQGSjAkhhBBCCCGEBkgyJoQQQgghhBAaIMmYEEIIIYQQQmiAJGNCCCGEEEIIoQEym6IQQgghxFuWnp5OamqqpsN4a5KTk5W/tbSkLaCwkfp5Pbq6umhra+dLWZKMCSGEEEK8JWq1mvDwcGJiYjQdyluVkZGBjo4Ojx8/lof9Qkjq5/VZWFhgb2+PSqV6o3IkGRNCCCGEeEuyEjE7OzuMjIze+EHuXZGenk5ycjL6+vr51qIg8o/Uz6tTq9UkJCQQGRkJgIODwxuVJ8mYEEIIIcRbkJ6eriRi1tbWmg7nrUpPTwfAwMBAHvYLIamf12NoaAhAZGQkdnZ2b3TPpB1SCCGEEOItyBojZmRkpOFIhBBvKutz/KZjPyUZE0IIIYR4iz6UrolCvM/y63Os8WQsIyODhQsXUrduXVxdXenfvz/BwcEv3T86OpqRI0fi7u6Oh4cHU6ZMITExMds++/bto2XLlri4uNC+fXvOnj2rvLZo0SKcnJxy/TNu3LgCu04hhBBCCCGE+DuNJ2NLly5l48aNfPPNN/z8889kZGTQr18/UlJSct1/2LBhBAUFsXbtWhYsWMDx48eZPHmy8vq5c+fw9fWlS5cubN++HS8vLwYMGMC9e/cA6Nu3L6dOncr257PPPsPIyIjevXu/hSsWQgghhHi3ffrppy/9ctvJyYmoqKhXKufOnTscO3asYIN9A2PHjuXTTz/N8/GLFi2iYcOGGo3hffH48WP27NmTp2N9fX2pV68eT548eeVjnJyc2LZtW57O9zo0OoFHSkoKfn5+jBo1Ch8fHwDmz59P3bp1OXDgAK1bt862/+XLlwkICGDv3r2ULVsWgKlTp9KvXz9GjBhBkSJF+OGHH2jcuDE9e/YEYMyYMVy+fJl169YxdepUjI2NMTY2Vsq8ceMG69ev55tvvsHJyentXLgQQrzj1Gp1oelqVZhiEeJD0qJFC8aPH5/ra5aWlq9UxsCBA+nQoYPyHFjYjB8/XpncIi/69u1L9+7d8zGiD9eYMWNwdHSkVatWr3Xcw4cPOXToEOvXr8fW1vaVjzt16hSmpqavG+Zr02gyFhgYyIsXL/Dy8lK2mZmZ4ezszPnz53MkYxcuXMDW1lZJxAA8PDxQqVRcvHiR5s2bc+nSJcaOHZvtOE9PTw4cOJBrDFOnTqVmzZp06NAhH69MCCHebyqViuDgYGWhUE3R19enePHiGo1BiA+VgYHBaz3cvove9GH8n40A4u0rWrQop0+ffu2Jc97We1uj3RTDw8OBnPPz29nZKa/9XURERI599fT0sLCwICwsjNjYWBISErC3t3+l8o4ePcrly5cZM2bMm16KEEJ8cJKTk0lKStLoH00ng0KIf3flyhW6detGjRo1qF+/Pl9++SWPHz8GoGHDhoSGhrJ48WI+/fRTZsyYQePGjbMdHxcXh4uLC8eOHWPbtm00adKEn3/+GR8fH6pVq8awYcOIiIhg1KhRuLm5Ua9ePbZs2aIc//z5cyZMmEDdunWpXLkyXl5eTJgwIdt8A0FBQXz++efUqFEDT09PRowYwbNnz4CcXQQPHTpE586dcXV1pWrVqnTs2JGTJ0++9Pr/2U3xwoUL9OzZk+rVq1OlShVatGjBzp07ldfVajVLly6lXr16uLq6Mm7cuGw/50JCQnBycmLFihXUqVOHRo0aER8fT0xMDFOmTKF+/fq4uLjQpUsX/P39AThy5AgVK1bM1nW0ffv22Ro9nj9/jru7OxcvXiQjI4MVK1bQrFkzqlSpQvXq1enXrx+PHj166XWmp6czf/58vL29cXV1ZdiwYUyfPj3bvbt37x79+/fHzc0Nb29vRo4cma3b4MOHD/nss8+oUaMGbm5ufPbZZ9y6dQvI7BYbEBDA9u3blfuZlJTE999/T6NGjahatSrt2rVj//792WKaO3cuTZo0wcPDg+bNm7Np06Zsce/atYu2bdvi4uJCo0aNWLdunfLaB9FNMeuDoKenl227vr4+z58/z3X/f+6btX/WQ8HLysvtF/aaNWto0KABlSpVyvM1ZMlaAO5Dl1Wn/5xURRQOUj+F27tSPyqVSlljpbBITExErVYX+Dn+/rcoXN6F+klOTiYjI4P09PQ36vpWGKjVatRq9b9eR3p6OgMHDqRz587MmDGDp0+fMmPGDMaNG4efnx+//PILnTp1onnz5gwYMICIiAjWrVtHQEAANWrUAGD37t2YmZlRu3Ztdu3axePHj9m3bx/Lly8nLCyMIUOGcPbsWQYNGsSgQYNYs2YNkydPpkGDBlhYWDBmzBgiIyNZsGABNjY2XLp0iQkTJlC2bFl69uxJbGws3bt3p0KFCqxZswaVSsWUKVP48ssvWbduXbbrvH79OkOHDmX06NE0bNiQuLg45s+fz+jRozly5Eiuz6gZGRnK8REREXz22Wd0796dyZMnk5qayurVqxk/fjy1atXCxsaGlStXsmrVKiZPnoyzszObN29m27ZtuLu7k56eTkZGBgDbt2/Hz8+PpKQk9PT06NmzJ6mpqcyePRtLS0t++ukn+vbty4YNG/D09ERfX58zZ87QokULoqKiuHXrFhkZGURGRmJtbc2pU6cwMzPD1dWVtWvXsmrVKmbNmkX58uUJDg5m0qRJzJw5k8WLF+da13PnzmXHjh1MmTKFMmXKsHHjRn788Udq1qxJeno6kZGRdOvWjVatWuHr60tycjJLlizhk08+YefOnRgZGTF8+HAqVqzI5s2bSUtLY+7cuQwePJj9+/fz/fff88UXX2Bvb8+ECRNIT09n+PDh3Lhxg0mTJlGyZEl2797Nl19+yYIFC2jcuDE//fQTv//+O99++y12dnYcO3aMyZMnU7ZsWWrUqMG+ffsYM2YMI0aMoGHDhty4cYP//e9/GBsbKz3msj6vL3t/Z2RkkJiYqNTL3z8fr9p9XqPJmIGBAZA5dizr35D5wyq3X/QGBga5TuyRnJyMkZER+vr6Snn/fP2f5T1+/Bh/f39Wrlz5xtcBmWsM3Lx5M1/Keh88fPhQ0yGIfyH1U7gV9voxNDTE2dlZ02Fk8+DBg7f2EF7Y6+dDV9jrR0dHJ8cXxOeuRbD5yD2SUjSToBnoafNxo7LUqlzklY/JyMhg9+7d2VoisjRo0IBp06YRGxtLdHQ0lpaWWFtbY2try8yZM4mKiiIpKQkjIyNUKhV6enoYGBhQsmRJKlWqxPbt26lcuTKQmXS0aNGC1NRUUlNTSUtLY9SoURQvXpzixYtToUIFdHV16dKlCwBdunRhy5Yt3Lp1i2rVquHu7k6NGjUoX748AE2aNOHHH3/k5s2bJCUlsWvXLuLj45k+fTpmZmZA5jix/fv3ExsbqzxwJyUlkZaWxpgxY+jcuTMANjY2fPLJJwwdOpTHjx/n6JkFkJaWhlqtJikpidjYWAYOHEjPnj2VB/WePXuyc+dObt++jbGxMT/99BNdu3alUaNGAHz55ZecO3dOiSHrvdOpUyeKFSsGwLFjx7h+/TqbN2+mXLlyQOb4qitXrrBq1Spmz56Nh4cHJ06coEGDBpw4cYKKFSvy9OlTTp8+TdOmTTl69Ch169YlNTUVe3t7pk6dSq1atQCwtramUaNGHDp0SGn4+LvExEQ2bdrEiBEj8Pb2BmDkyJFcunRJifunn37Czs6OkSNHKsfNmDGDhg0bsnv3btq2bcujR4/w8PDA2toaXV1dvv76ax4+fEhCQoKyGLWuri5GRkbcuHGDI0eO8P333+Pp6QlAv379uHnzJitWrMDb25sHDx5gYGCAjY0N1tbWfPTRRxQrVgwHBweSkpJYu3YtTZs2pVu3bgDY29szevRotLS0lOtMTU3N9ZohM79IS0vj/v37ub6eW3KeG40mY1ldDiMjIylRooSyPTIyMtfJNOzt7Tl06FC2bSkpKcpq9hYWFhgZGREZGZltn8jISIoUyf4D5tChQ1hZWVGnTp18uRZdXV3lA/AhS0xM5OHDh5QqVarQfXMupH4Ku3elfgrjZBmlS5d+Ky1j70L9fKjehfpJTk7m8ePH6OvrZ/sSes/ZRzx+qtneNXvOBONTo+Qr76+lpUWDBg0YMWJEjteMjIwwMDDAwMCAzz77jNmzZ7Ns2TI8PDyoX78+LVq0UK5fpVKho6Oj/L9Tp04sWLCAiRMnEhYWxp9//sm0adMwMDBAV1cXgPLlyyv/NjY2xsHBQTne3NxcKdfAwICePXty5MgR9u7dy6NHj7h79y4hISGUK1cOAwMD5T1jZ2enxO/i4oKLiwsA2traaGlpYWBgQLVq1bC1teWnn37i/v37PHr0SPkiXldXN1udZtHR0VFiKV++PDY2NmzZsoXbt2/z6NEjpRuejo4OSUlJPH36FFdX12xlubm5ce/ePQwMDJSGh7Jlyyr7PHz4EFNTU6pUqZLt3O7u7pw+fRoDAwMaNWrEsmXLMDAw4Pz589SuXZvQ0FAuXbpE69atOXv2LF9//TX6+vo0a9aMP//8kx9++IEHDx7w4MED7t27h52dXa7XeO/ePZKSknB3d8/2uru7O4GBgRgYGHD79m3u3buX47k7KSmJ4OBgDAwM+Oqrr5g1axa//vorHh4eeHt707JlS2Wsl5aWFtra2hgYGBAUFARArVq1sp3T09OT+fPnY2BgwKeffsqxY8do0aIFlSpVwsvLi5YtW1K0aFEA7t69S+vWrbMdn5WYZXlZvf69fkuUKKHUS5a7d+++9JgcZbzyngWgYsWKmJiY4O/vryRjsbGx3Lhxgx49euTY393dnXnz5hEUFETJkpk/MAICAgCoUaMGKpWK6tWrExAQoHxrAeDv70/NmjWzlXXhwgU8PDzQ0cmfW6BSqV57YOD7zNDQUO5HISb1U7hJ/by+t/nwLfVTuBXm+tHS0lIeKLW1tZXtHzWowE+/3yQxOU0jcRnq6/BRg/LZYvovKpUKExMTypQp86/7+fr60r17d44ePcrp06eZPn06a9asYceOHejp6aFSqZR7AtC2bVvmzJnDiRMnuH37Ni4uLlSoUAHIvH9AtodjlUqV7X5m7aOlpYVKpeKLL77gzp07tG7dmpYtW1K5cmW+/vpr5ThdXV3l3y+7zqzXAwIC+Oyzz/Dx8aFGjRq0bduWxMREBg8enO0a/i4rDm1tbe7evUu3bt2oXLkytWvXplmzZlhaWtK5c+dsx/8znr/HmHV9RkZGOc6X2/l1dHTQ1tamYcOGTJ48mYcPH3Lu3DmmT59OaGgoq1ev5tq1ayQmJuLp6YlKpWL16tUsWbKEDh06ULt2bfr06cPhw4fZs2dPrufIagH6Z9x/v3dqtZpatWoxadKkHMebmpqira3Np59+SsuWLTl+/Dhnz55l0aJFLF++nB07dmBjY5OtvKz78M/P0t+vuWzZshw8eJCAgABOnz7NiRMnWL16NTNnzqRDhw7o6uq+tN7+Xn8vez0rDkNDwxwJ2+t8aanRZExPT48ePXowb948rKyscHR0ZO7cudjb29O0aVPS09OJiorC1NRU+UaievXqDB8+nMmTJ5OQkMDEiRNp37690vLVp08fBgwYgLOzM/Xq1WPr1q3cvHmT6dOnZzv3jRs3+OijjzRx2UIIIYQQijrVilKnWlFNh5Hv7t+/z7p16/jf//5Hly5daN++vfKFe2BgoNL69HdmZmY0adKEgwcPEhgY+EbTwt+8eZMTJ06wefNmqlWrBmR2O3v06JEyC2u5cuX49ddfiYuLU2ZOvH79Ov369WP79u3ZyvPz88PT05NFixYp23788UeAV2qZ//nnn7G2tmbNmjXKtiNHjijHW1pa4uDgwMWLF7NNZHLt2jWlJTA3Tk5OxMXFcfv2bSVxVavVXLx4Uem1ZWdnR5UqVdi0aRPPnj2jRo0alChRgq+//ppffvkFLy8v5Uut5cuXM3jwYAYMGKCcY/Xq1S+9xpIlS2JgYMAff/yRbR6GP//8U2kxKl++PHv37sXBwUFJ3mJiYhgzZgx9+vShfPnyLFmyhAEDBtCxY0c6duxIREQE9erVIyAggJYtW+a4ZoCLFy/SoEEDZfuFCxeUa16/fj3W1ta0atWKOnXqMHr0aPr06cPevXvp0KEDZcuW5erVq9nKnTlzJmFhYSxcuPCl9zu/aXzR52HDhtGpUycmTJhA165d0dbWZvXq1ejq6hIWFoa3tzd79+4FMrPMxYsXU6xYMXr16sVXX31FvXr1si367O3tzYwZM9i0aRMdOnTg3LlzLF++PNt0+ABPnjzBwsLiLV6pEEIIIcT7IykpiSdPnuT6JyUlBUtLS/bs2cPEiRO5d+8eQUFB7NixA3Nzc6VFzdjYmIcPH/L06VOl3I8++oiDBw/y6NGj115T6u9sbGzQ0dFh3759BAcHc/XqVb766islPoA2bdpgbm6Or68vgYGBXLt2jUmTJlGhQoUcY8AcHBy4desWFy5cICQkhK1bt7JgwQIg53wFubG3tyc8PJzjx48TGhrKgQMHlGfYFy9eANC/f382bNjAr7/+yoMHD/j++++5cuXKv5br7e1NpUqVGDlyJAEBAdy7d4+pU6dy+/ZtevXqpezXsGFDfvnlF6UbZPHixSlWrBg7d+7MNuOjg4MDp0+f5u7du9y/f5/58+dz4MCBl16joaEhn376KQsXLuTQoUM8ePCA2bNn8+effyr7dOvWjbi4OEaNGkVgYCCBgYEMHz6cq1evUqFCBczNzTl27BgTJkzg5s2bBAcH8/PPP6Orq6t0vzQ2NiY0NJTw8HDKli1LgwYNmDJlCseOHePBgwcsXryYw4cP07dvXwCioqKYOnUqhw8fJjQ0lJMnT3Lz5k3c3NwAGDBgAHv37uXHH3/k0aNH/Pbbb2zatOmNF+l+XRptGYPMJj5fX198fX1zvFasWDGlL20Wa2vr/8xW27dvT/v27f91n7+/QYQQQgghxOvZt28f+/bty/W1BQsW0Lx5c3744Qe+/fZbunbtSlpaGq6urqxZswYTExMgc8ry2bNnc+fOHXbt2gWAl5cXlpaWVK9eXZlUIy+KFCnCrFmzWLRoERs2bMDW1hYfHx969+6ttEgZGhoqXde6dOmCgYEBPj4+uS57NGzYMJ4+fcqgQYOAzFa1GTNm4Ovry9WrV3N88f9PPXv25P79+4wePZqUlBRKlSrFiBEjGDNmDEePHqVRo0Z0796djIwMli1bxtOnT6lbty6dOnXiwYMHLy1XW1sbPz8/Zs+ezZAhQ0hJSaFKlSqsXbsWV1dXZb+GDRuyYMECZWIOgNq1a7Nly5Zsi27PmTOHqVOn8tFHH2FsbEy1atWYMmUKkydP5vHjx8qYq7/78ssvSU1NVZYNaNCgAY0aNVImHClevDg//fQT3377Le3atQOgfv36rF+/HisrKwB++OEHZs+eTe/evUlMTKRSpUqsXLlSGcrUpUsXxowZQ9u2bTl79izfffcd3333HePHjyc2NpYKFSqwaNEimjRpAsCQIUNITU1l2rRpPHnyBFtbW7p27crAgQOV+zF16lTlvI6OjowbN+4/c4j8plIX9IjnD0BWE2fVqlU1HInmJSQkcPPmTSpVqlRo++x/yKR+Crd3rX7u3r370lmm3hYDA4O3NnnSu1Y/H5p3oX6SkpJ48OABpUuX/tdJAd5H6enpJCUlKbPi/ZsXL17g7e3NkiVLqF279luKMHejRo0iKioKPz+/PB0/f/58fv/991xnnczi5uaGv7//K8++VxBep35yc/DgQWrUqKEkVgB9+/bF3t6eGTNmZNt34cKFWFpaZluD7F30b5/n18kNNN5NUQghhBBCiOfPn7N//37Gjx+Po6MjXl5eGoslJSWFa9eucePGjVynrH8V165d4/Lly/95vJ6eHlu3buXWrVuEh4fn6Vyatnr1akaOHKl0MVy7di3nzp2jbdu2OfaNjo7m4sWLStfRD50kY0IIIYQQQuPS09MZP348N27cYM6cORpdRiMwMJAePXqgpaVFnz59Xvv4J0+e8OmnnxISEsLgwYP/dd9hw4Yxd+5cxowZo4wde9fMmzcPY2NjevfuTevWrfntt99ydInM8tFHH/Hnn3/y8ccfK7Oif8g0PmZMCCGEEEIIKysrLly4oOkwgMy1xv744488H29ra8vly5dfad/u3bu/0ayRhUGxYsVYvHjxK+1bpUoVjh49WsARvTukZUwIIYQQQgghNECSMSGEEEIIIYTQAEnGhBBCCCGEEEIDJBkTQgghhBBCCA2QZEwIIYQQQgghNECSMSGEEEIIIYTQAEnGhBBCCCGEEEIDZJ0xIYQQQgjxWho2bEhoaKjyf11dXWxsbKhfvz5ffvklVlZWGoxOaJq/vz89e/bk8OHDFCtWTNPhFGqSjAkhhBBCiNfWt29f+vbtC0BSUhK3b99m7ty59OjRg19++QVTU1MNRyhE4SfdFIUQQgghxGszMjLC1tYWW1tbihcvTqNGjfDz8yMsLIxVq1ZpOjwh3gmSjAkhhBBCiHxRtGhRmjRpwp49e5RtMTExfPPNN7Ro0QI3Nze6dOmCv7+/8vqiRYvo2rUrS5YswdPTk5o1azJu3Dji4+OVfW7fvs3AgQNxd3enSpUqSuKXJTExkfHjx1OnTh2qVq1K+/btOXDggPJ6eno6a9eupVmzZlStWpVmzZqxadMmAJ4/f07lypWz7T9jxgwqVqxIVFSUsq1jx44sXboUgEOHDtG5c2dcXV2pWrUqHTt25OTJk8q+n376KfPmzeN///sfNWvWpHr16owcOTLbNf1XGf+0aNEievfuzcqVK6lXrx5Vq1alR48e3Lt3L9u9njJlCvXr18fFxSXXe92jRw+GDx9O9erV+eabb9i2bRvNmjVjy5YtNGzYkGrVqjFs2DAiIiIYNWoUbm5u1KtXjy1btijlPH/+nAkTJlC3bl0qV66Ml5cXEyZMIDExMdfYC+J+vC8kGRNCCCGE0LDvvvuOYsWK/eeftm3b5ji2bdu2r3Tsd999l+24uLi4XLe/qQoVKhAcHMyLFy9IT0+nb9++XLx4kWnTpvHrr79SoUIFPvvsM65cuaIcc/XqVU6dOoWfnx9Llizh/PnzfPXVV0BmotW3b18sLCz4+eef2b17N82bN2f27NncvHkTgAULFnDr1i1WrlzJ3r17qVevHsOHDyckJASAWbNmsXTpUoYMGcJvv/1G9+7dmT59OmvXrsXc3Jzq1atz+vRpJZ4zZ84AKIlMZGQkN27coFGjRly7do2hQ4fSqlUrfvvtNzZv3oyVlRWjR48mJSVFKWPt2rXY2NiwZcsW5s6dy+HDh1m7di3AK5fxTxcuXODixYusXLmSjRs38uzZM6ZMmQKg3OsLFy4wd+5ctm3bluu9Pn/+PDY2NuzcuZNPP/0UgLCwMA4dOsSKFStYuHAhhw8fpk2bNlSuXJmtW7dSr149Jk+eTHR0NABjx47lxo0bLF68mP379zNu3Dh27NjBL7/88tLYC+J+vA9kzJgQQgghhIbFxsZmmxDjZYoXL55j25MnT17p2NjY2Gz/V6vVhIaG5tj+pszMzACIj4/nwoULXL9+nZ07d1K8eHEMDAyYMmUKV69eZfXq1SxYsAAAlUrF999/T5EiRQCYOHEi/fv35/79+1hYWNCzZ0+6d++OsbExAMOGDWPVqlXcunWLSpUq8ejRI4yNjSlevDhmZmZ8+eWXuLu7Y25uTnx8PJs2bWLs2LG0adMGgFKlShESEsLKlSvp1asXDRs2ZMOGDQBERETw4MEDfHx88Pf3p0WLFhw/fhxHR0ecnJy4efMmX3/9Nd26dVOuuWfPnvTv359nz57h4OAAQLly5RgxYoRyvjp16nD58mUAtLW1X6mMf0pLS2POnDmYm5sD0KVLF+bOnQvAqVOnuH79Or/99hsVKlQAyPVeZ92/rDF9ly5dIi0tjdGjR1O+fHkqVqxIxYoV0dXVpU+fPgD06dOHX3/9lYcPH2JpaUmdOnVwd3fHyckJgGLFivHTTz9x+/btl74vCuJ+vA8kGRNCCCGE0DAzMzMcHR3/cz9bW9tct73KsVlJUhaVSoWjo2OO7W8qLi4OABMTE27fvo2pqSnly5cnKSlJOW/NmjU5deqUckypUqWURAygevXqQGb3xObNm9OtWzd2797NjRs3ePToEYGBgQBkZGQA0L9/fwYNGoSXlxcuLi7UqVOHNm3aYGpqypUrV0hNTaVGjRrZ4vTw8GDdunU8e/aMBg0aMGvWLIKDg7l48SKVK1emfv36rFu3DoDjx4/TqFEjACpVqoS5uTkrV67k/v37BAUFKfGkp6cr5ZcpUybb+UxNTZXE91XL+CcbGxslEcsqMzU1VblXpqamSiL2snttbW2d6+Qqf0/0jYyMsiVA+vr6AEorVbdu3Thy5Ajbt2/n4cOH3L17l5CQkBzX/HcFcT/eB5KMCSGEEEJo2IgRI5RWg9e1a9euPB1namqqdOPLT9evX6dUqVIYGxujVqtz3UetVqOj89djqK6ubrbXsx7AtbW1efLkCZ988glWVlY0bNgQb29vqlatSv369ZX93dzcOH78OKdPn+bs2bPs2LGDZcuWsWrVKoyMjHKNISuR09HRoVSpUpQpU4ZTp05x+fJlvLy88PLyYvLkyYSEhHD69GmWL18OQEBAAJ999hk+Pj7UqFGDNm3akJiYyODBg7OVr6en99J79Kpl/NO/lfmq99rAwCDX/f5ZB1pauY9mysjIYODAgdy5c4fWrVvTsmVLKleuzNdff53n2PN6P94HkowJIYQQQoh8ER4ezuHDh+nfvz8ATk5OxMXFcefOHaXlRa1Wc/HiRcqVK6cc9+DBA+Li4pQWm6zua87OzuzevZuYmBj279+vJAy3bt1SygJYuHAhNWrUoFGjRjRq1Ihx48bRqlUr9u/fz6hRo9DV1eXixYtUqlRJOeeFCxewtbVVWpoaNGjA6dOnuXr1KrNmzaJUqVIULVqUxYsXo6enp7Ss+fn54enpyaJFi5Syfvzxx2zx/Jf8KOOfsu717du3ldax3O71m7p58yYnTpxg8+bNVKtWDYDU1FQePXqUazfaV1EQ9+NdIRN4CCGEEEKI15aQkMCTJ0948uQJwcHBHDp0iH79+lGsWDFlrJG3tzeVKlXC19eXixcvcu/ePaZOncrt27fp1atXtrJGjx7N7du3OXPmDFOnTqVly5Y4Ojpib29PYmIiv//+O48fP+bUqVNKK2JWt7ng4GAmTZrE2bNnCQ0NZf/+/Tx+/Bg3NzdMTEz45JNPWLhwIbt37yYoKIgNGzawceNG+vbti0qlAjIXsj5+/DjR0dFKN8latWqxc+dO6tevr7QuOTg4cOvWLS5cuEBISAhbt25VxmO96mQT+VHGP2Xd65EjRxIQEPDSe/2mbGxs0NHRYd++fQQHB3P16lW++uornjx5kufYC+J+vCukZUwIIYQQQrw2Pz8/ZXp5XV1dHBwcaNmyJX379lUm2tDW1sbPz49Zs2YxcuRIUlNTqVKlCmvXrsXV1VUpy8HBgUqVKtG9e3e0tbVp06YNo0aNAqB58+Zcv36dWbNmER8fj6OjI507d+bw4cNcvXqVrl27MmnSJGbPno2vry8xMTE4OjoyatQo2rVrB8C4ceOwtLRk3rx5PH36lFKlSjFx4kQ+/vhjJQY3NzeMjY1xcnJSxkjVrl2bbdu2KePFIHPyi6dPnzJo0CAgc2KKGTNm4Ovry9WrVylbtux/3rv8KOOfsu717NmzGTJkCCkpKbne6zdVpEgRZs2axaJFi9iwYQO2trb4+PjQu3dvjhw5kqcyC+J+vCtU6ve97e8tuHr1KgBVq1bVcCSal5CQwM2bN6lUqdJL+2gLzZH6Kdzetfq5e/euMiBfUwwMDPK1+82/edfq50PzLtRPUlISDx48oHTp0i8dt/O+Sk9PJykpCQMDA7S1tbO9tmjRIrZv357nB3nx5v6tfkTu/u3z/Dq5gXRTFEIIIYQQQggNkGRMCCGEEEIIITRAkjEhhBBCCKExQ4cOlS6K4oMlyZgQQgghhBBCaIAkY0IIIYQQQgihAZKMCSGEEEK8RTKRtRDvvvz6HEsyJoQQQgjxFujq6gKZ0/ALId5tWZ/jrM91Xml80eeMjAwWL17Mr7/+SlxcHO7u7kycOJHixYvnun90dDTTpk3jxIkTqFQqWrVqxejRozE0NFT22bdvH4sWLSIkJIQyZcowZswYvLy8lNdTU1NZuHAhO3bsIC4ujipVqjB+/HgqVapU4NcrhBBCiA+TtrY2FhYWREZGAmBkZIRKpdJwVG9Heno6ycnJALKOVSEk9fPq1Go1CQkJREZGYmFh8cb3S+PJ2NKlS9m4cSOzZs3C3t6euXPn0q9fP3777Tf09PRy7D9s2DASExNZu3YtsbGxjB8/noSEBGbPng3AuXPn8PX1ZfTo0dSpU4ctW7YwYMAAduzYoazePXnyZI4dO8asWbMoWrQoCxYsoH///uzbtw9TU9O3ev1CCCGE+HDY29sDKAnZhyIjI4O0tDR0dHTQ0pKOWYWN1M/rs7CwUD7Pb0KjyVhKSgp+fn6MGjUKHx8fAObPn0/dunU5cOAArVu3zrb/5cuXCQgIYO/evUpiNXXqVPr168eIESMoUqQIP/zwA40bN6Znz54AjBkzhsuXL7Nu3TqmTp1KcHAwW7duZfny5dStWxeAadOm0b59e65du5atBU0IIYQQIj+pVCocHByws7MjNTVV0+G8NYmJidy/f58SJUpk680kCgepn9ejq6ubby2IGk3GAgMDefHiRbYEyMzMDGdnZ86fP58jGbtw4QK2trZKIgbg4eGBSqXi4sWLNG/enEuXLjF27Nhsx3l6enLgwAEATp8+jampKfXq1ct2TlnfQgghhBBvi7a29gfVHSwjIwMAfX19DAwMNByN+CepH83RaDIWHh4OgIODQ7btdnZ2ymt/FxERkWNfPT09LCwsCAsLIzY2loSEhBxNhn8v78GDBxQvXpwDBw6wcuVKIiIicHZ2ZuzYsdmSvNeV1X/0Q5eYmJjtb1G4SP0Ubu9K/ahUqkL3zWliYmKBz1D3rtTPh0rqp3CT+incpH7yl1qtfuXxoBpNxrIq/J9jw/T19Xn+/Hmu++c2jkxfX5/k5GSSkpJeWl7WoMT4+HiCgoJYunQpo0ePxszMjGXLltGtWzf27t2LtbV1nq4lNTWVmzdv5unY99HDhw81HYL4F1I/hVthrx9DQ0OcnZ01HUY2Dx48eGsPEYW9fj50Uj+Fm9RP4Sb1k39yy1lyo9FkLKsZNCUlJVuTaHJycq7fuhoYGJCSkpJje3JyMkZGRujr6yvl/fP1rPJ0dHSIj49n/vz5SkvY/PnzqV+/Ptu3b6dfv355uhZdXV3KlSuXp2PfJ4mJiTx8+JBSpUoVum/OhdRPYfeu1E9hnP2tdOnSb6Vl7F2onw+V1E/hJvVTuEn95K+7d+++8r4aTcayuhxGRkZSokQJZXtkZCROTk459re3t+fQoUPZtqWkpBATE4OdnR0WFhYYGRnlmKEoMjKSIkWKKGXo6Ohk65JoYGBA8eLFCQkJyfO1qFQqjIyM8nz8+8bQ0FDuRyEm9VO4Sf28vrf58CD1U7hJ/RRuUj+Fm9RP/nidLy01OndlxYoVMTExwd/fX9kWGxvLjRs3cHd3z7G/u7s74eHhBAUFKdsCAgIAqFGjBiqViurVqyvbsvj7+1OzZk2ljLS0NK5evaq8npSURHBwMCVLlszX6xNCiNeRNRarMLY8CSGEECL/aTQZ09PTo0ePHsybN4/Dhw8TGBjI8OHDsbe3p2nTpqSnp/PkyRNlLFi1atWoXr06w4cP58qVK5w7d46JEyfSvn17peWrT58+7NmzhzVr1nDv3j3mzJnDzZs36dWrFwA1a9akdu3ajBkzhgsXLnD37l1Gjx6NtrY27dq109i9EEIUTgXd9e3vssZivayV523GIoQQQoiCp/FFn4cNG0ZaWhoTJkwgKSkJd3d3Vq9eja6uLiEhITRq1IiZM2fSsWNHVCoVixcvZsqUKfTq1Qt9fX2aN2/OuHHjlPK8vb2ZMWMGS5cuZf78+ZQrV47ly5dn65a4aNEi5s2bx5AhQ0hKSqJ69eqsX78eKysrTdwCIUQhplKpCA4OViYB0hR9fX2KFy+u0RiEEEIIkb80noxpa2vj6+uLr69vjteKFSvGrVu3sm2ztrZm4cKF/1pm+/btad++/UtfNzExYfLkyUyePDkvIQshPjB/n61VvDteZ2phIYQQQhM0nowJIYQQ/+X58+cEBQURFBREREQEUVFRREVFER0djampKb///nu2/fv378+qVavQ1dVVBqRn/W1lZYWDgwMODg64urrSu3dvzVyUEEKID54kY0IIIQolf39/Fi9eTFBQENHR0S/dT19fP0crmK6uLpC5BmRqaiqxsbG5Htu8efMcydjnn39OcnIyzs7O1KxZE3d3d4yNjd/8goQQQoh/kGRMCCGExkRHR+Pv78+FCxfo0aMHpUqVUl7LyMjgjz/++M8y1Go18fHxmJqaKtvKlStHrVq1SE5OJjExkcTERBISEkhISODFixfKfllLrPzdr7/+yrNnz5T/a2tr4+LiQs2aNSlWrBjGxsZUrFgxbxcshBBC/I0kY0IIId6a5ORkLl++zNmzZzl79iyBgYHKLJHOzs7ZkrGsf9vZ2VGqVClKlixJyZIlcXR0xNraGisrK4oWLYqrq2uOsWEjRoxgxIgRucaQmJhIWFgYYWFhmJubZ3vt2bNn2RIxgPT0dC5fvszly5cBmDRpEhUrVmTJkiU0bNjwTW6HEEKID5wkY0IIIQpUYmIip06d4uDBgxw/fpyEhIRc97t69SodO3ZU/m9vb4+/v/+/LkBqYGDw2pN0GBoaUqZMGcqUKZPjNWtra+Li4rh16xZ//vkn/v7+nD17lmvXrmVbWiAwMBBbW9tsx8bExABgYWHxWvEIIYT4cEkyJoQQokANHjyY8+fP5/qak5MTXl5e1KpVCxcXl2yvqVSqf03ECoqJiQk1atSgRo0a9O3bF4DY2FhOnjzJb7/9xpUrVwgNDaVKlSrZjlu5ciUTJkygWbNmfPLJJ7Rt2xYzM7O3Hr8QQoh3hyRjQggh8s29e/eyresIUL9+fSUZMzc3p379+tSpUwdPT0+sra01EeZrMzMzo0GDBtjb21OpUiV0dHRytMj98ssvpKamsnv3bnbv3o2+vj4fffQRAwYMoF69ejLNvhBCiBwkGRNCCPFGYmNj2b17N9u3bycwMJAtW7bg5OSkvN6kSRMePnxIkyZNcHd3V2Y6fJfp6ell+39aWhr16tUjPDycx48fA5nj4zZu3MjGjRupUKECAwYMoGfPnjm6NwohhPhwaWk6ACGEEO+moKAgZs6cSePGjZk5cyaBgYEAbN++Pdt+RYsWZdKkSdSuXfu9SMRyo6Ojw/z58wkODubEiRMMHjwYKysr5fXbt28zatQoHB0d2bZtmwYjFUIIUZhIMiaEEOKVqdVqjh8/Tvv27WnSpAkbN24kMTFReb1q1ao5xlJ9SLS0tKhbty6LFy8mNDSUjRs34uPjo7yura1N3bp1NRegEEKIQkW6KQohhHglx44dw9fXlwsXLmTbbmBgQLt27fj444+pUKGChqIrfAwMDOjatStdu3bl9u3brFq1Ch0dnRzdFJcsWYKxsTHdu3d/b1sOhRBC5E6SMSGEEK8kPDw8WyJWpEgRunTpQufOnXOs1yWyq1ChAnPmzMmxPS4ujgkTJhATE8O0adOYOHEi3bp1Q0dHfj0LIcSHQLopCiGEyEGtVivrZmXp3LkzFStWxNXVlQ0bNnD06FH69esnidgb2L17t3Kf7927R69evXB2dmbDhg2kp6drNjghhBAFTpIxIYQQ2Zw6dQovLy969uyZbbu2tjaHDx/m0qVLdOvWTbrU5YOuXbty6tQpGjdurGy7c+cOPXr0oEqVKuzYsSPbYtNCCCHeL5KMCSGEACAwMJD27dtTt25d/P39+e2337h06VK2fYoWLSrrZeWzOnXqcPDgQY4fP55tso/AwEA6dOiAj49PjnF6Qggh3g+SjAkhxAcuMjKSzz//nCpVqrBz505le+XKlUlJSdFgZB+WevXqcfToUY4cOUKdOnWU7SdOnODnn3/WYGRCCCEKiowQFkKI91RichqPn8QT9uwF0bHJxMQn8zw+mbiEFFJSM0hJTiHg2DZO7llNcmK8cpy5pS2deg2jdduPyTAy4cHj59hbG2OoL78y3oYGDRpw8uRJdu7cyejRo3n27Bnjx4/XdFhCCCEKgPxmFUKI90BkdAJ3gmO4GxzD3ZAYgsJiiY5Lfun+0Y9vcfXwMmKfPFS2aesaUM69I6VrtCVCy4DVu29mO8bCVJ9S9maUdjSnTFEzdDOSMTNQS7fFAqBSqWjfvj0tW7bk5s2bWFpaZnt9/fr1WFlZ0bp1aw1FKIQQIj9IMiaEEO+gmLhk/rjzhCt3nvDn3adERiW81vEJsZHZErFilRtSybsn+sYW/37OuCf8ceeJss1YX4uSRQwpVcSAckUNsbfUk+QsH+np6VGtWrVs20JDQxk8eDDx8fG0a9eOBQsWULJkSQ1FKIQQ4k1IMiaEEO+IsKcvOHctjLNXwwgMiuLfJtkzM9bD0daEorbGFLUxwcbCEAsTfSxM9TE10kNXpxnt2lzkeUwMCxcupKZHLVLTMkhKSSf2RTLP41N4Hp/Mk5hEwp6+ICIqgZDIOJ7HZx9D9iI5gxuPXnDj0YvM8xppU8HRCKdiRlQoZoSejgxNzm9r1qwhPj6zW+nOnTs5cOAAEydOZOTIkTLDpRBCvGMkGRNCiELsRVI6f96P588Hj3kUeT3XfXS0tahUyopKpa0oV8yC8sUtsDY3UFqo7t+/z44dvzJixIhsx235dTNWVlZoa2sr28yBIlZGuZ5HrVYTHZfM/dDn3A99zsUbwdwPSyApJUPZJzYhnQt34rhwJw49HRUVixvjUtqYCo5G6Epili/Gjx9PmTJlGDlyJOHh4SQmJjJu3Dg2b96Mn58frq6umg5RCCHEK5JkTAghChm1Ws29sETOBcYSGPyC9Iyc+xQvYoKHsz1uFeyoWNoKfV3tHPukp6ezcOFCJkyYQEJCAs7OzjRv3lx53dbW9rXiUqlUWJkZYGVmQM1KRaheSouExEQiY1K4F5bIndBE7oclkpqe2WSXkqbmyoN4rjyIR09HRaUSxtQoZ0rZooZoSVfGPFOpVHTr1o1WrVoxceJEFi9eTEZGBpcvX8bd3Z1x48Yxfvx49PX1NR2qEEKI/yDJmBBCFBLJqRlcvBPHucDnPHmemuP1MkXNqevmSK0q9hSzM/3XsgIDA+nduzf+/v7KthkzZmRLxvKDlkqFvaU+9pb61HG2IDUtg/vhSVwPiuda0AsSkzMzyZQ0dWYL3/14LE10qFnejBrlTTE3ll9DeWVubs6CBQvo0aMHffr04fr166SlpfHNN9+wbds2tm7dipOTk6bDFEII8S/kt6AQQmhYfGIaZ24852xgbLYufwCmhtq4lTXF09maep5V/rOsjIwMlixZwujRo0lKSlK2DxkyhBkzZuR77P+kq6OFU7HMMWPtvDJb+K4+iOd60AsS///aouPTOHg5ikN/RFHB0YhaFc2oUMxIWsvyyN3dnYsXLzJjxgxmzJhBWloaUVFRFClSRNOhCSGE+A+SjAkhhIbEJqRx7EoM52/HkpaefTaO0vYGeFU0x7mkMdpaKgwMDP6zvJCQEPr06cOhQ4eUbRUqVGD16tV4e3vne/z/RVtLRQVHIyo4ZiZmgcEvOH87ljuhiagBtRpuhSRwKyQBW3NdajubU72sKXq6Mrbsdenr6zNlyhQ6duxI3759mTRpEhYWFpoOSwghxH+QZEwIId6yhOR0TlyN4cyN58r4KgAtFbiVM8Xb2Rx7q9cb77Np0ya++OILYmJilG1Dhgxh9uzZGBnlPiHH26SjraJKKROqlDIhOj6Vi/8/ycfzF2kAPHmeys6zTzlwMQoPJzO8KplLF8Y8qFatGgEBAdkmZQGIiIhgx44dDBgwQJYeEEKIQkR+0wkhxFuSnJrBmRvPOXEtJlt3RF0dFR5OZng7W2Bh8vo/ljMyMlixYoWSiDk6OrJmzRqaNGmSX6HnK0sTXRq7WdGwmiWBwQmcuhHDg/DMLpWJKRkcvxrDqesxuJU1pb6LJTZmMl376/hnIqZWq+nXrx+7d+9mx44d+Pn54eDgoKHohBBC/J0kY0IIUcAy1Gou3onjwKUo4hPTle3aWlCrojk+LhaYGOb9x7GWlhbr1q2jatWqtGnThsWLF2NpaZkfoRcoLS0VziWNcS5pzONnyZy6HsOVB/GkZ0B6Bly4E8fFu3G4lDbBx8UCe0uZHTAvzpw5w+7duwH4/fffqVatGj/99BNNmzbVcGRCCCEkGRNCiAL06EkSu849JfRpsrJNpYIa5Uxp5GqJhcnrt/qo1WoiIiKwt7dXtpUsWZKrV69SsmTJfIn7bStqrc/H9YrQvKY1Z28+5+zNWJJTM1CrUWZhdC5hTGM3Sxxeswvnh65OnTr8/vvv9O7dm/DwcJ48eUKzZs0YN24cU6dORUdHHgWEEEJTND5KOiMjg4ULF1K3bl1cXV3p378/wcHBL90/OjqakSNH4u7ujoeHB1OmTCExMTHbPvv27aNly5a4uLjQvn17zp49m+31Xbt24eTklONPSEhIgVyjEOLDE5eYxpaTkSzbHZotEatS0pjhHYrzkbddnhKxp0+f0rZtW7y9vYmNjc322ruaiP2dmZEOzWpYM6ZzCZpWt8JI/69fUzcevWDhzhA2Hg0nMiZFg1G+e5o1a8bVq1dp0aKFsm3mzJn4+Pj86+9cIYQQBUvjydjSpUvZuHEj33zzDT///DMZGRn069ePlJTcf9EOGzaMoKAg1q5dy4IFCzh+/DiTJ09WXj937hy+vr506dKF7du34+XlxYABA7h3756yz61bt/Dw8ODUqVPZ/kgfeiHEm8rIUHPmxnO+3RrMxbtxyvYiFnr0a16U7g3tsTXXy1PZ/v7+uLm5sXv3bu7du8fgwYPzK+xCx1BfmwbVLBnTuSStPKwxNfxrHNTVhy/4fkcwv56M5GmsJGWvysbGht27dzN37lylNez06dO4uroq3RiFEEK8XRpNxlJSUvDz82PYsGH4+PhQsWJF5s+fT3h4OAcOHMix/+XLlwkICGD27NlUrlwZLy8vpk6dys6dO4mIiADghx9+oHHjxvTs2ZOyZcsyZswYKleuzLp165Rybt++jZOTE7a2ttn+/HPQsxBCvI7ImBRW7A3lN/+nJKdmTtBhoKdFG08bhrYrRlkHwzyVq1ar2bhxI3Xr1lVa8G1tbenevXu+xV5Y6elq4V3ZAt9OJWjlYY2xQeavLbUaLt2NY+amOyzd8ifPnif+R0kCMscXjho1ipMnTyotqVFRUbRp0yZHLxIhhBAFT6PJWGBgIC9evMDLy0vZZmZmhrOzM+fPn8+x/4ULF7C1taVs2bLKNg8PD1QqFRcvXiQjI4NLly5lKw/A09MzW3m3bt3KVoYQQryJ9Aw1R/6IZuHOYB49+atLYs3ypoz8qAS1nc3R1srbdOKJiYlMmDCBSZMmkZqaCoC3tzd//PEHzZs3z5f43wW6OllJWUma1bDCUC/z11dGBuw7+5D+Mw6x5rfrxCemajjSd0OtWrW4fPkyHTp0AKBbt27UqlVLw1EJIcSHR6OjdsPDwwFydA+0s7NTXvu7iIiIHPvq6elhYWFBWFgYsbGxJCQkZBvU/s/ynj9/TkREBBcuXGDjxo1ER0fj4uKCr68vpUuXzvO1qNVqEhIS8nz8+yJr/N4/x/GJwkHq5/WoVCoMDf+9NSvkaRJbTz0hPPqv7nLWZrp8VMeW0vZ5awnLEhwczPDhw7l165aybejQoXzzzTfo6upq7GfOq9yXgqKvq4WPiyWeTmacuvGc09efk5yaQWpaBtuO3eWAfxAdfUrT1KM4ujr5+33j+/b50dfX58cff2T9+vV06tTpnb+u961+3jdSP4Wb1E/+UqvVr7ymo0aTsawK19PLPn5CX1+f58+f57r/P/fN2j85OZmkpKSXlpecnPlt9Z07d4DMmzRz5kySkpJYtmwZ3bp147fffsPGxiZP15KamsrNmzfzdOz76OHDh5oOQfwLqZ9XY2hoiLOzc66vpWeoOfpnNEf/jCbj/9dt1lJB3SoWNHK1fONE4MSJE4wdO5a4uMxxZ0ZGRvj5+VG1alXu3r37RmW/qX+7L28tBn1tmrhZ0cDVjssP09l18h5p6WriE1NZv+82u07co7GrOZVLGOb7Isfv2+fHw8ODR48eZdt25swZoqOjadWqlYaiyrv3rX7eN1I/hZvUT/7JLWfJjUaTMQMDAyBz7FjWvwGSk5Nz/dbVwMAg14k9kpOTMTIyQl9fXynvn69nlVezZk3Onj2LpaWl8gt68eLF+Pj4sG3bNgYMGJCna9HV1aVcuXJ5OvZ9kpiYyMOHDylVqpTGvjkXLyf183pe9hD/9HkKv5yIJORvsyQ6WOnxUR07HG3yZ9r1O3fuKIlYqVKlWLp0KS1atCAxMRG1Wp0v58ir/E5u3oSJoQ592lSkcU0Hfj50l5N/hqFWQ8yLdLacjuLyQzN6NK+Ac6k3X3ftQ/n8PHjwgEmTJhEdHU1YWBgzZ8585YcKTfpQ6uddJfVTuEn95K/X+dJUo8lYVpfDyMhISpQooWyPjIzEyckpx/729vYcOnQo27aUlBRiYmKws7PDwsICIyMjIiMjs+0TGRlJkSJFlP9bWVlle93Q0JBixYopk4DkhUqlwsjIKM/Hv28MDQ3lfhRiUj95o1arCbgVy57zz0hNy0yItFTQoJolDapZ5nlcWG769u3L1atXAZg2bZrSai+/JHNX3MEK30896NgghrW7b/DHnScA3AuNZcrqC3g429O7tTPFi5i+8bne98/Prl27iI6OBmD58uVcvXqVbdu2YWdnp+HIXs37Xj/vOqmfwk3qJ3+8zpeWGp3Ao2LFipiYmODv769si42N5caNG7i7u+fY393dnfDwcIKCgpRtAQEBANSoUQOVSkX16tWVbVn8/f2pWbMmAL/88guenp7ZxlrEx8fz8OFDadkSQrxUfFI66w+Hs+PsUyURszbTZWArRxq7Wb1xIvbPFn2VSsWsWbOYP38+JiYmb1T2h6RsMQumDvRiSn8vSjmYKdsDboQzZN5Rlm39k+fxyf9Sghg3bhw//PCD0hp2+vRpPDw8lC8HhBBC5B+NJmN6enr06NGDefPmcfjwYQIDAxk+fDj29vY0bdqU9PR0njx5oowFq1atGtWrV2f48OFcuXKFc+fOMXHiRNq3b6+0fPXp04c9e/awZs0a7t27x5w5c7h58ya9evUCoF69emRkZDB69Gju3LnD1atXGTp0KFZWVnTs2FFj90IIUXjde/yCRTuDCQz+60scTyczhrUtRglbg3858tX88ccftGzZMscssgYGBoWqS+C7QqVSUb2iHd+P8OHLT9ywNs+so4wMNXvPPGTgrMPsPHGP1LQMDUdaePXr149Tp07h6OgIQFBQELVr15b1yIQQIp9pfNHnYcOG0alTJyZMmEDXrl3R1tZm9erV6OrqEhYWhre3N3v37gUyf8EuXryYYsWK0atXL7766ivq1auXbdFnb29vZsyYwaZNm+jQoQPnzp1j+fLlylT2Dg4OrF27loSEBLp27Urv3r0xNTVl/fr1ypgzIYSAzIf3Xw7dYsmuh8QmpANgYqBNr8b2tK9ti57um/8I/e233+jbty8RERGMGDGC4ODgNy5TZNLWUtHYowTLxzbi0xaVMNDLXEvyRWIqq3ZeY+i8I5y/Ea7xMXiFlbu7OwEBAUrPkvj4eNq2bcu8efPkngkhRD5RqeUn6hvL6rpRtWpVDUeieQkJCdy8eZNKlSpJn+NCSOrn1cXEJfPdxotcvv1E2VbWwZBP6tlhavTmw23T09NZuHAhfn5+yjYPDw++/fZbLCwscuxvYGBQ6LpS3717V+m5oCmvc1+iYpP4ce9NDl94xN9/87lVsOWzdlUoaW/28oP5cD8/CQkJ9OnTh82bNyvbhgwZwqJFizQYVU4fav28K6R+Cjepn/z1OrmBxlvGhBCisLl67ylffndUScRUQGM3S/o2dciXRCwhIYGvvvoqWyL28ccfs3z58lwTMZE/rMwM+LKLG999WR/n0n9N5HT59hOGfXtMxpO9hJGRET///HO2XigNGjTQXEBCCPEe0ehsikIIUZhkZKj59fBtNu4PVNYOszDVp5uPPcVt8ufH5dOnTxk8eDA3btwAQFtbmzFjxtClSxcZH/aWlCtuwazB3py+8pg1v10nMjpRGU92/HIoXZs60bJ26XxfNPpdplKpmDRpEpUqVSIoKEjGWAshRD6RZEwIIYD4xFS+3XCRCzf/WuKiWnkbRnarwbPIkHzpjnfv3j2++OILHj9+DICpqSnz5s2jdu3ab1y2eD0qlQrvao54ONuz88Q9Nh+6TVJKujKebN+ZB3zWtgo1KxWRJPlvPv7441y3BwUFUbJkybccjRBCvPvkaz8hxAcvKDyWEd8fVxIxLRV0b16RKQNqY2n25rMlQuaCmv369VMSMQcHB9avXy+JmIbp6WrTuVEFVoxrTGP3EmTlXaFPXjB1tT+TfzhHcEScZoMs5FasWIGTkxO//PKLpkMRQoh3jiRjQogP2ukrjxm14ARhT18AYGqkx5QBXnRp4pSvizgbGhoyduxYACpVqsSGDRsK3YQcH7KXjSe7dCuSofOOsnrXNRKSUjUYYeF05swZvvjiC5KTk+nSpYvMtCiEEK9JuikKIQodtVpd4F3D0jPUbPj9Jr8evqNsK1PUnP/18aCIVcHMJNWsWTO0tbWpXbv2a89WpaOj81buy4cuazzZqT8fs2b3dZ5EJ5KeoWbH8XscvRBM/SrGODm9O8lGQb9n3N3d6d27tzIZja+vL0FBQXz//fdoa2u/1VjeZYXp3hSmWIT4EEgyJoQodFQqFcHBwSQnF8zMdgnJ6fx4MITA4HhlW43y5nxcvyhxUY+Ji8rcZmJigr29fZ7OkZaWxvHjx2nUqFG27Y0bN85Tedra2gV+X17Vm9yXd4FKpaKuqyPuzkXYdvQuW4/cISUtg+cvUtjln8L1kAAGfVSNiiWt/rswDXsb75mxY8diamrKggULAFi8eDGBgYF89913GBoaAqCvr0/x4sULLIZ3XWH5bEs9CfH2STImhCiUkpOTC2QNq/DoZH48HE5UXBqQOT6shbs1dZzNyUhPISn9r33zuhB8UlISvr6+HDt2jIkTJ9K5c+f8CB0ouPvyOvJ6X941Bno6dGtWkcbuJfD77Tqnr2SO97sXGovvwpM0rFmcXq2cscqncYUF5W28Z/r164etrS2TJ08mLS2NQ4cO0b17d5YsWYKlpWWBnvt9URg+20KIt0/GjAkhPhiBwS9YtjtUScSM9bXo26wo3pUt8q1bTmxsLAMHDuTYsWMAzJ07l2fPnuVL2UIz7KyMGNvLna/71MDO/K/vMI9cCGbQrENsPXKH1LT0fynhw9CuXTuWLl2KsbExkLnoac+ePQkLC9NwZEIIUXhJMiaEeO+p1WpOXoth/aFwUtIyx/sUtdJjcNtilHUwzLfzPHnyhN69e3Pp0iUgc7HcRYsWYW1tnW/nEJpTpYwVA1sUoU8rJ0wMdQFITE5n7Z4bDJl7NNuyCB8qLy8v1q1bh52dHQAPHz7kq6++kkk9hBDiJSQZE0K819LS1Ww/84S955+R9ThYpZQxA1s5Ymmim2/nCQoK4tNPP+XOncwJQaysrPDz88PT0zPfziE0T1tLRfNaJVg+thEtvEopU+E/fvqCKavOMWXVOUKfxP97Ie85Jycn1q9fT8mSJTE2Nmby5MkyIYQQQryEjBkTQry3XiSls+FoOA/C/xqH0bCaJY3cLNHKx4fDGzdu8PnnnxMVlTnzh6OjIytWrJBFcN9j5ib6fNGpGs29SrFyx1Wu38/sinrhZgR/3I6kXb2yfNy4AkYG+Zfwv0scHR1Zt24dwcHBVKpUSdPhCCFEoSUtY0KI91JkTApLd4coiZiOtopP6tnRpLpVviZi/v7+9O3bV0nEypcvr7QKiPdfGUdzZn5RB98eNbA2z5zIIy1dzdajdxk06zBHLjwiI+PD7KJnbW2Nq6trtm3p6emcOnVKMwEJIUQhJMmYEOK9c/dxAsv2/DVRh4mhNv1bFMW1rGm+niclJYWvv/6aFy8yF4yuXr06a9euVcbLiA+DSqWinlsxlo9pxCeNK6Crk/mrNToumfmbLjN60UluP4rWcJSap1arGTJkCPXq1WPp0qWaDkcIIQoFScaEEO+VC3diWXMgjKSUDAAcrPQY3LoYJWzzf/pxPT09FixYgLGxMT4+PqxYsQIzM7N8P494Nxjo69CjRSWWjm6IV1UHZfutR9GMXHCChb9cJjruw526fNeuXSxfvhy1Ws3gwYOZPHmyTOwhhPjgSTImhHgvqNVqDl6KYuupJ2T1CnMuYcTAlo5YmBTc8NhKlSrx008/MX/+fAwMCvd6U+LtsLc25n+9PZg6wIviRUyU7QcDHjFo1mF2HL9LalqGBiPUjLZt2zJu3Djl/1OmTGHo0KFkZHx490IIIbJIMiaEeOelpav59WQkR/78qytY7UrmdG9gj75u/v2YU6vVHDx4MMfDY7ly5dDRkfmQRHZuTnYsHNmA/u2qYGyQ+f5ISEpj9a7rDJ13lEu3IjUc4dulUqmYMWMG3333nbJtyZIl9O3bl7S0NA1GJoQQmiPJmBDinZaYnM7ag2Fcvpc5nbgKaOVhTZtaNmhp5d9EHWq1mrlz5zJixAimT58u3avEK9HR1qJtvbIsH9uYpp4llanwQ5/EM2nlWWauCyAyOkGzQb5lw4cPZ926dWhrawOwbt06unXrRkpKioYjE0KIty/PyVhsbCwnTpxQ/h8SEsKGDRuIi4vLl8CEEOK/xMSnsmJvKPfCEoHMGRO7NSiCd2WLfD1Peno6U6ZM4ccffwRg8+bNysLOQrwKC1N9hn7syndf1qdiSUtl+5krYXwx5wibD90mNS1dgxG+XT179mTz5s3o6mZO/f/rr7/SsWNHkpI+3DF1QogPU56SsXv37tGqVSsmT56sbAsODmbmzJl89NFHPH78OL/iE0KIXIU+TWbp7lAiYlIBMNbXon/zolQpZfIfR76e1NRURo0axdatW4HMrlZTp06lRo0a+Xoe8WEoV9yCOUPrMryrGxYm+gAkp6Tz476bDJl7lIuBERqO8O3p2LEjO3fuVMZa7tmzhxEjRmg4KiGEeLteORlbvHix8u+5c+dSpEgRNm3apGzz8vLi+PHjWFhYMGfOnPyNUggh/iYw+AUr94USl5jZkmBtpsug1sUoYZe/E2gkJSXRuXNndu/eDYCOjg5z5syhQ4cO+Xoe8W5QqVQYGhqiesN16lQqFQ1rlmDZ2Ea0qVuGrN60j5++YPIP55ixNoDIqA+j62KLFi3Yt28fJiYmVKhQgYkTJ2o6JCGEeKteKxkbMWIEKSkpXLp0iaFDh1KkSJFs+1hbWzNo0CDOnTuX74EKIQTA+dux/Hg4nJS0zDFbJe0M+LyVIzZmuvl6noSEBD777DN27twJZE5jP3/+fJo3b56v5xFvRkdH562N3zM0NMTZ2RlDQ8N/3e9V4zEx1GVA+6p8P8IH59JWyvazV8P4fM4Rfjl4i5TU97/roo+PD4cPH+bQoUPY29trOhwhhHirXnn6r3Xr1rF48WJCQkJQqVQkJibmul9aWhqpqan5FqAQQkDmA+6xKzEcuBSlbKtSypiP69opi+zml7i4OIYMGaKMCzM0NGThwoXUqlUrX88j3py2tjYqlYrg4GCSk5M1HQ76+voUL178tY4pXdScWYO9OXoxhDW7rxMTl0xKajo//R7I4QvBDGhflZqVivx3Qe8wDw+PHNvi4uJ48eKFJGhCiPfaKydjnp6eeHp6AuDu7s6SJUvw8PDAyuqvb/NiYmJYvnx5rj9UhRAirzIy1OwOeMrZm7HKtjqVzWnpbo3WG3YZy82MGTOURMzc3JyVK1fi7Oyc7+cR+Sc5Ofmdnvwhs+ticTwr27PxQCC7Tz0gI0NN2NMXTFl1Ds/K9vRvX5UiVkaaDvWtSExMpG3btoSEhHD48GFKlCih6ZCEEKJA5GlhnJEjR/Lxxx/TqFEjXF1dsbKyIjo6mj/++AM9PT2+/fbb/I5TCPGBSktXs/lEBFcfvlC2tahpRb2qlv9y1JsZOXIk165dIzY2loMHD2JmZvZOP+iLd4exoS7921WliUdJlm+7wvX7zwDwvx7O5VuRdGpUgY8alENPV1vDkRasL7/8kmPHjgFQr149jh49SunSpTUblBBCFIA89e0pXbo0u3fvpkuXLiQkJCgPLR9//DE7duyQH5hCiHyRlJLB2oNhSiKmpYLOde0KNBEDsLGxYfXq1WzevJnq1asX6LmEyE0pBzNmflGHkd1rYGWWOetiSloGG/cHMnjuEc7fCNdwhAXr66+/pkKFCgAEBQVRv3597t69q+GohBAi/+WpZQygSJEijBkzJj9jEUIIRWxCKiv3hRIWlbkQrK6Oim4+RahY3Djfz/Xs2TMMDQ0xMvqrC5idnR3m5ub5fi4hXpVKpcKnejE8nIuw6cAtdp28T0aGmvBnCUxd7Y9nZXsGdKiKneX713WxePHiHD9+nEaNGnHjxg2Cg4Px8fHhyJEjSpImhBDvgzyPeg8ICOCPP/4AICwsjEGDBtGmTRuWLFmSX7EJIT5Qj5/Gs3D7AyURM9TXol+zogWSiD158oS+ffsyZMiQl05MJIQmGRno8lnbKiwc6UPVsjbKdv/r4Xwx5wjbjt4lLT1DgxEWDHt7e44ePUqVKlUACA0NxcfHh8DAQA1HJoQQ+eeVk7GnT58q/96xYwe9evXi4MGDQGZ3An9/f0qWLMny5ctZuXJl/kcqhPgg3A2JYcyiUzyLzZyV1dxYh0EtHfN9DTGAiIgI+vbty/379zl//jzTpk3L93MIkV9K2psx/fPajOpeA0vTvxaMXrP7Ol99d4wbD55pOML8Z2dnx5EjR3BxcQEyv/z18fHhxo0bGo5MCCHyxysnY507d1a+jVq7di0dOnTA19eXJ0+ecObMGYYMGcLixYsZPnw4W7dufeUAMjIyWLhwIXXr1sXV1ZX+/fsTHBz80v2jo6MZOXIk7u7ueHh4MGXKlBzfZu/bt4+WLVvi4uJC+/btOXv27EvL27VrF05OToSEhLxyzEKIgnHl7hP+t/QUMfGZU5QXsdDl81aO2Fno5fu5wsPD6dOnDw8fPgTA0dGRzz//PN/PI0R+UqlU1K9ejGVjGtG6TmmyJhMNCo9jzOJTLNr8B7EvUjQbZD6ztbXlyJEjuLq6Aplfovj4+HDnzh3NBiaEEPnglZMxBwcHunbtSmRkJPfv36d9+/YAHD9+HLVaTaNGjQCoWrUqYWFhrxzA0qVL2bhxI9988w0///wzGRkZ9OvXj5SU3H+ZDBs2jKCgINauXcuCBQs4fvw4kydPVl4/d+4cvr6+dOnShe3bt+Pl5cWAAQO4d+9ejrJCQ0OZOnXqK8cqhCg4AdfDmfzDORKTMxe5LW1vxMCWjpgb53lo60uFhobSu3dv5YufYsWKsWbNGooVK5bv5xKiIBgb6jKwowvfflmPcsX+Gtt4wD+Iz2cf5lDAo7e2GPbbYG1tzeHDh6lRowYArq6ur72emxBCFEavnIxt3LiRpUuXoqOjg5mZGfHx8QCcPHmSokWLUqpUKQAePXqEpeWrzXSWkpKCn58fw4YNw8fHh4oVKzJ//nzCw8M5cOBAjv0vX75MQEAAs2fPpnLlynh5eTF16lR27txJREQEAD/88AONGzemZ8+elC1bljFjxlC5cmXWrVuXrayMjAx8fX2pXLnyq94CIUQBOXYxmOlrA0hNyxz34u5chEFtSmKon//TdwcHB9OnTx9CQ0MBKFmyJGvWrMHBwSHfzyVEQStf3JJ5X9ZnYIeqGOpnfnER+yKFBb9cZtzS0zwKj/2PEt4dVlZWHDp0iK+++oqdO3diYJD/XZeFEOJte60JPLy8vLCyssLT05PFixezcuVKDh8+TMuWLQHYv38/CxYsoE6dOq9UXmBgIC9evMDLy0vZZmZmhrOzM+fPn8+x/4ULF7C1taVs2bLKNg8PD1QqFRcvXiQjI4NLly5lKw8yF6z+Z3nLly8nNTWVgQMHvvL1CyHy357TD/hu0yUyMjK/xa/vVoz/9fZATyfP8wu91KNHj+jTp4/Sel+6dGn8/Pywt7fP93MJ8bZoa6lo7V2GZWMaUtfVUdl+/f4zhn17jN3nIkhJez8m+LCwsGD+/PkYGhpm2/4+tQIKIT4seXraGT9+PJaWlixevBgvLy8loZk5cyZFixZl5MiRr1ROeHjmOin//Ebazs5Oee3vIiIicuyrp6eHhYUFYWFhxMbGkpCQkOPB6p/lXblyBT8/P+bOnYu29vu9cKYQhZVarebXw7dZvu0KWc9RLbxKMaJbdXS08z8RCwkJoU+fPkoretmyZfHz88POzi7fzyWEJlibGzL605pMGeCFg3XmzKPpGWoOX37K99uDCQx+8R8lvJtCQ0Nxd3fP9UtcIYQo7PI0GMPKyorVq1fn2L5x40aKFi36yuVkTbyhp5d9cL6+vj7Pnz/Pdf9/7pu1f3JyMklJSS8tLzk5c0KAhIQERo0axahRoyhVqpTyYPam1Go1CQkJ+VLWuyyrTmWK8MKpsNSPWq1m44G77Dr1UNnWrm4pujYpR3JyUo5vvfODjY0NZcuWJTIykvLly/PDDz9gbW2d7+cRAjI/Y5pqralY3IQ5gz3ZefIhO048JC09g+j4NNYdCqdyCWNae9pgYZL/YzFfRX7fl/DwcJo1a8bdu3dp3bo1ixYtUoZNvCtUKlWB/Mx7EwXx/i0sv39E7qR+8pdarUaVNcPSf3ijn8YnTpwgICCA2NhYLC0tqVmz5mslY1n9vVNSUrL1/U5OTs71B5OBgUGuE3skJydjZGSEvr6+Ut4/X88qb9q0aZQuXZouXbq8cpyvIjU1lZs3b+Zrme+yrBnqROGkyfrJyFCz50IMF+/+9S19Y1cz3IqnERgYiKGhIc7Ozvl+XgMDAxYuXMiCBQsYMGDAK49tFSIvHjx4oPGHGvcyhjTy8OG7n/y5E5r5ebv+6AV3HifQ2M2K2s7maGu92sNCfsnv+5KYmIiFhQUA8fHxDBkyBJVKpaxN9i4oqJ95b6Ig37/yfFC4Sf3kn9wakHKTp2QsJSWFL774glOnTqGtrY2lpSXR0dGsXLmSWrVqsWLFilcKIKvLYWRkJCVKlFC2R0ZG4uTklGN/e3t7Dh06lCOWmJgY7OzssLCwwMjIiMjIyGz7REZGUqRIEQC2bt2Knp4ebm5uAKSnZ87c1rp1awYNGsSgQYNe4078RVdXl3LlyuXp2PdJYmIiDx8+pFSpUoXumz6h+fpJS8tg8dZrSiKmUsFnbSrRxP2vWQxf9ZukvDAwMGDMmDEFVr4QWcqUKaPxcUwqlQoDAwM+b1MS/xtP2RPwjPikdFLS1Ow9/4zL9+Jo72VbIGv4vUzp0qXz/b7s27ePzp07c+zYMV68eMHQoUPZvXs3NWvWzNfzFJSC/JmXVwVRT5r+/SP+ndRP/rp79+4r75unZGzRokVcvHiROXPm0KpVK7S1tUlLS2P37t1MmTKFZcuW8eWXX/5nORUrVsTExAR/f38lGYuNjeXGjRv06NEjx/7u7u7MmzePoKAgSpYsCUBAQAAANWrUQKVSUb16dQICAujcubNynL+/v/JD+Z+zNP7555/4+vqycuVKKlSokJfbAWT+MDUyMsrz8e8bQ0NDuR+FmCbqJykljfkbL3DhZmbXYG0tFcO7Vqd+9YKZTj4kJITJkyczbdo0maBDvDU6Ojqo1epCNdOfSqXCtawpTsWM2H8pioDAWNRAWFQKy/eE4u5kRvMaVgUye+k/FcRDnpGREXv27KFFixacOHGCuLg42rZty6FDh96ZhKywKciHcXk+KNykfvLH63zJkqdkbPfu3QwZMoS2bdv+VZCODu3bt+fZs2ds2rTplZIxPT09evTowbx587CyssLR0ZG5c+dib29P06ZNSU9PJyoqClNTUwwMDKhWrRrVq1dn+PDhTJ48mYSEBCZOnEj79u2Vlq8+ffowYMAAnJ2dqVevHlu3buXmzZtMnz4dQEnismRN7FG0aFGlq4MQIn8lJKUydbU/1+8/A0BPR4sxvdzxcC6YJCk0NJTPPvuMx48f07dvX5kxUbw12traqFQqgoODlbHKmmJiYpLtfW+or017L1uqlzNlx5knhEWloAYCbsVyI+gFLT2scS1jUihbav6LkZERW7ZsoUWLFly8eJHnz5/TpEkTDh8+TPXq1TUdnhBCvFSepiyLiop6af9mZ2fn15oUY9iwYXTq1IkJEybQtWtXtLW1Wb16Nbq6uoSFheHt7c3evXuBzCxz8eLFFCtWjF69evHVV19Rr169bIs+e3t7M2PGDDZt2kSHDh04d+4cy5cvzzYdvhDi7YlLSGH88jNKImaor8PkAV4Flog9fvxYScQgswuxjo5mJisQH66sSaU0+Sc1NTXX2ErYGjC4TTFaeVijp5OZeMUnpbP5RCSrfn/Mk+c5x2a/C4yNjfn+++/x9vYGICYmhsaNG3P58mUNRyaEEC+XpyeUEiVKcPHixRzreQGcP3/+tRZP1dbWxtfXF19f3xyvFStWjFu3bmXbZm1tzcKFC/+1zPbt29O+fftXOr+np2eOcwgh8sfz+GQmLD/Dw7DMhWdNjfSYMqAW5YsXzOQZYWFh9O3bV1nQuXTp0qxevRobG5sCOZ8Q7yptLRXelS2oWsqE3f5PuRaUOY7zfngSC3YEU7+qJT4uFugWwHp/BcnQ0JCtW7fSqVMnTp48SXR0NL/88osyTlwIIQqbPCVjXbp0YdasWRgYGNCqVStsbGx4+vQpu3fv5ocffmDIkCH5HacQ4h0THZvE+OVnCI6IA8DSVJ9vBtWmpL1ZgZwvPDw8WyJWqlQpScSE+A/mxjp0b2hPYPALdp17SnR8GukZcOTPaP64H0c7L1sqOL5b40dMTEzYu3cvLVq0wNXVlZkzZ2o6JCGEeKk8JWNdu3blxo0bzJs3j2+//VbZrlar6dChAwMGDMi3AIUQ755nzxMZv+w0oU8yv223Njdg+ud1cLQ1KZDzZSViISEhQObY0NWrV2Nra1sg5xPifVOxuDFlHAw5+mc0J67GkKGGqLg01hwIw6W0Ca08rDEzene6+5qYmHDgwAEMDAzeyTFwQogPR55+smppaTF9+nT69u1LQEAAz58/x9zcHA8PDxmbJcQHLjIqgfHLTxP+LHMRdDtLQ6Z/Xgd7a+MCOV9ERAT9+vUjODgYyOxGvXr1auzs7ArkfEK8r/R0tGhWwxrXMqbsOPuEhxFJAFx5EM+tkASaVreiVkUztN7y2mR5lduMgJcuXUJPT++dWodMCPF+y1MyNm7cOL744gvKli2bI/m6f/8+c+bMYfny5fkSoBDi3RH29AXjl5/mSXTmYqEO1sZMG1QbO6uC6+a0c+dOgoKCAChevDirV69WZlcVQry+IpZ6DGhRlEt349h7/hkJyRkkp2bwm/9TLt2Lo4OXLY42+poO87WdP3+epk2boqury9GjR6lcubKmQxJCiFdPxrJmJgPYsWMHjRs3Rls755okJ06c4MyZM/kTnRDinRESGceE5Wd49jzz23RHWxOmf14ba/OCXTyyf//+REVFcfz4cZnCXoh8olKpqFHejIrFjfn9wjMu3Mkc+xn6NJklu0OoVdGcptUtMdAr+LXJ8svXX39NTEwMAA0bNuTo0aMvnRlaCCHelldOxqZMmcKJEyeU/79skg61Wk2dOnXePDIhxDsjKDyWCcvPEBOXua5SCXtTpg2sjaVZwS98q1KpGDNmDIMGDZK1AoXIZ8YG2nzkbUeN8plrk0XEpKJWw9mbz7n2MJ42njZUKWX8TozL+vnnn2natCnnz58nMjJSScgqVaqk6dCEEB+wV07Gpk6dypkzZ1Cr1fzvf//j888/p0SJEtn20dLSwszMDE9Pz3wPVAhROD14/JwJy88Q+yJzbaIyRc2ZOtALc5OC6cb09OlTnjx5ku0BSqVSSSImRAEqVcSQIW2Lc/p6DIf/iCY1XU1cYjobj0VQwdGQtrVssTbT1XSY/8rCwoIDBw7QpEkTLly4QEREBA0aNODYsWNUrFhR0+EJIT5Qr5yMFSlShA4dOgCZDz4+Pj5YWhbMWkFCiHfDneBoJq44S3xi5uKy5YpbMHWAF6ZGegVyvmfPntGvXz8iIyNZuXKlDMIX4i3S0VZR38USl9Im7PJ/SmBw5iQ9t0MTmb/9EXWrWODjYom+buFdmywrIWvcuDGXLl3KlpA5OTlpOjwhxAcoTz8xO3ToQHx8PPfu3QMgLi6Ob775hkGDBrFjx478jE8IUUgFBkUxYfkZJRGrWNKSaQNrF1giFhUVRb9+/bh37x5xcXFMnDiRjIyMAjmXEOLlLE116dnInh4Ni2BulDlmLD0Djl2J4bttj/jjXhxqtVrDUb6cpaUlBw8exNXVFchcGqNBgwbcvn1bs4EJIT5IeUrGjh8/TosWLdiyZQsAEydO5OeffyYiIoJx48bx66+/5muQQojC5VZQFJNWniUhKQ2AKmWtmTLAC2PDgummFB0dTb9+/bh79y6Q2VK/YMECtLQK7zfwQrzPVCoVlUuaMLxjCepXtUD7/z+KsQnp/HIikhV7H/P4WbJmg/wXVlZWHDp0iGrVqgEQFhZGw4YNiYuL03BkQogPTZ6eZJYtW4a3tzeDBw8mNjaWgwcPMmDAALZv386AAQNYv359fscphCgkbgVFMfFviVi18jZM6lcLI4OCScRiYmLo168fd+7cAcDOzg4/Pz+KFy9eIOcTQrw6fV0tmte05qv2xalY/K8lLIIik1i8K4Ttp58Qn5SuwQhfztramkOHDuHi4gLA+PHjMTU11XBUQogPTZ6SscDAQHr16oWJiQknTpwgPT2dZs2aAVCnTh1lzR8hxPvl9qPobImYSzkbJvT1xEAvT0sW/qfnz5/Tv39/pftQViL2z8mDhBCaZWOuR6/GDvRuYo/N/0/koQYCbsfy7dZHnLjyjLT0wtet2MbGhsOHD7Np0yY+//xzTYcjhPgA5SkZ09fXJy0t82Hs1KlTWFtbKzMRPX36FDMzs/yLUAiRb1QqFYaGhnmahvr2o2gmrjiTLRH7+rOCT8QCAwMBsLW1ZfXq1ZQsWbJAzieEeHNOxYz5sn1xWtS0Rl838+dMUkoG20+HM2TuUc5eDSt048lsbGzo0qVLju0pKSkaiOb99Sa/f4R4n+UpGatevTp+fn7s2bOH/fv307RpUwCuXbvG4sWLqV69er4GKcT7SBMPJIaGhjg7O2NomH0h5v+KJSsRe/GWErHU1FT69OnDzZs3gcyHpdWrV1OqVKkCOZ8QIv/oaKuoV9WCkR1LUKPcX93+Qp/EM2NtAGMWn+LmgygNRvjffv31VypXrvzB9fTR0dEpsN9NL/v9828KW+IuREHI05PU//73PwYMGMDIkSMpV66c0rQ/cOBADA0NGTVqVL4GKcT7SKVSERwcTHKyZge56+vr/+v4q38mYlXL2vB1AXZNBNDV1aVTp05cvXoVa2trVq9eTenSpQvsfEKI/GdqpEOnunZ4VDTj9wvRPAjPnAr/5sMoRi8+iVdVB3q2rEQxu8I1Tuu3336ja9eupKen4+Pjw/Hjxz+YrtHa2trvzO8mId4XeXqaKl68OHv37uXZs2fY2Ngo25csWYKzszN6egUztbUQ75vk5GSSkpI0HcZLZa4jlj0Rm/iZJwb6BZeIZenWrRva2tpUqVKFMmXKFPj5hBAFo4StAUPblyIq2YS1e24QEhkPwNmrYfhfD6eZZ0m6NHXCysxAw5FmqlmzJuXKlePWrVs8fPhQWYfsQ0oMCvvvJiHeJ3meF1qlUhESEsIvv/xCVFQU8fHxWFtbSyImxHvibnAMX684+9YSsdy6o7Rr146yZcsWyPmEEG+PSqXCs4oDi0c1YEjnalia6gOQkaFm39mH9J9+kFU7rxEdp/kEwMHBgSNHjlC+fHkA7t+/T4MGDQgJCdFwZEKI91GekrHk5GT69etHly5dmDx5MmFhYVy9epWmTZvy9ddfK5N7XL58mVOnTuVrwEKIgncvJIYJK87w4v8XdK5S1rpAE7G4uDgaNmzI5s2bC6R8IUThoK2tRbNapVg5rjHdm1fEUD9z0eiUtAx2nrhHv+mH8PvtOjFxmu0iV7RoUY4ePUq5cuUAuHfvHg0bNiQ0NFSjcQkh3j95SsYWLVrE3bt3WbdunfJttrOzs7LW2IoVKwBISkpi5syZ+RetEKLABYXFZraI/X8iVrmMNZM+q1VgiVh8fDytWrXi2LFjdOvWTRaNF+IDYKCvQ5cmTqwc14T29cuip5P5OJKSms72Y3fpN+Mgfr9d59nzRI3F6OjoyNGjR5XW+Tt37tCwYUPCwsI0FpMQ4v2Tp2Rs7969fP7559SsWVPZZm5uzvDhwxk8eDCrV68mKSmJq1evEhERkW/BCiEKVuiTeCasOENcQuaUzpVKWTGpX8ElYi9evKB169acPHkSADMzM+WbaCHE+8/CVJ/P2lZh1fgmtK1XBt3/T8qSU/4/KZt+iIW/XCYkMk4j8RUrVoyjR48q41Zv375NgwYNCA8P10g8Qoj3T56esCIjI186s1m1atVISEigZcuWREdHM3jw4DcKUAjxdoQ/e8H4ZaeV7kHli1swuX8tDAsoEUtISKBNmzYcP34cAAsLCw4ePIibm1uBnE8IUXhZmhnQv11VOvqUY8uRO+w/F0RqWgZp6RkcDHjEofOPqFXFgY4NylGxpNVbja148eIcPXoUHx8fHjx4QFBQELdu3cLe3v6txiGEeD/l6SmraNGiBAUFUaNGjRyvnTx5khIlSnDgwIE3Dk4I8XY8iU5k/PIzPHueOXi+dFEzpgzwwshAt0DOl5iYSLt27Th69CiQ2bJ+4MCBXH+mCCE+HNbmhgzs4MLHjSqw6+R99p15wIukNNTqzNkXz14No0IJC1rVKY13NUf0dLXfSlwlSpTg6NGjtGzZkoULF1K/fv23cl4hxPsvT8lYp06dWL58udKdKDk5mXv37rFlyxbWrVvH0KFD8zVIIUTBef4ilTm/niYyKnMNoOJFTPlmYG1MjQpmZtSkpCTat2/PoUOHgMyuiQcOHMDd3b1AzieEePdYmhnQq5UznRuV5/ezD9l54h5RsZmt9rcfxXD70WVW77pOU8+StPAqhZ2VUYHHVLJkSa5cuYK29ttJAIUQH4Y8JWP9+/cnJCSEbt26AdC9e3cgc2rqtm3bMnDgwPyLUAhRYOKT0ln1ewgR0ZkPOQ42xkwbVBtzE/0COV9SUhIdOnRQWs5NTU3Zv38/Hh4eBXI+IcS7zchAl44NytOmbhmOXQxh96kH3H/8HIDYFylsOXKHbUfv4Opkh3fVIpiqci6RkZ9yS8RWrFjBRx99lG3dVSGEeFV5SsZUKhVTp06lb9++nDt3jpiYGExNTfHw8FDW5RBCFG4Jyen47X9MRHTmZB12VkZMH1SnQBdevXbtmjJGzMTEhN9//51atWoV2PmEEO8HXR1tmniWpLFHCQIfRrP79H3OXHlMWrqaDDVcCozkUmAk+roqvO9Dc68yOJW0RKVSFVhMarWaKVOmMGXKFJYuXcqRI0ewtrYusPMJId5Pr52M7du3D4AWLVpQokQJ+vbtq/yw8/Pzo02bNnz11Vf5GqQQIn8lpaSz5kAYYVGZiZi1uQHTB9XG1tKwQM9bs2ZNdu/eTdeuXdm6dSu1a9cu0PMJId4vKpWKSqWtqFTaiujYJPb7B3HQP4jI6Mwp8JNT1Ry+EMrhC6EUsTKitktRars4UKG4JVpa+ZuYRUVFsWrVKgCuXLlC48aNOXz4MFZWb3eCESHEu+2Vp7ZPT09n8ODBjBgxghMnTgCZ3wo9fvyY8uXL4+Hhgb29PatWreLRo0cFFrAQ4s0kp2aw9mA4IU8zuyaaGuow/fM62Fsbv5XzN2zYkPv37+Pt7f1WzieEeD9ZmhnQpYkTP/yvCTM+r0N9t6Lo6vyVcEVEJbD92F18F56k77QDrNh+hSt3n5CalpEv57e2tubo0aM4ODgA8Mcff9C4cWOioqLypXwhxIfhlVvGNm/ezIkTJ1iwYAFNmzbN9trQoUOpXLkySUlJNGvWjJ9//pnRo0fne7BCiDeTmpbB+kNhBEVmzppopK/F521K4mhrUjDnS01l+/btfPzxx9m2Gxu/ncRPCPH+09JSUbWcDWWLGlG7HDxPt+TMtUiu3H1KRkbmGLJnz5PYfeoBu089wFBfG5dytrg52VHdyQ4Hm7z/PCpfvrwy7X14eDiXL1+madOmHDx4EEtLy/y6RCHEe+yVk7GdO3fyySef5EjE/s7AwICPPvqIw4cP50twQoj8k5au5qcjEdwPz0zEDPS06Nu0KA7WBTNGLDU1VemOeP36dSZPnlyg4zeEEEJfV4v6LkVp8X/t3Xd8TfcbwPHPzd6JIAkSJFbESkISsWoVVW3TYba1V2nVaIxStYsqNavUqtaqEa2Wqj0qsQliBCHIIlN2cs/vj/tz9TZRQZIbPO/XKy/uOd/zPc+5x5H73O9qXJXk1CyOno/i8NkoTl+OIydX0yKWnplLyPloQs5rFm52Km1BbbcyeLja4+FWmvJlLJ/o/6oaNWpoE7KYmBhOnDihTcjs7OyK4jKFEC+QAidj4eHhDBo06LHlvL29WbFixTMFJYQoXGq1woYDMVy+rZm+3sRIRa9Xy1GhjClGRkYoilKoiVJOTg7vv/8+mzZtAmDmzJl8+OGH2uUwhBCiqNlYmtDatxKtfSuRmp7NsbAYTlyM4fSlOBLvZ2rLRd9LI/qeZmFpADsrU2q62lO9YimqOttSxdnusUt9uLu7s2fPHlq0aEFsbCzHjx+nbdu27Ny5E1tb2yK9TiHE863AyVhOTg7m5rqD+w0NDdm5c6fOKvSGhoYYGBR4KBpqtZoFCxbwyy+/kJKSgo+PD+PHj8fFxSXf8gkJCUyZMoUDBw6gUql4/fXXGTlypE5s27dvZ/78+dy6dQs3NzdGjRqFv7+/dv/58+eZOXMmZ8+exdTUlDZt2hAYGIi1tXWB4xbieaEoCkFH4giNSAXAyFBFj1fLUdFB0yJmaGiISqUiMjKSzMzM/6qqQLKzsxkxYoR2sh8TExMWLVoEaL7UeRwrKyud/1OEEOJZWZob09zbmebezqjVCtfvJHHyUiwnL8VyMSJB22oGkHg/U7vA9AMO9hZUdbbFtbwtFR2tcXG0plwZS4wMH37e8fDw0CZkcXFxHD16lJ49e7Jly5ZivVYhxPOlwMmYo6Mj169fz7Mwa8WKFXVeX758mfLlyxc4gEWLFrFmzRqmT5+Ok5MTX3/9NX379uW3337DxCTvN1FDhgwhPT2dlStXkpyczNixY0lLS2PGjBkABAcHExgYyMiRI2ncuDEbN26kf//+BAUFUaVKFe7evUuvXr1o3bo1EyZMICEhgS+++ILRo0ezcOHCAsctxPNix/F4jl1OAcBABe+3cMTNKe+siZmZmWRkZDzTubKzsxk1ahR//fUXAMbGxsydOxcfH58C121qWjRrnAkhBGjGmFVxtqOKsx0dW1UnKzuXK5GJXLh+jwvX4wm7fo/UjBydY2Lj04iNT+Pvsw8TNCNDFRXKWuHiaE1FR2ucHa1xdnDmjx1/8lrbNpiYmGg/mwghxKMUOBlr0qQJ69ev57333ntky1d2djYbN26kRYsWBaozKyuL5cuX89lnn9G8eXMA5syZQ9OmTdm5cycdOnTQKX/q1CmOHj3KH3/8QZUqVQCYNGkSffv2Zfjw4Tg6OrJ06VJat25N9+7dARg1ahSnTp1i1apVTJo0idu3b9OkSRMmTZqEkZERrq6udOrUiTlz5hT0rRDiubHvbAIHziUCoAI6NXPA3aVoJs/Izs5m5MiR7Nq1C9C0iM2dO1dmTRRClGgmxobUcitNLTfNGmFqtUJkTArhtxK5ejuJ8MhErt1JIjMrV+e4nFyFG9Ep3IhOyVNno06TcXYsxZ5zGVyMuYpzWWsqOFhR1s680KfYF0I83wqcjD0Y/zF06FAmTpyYZ5agtLQ0xo0bR1RUFF27di1QnRcvXiQ1NVWnC6GNjQ0eHh4cO3YsTzJ2/PhxypYtq03EAHx9fVGpVJw4cYJ27dpx8uRJRo8erXOcn58fO3fuBKBevXrMnj1bu+/q1ats3bqVxo0bF+yNEOI5EXIxiT9PPJxi+S3/MtRzK5quuNnZ2Xz22Wfs2bMH0CRi8+bNk+dKCPHcMTBQUamcDZXK2dDq/52BctUKd+LucyM6mcjoFG7GpBAZk8LtuPvk5Cp56lCbleNmEtw8fP3hNnUuRuTiUr40FRysqFDWCmcHK8qXtcK5iGa0FUKUfAVOxtzc3Jg2bRqff/45rVq1wt/fn8qVKwNw+/ZtDh06RE5ODjNnztSuufE40dGamYz+Xd7BwUG7759iYmLylDUxMcHOzo6oqCiSk5NJS0vLM97kUfW1bduWiIgIKlSowIIFCwoU86MoikJaWtoz1fEiSE9P1/lT5E+lUuUZg1mYTl9LYeuRu9rXbevb4+dedIPIv/rqK20iZmpqyrx582RBZyFEHunp6ShK3uSlsOr+55+FrbS1IaWtS+Fd7eGX0Tm5amLj04mMvc+du2lE3Uvlzt007txNJTX9YVdHtTqXU3/MJjM1Ad+3v8i3Nc3KzJAytsaUsTGmjK0xZW1MKGNrjL21MUaGL29rWlH+mxEPyee3wvUkE6MVOBkDaN++Pe7u7ixdupQ9e/Zop7A3NzenZcuWDBgwgOrVqxe4vgc3/N9jw0xNTUlKSsq3fH7jyExNTXXGu+RXX34TE8yaNYv09HS+/vprunfvztatW596/aPs7GzCwsKe6tgXUUREhL5DKNHMzc3x8PAokrovRqbyy4FYHvzqalbbjuZ1i3a9m549e7J//36Sk5OZP38+DRs2LNLzCSGeT9evXy/yD3v6+P1jYwA2DuDuYAhYoyhWpGWquZeSw93kHJYumE7U5cMAHN0yCZ+ALzA2tdCp435GLvczcomI0R1fa6CCMrbGuJQxw7msKS5lzHAsZfLSJGjF8W9GPCSf3wpPfjlLfp4oGQNNC9lXX30FQHJyMmq1+qnX0TAz08zmlpWVpf07aCYSyK/VwMzMjKysrDzbMzMzsbCw0A78/3eZR9VXp04dABYsWMArr7zCX3/9RUBAwFNdi7GxsUzbjSZhjoiIoHLlykXa8vO8K6r1tq5Fp/Pz3hj+v84pvtVtaNfAvkjO9U8VK1Zk2bJlxMXF5ZnkRwghHnB1dS3SlrGS+vvHo8JYOnQ4QmJiIvG3w4g9Mptpc5aTnGlE1L00YuIzuBGVSHJaTp5j1QrEJmYTm5jNiXBNi5qRoYry9ia4lTOnSjlzKjmYYWxU8JmsnydF+W9GPFSSn5/nUUFmj37giZOxf7KxsXmWw7VdDmNjY3VmZYyNjaVGjRp5yjs5OWknB3ggKyuLxMREHBwcsLOzw8LCgtjYWJ0ysbGxODo6AnDt2jVu3rypnTAENDNF2tnZERMT89TXolKpsLCweHzBl4S5ubm8H8Xs9t1MftwVpR2/UNfVirf8yxRJ4peZmYmBgQHGxsbabZUrV9Z2XRZCiPwUx4e8kvj7p3HjxuzZs4fWrVsTHx/PqZPH+WJEb3bu3Kkdgx8eHk5ichp3k7O4m5RNXHK25s+kLGISsrRfsoFm8pCbcZncjMtk39lEjAxVVCxrSpVyFri7WFDO3qTIvvQrbpIYFK+S+Pw8j57k+dPr1yju7u5YWVkREhKi3ZacnMyFCxfy/Xbdx8eH6Ohobty4od129OhRAOrXr49KpcLb21u77YGQkBAaNGgAwN9//82QIUNITk7W7r958yYJCQk6E4MI8TyJTcxixc47ZGZrfltXr2BBx6YORTJrV0ZGBkOGDGHUqFFkZ2cXev1CCPEi8vLyYu/evZQpUwbQTErWqlUr7t27py1jZmKAcxkzPKtY86qXPV2bOzLkLRcmfODKR69XoINfaTyrWFHaxlin7pxchWvRGfx1Kp75v95i5sabbAu5y/XodNRqaVUSoiR7ppaxZ2ViYsIHH3zArFmzsLe3p0KFCnz99dc4OTnRpk0bcnNziY+Px9raGjMzM+rVq4e3tzfDhg1jwoQJpKWlMX78eAICArQtX7169aJ///54eHjQrFkzNm3aRFhYGFOnTgWgQ4cOLFmyhMDAQD777DOSkpKYMmUKdevWLfCU/EKUJAn3s1n+5x1SMzWLllZ2NOP9lo5FMp4gPT2dIUOGEBwcDIClpSWTJ08u9PMIIcSLqG7duuzbt49WrVoRExPDqVOnaNGihXYM/qMYGxlQ0cGMig4Ph3SkpOVwNSpd+5Nw/2EXx8T7ORy+kMThC0lYmhlQq5IV3lWtqVjW9IVpMRPiRaH3DsZDhgzhvffeY9y4cXTt2hVDQ0OWLVuGsbExUVFRNGnShD/++APQNPktWLAAZ2dnevTowdChQ2nWrBkTJkzQ1tekSROmTZvG2rVrefvttwkODmbx4sXaVi87OztWrVoFQNeuXRk8eDAeHh4sW7YMQ0PDYr9+IZ5FakYuK3ZGkZSmWf+mnL0J3Vs5YVIEYwfS09P55JNPtImYhYUF77zzTqGfRwghXmS1atVi37592qEaoaGhNG/enLt37z7mSF3WFkZ4VrHm3SYOjOxYicD3KvKWfxmqljfnn50iUjPUHL2UzOLfb/PN5kj2nknId2yaEEI/9NoyBmBoaEhgYCCBgYF59jk7O3Pp0iWdbaVLl2bevHn/WWdAQMB/TsTh6urK999//1TxClFSZGarWflXFHFJmq6CpW2M6d2mHOamhf+lQlpaGp988om2C7ClpSWLFy/G09Oz0M8lhBAvOnd3d/bv30/Lli25deuWziRkT8ve2piG7rY0dLclPTOXi7fSOH8jlcu308jO0XRVvJeczc6T8ew6FU+tSpY0rGmLq6OZtJYJoUd6T8aEEE8uV63w895obt3VLNlgbW5InzblsDIv/Ec6NTWVwYMHc+LECQCsrKxYvHgx9erVK/RzCSHEy6JatWrs37+f4cOHs2LFCu7du6ddoudZmZsa4lXFGq8q1mRmqzkXcZ+T4Slci9bUr1YgNCKV0IhUnEqZ0KyOHXVdZeFpIfRBkjEhnjNqRWHjoViu3Nasu2JmYkCvNuUoZW38mCOfXFJSEoMGDeLs2bMAWFtb8/3332uXhRBCCPH03NzcCAoKAtCZyKMwmRobUL+aDfWr2ZCQks2xy8kcu5zC/QxN9/bohCw2HIhl58l4Xq2fRSfHckUShxAif3ofMyaEeDI7jt3j9NX7gGatme6tnChn/2zdW/KTkJBA3759tYmYra0tS5culURMCCGKUFJSEkOHDuX27duFXncpa2Pa1C/NqE6V6PyKAy5lH/7uSLyfwy/7bzHgq10cOndPu0yKEKJoScuYEM+RA6GJHDyfBIBKBV1eccTVqWjWYDE2NtauI2Zvb8+SJUvyXf9PCCFE4UhJSWHgwIGcO3eO8+fPs3z5clxcXAr9PEaGKjzdrKnnakVETAb7QxO5dCsNgPjkTDYdjGb3SSNaeZbCu6p1kSyTIoTQkJYxIZ4TJ8NT2H78YTeWAP+y1KpkWWTns7Ky4rvvvqNZs2asWLFCEjEhhChimZmZpKVpkqLo6Gh69uzJ9evXi+x8KpUKVydzer5ajiFvOeNZ1U67LzE1h02H45j/6y2u3kkrshiEeNlJMibEc+BiZCqbDsVqX7/qZY9vDZsiP6+trS0LFy7Ezc2tyM8lhBAvuzJlyrBs2TKqVq0KQGxsLD179swzs3RRKGdvSv8ObswZ+go1Kz6czCM6IYsf/ozix11R3EvOLvI4hHjZSDImRAl3MzaDNXtjUP+/+35Ddxta1LMr9PNcu3aNQYMGkZSUVOh1CyGEKJgHCZm7uzsA8fHx9OrVizNnzhTL+au62NH/9Ur0f6085UubaLeHRabxbVAku0/Hy3gyIQqRJGNClGCxiVms3BVF9v9/8dWpbMkbfmUKfU2Y0NBQunXrxsGDBxkwYAApKSmFWr8QQoiCs7e3Z9myZdolRFJSUujXr592rcfi4OpkzuA3nHmvSVmszTXrV+bkKuw6lcC8rZHSdVGIQiLJmBAlVFJqDst3RpGeqQagSjlzOjVzLPSB1GfPnqV58+baaZVzc3PJyckp1HMIIYR4MjY2NixZsgQ/Pz8A0tPTGTRoEAcOHCi2GAxUKupXs2HEuxVpWtuWB79+4pKy+eHPKIL+jiMzW11s8QjxIpJkTIgSKC0zl+U775CUqkmKytub8EFLJ4wMCzcRO336NF27diU+Ph6AOnXq8MMPP1CqVKlCPY8QQognZ2FhwcKFC2nevDmgmeBj586dxR6HqbEB7X3K8PGbzlT8x3T4IZeSmbc1kuvR6cUekxAvCknGhChhsnLU/LgrmthEzUBpe2sjerYph5lJ4T6uISEh9O/fX9slsUGDBixZsgRbW9tCPY8QQoinZ2pqyuzZs2nXrh0tW7ZkwoQJeoulnL0pA16vwJsNy2BspPlyMD4lh6Xb7/D70btk50grmRBPStYZE6IEyVUrrN0Xw43YDACszAzp3aY81uaF+6ju3r2bwMBAsrM1CV/r1q355ptvMDCQ72eEEKKkMTY2Zvr06eTm5mJkpN+PbgYqFf41balWwYJNh2KJiMlAAQ6dT+LSrTQ6N3OkQhnTx9YjhNCQT15ClBCKorDl7zguRmoGRZsaq+jVphylbYwL9TxBQUEMHz5cJxH77bffsLCwKNTzCCGEKDyGhoaYmJjobLt69SqrVq1CUYp/dsMyNsb0a1ee9j6ltV3o45Ky+e73WxwJS9JLTEI8j6RlTIgSYufJeE5c0XQZNDSAD1s6Ub504X+7eOLECdRqTVeSDh06MHfuXMzMzAr9PEIIIYpOZGQk/fr1Iy4ujvj4eIYOHVroM+0+joGBiqa17ajubMEvB2K5fS+TXDX8GnyX69HpvNO4LGYmhsUakxDPG0nGhCgBDp9PZN/ZRABUQOdmjlQpXzQtVV9++SXJyck4OTkxatQojI0Lt+VNCCFE0QsODiYuLg6A5cuXk5qayueff66X7uaOdiYMfL0CO47f4/AFzVqVoRGp3L6XSbfmTtJtUYj/IMmYEHp2+loK247e075+o2EZ6rhaFdn5jIyMmDVrFkZGRsX+LaoQQojC0bFjRxRFYcqUKSiKwvr160lKSmLq1Kl5ujMWByNDFR38yuDqZM7GQ7FkZKmJT8nhu99v8YZfGfzcZXIoIfIjY8aE0KOLkffZeDBW+7plvVL41yy8X1jZ2dlMmTKFK1eu6Gw3NjaWREwIIZ5znTp1YurUqRgaaroC7tixg8GDB5Oamqq3mGpVsmTIm844/781LFcNQUfusuVwHDm5Mo5MiH+TZEwIPbl8M4EVOyLJ/f9MwL7VbWjtVXjre2VkZDBs2DDWr1/PgAEDiIyMLLS6hRBClAxvvPEG8+bN0479DQ4Opm/fvtr1I/WhlLUxA9pXoLHHwy8Xj15O5ocdd0hJz9FbXEKURJKMCaEHt+PuM/GHYLL+vyZLrYqWvOVfptBaq1JSUvjoo4/Yv38/AElJSdy4caNQ6hZCiJJIpVJhbm7+Urb6N2vWjKVLl2JtbQ3AuXPn6NGjB3fu3NFbTA+6LXZq5qCdbfFGbAYLf73F7buZeotLiJJGkjEhitm9pHTGf/83yalZALg6mtH5FQcMDArnA0RMTAw9evTg+PHjAFhYWPDdd9/RpEmTQqlfCCGelJGRUZFPdW5ubo6Hhwfm5uaPLfsiTrvu6enJqlWrcHBwACAiIoIjR47oOSrwqmLNgPblsbHQdKVMSstl8R+3OX01Rc+RCVEyyAQeQhSj++nZTFgaTGxCOgDl7E35sJUTxkaF873ItWvXGDhwIFFRUQCUKlWKRYsWUbt27UKpXwghnoahoSEqlYrIyEgyM/XbKmJqaoqLi4teYygq1apVY/Xq1QwYMIC2bdvy7rvv6jskAJzLmPHxG878tCeam3GZ5OQqrD8Qy72UbFrWK/VStmYK8YAkY0IUk6zsXKYsDyEiKhkAB3sLBnRwxtQwt1DqP336NB9//DFJSZpphStUqMDixYupXLlyodQvhBDPKjMzk4yMDH2H8UIrX748a9euxdLSUt+h6LC2MKLfaxXYeiSO4/9fU3PXqQTiU3J4u1FZbVdGIV420k1RiGKQm6vm65+Oc/6aZgp7G0sTJvX3x9aycNb42rt3L/369dMmYjVr1uSnn36SREwIIV5CVlZWeVqbdu/eza+//qqniDSMDFW807gs7X1Ka7edDE9h5V9RpGcWzheTQjxvJBkToogpisKiTWcJPhcNgJmJIV/2bUiFsoW3llhsbKz222Y/Pz+WL19OmTJlCq1+IYQQz69jx44xcuRIxo4dy5IlS/Q6Zk6lUtG0th3dWjhqW8OuRqXz/R+3Sbifrbe4hNAX6aYoRBH7acdFdoZoZjI0MlTxeU9fqlcsvCnsATp37kxsbCy3bt1iypQpGBsXToubEEKI59/BgwfJytJMGjV//nzu3LnDuHHjMDLS38fAOpWtsLEwYvWuKFIz1cQkZvPdttv0fLUc5Uub6i0uIYqbtIwJUYR+PXiVDbsuA6BSwfCu9fGq4fDM9eb3rebHH3/MV199JYmYEEIIHcOGDWPo0KHa15s2bWLIkCGkpaXpLyigkoMZH3VwprSN5vdWSnouS7bf4Vp0ul7jEqI4STImRBHZf/IWS4POaV/3D6hDU68Kz1xvWloaQ4cOZefOnTrbVSoVBgbySAshhNClUqno06cP06dP17aGHTx4kJ49e3L37l29xlbaxpiPXq9AJQfNotWZ2WpW7Iwi9HqyXuMSorjIJzchisDJS7F8u+6k9nXn1tXp0MTtmeuNi4ujV69e7NmzhzFjxmjXEhNCCCEe5/XXX2fJkiXaxaHDwsJ4//33uXbtml7jsjQzpHfbctRwtgAgJ1dhxZ+R7Dp6Q69xCVEcJBkTopBdvpnAVyuPkpOr6UrYtmEl3m/n/uz1Xr5Mt27duHDhAgAmJibk5OQ8c71CCCFeHj4+Pvz444+UK1cOgDt37vDhhx9y4sQJvcZlYmTAh62c8KyimdxKUWDu+tNs3ntFr3EJUdRKRDKmVquZN28eTZs2xdPTk379+hEZGfnI8gkJCYwYMQIfHx98fX2ZOHEi6em6/Yu3b99O+/btqVu3LgEBAXlWob9y5Qr9+/fHz88Pf39/hgwZwp07d4rk+sTLIzImhQlLg8nI0kzR61+nHB+9W++ZF7Q8fPgw3bt3JzpaMyNj+fLlWb16NQ0bNnzmmIUQQrxcqlatyk8//YS7u+aLwn9/htIXQwMVHZs60MjDVrttxbYLrPjtvF5ngBSiKJWIZGzRokWsWbOGyZMns27dOtRqNX379tXO/PNvQ4YM4caNG6xcuZK5c+eyf/9+JkyYoN0fHBxMYGAgXbp0YcuWLfj7+9O/f3+uXr0KaJK5Xr16YWZmxurVq1m6dCnx8fH07duXzMzM4rhk8QK6m5jOl0uPkJKm+Xdbu0ppPnu/PoYGz5aIbdiwgcGDB5Oamqqpt3Ztfv75Z6pWrfrMMQshhHg5OTg4sHLlSpo0acK0adOoX7++vkMCwEClooNvadr7PpzsavO+cOatP01urlqPkQlRNPSejGVlZbF8+XKGDBlC8+bNcXd3Z86cOURHR+eZoADg1KlTHD16lBkzZlCrVi38/f2ZNGkSW7duJSYmBoClS5fSunVrunfvTpUqVRg1ahS1atVi1apVAOzatYu0tDRmzpxJ9erVqV27Nl9//TVXr17l5MmTec4pxOOkpGXx5dIjxCVovl10LW/DuF5+mBgbPnWdarWa2bNnM3nyZHJzNS1trVq1kjXEhBBCFApLS0sWLVpEu3btdLar1Wqys/W35pdKpeLV+mUZ9F49HnQs2XXsJjNWHyc7RxIy8WLRezJ28eJFUlNT8ff3126zsbHBw8ODY8eO5Sl//PhxypYtS5UqVbTbfH19UalUnDhxArVazcmTJ3XqA81CuA/q8/f3Z9GiRZiZmWn3P5iFLjlZZu8RTyYjK4fJy0K4GZ0CgFNpCyb288fS/NmmmJ80aRIrVqzQvu7RowfffPMN5ubmz1SvEEII8UB+3ei/+eYb+vbtS0JCgh4ieug1/8qM/LCBdnHoI6FRTFt5lKzsXL3GJURh0vuizw/GwDwYSPqAg4ODdt8/xcTE5ClrYmKCnZ0dUVFRJCcnk5aWhpOT0yPrc3Z2xtnZWWf/kiVLMDMzw8fH56muQ1EUva/XURI86HdeUvqfF7WcXDXfrDlDWEQ8ALaWJozp7oWpkfo//z2oVKrHJlVvvvkmv/76K2q1ms8//5xOnToVauxCCPEyS09PLxHjkAry+6A4rVq1iiVLlgDQtWtXFi5cqPMFeHGrX92ewPc9mbXmDNk5ao6HxfDlkr8JfN8TM5On730idL1sn9+KmqIoBZ4vQO/J2IObbmJiorPd1NSUpKSkfMv/u+yD8pmZmWRkZDyyvkeNB1u9ejU//fQT48aNw97e/qmuIzs7m7CwsKc69kUUERGh7xCKnFpR2BqcwJnrmqTLxEhFl6Z2JMTcICHmv481NzfHw8PjP8t4e3szdepUrK2tadKkSWGFLYQQArh+/XqJ+OBZkN8HxcnDwwMHBwdiY2O5ffs2H3zwAV9//bXefg9dv34d05x0ur1iz5r998jOUTh3LZ4vFh+iW/MymBnrvZPXC+Vl+PxWXPLLV/Kj92TsQVfBrKwsnW6DmZmZ+X5TZGZmlu/EHpmZmVhYWGBqaqqt79/7/12foijMnTuX7777jo8++ogPP/zwqa/D2NhYJlRAkyxHRERQuXLlEvVNX2FTFIVV2y9rEzEjQxWjPvSmtlvBkvn8vi05efIknp6eOgs3v/baa4UTsBBCCB2urq4lpmWsJPHx8WHjxo0MGDCAsLAw7t+/z+DBgxk5ciTdunUr9ngf3KeaNaGqWyJfrT5FWkYON+Oy+OXv+3ze3Rsri2cbFiBens9vxSU8PLzAZfWejD3ochgbG0vFihW122NjY6lRo0ae8k5OTuzatUtnW1ZWFomJiTg4OGBnZ4eFhQWxsbE6ZWJjY3F0dNS+zs7OZsyYMWzbto0xY8bQs2fPZ7oOlUqFhYXFM9XxIjE3N3+h34+fd1xk+5GbABio4LMPGuBbu/xT1aVWq/n+++9ZtGgR/fr1Y8iQIYUZqhBCiHzIB85HK1euHCtXruTzzz9n9+7dqNVqpk+fzvXr1xk1ahTGxsWX/PzzPnm6WzD1IwvGf6+Zufjq7WQmrzzJ5AGNsLM2LbaYXmQv+ue34vIkX1rovW3X3d0dKysrQkJCtNuSk5O5cOFCvuO3fHx8iI6O5saNh6uyHz16FID69eujUqnw9vbWbnsgJCSEBg0aaF+PHDmSHTt28M033zxzIiZeLkH7w1n31yXt6086edK47tMlYmlpaXz22WcsWrQI0MwEeurUqUKJUwghhHhaFhYWzJ49m759+2q3rV+/nkGDBuU7jKS4VHW246tBjbXJV0RUMmMWHeJekv67nArxNPSejJmYmPDBBx8wa9Ysdu/ezcWLFxk2bBhOTk60adOG3Nxc4uLitGPB6tWrh7e3N8OGDePs2bMEBwczfvx4AgICtC1fvXr14vfff2fFihVcvXqVmTNnEhYWRo8ePQDYvHkzf/zxB8OGDcPX15e4uDjtz4PzCJGfnSE3WPbree3rfm/VprVvpaeq6+bNm3Tp0oW//voL0HyLMmzYMDw9PQsjVCGEEOKZGBgY8OmnnzJ16lRta1hwcDBTpkzRa1yVytkwfXATythqhrfcir3PmIWHiY2XidTE80fvyRhoFnF+7733GDduHF27dsXQ0JBly5ZhbGxMVFQUTZo04Y8//gA0H1gXLFiAs7MzPXr0YOjQoTRr1kxn0ecHCxiuXbuWt99+m+DgYBYvXqydDWjbtm0AzJw5kyZNmuj8PDiPEP928PRtFvxyWvu6W1t33mz2dDNM/f333/j4+GgnfbG0tGT+/Pn07t27xI0fEEII8XJ78803+eGHHyhVqhT29vaMGDFC3yFRoawVXw1ugqO9pktd1L1URi08xJ279/UcmRBPRu9jxgAMDQ0JDAwkMDAwzz5nZ2cuXbqks6106dLMmzfvP+sMCAggICAg333Lly9/6ljFy+l4WAyz15zgwVjvt5pVocur1Z+4HkVRWLx4MZ9++ql2QU1nZ2fmz58vE8AIIYQosby9vVm3bh337t3Ls3yQvjiVtmT64CaMW3yY23Gp3E1MZ8zCw0wZ2AgXR2t9hydEgZSIljEhSrJzV+/y1cqj5ORqMrFXfSvS581aT9yClZGRQe/evRk0aJA2EWvYsCFr166VREwIIUSJV758eerUqaOz7f79+0ydOpXk5GS9xFTGzpyvBjehkpMm+YpPzuDzRYe5EaWfeIR4UpKMCfEfwiMTmbQshKwcNQCN65VncEfPp+pKqCgKZ86c0b4eNmwYy5cvx87OrrDCFUIIIYqNWq1mzJgxrFu3jm7dunH16lW9xFHK2oypHzXGrbwtAIn3Mxmz6DBXbyXqJR4hnoQkY0I8ws3oZMYvOUJ6Zg4A9d0dGNGtPoYGTzemy9zcnM2bN+Pi4sKaNWuYPXt2sU4PLIQQQhSm27dvc/r0aQBu3LhBt27dtJNSFTdbK1OmftSIai52AKSkZTF28d9cvpmgl3iEKChJxoTIx524+3zx/d+kpGkWD6/lVprRPXwwNir4I6MoCvfu3dPZVrlyZa5cuULXrl0LNV4hhBCiuLm4uLBu3Trc3d0BzXItw4cPZ+bMmdru+MXJysKEKQMbUbOyPQCp6dmMW/w3F67fe8yRQuiPJGNC/Ev0vVTGfneY+ORMAKo42/JFbz/MTAo+301SUhIdO3akefPm3L+vO7OTqaksTCmEEOLFUKFCBX788Ufat2+v3bZ69Wp69+5NTExMscdjYWbMxP7+1K1aBoD0zBy+XHKEs+FxxR6LEAUhyZgQ/xAbn8bn3x3mbpJmvbnK5WyY1L8RluYF70548uRJ6tevz6ZNmzh37hz9+vUrqnCFEEIIvTM3N2f69OmMGzdO2/3+9OnTdOrUiSNHjhR/PKZGjO/bEO8aDgBkZOUycWkwJy/GFnssQjyOJGNC/N/dxHQ+/+4wcQnpALg4WjN5QCNsLE0KdPyDaev9/f21g5jt7Ozo1q1bkcUshBBClAQqlYrOnTvz448/Uq5cOQDi4+MZMGAAoaGhxR6PqbEhY3v54uuhmYY/K0fN5OUhHL0QXeyxCPFfJBkTAriXpEnEYuLTAM1iklMHNsLOumBdClNSUujWrRsfffQRWVmacWY+Pj6cPHmSN954o8jiFkIIIUqS2rVrs2HDBpo2bQrAq6++Su3atfUSi4mxIaN7+NCoriY5zMlVM23FUQ6fvaOXeITIjyRj4qWXkJLB2O/+JupuKgDlylgy9aNGlLIxK9DxZ8+epUGDBqxbt067bciQIRw6dAhXV9ciiVkIIYQoqezs7FiwYAFjxoxh4sSJT7UcTGExNjJg5AcNeMXLGYBctcLM1cfZf/KW3mIS4p8kGRMvtaT7mYz97m9ux2km2XC0t2DqwMaUtjUv0PErVqzAz8+Py5cvA2BjY8PGjRuZO3cuJiYF694ohBBCvGgMDAzo1q0bVlZWOtv37dvHokWLyMnJKbZYDA0NGNbNm1Y+LgCo1QrfrDnBrqM3iy0GIR6l4NPDCfGCSUzJ5Ivv/yYyJgWAsqXMmfpRY8qWKlgiBpr+8BkZmsk+vL292bBhA1WqVCmSeIUQQojnWXR0NOPGjSMpKYmQkBBmzJiBk5NTsZzb0EDFkE5eGBsZsuNIBIoCc9efIidXTTv/ysUSgxD5kZYx8VJRFAWA+OQMPv/uEBFRyQCUtjVj6sDGONpbPFF9w4YN49VXX+Wjjz7i8OHDkogJIYQQj3DixAntci8nT57kvffeY8+ePcV2fgMDFYPercubTd202xZuPMOvB68WWwxC/Ju0jImXikql4uyFq3y78TJxSZqJNuwsjRjQ3pnUxCjCEx99bE5ODkePHqVRo0Y627/99ltMTEy4davg/c+trKyK7dtAIYQQoiR4/fXXqVChAiNHjiQqKoqkpCQ+/fRTunbtyogRI4plHU6VSkXft2pjbGTApr3hACwNOkdOjpp3WlQr8vML8W/SMiZeKrHxacz+5dLDRMzKiH6vlcfaTCEjI+ORP1euXKFz58707NmTgwcP6uxTq9X/eWx+P9nZ2Xp+J4QQQoji5+npyS+//ELr1q2129auXUuXLl24dOlSscSgUqno8boHXV6tod22YtsF1v11SduDRojiIsmYeGlE30tl9KJD3EvWJEL21kYMeK089taPXtBZURR+++03OnbsyNmzZ1EUhS+++EKSKSGEEOIp2draMnv2bL744gvtZFfh4eF06dKFZcuWkZubW+QxqFQq3m/nzoev1dRu+3nHRVZsuyAJmShWkoyJl8LtuPuMXnhIu6BzWVtj+r9WATurRydi8fHxjBgxgs8//5zUVM20987OzsycORNj40cfJ4QQQoj/plKp6NSpE+vWraN69eqAZjjAihUrSEhIKLY4OrWuTp83a2lfb9kXzvwNp8nNVRdbDOLlJsmYeOHdjE5mzMJD3EvSzHroWMqUfu3KY2v56CGTe/bs4e233+avv/7SbnvzzTf55ZdfqFu3bpHHLIQQQrwMqlWrxtq1a+nduzcqlYrx48dTpkyZYo0h4JWqfNyxHg+WQ/vr6E1mrD5OVnbRt9AJIRN4iBda+K1EJiw9QtJ9zRgx1/I29G5TDiNV/uubpKSkMH36dH799VftNjs7O8aOHUu7du2KJWYhhBDiZWJiYsKwYcN46623cHNz09mXkJBATk4OZcuWLdIY2jasjKW5Md/8fIKcXIUjoVFM/CGYsb18sTCT3jCi6EjLmHhhhYbf5fNFh7WJWFVnW6Z+1Bgr80d/B/Hll1/qJGLNmzdny5YtkogJIYQQRezfiRjAoEGD8PDwYP369UU+lqtJvQp80achpiaGAJwNv8u4xX+TnJpVpOcVLzdJxsQLKfhcFF8uPUJ6pqYFzMPVnskDG2NtYfKfxw0ZMgQzMzOsrKyYPHky8+bNK/buEkIIIYSA9evXs27dOu7evUuXLl149913iY6OLtJzetdwYMrARliZa1rDrkQmMnrhQe4mphfpecXLS5Ix8cLZfewmX606RnaOZvBtg5qOTOzvr/2P9Z9SUlJ0XleuXJkZM2awefNmAgICUD3oQC6EEEKIYtW8eXPeffdd7estW7bg4eHB6tWri7SVzL2SPdMHN8HeRrPuWWTMfUYtOEhkTMpjjhTiyUkyJl4oQfuv8u26U6jVmv+km9d3ZmwvX8xMdLsmJiQkMGbMGDp37kx6uu63XS1btqRcuXLFFrMQQggh8nJ0dGTjxo1s2LBBO2YsISGB7t2788Ybb3D79u0iO3elcjbM+Lgp5UpbAhCbkM6oBQe5cP1ekZ1TvJwkGRMvBLVaYflv51n26znttg5NXBnWxRsjw4f/zB+sG/bWW2+xbds2IiMj+e677/QRshBCCCEKoGPHjly4cIGuXbtqt/3+++94eHiwZMkS1OqimYbeqbQlMz5uglt5WwBS0rIZt/hvDp+9UyTnEy8nScbEcy8rO5evfzrOln3h2m3d2rrTP6AOBgYPuxlGRkby5ptvMnz4cO0aJtbW1vkOGBZCCCFEyVGmTBnWrFlDUFAQTk5OACQnJzNgwAD27NlTZOctZWPGV4Mb41ld0zKXnaNmxo/H+PXg1SI7p3i5SDImnmspaVmMX3KEQ2c031IZqGDQe/Xo2qaGdrxXTk4Oc+bMoVatWmzbtk177KuvvsrWrVsJCAjQR+hCCCGEeEJvvfUWFy5coEePHgB06NCBVq1aFek5LcyM+bJvQ1o2cAFAUWBp0DmW/XpOOyxCiKcl64yJ51b0vVQmLA3mdtx9AExNDBn1YQN8PJy0ZQ4fPsygQYM4e/asdlvZsmUZO3Zskf/nLYQQQojCV6pUKVauXEn37t2pUqWKzmRbiqJw7NgxfH19C/WcRoYGDO3iRdlS5qz/6zKgGaceE5/G8K7emJnKR2rxdKRlTDyXLt9MIHD+QW0iZmdtyleDGuskYgkJCbRt21abiKlUKvr378/27dslERNCCCGecy1btqRSpUo624KCgvDz86Njx46FPsGHSqXig3Y1+bijp3YYxJHQKEYvOiRT34unJsmYeO4cOHWLMQsPkZiSCYCzgxVff9KUai6ldMqVKlWKcePGAeDl5cWRI0f4/vvvsbW1LfaYhRBClAxGRkZFvniweHZPc59SU1P55JNPANi4cSM1atRg+vTpZGZmPnM8/4ylbcNKjO/jh/n/W8Ou3kpixNz9XL6Z8MznES8faVMVzw21WmHNnxdZv+uydlstt9KM7eWLtYUJISEhVK9enVKlHiZlw4cPx8nJiQ8//BBDQ0N9hC2EEKIEMTQ0RKVSERkZWSgf0p+VlZWVdkIK8dDT3CdFURg6dChfffUV8fHxpKamMmbMGL777js+//xzWrZs+VTrh5qamuLi4qKzrb67I18PacrkZSHExKcRn5zJmIWHGNrVm6aeFZ74HOLlJcmYeC5kZOYwe+1JjoRGabe96luRj96tR0z0HQYNGMNPP/3EsGHDmD17traMiYkJPXv21EPEQgghSrLMzEwyMjL0HQampqb6DqFEe9L71K5dO/z9/VmwYAEbNmxArVZz8+ZNBg4cSOPGjRk1ahSurq6FElslJxu++bQZX606xvlr98jKUTNz9XFuRqfQtU0NnRmdhXgUvXdTVKvVzJs3j6ZNm+Lp6Um/fv2IjIx8ZPmEhARGjBiBj48Pvr6+TJw4Mc+ivdu3b6d9+/bUrVuXgIAAjhw58shz9+3bl/nz5xfqNYnCFZuQxsgFB7WJmIEK+r5Vmz4dqjNt6mSqV6/OTz/9BMD8+fO5cuWKPsMVQgghhB7Z2toyduxYNmzYQIMGDbTbDx8+zDvvvMOsWbMKbW0yWytTJg/wp5XPw5azdX9dYvLyEO6nZRXKOcSLTe/J2KJFi1izZg2TJ09m3bp12gQpKyv/f8BDhgzhxo0brFy5krlz57J//34mTJig3R8cHExgYCBdunRhy5Yt+Pv7079/f65e1V0PIisri88//5yDBw8W5eWJZ3TmchzD5uzn+p1kACzMjPiijx+pt0Jwd3dnwoQJ2mTc3t6eb7/9ttC+8RJCCCHE86tGjRosX76cr7/+WtsVNCcnh+joaAwMCu8jsLGRIZ929qJXBw8eNIYdD4th2Lf7uX4nqdDOI15Mek3GsrKyWL58OUOGDKF58+a4u7szZ84coqOj2blzZ57yp06d4ujRo8yYMYNatWrh7+/PpEmT2Lp1KzExMQAsXbqU1q1ba6c7HTVqFLVq1WLVqlXaek6ePMk777zD8ePHsbGxKbbrFQWnVits2HWZ8Uv+JjlVk5iXK21JR18jPun9Nu+//z63bt0CNIN8P/30U8LDwxk8eDBGRtL7VgghhBCaGRDbtWvHr7/+ysCBA7G1tWXEiBE6ZdRq9TNP6qJSqXinRTUm9vfH2sIEgOh7aXw27yB7Tzy6x5cQek3GLl68SGpqKv7+/tptNjY2eHh4cOzYsTzljx8/TtmyZalSpYp2m6+vLyqVihMnTqBWqzl58qROfQB+fn469e3fv5+mTZsSFBSEtbV1EVyZeBb307OZuuIoq7eH8WAtxfruDmReXkPHgHYEBwdry7Zv357Q0FC+/fZbnYk7hBBCCCEeMDc3Z/DgwezcuZNy5crp7AsKCqJ79+6cPn36mc/jWd2Bb4e/QlUXOwCysnOZveYkizefJTsn95nrFy8evTYhREdHA+R5KBwcHLT7/ikmJiZPWRMTE+zs7IiKiiI5OZm0tLQ8sxL9u75hw4YV1iVoKYpCWlpaodf7vHnQZfDf4/gKKiIqhdnrzhATrzlepYL3WrjxzituLL1fhx//X65mzZpMmzaNNm3aABTovVepVJibmz9VXEIIIYR4/llYWOi8TktLY8GCBcTFxfHhhx/SunVrPv30UypXrpzn2PT09AK1oFmZwpe9vFn5xyV2H9esdfb74eucv3qXTzvVoXxZy0K5lsL0rJ/fhC5FUQo8c6dek7EHN9zExERnu6mpKUlJefvYpqen5yn7oPw/Z9vJr76inr42OzubsLCwIj3H8yQiIuKJyiuKwvHwVP48mUhOLmSlJ2NqBN1edaOaUxaXLl3E39+f+vXr0759e15//XWMjIye6D03NzfHw8PjCa9ECCGEEC+q6OhorKysiIuLA2DXrl3s3buXN954g4EDB1KhwsNp6q9fv/5EyUrT6iosDUvx+7EEctUQEZ3CyIVHaN/ADk83i6eaZr+oPennN/Fo+eUs+dFrMmZmZgZoxo49+DtopjHNrwXDzMws34k9MjMzsbCw0E4P++8yj6qvMBkbG1O1atUiPcfzID09nYiICCpXrlzg9zwlLYvvgy5wLCyRrPQUrp/8jYjT2wgICODNVkt1yh44cOCpYyuJ/+kJIYQQQn/c3NzYvHkzW7ZsYeHChdy7d4/c3FyCgoLYtm0b77zzDh9//DFVq1bF1dX1iceW1awJTRqkMHdDKLfjUsnOVdgaksDdNFP6vumOhZlxEV3Zk3maz2/i0cLDwwtcVq/J2IMuh7GxsVSsWFG7PTY2lho1auQp7+TkxK5du3S2ZWVlkZiYiIODA3Z2dlhYWBAbG6tTJjY2FkdHxyK4godUKlWepu+Xmbm5eYHej9Dwu3yz5gRRMXe5fuJXrp/aRk6Wpsvhpl/WMWH8WGnNEkIIIUSRMTIyomPHjrz++uv89NNPrFy5kpSUFHJyctiwYQNBQUF8+umnzJw586nqr+lmwbfDS/PD1nP8GXwDgMOh0YTfTmZYV29quZUuzMt5JgX9/Cb+25M0AOh1Ag93d3esrKwICQnRbktOTubChQv4+PjkKe/j40N0dDQ3btzQbjt69CgA9evXR6VS4e3trd32QEhIiM46E0L/cnLVrN4eRuC3f/L3H8vZ80N/roRs0CZiRkZG9O3bF3t7ez1HKoQQQoiXgYWFBf3792fHjh0MGDAAS0vN2K6srKxnHktlZmLExx09Gd3dB0tzTWtYTHwaYxYdYunWUDKycp45fvF80mvLmImJCR988AGzZs3C3t6eChUqaNeCaNOmDbm5ucTHx2NtbY2ZmRn16tXD29ubYcOGMWHCBNLS0hg/fjwBAQHalq9evXrRv39/PDw8aNasGZs2bSIsLIypU6fq81LFP9yISmbasr3s3bZGpyUMNElY7969GTNmTL6DZ4UQQgghipKNjQ0ff/wxH3zwAStWrGDLli18/vnnOmWSk5OJj49/4s8qjeuVp5qLHd+sOcGF6/EoCvx64BrHL8QwpLNXiWolE8VD74s+DxkyhPfee49x48bRtWtXDA0NWbZsGcbGxkRFRdGkSRP++OMPQNPkt2DBApydnenRowdDhw6lWbNmOos+N2nShGnTprF27VrefvttgoODWbx4sc50+EI/cnPVbNh1maFz9rFhYWCelrD+/ftz5coVvv/+e0nEhBBCCKFXdnZ2DBs2jAMHDuSZzXvhwoVUrVqVHj16PPEEbg72Fkwb1IQ+b9bCxEjzUfzO3VRpJXtJ6X11XENDQwIDAwkMDMyzz9nZmUuXLulsK126NPPmzfvPOgMCAggICCjQ+ffs2VPgWMXTuxmdzJx1pwiPTASgsmd7Tu+YKy1hQgghhCjR/jnJHGimw58zZw65ubn8+OOPrF69mrfffpsxY8YUeFiMoYGKgFeq0qCmI3PXneLijQRtK1nIuWj6v10HXw+nx1cknnt6bxkTLy5FUdi7bz/1/VvSfeQP2kTMQAUfD+zFqFGjCQ8Pl5YwIYQQQjw31Go1gwcPplSpUoDm887mzZvx8fHhlVdeYevWreTmFmyBZ2cHa6Z/3JTebzxsJYuJT2PyshCmLA8hJl7WsH3RSTImCl1WVhZr1qyhTj1vWrZozsngvVwO2QRAhbJWzPykKX3eqsf06V9RqVIl/QYrhBBCCPEErKys+PLLL7lx44Z2roMHDhw4QEBAAO7u7ixcuLBAE38YGqh4u3lV5o5oTt2qZbTbQ85HM2jmHjbsukx2TsGSO/H8kWRMFJqYmBimTZtGhw4d6NevH+dDT2v3JUWH096/AnNHNKdGJZkhUQghhBDPN2traz777DOuX7/O999/j7u7u3ZfeHg4Y8eOJSen4OO/nB2smTKwEZ+9X59S1v9fOzc7l9Xbwxj89V4On73zxOucFYeSFFNJiqWg9D5mTDz/Tpw4wdy5c1m/fn2eBbdtyrrS6NUujBnSjfKlzYi8cV1PUWq+yfrnt1dCCCGEEM/KzMyM/v3707dvX3bs2MHs2bPZvXs3/fv3x9raWqfsuXPnqFWr1iPXoVKpVLzi7UyDmo6s+fMi2w5dQ61A1N1Upq86hnulUvTsUKtEzbqoUqmIjIwkMzNTr3GYmpri4uKi1xiehiRj4pmcPXs272BVlQFOVf3w8HuL4QM70s7flevXrpKRkaGfIP/P1NRUr+cXQgghxIvLwMCA9u3b0759e86cOYODg4PO/tjYWLy9vXF1dWXgwIH07NlTO+7s3yzNjekXUIfWvhVZEhTKuav3ALh4I4HRCw/RsLYT3dt74OJone/xxS0zM1Pvn/OeV9JNUTyR5ORkndelnVxxcqkGgLGpFVUavE2rPt/z6dg5bFz4Ka83dsPQoOCrkAshhBBCPO/q1auXZzr8ZcuWkZ2dzeXLlxk+fDgVKlSgd+/eHDt27JHd61zL2zLto8Z80cdPJ/EKPhfNx1/v4Zs1J4iMSSnSaxFFS1rGxGPdv3+fDRs28P3335Odnc2JEydITs3il91X+P3wNSp4vkPZGslUqPkKVSuWpbmHGa81r4OFhdnjKxdCCCGEeAl4eXnRokUL9u7dC0B6ejorVqxgxYoV1K5dm969e/PBBx9QtmxZneNUKhW+Hk7Ur+HArmORrPkzjPjkTNQK7Dtxi/0nb9G4bnk6v1qDyuVs9HFp4hlIMibypVar2bt3Lz/++CObNm0iNTVVu2/K/E2ERpuTnqkZlFqumj+lrE3p3t6Dhh6luXTpor7CFkIIIYQokdq1a0e7du0ICwtj8eLFrFq1iqSkJEAzlmz48OGMHDmSkSNHMnXq1DzHGxoa0LZhJV7xqsCvB68RtD+clLRsFAUOnbnDoTN3aFjbiXdbVKNGpVKPHJcmShZJxoSOS5cusWrVKn766SciIyPz7LdzcOWPQxcp41IHABMjA95uXpV3W1bD3NSItDRZD0MIIYQQ4lFq1qzJ3LlzmTZtGuvWrWP58uX8/fffAOTk5FCxYkWd8g+6MD5IrsxMjejUujodmriy40gEW/ZdJfG+ZvKM4HPRBJ+LppqLHW80daNJvQoYG8mopJJMkjEBaB70V199ld27d+fZZ2llQ/kaTXCo3hw7p2qoVCoMDVS08atEp9bVKWNnroeIhRBCCCGeX5aWlvTp04c+ffpw6dIlVqxYwcaNG+nSpYtOuf379/PRRx/RrVs3unbtStWqVQGwMDPmnRbVaN/YlZ3BN9i0N5z4ZM0kGlciE5m95iQrfjvPa41cadewEqVsZPhISSTJ2EsqNTUVS0tL7WuVSqXTR9nQ0JA63k2wcPHH1tkbQyMTAAxU0Ly+C13b1MCptGWeeoUQQgghxJOpUaMG06dP56uvvsrTvXDt2rVcvHiR8ePHM378eHx8fOjWrRudOnWifPnymJkY8WazKrTzr8zB07f59eA1rt3WdH9MSMlkzZ8XWffXJXxqOtLKpyI+Ho4YGUprWUkhydhLJC4ujq1bt7J+/XqOHj3KnTt3dBKyzp07E3ruPDV92pJmWRcDk4eDQFUqaFS3PO+3dS8x06gKIYQQQrxI8hvnFRcXp/P62LFjHDt2jOHDh9OoUSPeffdd3n77bSpXrkwrn4q0bODChevx/HrwKsGhUagVUKsVQs5HE3I+GlsrE1rUd6GVT0UqOVnL2DI9k2TsBXft2jW2bt1KUFAQhw4dQq1Wa/dt27aNzp07oygKoVfvci7eiSptJ5OhPFzzwNBARYv6LrzToqokYUIIIYQQxWzz5s1ERkayfv161qxZw6lTpwDNEJPDhw9z+PBhhg8fzowZMxg5ciQqlYpabqWp5Vaa2IQ0dhyJYM/xSO4labowJt3PImj/VYL2X8XF0YrGdStQv4b9I6fXF0VLkrEX0MmTJwkKCiIoKIjQ0NB8y7i6upKekcX2IxH8fugaN6J116gwNTGkbcNKBDSrStlSMiZMCCGEEEJfXFxc+Oyzz/jss88ICwtj7dq1bNq0iQsXLmjL+Pv76xwTExPDxYsX6fpqI95vV5PTl2PZdfQmweeiycnVfDkfGXOfdX9dYt1fUMbGiFeiTGns6UyVCnYYyDqxxUKSsRdQr169OHv2bJ7t1atX56233qJhs3ZEZdiz49RtUs+e0Sljb2PKa41cec2/MrZWpsUVshBCCCGEKICaNWsyadIkJk2axMWLF9myZQv79u2jUaNGOuU2bNjAkCFDsLOzo23btnTo0IE+7dvx0bv1OHjqFgfP3OHC9Xs8aBC7m5zDpn3X2LTvGnbWptR3d8CnphOe1ctiaW6shyt9OUgy9gIKCAjQJmN+fn4EBATwatv23LlvxV9Hb7BibzKg2xJWs7I9bzRxw79uORnUKYQQQgjxHHB3d2fMmDGMGTMmz75t27YBkJiYyPr161m/fj0GBgb4+fnRpk0bOrRuzdDOLTgWdpcDpyK5eCNRe2xiSia7j0Wy+1gkhgYqqlcsRd2qZahbrQzulewxMTYsrkt84Uky9gLq1q0b5cuXp0279txJNGT/qVtMXXeD7By1TjlTE0Oa1CtPh8ZuVHWx00+wQgghhBCi0PXp0wd7e3t27NhBYmIiAGq1miNHjnDkyBEmTpyIlZUVY8eOZeKQIYScOEey2o7QqwmcvhJHZlYuALlqhbCIeMIi4lm/6zLGRga4V7KndpXSuFeyp3pFO/1d5AtAkrEXjFqtkKqUIs3Gh1HfnyU9MydPmeoV7XjVtxLNvCpgYVa4zc4qlQpzc3OZmUcIIYQQQo86depEp06dyMnJ4e+//+b3339n27ZtOuPM7t+/T+nSpQGwsTDEr6YzbXxd+OnnNTi41CY6zZyTF2O5czdVe0x2jprQq3cJvXpXu83BzgSXMqa4lDXFpawZjqVMMJQxZwUiydgLZsEvp/nr6M082+2sTWnmVYE2vpWoVM4mnyMLh7m5OR4eHkVWvxBCCCFEcTIyMkJRlBL1RfOTxGNkZESzZs1o1qwZM2bM4NatW+zevZtdu3axa9cuWrdurVP+0KFD9O/XFwAnJyeaNGmCf30/Srt4kEpZzkckEhufpnNMbGIWsYlZnAjXDIMxMlThVMqEcvYmlLM31f5paixDYf5NkrEXzOWbCdq/m5kYUNfNBu+qtlStYImhgYrs1FjCw2OLLR4rKyucnJyK7XxCCCGEEIXJ0NAQlUpFZGQkmZmZ+g4HU1NTXFxcnvp4Z2dnevToQY8ePbRJXVraw+Rq165d2r9HR0ezceNGNm7cCIC1tTX+/v541vejglsdzMu4c/FGPFdvJZGrfjg1fk6uwq27mdy6m8k/5ykobW2Mk70JDrbGlLUzwdHOhDK2xpgYvbxJmiRjL5gR79fn8Jk7WBim4+pghPH//3FnZ2WSrYd4TE1lRkYhhBBCPP8yMzPJyMjQdxiFKr/WtS5dumBjY8OhQ4f4+++/SU5O1u5LSUlh586d7Ny5Ex8fH44ePQpA2MXLXLuTzInQcO7n2hCbAveS837yvJeSzb2UbM7/MwbAzsqIsrYmONgZ42BnQhkbY0rbGGNtbliiWiSLgiRjLxjX8ra4lrclPDz8hfsPQwghhBBCFC0vLy+8vLwAyM3NJTQ0lEOHDnHw4EEOHjxIVFQUAD4+PtpjjI0MqORgRr8Zw4mLi6N69erU9KhFOZdqWJetjKGVM3fvq4hOyCInV3dxaQVIuJ9Dwv0cLt/WjcXYSEVpa2PsrY0pbWNEaWtNkmZvbYytpdELMS5NkjEhhBBCCCFEHoaGhnh6euLp6cnHH3+Moihcv36dQ4cOUb16dZ2yd+/e1SZqFy5c0JkoxMDAgIoVK1K9eg0qulajfqM25BrZEZuUTWxiFnFJWWRm6yZpANk5CtEJWUQnZOWNzQDsrIz/n6AZ4VDKHGMrByo5Fd3cCEVBkjEhhBBCCCHEY6lUKtzc3HBzc8uzLysrizfffJPz589z7do1FOVhcqVWq4mIiCAiIgL4k7atX8HdvZR2//nz5zkScgK7si6Y2zmTa2RH/P0c4lOyiU/JJled53TkqjVdIe8lZ8NtgGR+OxLDgsCWuDhaF/q1FxVJxoQQQgghhBDPpHz58kydOhXQTJkfFhbGpUuXtD/h4eFkZ2djZGSUJ5k7ePAgCxcu1L62tLTEzc0NV1dXXF3dKONUASu7cphaO3E/y0iThP1//Fl2zsOkT0GzzNPzRJIxIYQQQgghRKGxsrLCx8dHZ1xZdnY2ERER3L59GxMTE53y165d03mdmppKaGgooaGhOtt9fHxYvny59rWiKOzeewi1oTm2ZVx4pXH9Il3CqShIMiaEEEIIIYQoUsbGxlSrVo1q1arl2denTx8aNmzItWvXtD937tzR6eoIULFiRZ3XKpWKyRPHER8fD8Dt27cBu6K6hCIhyZgQQgghhBBCb2rUqEGNGjV0tqWnpxMREcH169eJjIwkMjKSBg0a6JRJTU3VJmJmZmaUK1eu2GIuLJKMCSGEEEIIIUoUc3NzatasSc2aNR9ZRlEURowYwc2bN1GpVM/lmmR6T8bUajULFizgl19+ISUlBR8fH8aPH//IlcUTEhKYMmUKBw4cQKVS8frrrzNy5EjMzc21ZbZv3878+fO5desWbm5ujBo1Cn9//yeqQwghhBBCCFFyWVlZ0bNnT0DTMvY8MtB3AIsWLWLNmjVMnjyZdevWoVar6du3L1lZedcTABgyZAg3btxg5cqVzJ07l/379zNhwgTt/uDgYAIDA+nSpQtbtmzB39+f/v37c/Xq1QLXIYQQQgghhBBFTa/JWFZWFsuXL2fIkCE0b94cd3d35syZQ3R0NDt37sxT/tSpUxw9epQZM2ZQq1Yt/P39mTRpElu3biUmJgaApUuX0rp1a7p3706VKlUYNWoUtWrVYtWqVQWuQwghhBBCCCGKml6TsYsXL5KamqrThdDGxgYPDw+OHTuWp/zx48cpW7YsVapU0W7z9fVFpVJx4sQJ1Go1J0+e1KkPwM/PT1vf4+oQQgghhBBCiOKg1zFj0dHRAHlmPnFwcNDu+6eYmJg8ZU1MTLCzsyMqKork5GTS0tJwcnJ6ZH2Pq+NpZGdnoygKZ8+efarjC5tKpSInJyfPdKD6cO/ePRITE0tEPBJLyY+lpMUjsUgsz3M8EkvJj6WkxSOxlPxYQPO5MzQ0tFBjURQFlUrFlStXnngSjJLyubMo3pdniaWg76Nek7H09HSAPAu/mZqakpSUlG/5f5d9UD4zM5OMjIxH1peZmVmgOp7Ggze7JM3gYmSk97lZdJSkeCSW/JWkWKBkxSOx5E9iebSSFI/Ekr+SFAuUrHgklvyVpFigcD93qlQqDAyevsNcSXpvSsLn8SeZ2VGv79yDWU+ysrJ0ZkDJzMzMd2ZDMzOzfCf2yMzMxMLCAlNTU219/97/oL7H1fE0vLy8nuo4IYQQQgghxMtLr2PGHnQXjI2N1dkeGxuLo6NjnvJOTk55ymZlZZGYmIiDgwN2dnZYWFj8Z32Pq0MIIYQQQgghioNekzF3d3esrKwICQnRbktOTubChQv4+PjkKe/j40N0dDQ3btzQbjt69CgA9evXR6VS4e3trd32QEhIiHbF7sfVIYQQQgghhBDFQa/JmImJCR988AGzZs1i9+7dXLx4kWHDhuHk5ESbNm3Izc0lLi5OOxasXr16eHt7M2zYMM6ePUtwcDDjx48nICBA2/LVq1cvfv/9d1asWMHVq1eZOXMmYWFh9OjRo8B1CCGEEEIIIURRUyl6nnIkNzeX2bNns3nzZjIyMvDx8WH8+PE4Oztz69YtWrVqxVdffcU777wDaGa0mThxIgcPHsTU1JR27doxZswY7XgxgKCgIBYtWkR0dDRVq1YlMDBQZ7r7gtQhhBBCCCGEEEVJ78mYEEIIIYQQQryM9NpNUQghhBBCCCFeVpKMCSGEEEIIIYQeSDImhBBCCCGEEHogyZgQQgghhBBC6IEkY0IIIYQQQgihB5KMCSGEEEIIIYQeSDImhBBCCCGEEHogyZh4ItevX8fLy4vNmzdrt4WFhfHBBx/g6elJy5Yt+fHHH3WOUavVzJs3j6ZNm+Lp6Um/fv2IjIws7tBfCvndn3HjxlGjRg2dn5YtW2r3y/0pejExMXnuQY0aNbT3SZ4h/Xrc/ZFnSP+CgoJo3749derU4fXXX2f79u3afbdu3WLAgAF4e3vTpEkTvv32W3Jzc3WO//nnn2nVqhV169alW7duXLhwobgv4YX2X/fnu+++y/f5+ie5P0UjJCQk3/e+Ro0atGrVCpDnp0RQhCigrKws5Z133lGqV6+ubNq0SVEURYmPj1f8/PyUMWPGKOHh4crGjRuVOnXqKBs3btQeN3/+fMXPz0/Zu3evEhYWpvTu3Vtp06aNkpmZqa9LeSHld38URVHee+89Zfbs2UpsbKz25969e9r9cn+K3r59+5Q6deooMTExOvchPT1dnqES4L/uj6LIM6RvQUFBioeHh/LTTz8pN27cUBYtWqS4u7srJ0+eVLKyspQ2bdoo/fv3Vy5duqT89ddfiq+vrzJ37lzt8Zs3b1bq1q2rbN26Vbly5YoSGBio+Pr66txD8fT+6/4oiqJ8+umnSmBgoM7zExsbqz1e7k/RyczMzPO+79y5U6lRo4ayceNGeX5KCEnGRIF98803Svfu3XU+7C9evFhp0qSJkp2drVOuTZs2iqJo/iPw8vJSfv75Z+3+pKQkpW7duspvv/1WvBfwgsvv/qjVasXT01PZuXNnvsfI/SkeS5YsUd54441898kzpH//dX/kGdIvtVqttGjRQpk+fbrO9t69eyuLFy9WfvvtN6V27dpKYmKidt+6desUb29vbTLcpk0bZebMmdr92dnZyiuvvKIsXry4eC7iBfa4+6MoivLaa68pK1aseGQdcn+KT2pqqtKiRQtl9OjRiqIo8vyUENJNURTIsWPHWL9+PdOnT9fZfvz4cXx9fTEyMtJua9iwIREREdy9e5eLFy+SmpqKv7+/dr+NjQ0eHh4cO3as2OJ/0T3q/ty8eZO0tDTc3NzyPU7uT/G4dOkSVapUyXefPEP691/3R54h/bp+/Tq3b9/mjTfe0Nm+bNkyBgwYwPHjx6lVqxa2trbafQ0bNuT+/fuEhYVx7949IiIidO6PkZERDRo0kPtTCB53f7KysoiIiHjk8yP3p3gtXryY9PR0Ro0aBSDPTwkhyZh4rOTkZEaOHMm4ceMoV66czr7o6GicnJx0tjk4OAAQFRVFdHQ0QJ7jHBwctPvEs/mv+3P58mUAVq9eTcuWLWndujWTJk0iJSUFQO5PMbl8+TLx8fG8//77NGrUiK5du3LgwAFAnqGS4L/ujzxD+nX9+nUA0tLS6NOnD/7+/nTs2JE9e/YA8vzo2+PuT3h4OLm5ufz555+0bduW5s2bExgYSGxsLCDPT3GKj49n5cqVDBw4EDs7O0Cen5JCkjHxWBMmTMDLyyvPN18AGRkZmJiY6GwzNTUFIDMzk/T0dIB8y2RmZhZRxC+X/7o/ly9fxsDAAAcHBxYvXszo0aM5dOgQgwYNQq1Wy/0pBjk5OVy7do2kpCQ++eQTlixZgqenJ/379+fIkSPyDOnZ4+6PPEP6df/+fQBGjRpFhw4dWL58OY0bN2bQoEHy/JQAj7s/D77MMDc3Z+7cuUydOpVr167RvXt3MjIy5P4UozVr1mBtbU3nzp212+T5KRmMHl9EvMyCgoI4fvw4v/32W777zczMyMrK0tn24AG1sLDAzMwMgKysLO3fH5QxNzcvoqhfHo+7Px999BHdunWjVKlSAFSvXp2yZcvSqVMnQkND5f4UAyMjI0JCQjA0NNS+x7Vr1+bKlSssW7ZMniE9e9z9WbJkiTxDemRsbAxAnz59ePvttwGoWbMmFy5cYMWKFU/0/Py7jNyfZ/e4+7NkyRKaNWuGvb299phq1arRrFkz9uzZQ8WKFQG5P8UhKCiIgIAAnf+n5PkpGaRlTPynTZs2ce/ePZo3b46XlxdeXl4AfPnll/Tt2xcnJydtd4MHHrx2dHTUNm3nV8bR0bEYruDF9rj7Y2BgoP0Q+UC1atUATfcEuT/Fw9LSUucXIGjuQ0xMjDxDJcB/3R95hvTrwXtYvXp1ne1Vq1bl1q1b8vzo2ePuD6CTiIGmi5udnZ08P8Xo4sWLREZG5ulBI89PySDJmPhPs2bN4o8//iAoKEj7AzBkyBCmTp2Kj48PJ06c0FmTIjg4GFdXV0qXLo27uztWVlaEhIRo9ycnJ3PhwgV8fHyK+3JeOI+7PyNHjqRnz546x4SGhgKaX5Zyf4relStX8Pb21nmPAc6dO0fVqlXlGdKzx90feYb0q1atWlhaWnLmzBmd7ZcvX6ZixYr4+Phw4cIFbXc50Dw/lpaWuLu7U7p0aVxdXXXuT05ODsePH5f7Uwged3/mzJlD27ZtURRFu+/WrVskJCRQtWpVuT/F5Pjx49rfJ/8kz08Joe/pHMXz559Tp9+9e1fx8fFRRo0apVy5ckXZtGmTUqdOHWXz5s3a8rNnz1Z8fX2VXbt26azBk5WVpa9LeKH98/7s2rVLqV69ujJ//nzlxo0byr59+5SWLVsqw4cP15aX+1O0cnNzlXfffVdp3769cuzYMSU8PFyZNm2aUrt2beXSpUvyDOnZ4+6PPEP6t3DhQsXLy0v57bffdNaxCg4OVjIyMpTWrVsrffr0UcLCwrTrJM2fP197/Pr165W6desqmzdv1q6T5OfnJ+skFZL/uj+hoaFKrVq1lPHjxyvXrl1Tjh49qgQEBChdunRR1Gq1oihyf4rDmDFjlJ49e+bZLs9PySDJmHhi/15U+MyZM0qnTp2U2rVrKy1atFBWr16tUz4nJ0eZOXOm0rBhQ8XT01Pp16+fEhkZWdxhvzT+fX/++OMPJSAgQKlbt67SuHFjZfr06UpGRoZ2v9yfohcXF6eMHj1aady4sVKnTh2lc+fOyrFjx7T75RnSr8fdH3mG9G/58uVKy5YtlVq1ailvvvmm8tdff2n3RUREKL169VLq1KmjNGnSRPn222+V3NxcneN/+OEHpVmzZkrdunWVbt26KRcuXCjuS3ih/df9+fvvv5XOnTsrnp6eiq+vrzJmzBidda0URe5PUevbt68ydOjQfPfJ86N/KkX5R9uxEEIIIYQQQohiIWPGhBBCCCGEEEIPJBkTQgghhBBCCD2QZEwIIYQQQggh9ECSMSGEEEIIIYTQA0nGhBBCCCGEEEIPJBkTQgghhBBCCD2QZEwIIYQQQggh9ECSMSGEEEUmNDSUwMBAmjdvTt26dWndujVffPEFkZGR+g6tWISEhFCjRg1CQkKeuo7Ro0fTsmVL7euWLVsyevToR5afP38+NWrUoEaNGnTt2vWpz/s4v/zyi/Y8/4xPCCFEwRnpOwAhhBAvpp9//plp06bh5+fHiBEjcHBw4MaNGyxbtoydO3eyatUq3N3d9R1miTdo0CC6d++ufb1gwQKsrKwee9z69esLVO5ptWrVimrVqrFo0SLCw8OL7DxCCPEik2RMCCFEoTtx4gRTp07l/fffZ+zYsdrtfn5+tG7dmoCAAD7//HM2b96sxyifDxUrVtR57eHhUaDjPD09iyCah+zt7bU/Qgghno50UxRCCFHoli1bhrW1NcOHD8+zz97entGjR9OqVSvS0tK0Xfny+/nwww+1x+3atYtu3brh5eVF7dq1adeuHT///LNO3atWraJdu3bUqVOHpk2bMmHCBO7fv//IODdv3oyHhwe//PILjRs3xtfXV9vKs2vXLt555x3q1KlD48aNmTJlCmlpaTrHFySmf8rKyqJ37974+fkRFhYGgKIorFy5ktdee426devy6quvsmzZMhRFAZ68m2J+WrZsyYIFC7QtlV5eXowYMYLU1FSWLFlCs2bNqF+/Pp988gkJCQna486dO0ePHj2oX78+Xl5e9OzZk9OnTz/RuYUQQjyatIwJIYQoVIqicOjQIVq2bIm5uXm+Zdq3b6/9e61atVi/fr3O/m3btrF69Wree+89APbt28fgwYPp3r07n3zyCRkZGaxZs4ZJkyZRu3Zt6tWrx7Zt2/j6668ZNWoUNWrU4Nq1a8yYMYP09HRmzJjxyHhzc3NZvnw5U6dOJSEhgSpVqvDbb7/x2Wef8cYbbzB06FBu377NnDlzCA8PZ8WKFahUqgLF9E85OTkMGzaMc+fOsWLFCmrWrAnAzJkzWbVqFb169aJx48aEhoYya9YscnJyGDBgwFPdg/wsX76cxo0bM2fOHM6dO8c333zD+fPncXBwYPLkydy6dYupU6dSpkwZvvzyS+7fv0/fvn1p2LAh8+fPJysri++++44+ffqwb98+rK2tCy02IYR4WUkyJoQQolAlJCSQmZmJs7NzgcpbWVnpdKk7c+YMGzZsoGfPnrz11lsAhIeH8/bbb+t0efTy8sLPz4+QkBDq1avH0aNHcXZ25v3338fAwABfX18sLCxISkp6bAwDBw6kefPmgCaZnDVrFk2bNmXWrFnaMpUrV6Znz57s37+f5s2bFyimB9RqNaNHjyYkJIQVK1ZQq1YtAJKTk/nxxx/54IMPCAwMBKBRo0bExcVx7NixQk3GrKysmDNnDkZGRjRq1IgtW7YQExPDL7/8ok2sDh48yMmTJwHNe56QkED37t3x9vYGwM3NjfXr15OamirJmBBCFAJJxoQQQhQqQ0NDQNPi9KSio6MZPHgwXl5ejBw5Uru9b9++AKSmpnL9+nVu3rxJaGgooOn6B9CwYUPWr1/PO++8Q+vWrXnllVd44403UKlUjz3vg1YqgGvXrhEdHc2AAQPIycnRbvfx8cHKyorDhw/TvHnzAsX0wKxZszh37hyDBw+mTp062u2nT58mJyeHNm3a6JQfN27c49+sJ1S3bl2MjB7+2i9TpgwWFhY6SZWdnR2XL18GoFq1atjb2zNw4EDatWtH06ZNady4sTZpFEII8ewkGRNCCFGobG1tsbS05M6dO48sk5aWRnZ2Nra2ttpt6enpDBo0CBMTE7799lttUgcQHx/Pl19+ya5du1CpVFSqVIkGDRoAaMdWtW/fHrVazZo1a1i0aBHz58+nQoUKfPbZZzrdIvNjYWGh/XtiYiIAEydOZOLEiXnKxsbGFjimB65fv46Pjw+rVq2ic+fOODo66pyrOCbByG9mxX9e979ZWlry888/891337F9+3bWr1+PmZkZb731FuPGjcPExKQowxVCiJeCJGNCCCEKXZMmTQgJCSEzMxNTU9M8+zds2MCMGTPYuHEjtWrVQlEURo8ezbVr11i7di2lSpXSKf/ZZ59x7do1Vq5ciZeXFyYmJqSnp7Nhwwadch06dKBDhw6kpKRw6NAhli5dSmBgIPXr19cmQI9jY2MDwMiRI/H19c2z/0ECWdCYACZPnoyvry+vvfYaEydOZNGiRTrnio+Px83NTVv+zp073Lx5k/r16xco5qLi5ubG119/TW5uLmfPnmXr1q2sXbuWihUralsGhRBCPD2ZTVEIIUSh6927N4mJiXz77bd59sXFxbF8+XKqVq2qHTu1YMECduzYwZQpU3S6DD5w4sQJ2rRpg5+fn7ZF5sCBA4BmPBbA0KFDGTx4MADW1ta89tprDBo0iJycHG1rVkG4ublRunRpbt26RZ06dbQ/jo6OfPPNN1y4cKHAMT1QpkwZypYty/Dhw9m9ezfbt28HNF0HjY2N2bt3r0755cuXM3z4cJ3WweK2Y8cOGjZsSFxcHIaGhnh5eTFhwgRsbGz+s9VTCCFEwUnLmBBCiELn6enJp59+yrfffsvVq1cJCAigVKlSXLlyhWXLlpGZmalN1Hbu3MnChQvp0KEDbm5unDlzRqebn6enJ3Xr1uW3336jVq1aODk5cfLkSZYsWYJKpSI9PR3QjBn78ssvmTFjBs2aNSM5OZkFCxZQuXLlJ1pc2tDQkGHDhjF+/HgMDQ1p0aIFycnJLFq0iJiYGG0CWZCY/q1Lly4EBQUxdepUGjVqhL29Pd27d2flypWYmJjg6+vLmTNnWLt2LSNHjsTAQH/fmXp7e6NWqxk8eDD9+/fH0tKS7du3k5KSkmeMmxBCiKcjyZgQQogi8dFHH+Hh4cHPP//MtGnTSEpKoly5cjRv3pyBAwdSrlw5APbs2YOiKGzbto1t27blqefSpUtMnz6dyZMnM3nyZEAzs+HEiRP59ddfOX78OKBJdLKzs1m3bh1r1qzBzMwMf39/AgMDMTY2fqLYO3bsiKWlJT/88APr16/HwsICb29vZs2ahYuLC0CBYvo3AwMDJk2axLvvvsuMGTOYNm0agYGBlC5dmnXr1vHDDz/g7OzMF198QZcuXZ4o5sLm4ODADz/8wNy5cxk7dizp6elUq1aN+fPn07BhQ73GJoQQLwqV8u9RxkIIIYQoMYYNG8bly5f5/fffC1R+/vz5LFiwgEuXLhVxZBqjR4/m6NGj7Nmzp1jOJ4QQLxJpGRNCCCFKoJiYGIKDgzl27JjOdPgFdfr0aaysrKhatWoRRKeZdOTmzZvEx8cXSf1CCPEykAk8hBBCiBLoxIkTfPnll5QqVYpPP/30iY/v3LkzX3zxRRFEprF79246d+7M/v37i+wcQgjxopNuikIIIYQQQgihB9IyJoQQQgghhBB6IMmYEEIIIYQQQuiBJGNCCCGEEEIIoQeSjAkhhBBCCCGEHkgyJoQQQgghhBB6IMmYEEIIIYQQQuiBJGNCCCGEEEIIoQeSjAkhhBBCCCGEHkgyJoQQQgghhBB68D9KZUkieQWw7wAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 1000x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "kde = stats.gaussian_kde(reaction_times)\n",
    "kde_pdf = kde(x_grid)\n",
    "\n",
    "plt.figure(figsize=(10, 4))\n",
    "plt.hist(\n",
    "    reaction_times,\n",
    "    bins=20,\n",
    "    density=True,\n",
    "    color='lightgrey',\n",
    "    edgecolor='white',\n",
    ")\n",
    "plt.plot(x_grid, kde_pdf, color='C0', linewidth=2, label='Estymacja jądrowa gęstości')\n",
    "plt.plot(\n",
    "    x_grid,\n",
    "    normal_pdf,\n",
    "    color='black',\n",
    "    linestyle='--',\n",
    "    linewidth=2,\n",
    "    label='Dopasowana normalna',\n",
    ")\n",
    "\n",
    "plt.title('Histogram + estymacja jądrowa gęstości')\n",
    "plt.xlabel('Czas reakcji [ms]')\n",
    "plt.ylabel('Gęstość')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5b38305c",
   "metadata": {},
   "source": [
    "## Interaktywne wygładzanie: estymacja jądrowa gęstości\n",
    "\n",
    "W estymacji jądrowej gęstości kluczowy jest **parametr wygładzania**.\n",
    "\n",
    "- Mniejsze wygładzanie daje bardziej „poszarpaną” krzywą (łatwiej zobaczyć drobne fluktuacje, ale też łatwiej pomylić szum ze strukturą).\n",
    "- Większe wygładzanie daje gładszą krzywą (łatwiej zobaczyć ogólny kształt, ale można ukryć ważne szczegóły, np. dwumodalność).\n",
    "\n",
    "Poniższy suwak pozwala zmieniać wygładzanie i od razu obserwować efekt na wykresie."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "c145de62",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6f68cff73b354ba6a2be590082567098",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "FloatSlider(value=0.3670977715849853, continuous_update=False, description='Wygładzanie:', max=1.5, min=0.15, …"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "73936df154fd4a3eb4a977a667a28ed1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "if os.environ.get('JPY_SESSION_NAME') is None:\n",
    "    print('Ta sekcja korzysta z widgetów Jupyter i wymaga uruchomienia w notatniku. W trybie wsadowym (np. nbconvert) jest pomijana.')\n",
    "else:\n",
    "    import ipywidgets as widgets\n",
    "    from IPython.display import display\n",
    "\n",
    "    kde_default = stats.gaussian_kde(reaction_times)\n",
    "    default_smoothing = float(kde_default.factor)\n",
    "\n",
    "    smoothing_slider = widgets.FloatSlider(\n",
    "        value=default_smoothing,\n",
    "        min=0.15,\n",
    "        max=1.50,\n",
    "        step=0.01,\n",
    "        description='Wygładzanie:',\n",
    "        readout_format='.2f',\n",
    "        continuous_update=False,\n",
    "    )\n",
    "\n",
    "    kde_out = widgets.Output()\n",
    "\n",
    "    def draw_kde(_=None):\n",
    "        smoothing = float(smoothing_slider.value)\n",
    "        x_grid = np.linspace(reaction_times.min(), reaction_times.max(), 400)\n",
    "        kde = stats.gaussian_kde(reaction_times, bw_method=smoothing)\n",
    "        kde_pdf = kde(x_grid)\n",
    "\n",
    "        with kde_out:\n",
    "            kde_out.clear_output(wait=True)\n",
    "\n",
    "            fig, ax = plt.subplots(figsize=(10, 4))\n",
    "            ax.hist(\n",
    "                reaction_times,\n",
    "                bins=20,\n",
    "                density=True,\n",
    "                color='lightgrey',\n",
    "                edgecolor='white',\n",
    "            )\n",
    "            ax.plot(x_grid, kde_pdf, color='C0', linewidth=2, label='Estymacja jądrowa gęstości')\n",
    "\n",
    "            ax.set_title(f'Estymacja jądrowa gęstości (wygładzanie = {smoothing:.2f})')\n",
    "            ax.set_xlabel('Czas reakcji [ms]')\n",
    "            ax.set_ylabel('Gęstość')\n",
    "            ax.legend()\n",
    "            fig.tight_layout()\n",
    "            plt.show()\n",
    "\n",
    "    smoothing_slider.observe(draw_kde, names='value')\n",
    "\n",
    "    display(smoothing_slider, kde_out)\n",
    "    draw_kde()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "43fcf3c8",
   "metadata": {},
   "source": [
    "## Przykład kognitywistyczny: dwie strategie i rozkład dwumodalny\n",
    "\n",
    "Czasem w danych widać więcej niż jeden „szczyt” rozkładu. W psychologii poznawczej może to wynikać z tego, że część osób (albo część prób) przebiega według innej strategii.\n",
    "\n",
    "Prosty przykład: w zadaniu decyzyjnym badany może czasem odpowiadać **automatycznie** (szybko), a czasem **w sposób kontrolowany** (wolniej), np. gdy bodziec jest niejednoznaczny. Jeśli te dwa tryby mieszają się w danych, rozkład czasów reakcji może wyglądać na dwumodalny.\n",
    "\n",
    "Poniżej tworzymy syntetyczne dane z dwóch strategii i sprawdzamy, jak wyglądają na histogramie oraz po wygładzeniu."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "4ec23600",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>strategia</th>\n",
       "      <th>reaction_time_ms</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>szybka</td>\n",
       "      <td>441.410879</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>wolna</td>\n",
       "      <td>639.459014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>wolna</td>\n",
       "      <td>596.494596</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>szybka</td>\n",
       "      <td>440.803467</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>szybka</td>\n",
       "      <td>452.223382</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  strategia  reaction_time_ms\n",
       "0    szybka        441.410879\n",
       "1     wolna        639.459014\n",
       "2     wolna        596.494596\n",
       "3    szybka        440.803467\n",
       "4    szybka        452.223382"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rng_strategie = np.random.default_rng(SEED + 2)\n",
    "\n",
    "n_trials = 200\n",
    "p_szybka = 0.55\n",
    "\n",
    "strategie = rng_strategie.choice(\n",
    "    ['szybka', 'wolna'],\n",
    "    size=n_trials,\n",
    "    p=[p_szybka, 1 - p_szybka],\n",
    ")\n",
    "\n",
    "rt_szybka = rng_strategie.normal(loc=430, scale=35, size=n_trials)\n",
    "rt_wolna = rng_strategie.normal(loc=580, scale=45, size=n_trials)\n",
    "\n",
    "rt = np.where(strategie == 'szybka', rt_szybka, rt_wolna)\n",
    "rt = np.clip(rt, a_min=200, a_max=None)\n",
    "\n",
    "strategie_df = pd.DataFrame({'strategia': strategie, 'reaction_time_ms': rt})\n",
    "strategie_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "fd43560d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "x_grid = np.linspace(strategie_df['reaction_time_ms'].min(), strategie_df['reaction_time_ms'].max(), 400)\n",
    "kde = stats.gaussian_kde(strategie_df['reaction_time_ms'])\n",
    "kde_pdf = kde(x_grid)\n",
    "\n",
    "plt.figure(figsize=(12, 4))\n",
    "\n",
    "plt.subplot(1, 2, 1)\n",
    "sns.histplot(\n",
    "    data=strategie_df,\n",
    "    x='reaction_time_ms',\n",
    "    bins=30,\n",
    "    stat='density',\n",
    "    color='lightgrey',\n",
    "    edgecolor='white',\n",
    ")\n",
    "plt.plot(x_grid, kde_pdf, color='black', linewidth=2, label='Estymacja jądrowa gęstości')\n",
    "plt.title('Dwie strategie: histogram + wygładzenie')\n",
    "plt.xlabel('Czas reakcji [ms]')\n",
    "plt.ylabel('Gęstość')\n",
    "plt.legend()\n",
    "\n",
    "plt.subplot(1, 2, 2)\n",
    "sns.histplot(\n",
    "    data=strategie_df,\n",
    "    x='reaction_time_ms',\n",
    "    hue='strategia',\n",
    "    bins=30,\n",
    "    stat='density',\n",
    "    element='step',\n",
    "    common_norm=False,\n",
    ")\n",
    "plt.title('To samo, z rozbiciem na strategie')\n",
    "plt.xlabel('Czas reakcji [ms]')\n",
    "plt.ylabel('Gęstość')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "058e72d3-4c1f-4c78-a756-32b486b9c09f",
   "metadata": {},
   "source": [
    "## Percentyle, kwartyle, decyle\n",
    "\n",
    "Percentyl $p$ to taka wartość, poniżej której leży $p\\%$ obserwacji.\n",
    "\n",
    "- 25. percentyl to pierwszy kwartyl (Q1),\n",
    "- 50. percentyl to mediana,\n",
    "- 75. percentyl to trzeci kwartyl (Q3).\n",
    "\n",
    "Percentyle są szczególnie przydatne, gdy rozkład jest asymetryczny albo gdy chcemy opisać \"typowy\" zakres bez polegania na średniej i odchyleniu standardowym.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "01000038",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>percentyl</th>\n",
       "      <th>wartość [ms]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>10</td>\n",
       "      <td>451.762932</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>25</td>\n",
       "      <td>489.291144</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>50</td>\n",
       "      <td>526.826779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>75</td>\n",
       "      <td>585.478804</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>90</td>\n",
       "      <td>638.555264</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   percentyl  wartość [ms]\n",
       "0         10    451.762932\n",
       "1         25    489.291144\n",
       "2         50    526.826779\n",
       "3         75    585.478804\n",
       "4         90    638.555264"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "percentiles = [10, 25, 50, 75, 90]\n",
    "values = np.percentile(reaction_times, percentiles)\n",
    "\n",
    "percentile_table = pd.DataFrame(\n",
    "    {\n",
    "        'percentyl': percentiles,\n",
    "        'wartość [ms]': values,\n",
    "    }\n",
    ")\n",
    "percentile_table"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "25453677-c1dc-424d-b79f-8a9a44f2a6ad",
   "metadata": {},
   "source": [
    "### Interaktywny percentyl: linia na histogramie\n",
    "\n",
    "Wybierz percentyl $p$ suwakiem i zobacz, gdzie leży jego wartość na histogramie czasów reakcji.\n",
    "\n",
    "Przypomnienie: $p$-ty percentyl to taka wartość, że około $p\\%$ obserwacji jest **nie większych** od tej wartości."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "a5b1673f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b39607a2155b4af696fe0004909cde94",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "IntSlider(value=50, continuous_update=False, description='Percentyl:', max=99, min=1)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "7801e755fbfe4d1a9b5bda4f9ad83028",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "if os.environ.get('JPY_SESSION_NAME') is None:\n",
    "    print('Ta sekcja korzysta z widgetów Jupyter i wymaga uruchomienia w notatniku. W trybie wsadowym (np. nbconvert) jest pomijana.')\n",
    "else:\n",
    "    import ipywidgets as widgets\n",
    "    from IPython.display import display\n",
    "\n",
    "    percentyl_slider = widgets.IntSlider(\n",
    "        value=50,\n",
    "        min=1,\n",
    "        max=99,\n",
    "        step=1,\n",
    "        description='Percentyl:',\n",
    "        continuous_update=False,\n",
    "    )\n",
    "\n",
    "    percentyl_out = widgets.Output()\n",
    "\n",
    "    def draw_percentyl(_=None):\n",
    "        p = int(percentyl_slider.value)\n",
    "        reaction_times_ms = np.asarray(rt, dtype=float)\n",
    "        value_ms = float(np.percentile(reaction_times_ms, p))\n",
    "\n",
    "        with percentyl_out:\n",
    "            percentyl_out.clear_output(wait=True)\n",
    "\n",
    "            fig, ax = plt.subplots(figsize=(10, 4))\n",
    "            ax.hist(\n",
    "                reaction_times,\n",
    "                bins=20,\n",
    "                density=True,\n",
    "                color='lightgrey',\n",
    "                edgecolor='white',\n",
    "            )\n",
    "            ax.axvline(\n",
    "                value_ms,\n",
    "                color='C3',\n",
    "                linewidth=2,\n",
    "                label=f'{p}. percentyl = {value_ms:.1f} ms',\n",
    "            )\n",
    "\n",
    "            ax.set_title('Percentyl na histogramie czasów reakcji')\n",
    "            ax.set_xlabel('Czas reakcji [ms]')\n",
    "            ax.set_ylabel('Gęstość')\n",
    "            ax.legend()\n",
    "            fig.tight_layout()\n",
    "            plt.show()\n",
    "\n",
    "            print(f'{p}. percentyl: {value_ms:.1f} ms (około {p}% obserwacji jest ≤ tej wartości).')\n",
    "\n",
    "    percentyl_slider.observe(draw_percentyl, names='value')\n",
    "\n",
    "    display(percentyl_slider, percentyl_out)\n",
    "    draw_percentyl()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "59683ecd-c95c-422e-99d4-00a13730cb55",
   "metadata": {},
   "source": [
    "### Interaktywna ranga centylowa: ile danych jest poniżej $x_0$?\n",
    "\n",
    "Czasem interesuje nas pytanie odwrotne niż „jaki jest 90. percentyl?”.\n",
    "\n",
    "Wybieramy konkretną wartość $x_0$ (np. 500 ms) i pytamy: **jaki odsetek obserwacji jest nie większy niż $x_0$?** To właśnie ranga centylowa dla $x_0$.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "b6b1ff64",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "e11e95a2a196433a99bcb5a6ddcb3a3d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "IntSlider(value=500, continuous_update=False, description='x₀ [ms]:', max=704, min=351, step=10)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "9c8aea937ae24d5da9d2b48a21e41824",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "if os.environ.get('JPY_SESSION_NAME') is None:\n",
    "    print('Ta sekcja korzysta z widgetów Jupyter i wymaga uruchomienia w notatniku. W trybie wsadowym (np. nbconvert) jest pomijana.')\n",
    "else:\n",
    "    import ipywidgets as widgets\n",
    "    from IPython.display import display\n",
    "\n",
    "    reaction_times_ms = np.asarray(rt, dtype=float)\n",
    "    min_ms = int(np.floor(reaction_times_ms.min()))\n",
    "    max_ms = int(np.ceil(reaction_times_ms.max()))\n",
    "\n",
    "    default_x0 = 500\n",
    "    if default_x0 < min_ms:\n",
    "        default_x0 = min_ms\n",
    "    if default_x0 > max_ms:\n",
    "        default_x0 = max_ms\n",
    "\n",
    "    x0_slider = widgets.IntSlider(\n",
    "        value=default_x0,\n",
    "        min=min_ms,\n",
    "        max=max_ms,\n",
    "        step=10,\n",
    "        description='x₀ [ms]:',\n",
    "        continuous_update=False,\n",
    "    )\n",
    "\n",
    "    rank_out = widgets.Output()\n",
    "\n",
    "    def draw_rank_percentyl(_=None):\n",
    "        x0 = int(x0_slider.value)\n",
    "        percentyl_rangi = float(stats.percentileofscore(reaction_times_ms, x0, kind='weak'))\n",
    "\n",
    "        with rank_out:\n",
    "            rank_out.clear_output(wait=True)\n",
    "\n",
    "            fig, ax = plt.subplots(figsize=(10, 4))\n",
    "            ax.hist(\n",
    "                reaction_times,\n",
    "                bins=20,\n",
    "                density=True,\n",
    "                color='lightgrey',\n",
    "                edgecolor='white',\n",
    "            )\n",
    "            ax.axvline(x0, color='C1', linewidth=2, label=f'x = {x0} ms')\n",
    "\n",
    "            ax.set_title('Percentyl rangi dla wybranej wartości x')\n",
    "            ax.set_xlabel('Czas reakcji [ms]')\n",
    "            ax.set_ylabel('Gęstość')\n",
    "            ax.legend()\n",
    "            fig.tight_layout()\n",
    "            plt.show()\n",
    "\n",
    "            print(\n",
    "                f'Percentyl rangi dla {x0} ms: {percentyl_rangi:.1f}% '\n",
    "                f'(odsetek obserwacji ≤ {x0} ms).'\n",
    "            )\n",
    "\n",
    "    x0_slider.observe(draw_rank_percentyl, names='value')\n",
    "\n",
    "    display(x0_slider, rank_out)\n",
    "    draw_rank_percentyl()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000025",
   "metadata": {},
   "source": [
    "## Jak opisać rozkład danych: cztery pytania\n",
    "\n",
    "Kiedy opisujemy jedną zmienną ilościową, warto konsekwentnie odpowiedzieć na cztery pytania:\n",
    "\n",
    "1. **Tendencja centralna**: jaka jest typowa wartość? (np. średnia, mediana)\n",
    "2. **Rozproszenie**: jak bardzo wyniki różnią się między sobą? (np. odchylenie standardowe, IQR)\n",
    "3. **Kształt**: czy rozkład jest symetryczny, czy ma ogon? (pomagają histogram i krzywa gęstości oraz porównanie średniej i mediany)\n",
    "4. **Obserwacje odstające**: czy są wartości wyraźnie oddzielone od reszty?\n",
    "\n",
    "Dobrym nawykiem jest łączenie wykresu z jedną–dwiema miarami liczbowymi, zamiast polegać wyłącznie na tabelce.\n",
    "\n",
    "Jedną z prostych miar kształtu jest **skośność**: dodatnia skośność oznacza zwykle \"ogon\" po prawej stronie (kilka bardzo dużych wartości), a ujemna — ogon po lewej.\n",
    "\n",
    "Uwaga kognitywistyczna: czasy reakcji często mają **dodatnią skośność** (długi prawy ogon). Jednym z powodów mogą być sporadyczne **przerwy uwagi** (chwilowe rozproszenie), które produkują bardzo długie czasy reakcji."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "01000026",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>miara</th>\n",
       "      <th>wartość</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>średnia</td>\n",
       "      <td>540.077187</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>mediana</td>\n",
       "      <td>526.826779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>odchylenie standardowe (s, ddof=1)</td>\n",
       "      <td>68.842267</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>skośność</td>\n",
       "      <td>0.278344</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                miara     wartość\n",
       "0                             średnia  540.077187\n",
       "1                             mediana  526.826779\n",
       "2  odchylenie standardowe (s, ddof=1)   68.842267\n",
       "3                            skośność    0.278344"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_rt = float(reaction_times.mean())\n",
    "median_rt = float(np.median(reaction_times))\n",
    "sd_rt = float(reaction_times.std(ddof=1))\n",
    "skew_rt = float(stats.skew(reaction_times, bias=False))\n",
    "\n",
    "summary_shape = pd.DataFrame(\n",
    "    {\n",
    "        'miara': ['średnia', 'mediana', 'odchylenie standardowe (s, ddof=1)', 'skośność'],\n",
    "        'wartość': [mean_rt, median_rt, sd_rt, skew_rt],\n",
    "    }\n",
    ")\n",
    "summary_shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000028",
   "metadata": {},
   "source": [
    "## Notacja: populacja a próba\n",
    "\n",
    "W statystyce rozróżniamy to, co dotyczy populacji (zwykle nieznanej), i to, co liczymy z próby.\n",
    "\n",
    "- **Parametry populacji**: np. średnia $\\mu$ i odchylenie standardowe $\\sigma$.\n",
    "- **Statystyki z próby**: np. średnia z próby $\\bar{x}$ i odchylenie standardowe z próby $s$.\n",
    "\n",
    "W praktyce prawie zawsze mamy do dyspozycji próbę, więc liczymy $\\bar{x}$ i $s$. Różnica między $\\sigma$ i $s$ pojawia się m.in. we wzorze na wariancję: w próbie dzielimy przez $(n-1)$, a nie przez $n$.\n",
    "\n",
    "W Pythonie kontrolujemy to parametrem `ddof` (delta degrees of freedom):\n",
    "\n",
    "- `ddof=0` — dzielenie przez $n$,\n",
    "- `ddof=1` — dzielenie przez $(n-1)$.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000029",
   "metadata": {},
   "source": [
    "## Miary tendencji centralnej\n",
    "\n",
    "Miary tendencji centralnej opisują \"typową\" wartość w zbiorze.\n",
    "\n",
    "**Średnia arytmetyczna**\n",
    "\n",
    "$$\n",
    "\\bar{x} = \\frac{1}{n}\\sum_{i=1}^n x_i\n",
    "$$\n",
    "\n",
    "Jest wygodna i ma dobre własności matematyczne, ale jest wrażliwa na obserwacje odstające.\n",
    "\n",
    "**Mediana** to wartość środkowa w uporządkowanym zbiorze (a przy parzystej liczbie obserwacji — średnia z dwóch środkowych). Jest bardziej odporna na odstające.\n",
    "\n",
    "**Moda** to najczęstsza wartość. Dla danych ciągłych zwykle nie ma jednej \"mody\" bez dodatkowego grupowania/zaokrąglania.\n",
    "\n",
    "**Średnia obcięta** usuwa określony procent najmniejszych i największych obserwacji, a potem liczy średnią. To kompromis między średnią a medianą.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "01000030",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Przykład (scores): n = 55\n",
      "Średnia: 5.399502179550958\n",
      "Mediana: 5.250359991799064\n",
      "Średnia obcięta (10%): 5.4063648337287695\n",
      "Moda: 5.2 (liczność: 3 )\n"
     ]
    }
   ],
   "source": [
    "scores = rng.normal(\n",
    "        loc=5,\n",
    "        scale=3,\n",
    "        size=55)\n",
    "\n",
    "# 1) Mały przykład „na piechotę”: policzmy miary centrum dla listy wyników.\n",
    "scores_sorted = sorted(scores)\n",
    "n_scores = len(scores_sorted)\n",
    "\n",
    "# Średnia\n",
    "mean_scores = sum(scores_sorted) / n_scores\n",
    "\n",
    "# Mediana: przy parzystej liczbie obserwacji bierzemy średnią z dwóch środkowych.\n",
    "middle_left = scores_sorted[n_scores // 2 - 1]\n",
    "middle_right = scores_sorted[n_scores // 2]\n",
    "median_scores = (middle_left + middle_right) / 2\n",
    "\n",
    "# Średnia obcięta: obcinamy po 10% z obu stron (tu: floor(0.1*n) obserwacji).\n",
    "g = int(0.1 * n_scores)\n",
    "trimmed_scores = scores_sorted[g : n_scores - g]\n",
    "trimmed_mean_scores = sum(trimmed_scores) / len(trimmed_scores)\n",
    "\n",
    "# Moda (dla danych dyskretnych): wartość o największej częstości.\n",
    "counts = {}\n",
    "for value in scores_sorted:\n",
    "    counts[value] = counts.get(value, 0) + 1\n",
    "\n",
    "mode_scores = max(counts, key=counts.get)\n",
    "mode_count = counts[mode_scores]\n",
    "\n",
    "# Moda dla danych ciągłych: np. przybliżenie po zaokrągleniu do 0.1\n",
    "rounded_scores = scores.round(1)\n",
    "counts = {}\n",
    "for value in rounded_scores:\n",
    "    counts[value] = counts.get(value, 0) + 1\n",
    "\n",
    "mode_scores = max(counts, key=counts.get)\n",
    "mode_count = counts[mode_scores]\n",
    "\n",
    "print('Przykład (scores): n =', n_scores)\n",
    "print('Średnia:', mean_scores)\n",
    "print('Mediana:', median_scores)\n",
    "print('Średnia obcięta (10%):', trimmed_mean_scores)\n",
    "print('Moda:', mode_scores, '(liczność:', mode_count, ')')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0af0aa6a",
   "metadata": {},
   "source": [
    "### Interaktywny przykład: przerwy uwagi jako obserwacje odstające\n",
    "\n",
    "W danych z czasami reakcji często obserwujemy sporadycznie bardzo długie odpowiedzi. Jednym z możliwych wyjaśnień są **chwilowe przerwy uwagi** (krótkie rozproszenie), które wydłużają czas reakcji w pojedynczych próbach.\n",
    "\n",
    "Poniższy widget pozwala dodać do danych kilka takich prób i zobaczyć, jak zmieniają się miary opisowe. Zwróć uwagę, że średnia zwykle reaguje silniej niż mediana i średnia obcięta.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "2ab8965d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d425d33c75f8457588d84d26107b2f89",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntSlider(value=1, continuous_update=False, description='Liczba prób:', max=10), IntSlider(valu…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "cf5d8d0fe68b43bfb77149dbf1e197ad",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "if os.environ.get('JPY_SESSION_NAME') is None:\n",
    "    print('Ta sekcja korzysta z widgetów Jupyter i wymaga uruchomienia w notatniku. W trybie wsadowym (np. nbconvert) jest pomijana.')\n",
    "else:\n",
    "    import ipywidgets as widgets\n",
    "    from IPython.display import display\n",
    "\n",
    "    lapse_value_slider = widgets.IntSlider(\n",
    "        value=1200,\n",
    "        min=800,\n",
    "        max=3000,\n",
    "        step=50,\n",
    "        description='Wartość [ms]:',\n",
    "        continuous_update=False,\n",
    "    )\n",
    "\n",
    "    n_lapses_slider = widgets.IntSlider(\n",
    "        value=1,\n",
    "        min=0,\n",
    "        max=10,\n",
    "        step=1,\n",
    "        description='Liczba prób:',\n",
    "        continuous_update=False,\n",
    "    )\n",
    "\n",
    "    outlier_out = widgets.Output()\n",
    "\n",
    "    def summarize(values_ms):\n",
    "        values_ms = np.asarray(values_ms, dtype=float)\n",
    "        q1 = float(np.percentile(values_ms, 25))\n",
    "        q3 = float(np.percentile(values_ms, 75))\n",
    "\n",
    "        return {\n",
    "            'n': int(values_ms.size),\n",
    "            'średnia [ms]': float(values_ms.mean()),\n",
    "            'mediana [ms]': float(np.median(values_ms)),\n",
    "            'średnia obcięta 10% [ms]': float(stats.trim_mean(values_ms, proportiontocut=0.1)),\n",
    "            'odchylenie standardowe (ddof=1) [ms]': float(values_ms.std(ddof=1)),\n",
    "            'IQR [ms]': q3 - q1,\n",
    "        }\n",
    "\n",
    "    def draw_outlier_demo(_=None):\n",
    "        lapse_value_ms = int(lapse_value_slider.value)\n",
    "        n_lapses = int(n_lapses_slider.value)\n",
    "\n",
    "        base = reaction_times\n",
    "        if n_lapses > 0:\n",
    "            lapses = np.full(shape=n_lapses, fill_value=lapse_value_ms, dtype=float)\n",
    "            with_lapses = np.concatenate([base, lapses])\n",
    "        else:\n",
    "            with_lapses = base.copy()\n",
    "\n",
    "        summary_df = pd.DataFrame(\n",
    "            [summarize(base), summarize(with_lapses)],\n",
    "            index=['bez przerw uwagi', 'z przerwami uwagi'],\n",
    "        ).reset_index(names='wariant')\n",
    "\n",
    "        with outlier_out:\n",
    "            outlier_out.clear_output(wait=True)\n",
    "\n",
    "            fig, axes = plt.subplots(1, 2, figsize=(12, 4), sharex=True, sharey=True)\n",
    "\n",
    "            for ax, values_ms, title in [\n",
    "                (axes[0], base, 'Bez przerw uwagi'),\n",
    "                (axes[1], with_lapses, f'Z przerwami uwagi (dodano: {n_lapses} × {lapse_value_ms} ms)'),\n",
    "            ]:\n",
    "                ax.hist(\n",
    "                    values_ms,\n",
    "                    bins=20,\n",
    "                    density=True,\n",
    "                    color='lightgrey',\n",
    "                    edgecolor='white',\n",
    "                )\n",
    "\n",
    "                mean_ms = float(np.mean(values_ms))\n",
    "                median_ms = float(np.median(values_ms))\n",
    "\n",
    "                ax.axvline(mean_ms, color='C3', linewidth=2, label='średnia')\n",
    "                ax.axvline(median_ms, color='C0', linestyle='--', linewidth=2, label='mediana')\n",
    "\n",
    "                ax.set_title(title)\n",
    "                ax.set_xlabel('Czas reakcji [ms]')\n",
    "\n",
    "            axes[0].set_ylabel('Gęstość')\n",
    "            axes[0].legend()\n",
    "            axes[1].legend()\n",
    "\n",
    "            fig.tight_layout()\n",
    "            plt.show()\n",
    "\n",
    "            display(summary_df)\n",
    "\n",
    "    for control in [lapse_value_slider, n_lapses_slider]:\n",
    "        control.observe(draw_outlier_demo, names='value')\n",
    "\n",
    "    display(widgets.HBox([n_lapses_slider, lapse_value_slider]), outlier_out)\n",
    "    draw_outlier_demo()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a39a6693",
   "metadata": {},
   "source": [
    "### Interaktywna średnia obcięta\n",
    "\n",
    "Średnia obcięta jest kompromisem między średnią a medianą.\n",
    "\n",
    "- Najpierw usuwamy określony odsetek najmniejszych i największych obserwacji,\n",
    "- a następnie liczymy średnią z pozostałych danych.\n",
    "\n",
    "Suwak poniżej ustala, jaki odsetek obcinamy **z każdej strony** (np. 0,10 oznacza 10% najmniejszych i 10% największych wartości).\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "d9d104a2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "95ee5ae6b94145bca83151c8b2e349c4",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "FloatSlider(value=0.1, continuous_update=False, description='Obcięcie:', max=0.4, step=0.05)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ca077e16e02b4cfc91bdde73ed71d879",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "if os.environ.get('JPY_SESSION_NAME') is None:\n",
    "    print('Ta sekcja korzysta z widgetów Jupyter i wymaga uruchomienia w notatniku. W trybie wsadowym (np. nbconvert) jest pomijana.')\n",
    "else:\n",
    "    import ipywidgets as widgets\n",
    "    from IPython.display import display\n",
    "\n",
    "    obciecie_slider = widgets.FloatSlider(\n",
    "        value=0.10,\n",
    "        min=0.00,\n",
    "        max=0.40,\n",
    "        step=0.05,\n",
    "        description='Obcięcie:',\n",
    "        readout_format='.2f',\n",
    "        continuous_update=False,\n",
    "    )\n",
    "\n",
    "    trimmed_out = widgets.Output()\n",
    "\n",
    "    def draw_trimmed_mean(_=None):\n",
    "        proportion = float(obciecie_slider.value)\n",
    "        x = np.asarray(reaction_times, dtype=float)\n",
    "        n = int(x.size)\n",
    "        g = int(proportion * n)\n",
    "\n",
    "        x_sorted = np.sort(x)\n",
    "        if g > 0:\n",
    "            x_trimmed = x_sorted[g : n - g]\n",
    "            lower = float(x_sorted[g])\n",
    "            upper = float(x_sorted[n - g - 1])\n",
    "        else:\n",
    "            x_trimmed = x_sorted\n",
    "            lower = float(x_sorted[0])\n",
    "            upper = float(x_sorted[-1])\n",
    "\n",
    "        mean_x = float(x.mean())\n",
    "        median_x = float(np.median(x))\n",
    "        trimmed_mean_x = float(x_trimmed.mean())\n",
    "\n",
    "        summary = pd.DataFrame(\n",
    "            {\n",
    "                'miara': ['średnia', 'mediana', 'średnia obcięta'],\n",
    "                'wartość [ms]': [mean_x, median_x, trimmed_mean_x],\n",
    "            }\n",
    "        )\n",
    "\n",
    "        with trimmed_out:\n",
    "            trimmed_out.clear_output(wait=True)\n",
    "\n",
    "            fig, ax = plt.subplots(figsize=(10, 4))\n",
    "            ax.hist(\n",
    "                x,\n",
    "                bins=20,\n",
    "                density=True,\n",
    "                color='lightgrey',\n",
    "                edgecolor='white',\n",
    "            )\n",
    "\n",
    "            ax.axvline(mean_x, color='C3', linewidth=2, label='średnia')\n",
    "            ax.axvline(median_x, color='C0', linestyle='--', linewidth=2, label='mediana')\n",
    "            ax.axvline(trimmed_mean_x, color='C2', linestyle='-.', linewidth=2, label='średnia obcięta')\n",
    "\n",
    "            if g > 0:\n",
    "                ax.axvline(lower, color='black', linestyle=':', linewidth=2, label='granice obcięcia')\n",
    "                ax.axvline(upper, color='black', linestyle=':', linewidth=2)\n",
    "\n",
    "            ax.set_title(\n",
    "                f'Średnia obcięta: obcięcie = {proportion:.2f} z każdej strony '\n",
    "                f'(usunięto {g} + {g} obserwacji)'\n",
    "            )\n",
    "            ax.set_xlabel('Czas reakcji [ms]')\n",
    "            ax.set_ylabel('Gęstość')\n",
    "            ax.legend()\n",
    "            fig.tight_layout()\n",
    "            plt.show()\n",
    "\n",
    "            print(f'n = {n}, n po obcięciu = {int(x_trimmed.size)}')\n",
    "            display(summary)\n",
    "\n",
    "    obciecie_slider.observe(draw_trimmed_mean, names='value')\n",
    "\n",
    "    display(obciecie_slider, trimmed_out)\n",
    "    draw_trimmed_mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000031",
   "metadata": {},
   "source": [
    "## Miary zmienności (rozproszenia)\n",
    "\n",
    "Miary zmienności mówią, **jak bardzo obserwacje różnią się między sobą**.\n",
    "\n",
    "**Wariancja** (dla próby):\n",
    "\n",
    "$$\n",
    "s^2 = \\frac{1}{n-1}\\sum_{i=1}^n (x_i-\\bar{x})^2\n",
    "$$\n",
    "\n",
    "To średni kwadrat odchyleń od średniej (z poprawką $n-1$). Wariancja ma jednostkę \"do kwadratu\" (np. ms²), co utrudnia interpretację.\n",
    "\n",
    "**Odchylenie standardowe** to pierwiastek z wariancji:\n",
    "\n",
    "$$\n",
    "s = \\sqrt{s^2}\n",
    "$$\n",
    "\n",
    "i ma tę samą jednostkę co dane (np. ms), dlatego jest interpretacyjnie wygodniejsze.\n",
    "\n",
    "Dodatkowo często stosuje się miary odporne na odstające:\n",
    "\n",
    "- **rozstęp** (max − min),\n",
    "- **IQR** (rozstęp międzykwartylowy, Q3 − Q1),\n",
    "- **MAD** — odchylenie medianowe (miara odporna na odstające).\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "01000032",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "scores: n = 55\n",
      "Wariancja (dzielenie przez n): 12.948770773175077\n",
      "Wariancja (dzielenie przez n-1): 13.188562824530171\n",
      "Odch. std (sqrt wariancji, n-1): 3.631606094351392\n",
      "\n",
      "Weryfikacja (numpy):\n",
      "var ddof=0: 12.948770773175077\n",
      "var ddof=1: 13.188562824530171\n",
      "std ddof=1: 3.631606094351392\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>miara</th>\n",
       "      <th>wartość</th>\n",
       "      <th>jednostka</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>rozstęp</td>\n",
       "      <td>338.667028</td>\n",
       "      <td>ms</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>wariancja (ddof=0)</td>\n",
       "      <td>4707.662617</td>\n",
       "      <td>ms^2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>wariancja (ddof=1)</td>\n",
       "      <td>4739.257668</td>\n",
       "      <td>ms^2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>odchylenie standardowe (ddof=0)</td>\n",
       "      <td>68.612409</td>\n",
       "      <td>ms</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>odchylenie standardowe (ddof=1)</td>\n",
       "      <td>68.842267</td>\n",
       "      <td>ms</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>IQR</td>\n",
       "      <td>96.187660</td>\n",
       "      <td>ms</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>MAD (skala=1)</td>\n",
       "      <td>47.827874</td>\n",
       "      <td>ms</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                             miara      wartość jednostka\n",
       "0                          rozstęp   338.667028        ms\n",
       "1               wariancja (ddof=0)  4707.662617      ms^2\n",
       "2               wariancja (ddof=1)  4739.257668      ms^2\n",
       "3  odchylenie standardowe (ddof=0)    68.612409        ms\n",
       "4  odchylenie standardowe (ddof=1)    68.842267        ms\n",
       "5                              IQR    96.187660        ms\n",
       "6                    MAD (skala=1)    47.827874        ms"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 1) Mały przykład „na piechotę”: wariancja i odchylenie standardowe dla `scores`.\n",
    "scores_array = np.array(scores, dtype=float)\n",
    "n_scores = int(scores_array.size)\n",
    "\n",
    "mean_scores = float(scores_array.mean())\n",
    "deviations = scores_array - mean_scores\n",
    "squared_deviations = deviations**2\n",
    "sum_squared = float(squared_deviations.sum())\n",
    "\n",
    "var_pop_manual = sum_squared / n_scores\n",
    "var_sample_manual = sum_squared / (n_scores - 1)\n",
    "\n",
    "sd_pop_manual = float(np.sqrt(var_pop_manual))\n",
    "sd_sample_manual = float(np.sqrt(var_sample_manual))\n",
    "\n",
    "print('scores: n =', n_scores)\n",
    "print('Wariancja (dzielenie przez n):', var_pop_manual)\n",
    "print('Wariancja (dzielenie przez n-1):', var_sample_manual)\n",
    "print('Odch. std (sqrt wariancji, n-1):', sd_sample_manual)\n",
    "\n",
    "print('\\nWeryfikacja (numpy):')\n",
    "print('var ddof=0:', float(scores_array.var(ddof=0)))\n",
    "print('var ddof=1:', float(scores_array.var(ddof=1)))\n",
    "print('std ddof=1:', float(scores_array.std(ddof=1)))\n",
    "\n",
    "# 2) Miary zmienności dla czasów reakcji (ms).\n",
    "rt = df['reaction_time_ms'].to_numpy()\n",
    "\n",
    "range_rt = float(rt.max() - rt.min())\n",
    "var_rt_pop = float(rt.var(ddof=0))\n",
    "var_rt_sample = float(rt.var(ddof=1))\n",
    "std_rt_pop = float(rt.std(ddof=0))\n",
    "std_rt_sample = float(rt.std(ddof=1))\n",
    "\n",
    "q1 = np.percentile(rt, 25)\n",
    "q3 = np.percentile(rt, 75)\n",
    "iqr = q3 - q1\n",
    "\n",
    "mad = stats.median_abs_deviation(rt, scale=1)\n",
    "\n",
    "dispersion = pd.DataFrame(\n",
    "    {\n",
    "        'miara': [\n",
    "            'rozstęp',\n",
    "            'wariancja (ddof=0)',\n",
    "            'wariancja (ddof=1)',\n",
    "            'odchylenie standardowe (ddof=0)',\n",
    "            'odchylenie standardowe (ddof=1)',\n",
    "            'IQR',\n",
    "            'MAD (skala=1)',\n",
    "        ],\n",
    "        'wartość': [range_rt, var_rt_pop, var_rt_sample, std_rt_pop, std_rt_sample, iqr, mad],\n",
    "        'jednostka': ['ms', 'ms^2', 'ms^2', 'ms', 'ms', 'ms', 'ms'],\n",
    "    }\n",
    ")\n",
    "dispersion"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fca94a14",
   "metadata": {},
   "source": [
    "## Dane przykładowe: efekt Stroopa (dwa warunki)\n",
    "\n",
    "W wielu badaniach z psychologii poznawczej porównujemy dwie proste sytuacje (dwa warunki). Klasyczny przykład to **efekt Stroopa**: nazwanie koloru napisu jest zwykle wolniejsze, gdy słowo oznacza inny kolor (warunek **niezgodny**), niż gdy słowo i kolor są zgodne (warunek **zgodny**).\n",
    "\n",
    "Poniżej tworzymy niewielki, syntetyczny zbiór danych z dwoma warunkami. To przykład do ćwiczenia opisowych wykresów porównawczych (zwłaszcza wykresu pudełkowego)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "bcf19b4a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>condition</th>\n",
       "      <th>reaction_time_ms</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>zgodny</td>\n",
       "      <td>455.083069</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>zgodny</td>\n",
       "      <td>467.881251</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>zgodny</td>\n",
       "      <td>552.458063</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>zgodny</td>\n",
       "      <td>591.199819</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>zgodny</td>\n",
       "      <td>406.562646</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>zgodny</td>\n",
       "      <td>545.286557</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>zgodny</td>\n",
       "      <td>511.069595</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>zgodny</td>\n",
       "      <td>540.300999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>zgodny</td>\n",
       "      <td>536.552444</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>zgodny</td>\n",
       "      <td>416.539617</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  condition  reaction_time_ms\n",
       "0    zgodny        455.083069\n",
       "1    zgodny        467.881251\n",
       "2    zgodny        552.458063\n",
       "3    zgodny        591.199819\n",
       "4    zgodny        406.562646\n",
       "5    zgodny        545.286557\n",
       "6    zgodny        511.069595\n",
       "7    zgodny        540.300999\n",
       "8    zgodny        536.552444\n",
       "9    zgodny        416.539617"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rng_stroop = np.random.default_rng(SEED + 1)\n",
    "\n",
    "conditions = ['zgodny', 'niezgodny']\n",
    "trials_per_condition_stroop = 40\n",
    "\n",
    "stroop_rows = []\n",
    "\n",
    "for condition in conditions:\n",
    "    if condition == 'zgodny':\n",
    "        mean_ms = 520\n",
    "    else:\n",
    "        mean_ms = 600\n",
    "\n",
    "    sd_ms = 60\n",
    "\n",
    "    stroop_reaction_times = rng_stroop.normal(\n",
    "        loc=mean_ms,\n",
    "        scale=sd_ms,\n",
    "        size=trials_per_condition_stroop,\n",
    "    )\n",
    "    stroop_reaction_times = np.clip(stroop_reaction_times, a_min=200, a_max=None)\n",
    "\n",
    "    for rt_value in stroop_reaction_times:\n",
    "        stroop_rows.append({'condition': condition, 'reaction_time_ms': float(rt_value)})\n",
    "\n",
    "stroop_df = pd.DataFrame(stroop_rows)\n",
    "stroop_df.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000033",
   "metadata": {},
   "source": [
    "## Wykres pudełkowy\n",
    "\n",
    "Wykres pudełkowy jest skróconym, ale bardzo informacyjnym opisem rozkładu.\n",
    "\n",
    "- Linia w środku pudełka to mediana.\n",
    "- Pudełko zwykle obejmuje przedział od Q1 do Q3 (czyli IQR).\n",
    "- \"Wąsy\" często sięgają do wartości w granicach 1.5×IQR od krawędzi pudełka, a punkty poza nimi są oznaczane jako potencjalne obserwacje odstające.\n",
    "\n",
    "Uwaga: obserwacja oznaczona jako odstająca nie musi być błędem. To sygnał, że warto sprawdzić kontekst pomiaru i interpretację.\n",
    "\n",
    "Czasami warto nałożyć na wykres pudełkowy punkty, aby zobaczyć rzeczywisty rozkład próby.\n",
    "\n",
    "W przykładzie poniżej porównamy dwa warunki w zadaniu Stroopa (zgodny i niezgodny)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "01000034",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAwgAAAGMCAYAAAB+u4XwAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjgsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvwVt1zgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAePZJREFUeJzt3XlcFPX/B/DXLiws96mgeHEEioAnIB54puVVHlmpeZd550WmlveteaBmKqKl5kmamR2WJn5LBcsr8cY7QG4QFhZ2fn/w28kF1F2uXeD1fDx8yM58ZuY9e857PpdEEAQBREREREREAKT6DoCIiIiIiAwHEwQiIiIiIhIxQSAiIiIiIhETBCIiIiIiEjFBICIiIiIiERMEIiIiIiISMUEgIiIiIiIREwQiIiIiIhIxQSAiqgY4JyYREWmLCQIRgMuXL2P69Ono0KED/Pz80KVLF3z66ad48OCBvkOrEGfPnoWXlxfOnj1b4n3MmDEDnTp1Eh936tQJM2bMKIvw9OK9997De++9V+b7jYiIgJeXFx4+fFjqfT169AizZs1C+/bt4ePjg1atWuHDDz/EuXPnNMrdvHkT7777bqmPRxUvNDQUXl5e+g5DJw8fPoSXlxciIiLK/VheXl4IDQ0t1T7K8jNZkcri3Imex1jfARDp265du7B48WIEBgZi6tSpqFmzJu7du4ewsDD8/PPP2LFjBxo2bKjvMA3e2LFjMWTIEPHx+vXrYWlpqceIDFOHDh2wd+9e1KxZs1T7efLkCd5++204OTlhypQpqFWrFpKTk7F//34MHToUa9euRdeuXQEAP/74I/7++++yCJ/IoOzduxfOzs6l2kdZfSaJqhImCFStnT9/HosWLcKgQYMwa9YscXlgYCC6dOmCN998EzNnzqyQO2GVXb169TQee3t76ykSw2Zvbw97e/tS72ffvn1IT0/Hjz/+qJGIvfrqq3jrrbc0EgSiqqpp06al3kdZfSaJqhI2MaJqLSwsDFZWVpgyZUqRdfb29pgxYwY6d+6MrKwssRlOcf+ebYpy/PhxDBw4EM2aNYOPjw9ee+017Nq1S2PfO3bswGuvvQZfX1+0a9cOc+fORWZm5nPjjIiIgLe3N/bv3482bdogICAAt27dEo/Xt29f+Pr6ok2bNli4cCGysrI0ttcmpmfl5uZixIgRCAwMRExMDICCNuzbt2/H66+/Dj8/P7z66qsICwsT27br0sToq6++QsOGDZGSkiIu27BhA7y8vPDnn39qxN2wYUPEx8cX2UdZvh6PHz/G+PHj0aJFC7Rp0wbh4eFFjqdQKLBq1Sp07doVPj4+aN68OYYPHy4+P+rnYNiwYTh48CC6desGHx8fvPHGGzh16pRYpnBzhuKaMmnT5CsxMRESiQT5+fkay42MjDB16lS8/fbbAAqaqKxfvx6AZpMELy8vrF+/Hn379oWfn59Y5u7du5g4cSLatGmDpk2b4r333sP58+c1jpGRkYElS5agS5cu8PX1Rc+ePXHgwAGNMp06dcLq1auxePFi+Pv7IzAwECEhIUhNTdUot3//fvTt2xdNmzaFn58f3njjDRw7dkyjjJeX13PfS6mpqfD29sb27dvFZf/++y+8vLwwffp0cZlKpUJgYCC+/PJLAAXNYEJCQtC2bVs0btwYQUFBCAkJ0XhPdurUCYsXL8bQoUPh5+eHWbNmPbc5SuH3u5eXF3bt2oVZs2YhICAAzZo1w6RJk5CYmKixnTaf32c9fvwYHTp0QN++fZGenl5smU6dOj33s6GOOyEhAZMnT0ZAQAD8/f3x2WefYfXq1Rqf4fz8fOzatQu9evWCn58fOnTogJUrVyInJ0fjeD///DN69+4NPz8/9OnTB9euXdNYr34///nnnxgxYgSaNGmCNm3aYMWKFeL7d+LEiQgODoZKpdLYdtasWejWrdtzn4+XNbMpyWcSAKKjozF48GA0adIEAQEB+Pjjj5GcnCyuf++99577HKs/t5mZmfjss88QFBSEZs2aYfLkydi+fXuRJmM//PAD+vbti2bNmqFNmzb47LPPkJaWplHm3LlzePvtt9GkSRN069YNf/zxh8Z6dbOuY8eOYeLEiWjWrBkCAgIwe/Zs8f20bNky+Pn5ISMjQ2PbjRs3okWLFsjOzn7u80jVD2sQqNoSBAGnT59Gp06dYGZmVmyZ7t27i383btwYe/fu1Vj//fff4+uvv0b//v0BACdPnsS4ceMwZMgQTJgwAQqFArt378b8+fPh4+ODJk2a4Pvvv8eKFSvw8ccfw8vLC3fu3MGyZcuQnZ2NZcuWPTfe/Px8bNu2DYsWLUJKSgrc3d1x5MgRTJs2Db169cJHH32ER48eYfXq1bh16xbCw8MhkUi0iulZeXl5mDx5Mq5cuYLw8HA0atQIALB8+XLs2LEDw4cPR5s2bXD58mWsXLkSeXl5GD16tE7PfYcOHbBo0SKcOXMGr7/+OgDgzJkzAICoqCgEBQUBAE6dOgVvb284OTkV2UdZvR5ZWVkYPHgwjI2NsWDBAkilUqxbtw73799Hs2bNxH2HhIQgOjoaU6ZMQb169XDv3j2sXbsWU6dOxdGjRyGRSAAAV65cQUJCAiZOnAhLS0usXbsWEyZMwKlTp2BjY6PT8/Sy53D37t0YMGAABgwYgKCgIHh5ecHIyAht2rRBmzZtAABvvfUW4uLicODAgSLNMTZt2oSpU6fC1dUVLi4uuHXrFgYMGIAGDRpg9uzZkMlk+OqrrzB06FBs27YNAQEBUCgUGDhwIJKSkjBx4kS4uLjg+PHjmDVrFhITE/Hhhx+K+9+9ezfq16+PJUuWIDk5GatWrcK9e/ewZ88eSCQS7Nq1CwsXLsSECRPQokULpKWlYcuWLZg2bRqaNWsmxrp3797n3uG1tbVF06ZN8ccff2DYsGEAICaZ0dHRYrmLFy8iNTUVHTp0QHZ2NoYMGQI7OzvMmTMHVlZW+Pvvv7F+/XrI5XLMnz9f3G7Xrl0YPnw43n//fVhYWCA2Nlbr12j16tV49dVX8fnnn+PBgwdYsmQJjIyM8PnnnwOAVp/fZz158gTDhg2Dra0twsPDYW1tXexx169fj9zcXPFxYmIipk6dipYtW6JWrVrIzc3F0KFDkZWVhZkzZ8LS0hKbN29GTEwMatSoIW732Wef4fDhw3j//ffRsmVLXL16FRs2bEBMTAy2bt0KiUSC3377DRMnTkSvXr0wffp0xMTEaCRmz5o2bRoGDhyI999/HydPnsTWrVtRt25dvPPOO+jfvz9++uknnD17Vvz8KxQK/Pjjj3j//fe1fs6Lo+tnMioqCsOHD0erVq2wZs0apKWlYe3atRgyZAgOHDgAuVyOOXPmaNzUyc7OxpQpU1CjRg34+voCKGh2GRMTg8mTJ6N27drYvXs3Vq1apXGsjRs3Yt26dRg4cCAmT56MBw8eYO3atbhw4QL27dsHuVyOf/75ByNGjECrVq2wbt06PHz4sNibWgAwZ84c9OvXDxs3bsSlS5ewevVq2NnZYerUqejfvz+2bduGH3/8EW+99Za4zeHDh9G9e/fn/g5SNSUQVVNJSUmCp6ensGLFihJtf+HCBcHX11dYvHixuGzLli3Cxx9/rFEuJSVF8PT0FL788ktBEATh008/Fbp16ybk5+eLZQ4fPix89dVXzz3WwYMHBU9PT+HQoUPiMpVKJQQHBwsjR47UKPvHH38Inp6ewokTJ7SO6cyZM4Knp6fwxx9/CFOnThVatGghXLp0SSyflpYmeHt7C4sWLdLYz4IFC8Tjf/zxx0LHjh3FdR07dixy3Gd169ZN+PTTTwVBEISsrCyhcePGQp8+fYTBgweLZTp06CCsW7fuuft4Vklfj507dwpeXl7CzZs3xTKPHz8WGjduLMaSk5MjjBgxQjh69KjGvrZt2yZ4enoKCQkJ4nPg6ekp3Lt3Tyxz7tw5wdPTU/jxxx8FQfjvtXzw4IEgCIIwePBgjXMWhP9ejzNnzrzwnHfu3Ck0b95c8PT0FDw9PYXmzZsL48aNE06fPq1Rbt26dYKnp6fGMk9PT2Ho0KEayyZNmiQEBgYKGRkZ4jKlUil069ZN6NevnyAIgrBr1y7B09NT+OuvvzS2nTlzpuDr6yukpKQIglDw+gcEBAjp6elimV9++UXw9PQUfv/9d0EQBGHJkiVFPn9XrlwRPD09he+///6F5/6sL7/8UmjatKmQm5srCIIgTJs2TejTp4/G87x27Vrx/Xn16lXh3XffFe7fv6+xn9GjRwvdunUTH3fs2FHo0qWLRpnCr9+zZZ99r3l6egrvvvuuRpkZM2YITZs2FQRB+8+v+rVLTk4WevToIfTq1UtITk7W+rnJyckR3nrrLaFz585CamqqIAiCsH//fsHT01O4fPmyWC4jI0MIDAwUn6ObN29qfE7UDh06JHh6egonT54UBEEQ+vbtK7z11lsaZb788kvB09NTOHjwoCAI/72fV69erVGuU6dOwujRowVBEIT8/HwhODhYCAkJEdd/9913QsOGDYV///33uefn6en5wu+Iknwm3377baFnz55CXl6euM2dO3eERo0aCTt37ixyDJVKJYwbN04ICAgQ31Pq1/Gnn34Sy+Xn5wuvv/66+FlMTU0VfHx8xO9BtaioKMHT01M81oQJE4Tg4GDx/S0IgnD06FGNc3/w4IHg6ekpTJs2TWNf7733ntCzZ0/x8dtvvy0MGjRIfHz+/PliP89EbGJE1ZaRkREAFGmioY24uDiMGzcOzZo1Q0hIiLh81KhRWLp0KZ4+fYorV67ghx9+EJs0qO/otWrVCrGxsejbty/Wr1+Py5cvo1evXlqNmKO+mw8Ad+7cQVxcHDp16oS8vDzxn7+/PywtLfG///1P65jUVq5ciSNHjmDIkCHiXTAAuHDhAvLy8oq0aZ89eza2bt2qy1Mn6tChg1hNfv78echkMgwZMgQXL15Ebm4ubt26JTaneJnSvB7R0dGoV68ePDw8xO1q1aql0bbZxMQEYWFh6N69O+Lj43HmzBns2bMHJ06c0NgXUNA07dn+GOq74OVRfT9o0CCcPn0a69evx6BBg1CrVi388ssvGDFiBJYuXfrS7Z99PwEFzRg6duyo0afB2NgYPXr0wJUrV/D06VOcO3cOLi4uGrUrANC7d2/k5OTg4sWL4rJOnTrByspK47GxsTGioqIAFDT/mDZtGtLT03HhwgUcPnxYbP5V+L35Iu3bt0dWVpZ47DNnzmDo0KEwMzMTj3Xq1CnxvdSoUSPs3r0bLi4uuHv3Ln7//XeEhYXhzp07RY5b+DnSReH28c7OzuL7QNvPr9qoUaNw8+ZNzJw5E3Z2dlrHMGvWLNy8eRMbNmwQ75afOXMGdevWhY+Pj1jO0tISHTt2FB+rR8Lq0aOHxv569OgBIyMjnD17FgqFAv/884/GdgDEWsHCCr9nnJ2dxeYvUqkUffr0wc8//yw+R99++y1at25d6k7Iunwms7OzcfHiRbRv3x6CIIivS926deHu7l7kdQGANWvW4LfffsPq1atRt25dAAXPsUwmQ5cuXcRyUqlUo1b6woULyM3NRc+ePTX217JlS7i4uIivwfnz59GuXTvIZDKxTNeuXcXfsGcV9557tslav379EB0djUePHgEoeI5dXV2LvDZEbGJE1ZaNjQ0sLCzw+PHj55bJysqCUqnUqIbOzs7G2LFjYWJigjVr1mh8SScnJ2POnDk4fvw4JBIJ6tevj5YtWwL4bxz67t27Q6VSYffu3di4cSNCQ0Ph4uKCadOmafx4FMfc3Fz8W92We968eZg3b16RsgkJCVrHpBYbGwt/f3/s2LFDHCHn2WOVZUe+9u3bIzw8HA8fPsSff/6J5s2bIygoSLzIvHLlCmrUqKFxEVOc0r4eaWlpxV5w1ahRQ6O9eGRkJBYvXow7d+7AwsICDRs2FF+PZ5/HwtX06mYihdtWlxUzMzO8+uqrePXVVwEA9+7dw8yZMxEeHo6+ffvC09Pzuds++34CCp4LR0fHIuUcHR0hCAIyMzORlpam0Qzl2TIANNrFF24aJpVKYWdnJ7avvn//Pj777DP8+eefkMlkcHNzE0cMK/zefBEvLy/UqlULf/zxB+zs7JCQkIDWrVujefPmOHfuHNq3b49//vkHkyZNErcJDw/Hpk2bkJqaCkdHR/j4+MDMzKxI++zCz5EuCr8XpFKpeF7afn7VsrOzUadOHaxatQp79+6FVPry+3ubN2/Gd999h7Vr12q0e09JSYGDg0OR8s8uU79GhV9rY2Nj2NnZISMjA2lpaRAEocjn53mjAcnlco3Hzz4fQMHF66ZNm/Dzzz+jVatW+PPPP7Fy5cqXnufL6PKZTE9Ph0qlwpYtW7Bly5Yi601NTTUeHz16FJs2bcLHH3+M1q1bi8tTUlJga2tb5HUq7jl+3mdO/V4s7jtK/Tq87FwLP8fdu3fH4sWLcfjwYYwcORLHjh3DBx98UGQ/REwQqFpr27Ytzp49i5ycnCJf/EDBSDHLli3DgQMH0LhxYwiCgBkzZuDOnTv45ptvinxBT5s2DXfu3MH27dvRrFkzmJiYIDs7G/v27dMo17NnT/Ts2RMZGRk4ffo0tmzZgunTp6NFixbFtrcvjrr9cUhICAICAoqsVyc12sYEAAsWLEBAQABef/11zJs3Dxs3btQ4VnJyMtzc3MTyjx8/xv3799GiRQutYn5Wy5YtYWlpiT///BNnzpxBt27d4OTkhAYNGuDs2bM4f/48OnToUKQd9rPK4vWws7PDvXv3iuz72c609+/fx7hx49ClSxd8+eWXqFu3rtiGPjIyUudzL6xwLdaLOqmqy7/66qt48803MXHiRI119evXx+zZs/Hmm2/i1q1bL0wQCrOxsSnSiRYoaPsOFDxXNjY2xT5fz5ZRe7bDrzrulJQU2NvbQ6VS4YMPPoBMJsOBAwfQqFEjGBsb49atWzh8+LDWMau1b98ef/75JxwcHODq6ooaNWogMDAQ+/btw+nTpyGXyxEYGAigoO3/0qVLMX36dPTt21dMfCdNmoTLly+/8DjPu7h8+vSpTvFq+/lV27FjB2JiYvD+++/jq6++EvtbPI/6jvbo0aPx2muvaaxzcnLC3bt3i2yTlJRU5PhPnjyBi4uLuFypVCIlJQV2dnbiBXDh90zhjujaqlu3LgICAnDs2DGkpqbC0tJS4w58RbCwsIBEIsGwYcOK1J4Amhfgly5dwsyZM9GzZ0+MGDFCo5yTkxNSUlKgUqk0koTinuPExESN71Wg4HlX10bY2toWeY4FQSjSkVnb83vttddw7NgxeHp6IisrC2+88YbO+6Gqj02MqFobMWIEUlNTsWbNmiLrnjx5gm3btsHDwwONGzcGUND578cff8TChQuLbXpw/vx5dO3aFYGBgTAxMQEAcbQM9QXFRx99hHHjxgEArKys8Prrr2Ps2LHIy8srctfwRdzc3ODg4ICHDx/C19dX/Ofk5IRVq1bh6tWrWsek5ujoiBo1amDKlCn49ddfxdFk/Pz8IJPJxCY1atu2bcOUKVOKrep+GZlMhjZt2uDXX39FTEyMeJHUqlUrnDx5EtHR0UWaLhRWFq9Hq1at8PDhQ40Lw+TkZFy4cEF8fOXKFeTk5OCDDz5AvXr1xItEdXKgy93uwiwtLREXF1ck7hcxMjJCzZo1cfDgwSIX4QDEjrTq5ECbu80A4O/vjxMnTmh0vszPz8fRo0fh6+sLExMT+Pv749GjR0XmVfjuu+8gk8ng5+cnLjt16pRGk51ff/0VeXl5CAoKQkpKCmJjY9G/f3/4+vrC2NhY3AbQvcalQ4cOuHz5Mk6dOqXxXnr48CH27NmDNm3aiO+B8+fPw9raGqNGjRKTg6dPn+L8+fMvPa66+dWzr9nt27d1vijW9vOrVqNGDQQHB+P111/H2rVrXzip140bNzBt2jS0bdsWH330UZH1AQEBePjwocYIXAqFQiPZVT+HR48e1dj26NGjyM/PR4sWLWBqaopmzZrh559/1vgM/Pbbbzo9F8/q378//vjjD3z//ffo3r17sTduypOlpSW8vb1x584djdfllVdeQWhoqDhCUXx8PMaNGwc3NzcsWrSoyH4CAgKQl5en8VwIgoDjx4+Lj5s0aQITExN8//33GttGR0fj8ePHaN68OQAgKCgIp06d0mgSFRkZCaVSWaJz7N+/P27cuIEdO3agdevWWt+UouqFNQhUrTVt2hSTJk3CmjVrcPv2bbz55puws7PDzZs3ERYWhpycHDF5+Pnnn7Fhwwb07NkTbm5uuHjxosaPonqYxiNHjqBx48ZwdnbGX3/9hc2bN0MikYhf7q1atcKcOXOwbNkyBAcHIz09HevXr0eDBg10mpDNyMgIkydPxmeffQYjIyN07NgR6enp2LhxI+Lj48WkRpuYCnvnnXdw6NAhLFq0CK1bt4a9vT2GDBmC7du3w8TEBAEBAbh48SK++eYbhISEaH0BWlj79u0xc+ZMmJubi02JAgMDsWfPHpiammpU2RdWVq/HG2+8ga+++grjx4/H5MmTYWlpiS+++ELjQrFx48YwNjbGihUrMGLECOTm5iIiIgInT54E8PI7/i/SsWNH/Pbbb1iyZAk6deqE6OhoHDp06KXbzZ49G++99x769u2LIUOGoFGjRlCpVIiKisL27dvxzjvviP0q1Herv//+ezRp0kS8M1nY+PHjcerUKQwZMkS8u79z5048ePBA7GvSt29f7N69G+PGjcPEiRNRp04d/Pbbbzh48CDGjx+vMbLOv//+izFjxmDIkCH4999/8fnnn6Ndu3binXwXFxfs2rULzs7OsLa2RmRkJL766isAmu3DL1y4UKQdeWGtWrWCVCrFyZMnxVGCGjduDAsLC3G+EzU/Pz988803WLp0KTp27IiEhASEhYUhMTHxpSNNBQYGQi6XY+nSpZg0aRKePn2KdevWwdbW9oXbFabt57ewmTNnIjIyEnPmzEFYWFiR9ampqfjwww9hbm6O0aNH48qVKxrv5Xr16qFnz57YvHkzxo0bh0mTJsHa2hrh4eFISkpC7dq1AQAeHh7o06cP1q1bh+zsbPj7+yMmJgbr169HYGAg2rVrBwCYMmUKhg4divHjx+Ptt99GbGwsNm3apNNz8axu3bphwYIFuHTpEj799NMS76c0pkyZgg8++ABTp05F7969xRHkLl68iLFjxyI3Nxfjxo1DZmYmFi5ciBs3bmg8x87OzvD390ebNm3E0b1q166NAwcO4Pr16+INBltbW3zwwQfYsGEDZDIZOnbsiIcPH2Lt2rXi8w8A48aNw/HjxzFy5EiMGjUKycnJWLNmjUafBF20aNECrq6uOHfuHFavXl36J4yqJCYIVO2NGTMG3t7e4ozKaWlpqFWrFjp06IAPP/wQtWrVAlBwV0wQBHz//fdF7vgAwPXr17F06VIsWLAACxYsAAA0aNAA8+bNw3fffScOufjOO+9AqVRiz5492L17N+RyOYKCgjB9+nSdv/DfeustWFhYYOvWrdi7dy/Mzc3RvHlzrFy5UrwI1CamwqRSKebPn49+/fph2bJlWLx4MaZPnw4HBwfs2bMHW7duRZ06dfDpp5/inXfe0SnmZ7Vv3x4SiQTNmzcX7yAHBgZCIpEgMDDwhcPuldXrYWJigh07dmDx4sVYtGgRJBIJBgwYgLp164rNAerXr49Vq1Zh/fr1GDNmDGxsbNC0aVN8/fXXeO+99xAdHV1kbHNt9evXD/fv38e3336LPXv2wN/fH+vWrcO77777wu18fHxw6NAhfPnll9i5cyeePHkCIyMjeHh4YObMmeJQr0BBh8bDhw9jxowZ6N+/P+bOnVvsPl955RXs3r0bn3/+OT755BNIJBL4+fnhq6++EvtumJmZ4euvv8aqVauwdu1aZGZmindRnz0mUNCh1draGh999BHMzc3Rp08fTJ48WVy/ceNGLFq0CDNmzICJiQk8PDzwxRdfYPHixYiOjhY77r/99tvo06fPCztem5mZITAwUKMGwdjYGC1bttTooAwAffr0wcOHD3Hw4EHs3r0bTk5OaN++PQYOHIhPP/0Ut2/fhru7e7HHsba2RmhoKFatWoVx48bBxcUF48eP1yqpK0ybz29hNWvWxJQpUzB//nwcOnQIb775psb669evix1QBw0aVGT7JUuWoG/fvggLC8OiRYswd+5cGBsbo3fv3rC1tdUYxnXRokWoX78+Dh48iC1btqBmzZoYMmQIxo4dK94UaNmyJbZs2YLPP/8c48ePR506dbB48WKN4W51YWpqilatWuHOnTsatVEVqW3btggLC8P69esxceJEyGQyNG7cGOHh4WjatKlGjWNx7ffHjx+PCRMmYPXq1Vi6dClWrVqFvLw8dO7cGe+++67Ge2XChAlwdHTEzp07sXfvXtja2uK1114TPzNAwffWzp07sXTpUkyePBkODg74+OOPtRqI4Hk6dOiA5OTkCm/CRZWHRChN3TgR0f+bPHkybty4UaRJAlVPnTp1QkBAQKkuYqh83Lx5E3fu3EHXrl01+vj0798fzs7O4qR5+qBQKNC+fXuMHTsWQ4cO1VscpfXo0SNcuHABnTt31uicPXHiRDx48ADffvut3mITBAE9evRA27ZtMXPmTL3FQYaNNQhEVCrqYT+joqI0hkYlIsOUlZWFSZMmYeDAgXj11VeRn5+PH374AVeuXMG0adP0EtOjR4/w7bff4o8//oBEIkG/fv30EkdZkUqlmDFjBjp37oz+/fvDyMgIkZGR+Pnnn7FkyRK9xJSZmYnt27fj8uXLePDggVZDa1P1xQSBiErl/PnzmDNnDurWrasxjCQRGaYmTZpgzZo1CAsLw6FDhyAIAry9vbF161a0atVKLzFJpVJ8/fXXsLCwwOrVqzXm4qiMatWqhS1btmDDhg346KOPkJeXB3d3d6xcubLIvAcVRS6XY8+ePVCpVFi8ePFzm7ERAWxiREREREREz+Awp0REREREJGKCQEREREREIiYIREREREQkYiflQv7++28IglDiCUiIiIiIiAyRUqmERCJBs2bNXliOCUIhgiCA/baJiIiIqKrR9hqXCUIh6poDjudORERERFWJehbwl2EfBCIiIiIiEjFBICIiIiIiERMEIiIiIiISMUEgIiIiIiIREwQiIiIiIhIxQSAiIiIiIhETBCIiIiIiEjFBICIiIiIiERMEIiIiIiISMUEgIiIiKgNZCiUexGcgS6HUdyhEpWKs7wCIiIiIKrsrtxMReeER8lUCjKQStGvqAh93R32HRVQiTBCIiIjohZKTk6FQKPQdhsFS5Objx/89hEoQxGU//u8mzI2yITcx0mNkFU8ul8Pe3l7fYVAp6TVBOHv2LIYMGVLsujp16uDXX3/Fw4cPsWDBAkRFRcHc3Bz9+/fHhAkTYGT03wdu165d2LZtG548eQIfHx/Mnj0b3t7eFXUaREREVdbTp08RGhoK4ZmLX9KkyDdFvLJmkeWJN09CbpSjh4j0RyKRYNq0abCwsNB3KFQKek0QmjVrhtOnT2ssu3DhAiZMmICxY8dCqVRi5MiRaNCgAfbs2YP79+9j1qxZkEqlmDhxIgDg22+/xfLly7FgwQJ4e3tj8+bNGD58OI4dO8YMloiIqJQsLCwwYcIE1iAUkpiYiIiICPTt2xeW1naIOKVZgyCVSNA3uGu1rEFgclD56TVBMDExQY0aNcTHWVlZWLJkCfr06YN+/frh+++/x+PHj7Fv3z7Y2NjA09MTSUlJWL58OT788EOYmJhg06ZNGDx4MHr37g0AWLx4Mbp06YL9+/dj9OjR+jo1IiKiKoM33J7P0dERtWvXxmv5ZkX6ILg1YB8EqpwMqg/Cpk2bkJ2djY8//hgAEB0djcaNG8PGxkYs06pVK2RmZiImJgZ16tTB3bt3ERQUJK43NjZGy5YtERUVxQSBiIiIKoSPuyPcXGyQlKaAg40c5nKZvkMiKjGDSRCSk5Oxfft2TJ06Fba2tgCAuLg4ODs7a5SrWbOgjd+///4LY+OC8GvVqlWkzLVr10ociyAIyMrKKvH2REREVLWpm1wpFAqNawYHKyNApURWFoc6JcMjCAIkEslLyxlMgrB7925YWVnh7bffFpcpFApYW1trlDM1NQUA5OTkIDs7G0BBU6XCZXJySt4pSKlUIiYmpsTbExERUdWWmpoKAIiNjUVKSop+gyHSQeHr5uIYTIJw6NAhvPnmm5DL5eIyuVyO3NxcjXLqC39zc3OxbHFlzMzMShyLTCaDh4dHibcnIiKiqi0uLg6RkZFwdXUt0tqByFDdunVLq3IGkSBcu3YNDx48QK9evTSWOzs748aNGxrLEhISAABOTk5i06KEhAS4u7trlHFycipxPBKJBObm5iXenoiIiKo29U1KuVzOawaqNLRpXgQA0nKOQyvR0dFwcHBAw4YNNZb7+/vj6tWryMzMFJedOXMGFhYWaNiwIRwcHODq6oqzZ8+K6/Py8hAdHQ1/f/8Ki5+IiIiIqKowiATh6tWr8PLyKrK8S5cuqFGjBj766CNcu3YNx48fx+eff44RI0aI7adGjBiB8PBwfPvtt7h16xZmzpwJhUKB/v37V/RpEBERERFVegbRxOjJkyfiyEXPMjU1xdatWzFv3jwMGDAANjY2GDhwIMaOHSuWGTBgADIyMrBmzRqkpqbCx8cH4eHhHLOZiIiIiKgEDCJB2LJly3PX1a9fH9u2bXvh9iNHjsTIkSPLOiwiIiIiomrHIJoYERERERGRYWCCQEREREREIiYIREREREQkYoJAREREREQiJghERERERCRigkBERERERCImCEREREREJGKCQEREREREIiYIREREREQkYoJAREREREQiJghERERERCRigkBERERERCImCEREREREJGKCQEREREREIiYIREREREQkYoJAREREREQiJghERERERCRigkBERERERCImCERERFStZCmUeBCfgSyFUt+hEBkkY30HQERERFRRrtxOROSFR8hXCTCSStCuqQt83B31HRaRQWENAhEREVULWQqlmBwAQL5KQOSFR2JNAmsWiAqwBoGIiIiqhaQ0hZgcqOWrBCSlKXDnURprFoj+H2sQiIiIqFpwsJHDSCrRWGYklcDCTPbCmgWi6oYJAhEREVUL5nIZ2jV1EZMEdU3B02zlc2sWiKojNjEiIiKiasPH3RFuLjZISlPAwUYOc7kMWQoljKQSjSTBSCqBo62ZHiMl0h/WIBAREVG1Yi6Xoa6TFczlMvFxcTULZqa8j0rVE9/5REREVO0VV7NQ0bIUSr0en0iNCQIRERERCmoS9HVhzvkZyJCwiRERERGRHr1sfgaiisYEgYiIiEiPXjQ/A5E+MEEgIiIi0qPnzc/AUZRIX5ggEBEREemJumOyv7fzc0dRylIo8SA+g02OqMKwkzIRERGRHhTumBzg7YSa9hYaoxix8zLpg0HUIBw6dAjdu3eHr68vevTogWPHjonrvvjiC3h5eRX596xdu3ahc+fO8PPzw8CBA3H16tWKPgUiIiIirRXXMfnc1XiN5ICdl0lf9J4gHD58GLNmzcKgQYNw9OhR9OzZE1OmTMHff/8NALh+/TreeOMNnD59WuOf2rfffovly5dj0qRJiIiIQJ06dTB8+HAkJyfr65SIiIiIXkibjsnsvEz6otcEQRAErF27FkOGDMGgQYNQr149jBkzBq1bt8a5c+cAADdu3IC3tzdq1Kih8U9t06ZNGDx4MHr37g0PDw8sXrwYZmZm2L9/v75Oi4iIiOiFtOmYzM7LpC96TRBiY2Px6NEj9OrVS2N5WFgYRo8ejdzcXNy9exdubm7Fbp+UlIS7d+8iKChIXGZsbIyWLVsiKiqqXGMnIiIiKilzuQztmro8t2OytmWIyoNe32GxsbEAgKysLIwcORJXr15FnTp1MGbMGHTq1Am3bt1Cfn4+fvrpJyxatAg5OTnw9/fH9OnTUbNmTcTFxQEAatWqpbHfmjVr4tq1ayWOSxAEZGVllfzEiIiIqEpTKBTi/yW9ZnCrZY5a9q5ITs+BvbUpzEyNi+xLmzJE2hIEARKJ5KXl9JogZGZmAgA+/vhjjB8/HtOmTcNPP/2EsWPHIjw8HPHx8QAAMzMzrF27FklJSfj8888xZMgQHDp0CNnZ2QAAExMTjf2ampoiJyenxHEplUrExMSUeHsiIiKq2lJTUwEU3OxMSUkp9f7SE8umDNHLFL5uLo5eEwSZrKCX/siRI9GnTx8AQKNGjXD16lWEh4dj8+bNCA4Ohr29vbjNK6+8guDgYPz222+oV68eACA3N1djvzk5OTAzK3n7PJlMBg8PjxJvT0RERFVbXFwcIiMj4erqCmdnZ32HQ6SVW7duaVVOrwmCk5MTAMDT01NjuYeHB06ePAkAGskBUNB8yNbWFnFxcQgMDAQAJCQkwN3dXSyTkJAg7rskJBIJzM3NS7w9ERERVW1yuVz8n9cMVFlo07wI0HMn5caNG8PCwgIXL17UWH7jxg3Uq1cPq1evRrdu3SAI/w3x9fDhQ6SkpMDDwwMODg5wdXXF2bNnxfV5eXmIjo6Gv79/hZ0HEREREVFVodcaBLlcjlGjRmHDhg1wcnKCn58fjh49iv/973/Yvn07LCwsEBYWhrlz52LYsGFITEzE4sWL0bx5c7Rr1w4AMGLECCxatAj169eHr68vNm/eDIVCgf79++vz1IiIiIhEWQolktIUGhOhERkqvY+TNXbsWJiZmWH16tWIj4+Hu7s7QkNDxeZDW7Zswdq1a9G3b1+YmJigc+fO+Pjjj8UqkgEDBiAjIwNr1qxBamoqfHx8EB4eXqRpEhEREZE+XLmdKM6IrB6q1MfdUd9hET2XRHi2/Q7h8uXLAABfX189R0JERESG6vHjx9i8eTM++OAD1K5d+7nlshRK7Dh6VWNGZCOpBEN7eLMmgSqctte5eu2DQERERFSVJaUpNJIDAMhXCUhKU+gpIqKXY4JAREREVE4cbOTiTMhqRlIJHG1LPhw7UXljgkBERERUTszlMrRr6iImCeo+CGamJesGmqVQ4kF8BrIUyrIMk0iD3jspExEREVVlPu6OcHOxKfUoRuzsTBWFNQhERERE5cxcLkNdJ6sSJwdZCqWYHAAF/RgiLzxiTQKVC9YgEBEREWlJPZ+BMje/Qo/7os7OHA2JyhoTBCIiIqpSymtSsmeb+Ciys5GRZ1Fm+34ZdWfnwsOlsrMzlQcmCERERFRllFc7/cJNfFSCgJQ8OygqqCZB3dm58LmVtLMz0YvwXUVERERVwvPa6bu52JS6JqG4Jj4CJEjNyC3VfnVRVp2diV6GCQIRERFVCeXZTr+4Jj4SCLC1MinVfnVlLpcxMaByx1GMiIiIqEooz0nJCs9nIJVIYGecArmJUan3DXB+AzIsrEEgIiL6f6mpqcjKytJ3GFQKjerKEX0tGSpBgFQiQcuG9khJSkBKGezb3gzo1sIeqRm5yM8Fjt55isTExFLv98bDjCIxe9axKoOIyVCYm5vD1tZW32FojQkCERERCpKD9evXIy8vT9+hUCnlC1IoVTLIpEqcvKPCyXI8VkRERKm2zxekeJRTGwL+q/m4elWAi+ljGElUpQ2PDISxsTHGjx9faZIEJghEREQAsrKykJeXh4CAAFhZ8e4tVYykjHwItxVFlrdw94CDVdk0XyL9ysjIwLlz55CVlcUEgYiIqDKysrKCnZ2dvsOgasLcUoV/HiVB9UxlgVQK1K1lD1MZu4qSfvCdR0RERKQnpjIp/FwtIf3/KzKpFPBztWRyQHrFGgQiIiKi58hRqpD2NA82FsbldtHu6myG2g6m5X4cIm0xQSAiIiIqRmxcNi7FZkKl+u/Ovqtz6YdMLY6pTIqathU7pwLR8zBFJSKtcZxuIqoucpQqMTkAAJUKuBSbiRwlRxaiqo81CESklSu3ExF54RHyVQKMpBK0a+oCH3dHfYdFRFQu0p7maXQcBgqShLSnebzTT1UeEwSqlJKTk6FQFB0WjsqHIjcfP/7vIVSCIC778X83YW6UXWaziJYnuVwOe3t7fYdBRJWIjYUxpFIUGV3IxoKXTlT18V1Olc7Tp08RGhoK4ZmLVSpfinxTxCtrFlmeePMk5EY5eohINxKJBNOmTYOFhYW+QyGiSkI9ulDhPgjsQEzVgVYJQufOnUu0c4lEguPHj5doW6LnsbCwwIQJE1iDUEhiYiIiIiLQt29fODqWbdMfRW4+Ik5p1iBIJRL0De5aaWoQmBwQVQ3pWXl4nJSD2g6msDYv3/ucHF2IqiutPlmPHj1C+/btdaqiT05OxqlTp0ocGNGLsLnI8zk6OqJ27dplvt/X8s2K9EFwa8A+CERUcf64mopz19OhEgCpBAjwskZrb1t9h0VU5Wideo8bNw5+fn5a7/jChQv4/fffSxQUERkeH3dHuLnYIClNAQcbOczlMn2HRETVSHpWnpgcAIBKAM5dT4dPA8tyq0moyGFOiQyJVnVlCxYsQN26dXXacb169bBgwYISBUVEhslcLkNdJysmB0RU4R4n5YjJgZpKKFj+MjlKFRJSc3UaopTDnFJ1plXK/dZbb2k8zszMxNOnT+Hk5ASlUomvv/4ajx8/Rrdu3eDv7w+goAlI4e2IyDBlKZSsGSAig1bbwRRSCTSSBKmkYPmLlLQWgMOcUnWmc2+bixcvomPHjti5cycAYOHChVi+fDm+++47DB06FL/++muZB0lE5efK7UTsOHoVh0/dxo6jV3HldqK+QyIiKsLa3BgBXtaQSgoeq/sgvKh5UWlqAdTDnD6Lw5xSdaFzgrBmzRq4u7tjwIAByM7OxuHDhzFw4ECcO3cO/fv3x6ZNm8ojTiIqB1kKpdjxGADyVQIiLzzSaqZkzqpMRBWttbctRnSrje7+DhjRrfZLOyi/qBbgZdTDnKqThMLDnJak2RJRZaFzGnzx4kWsXr0adevWxfHjx5GTk4M33ngDANC9e3d89913ZR4kEZWPpDSFmByo5asEJKUpXtjUiLMqE5G+WJsba90pubSTnT1vmFN2XqaqTucaBKlUClPTgvZ+kZGRsLa2Fkc3yszMhFwuL9sIiajcONjIYaSur/9/RlIJHG2f/0NXmloHIqKK9LJaAG33UdPWRKPmoCI7L7OmgvRB5xoEHx8f7N+/H3K5HD/++CM6dOgAiUSCpKQkbNmyBT4+PuURJxGVA3O5DO2auhSpDTAzff5XQ0lrHYiI9KGsJzuryM7LrKkgfdE5QZg+fTpGjRqFo0ePwt7eHmPGjAEA9OzZEyqVCmFhYWUeJBGVH13nN1DXOjybJLys1oGISJ/UtQBlobTNlrT1vJqK2g6mnNGZyp3O77DGjRvjl19+wd69e3H8+HE0aNAAADB37lx8//33JapBOHToELp37w5fX1/06NEDx44dE9c9fPgQo0ePRvPmzdG2bVusWbMG+fn5Gtvv2rULnTt3hp+fHwYOHIirV6/qHANRdabL/AbqWgd10yRtah2IiKqKsmi2pI3SdLAmKq0S/aJbWlqiSZMmGsu6detWogAOHz6MWbNmYebMmWjXrh2OHj2KKVOmwNnZGT4+Phg5ciQaNGiAPXv24P79+5g1axakUikmTpwIAPj222+xfPlyLFiwAN7e3ti8eTOGDx+OY8eOwd7evkQxEdGLcVZlIqrOyrrZUnEqqqaCqDg6v8vS0tKwbt06/PXXX0hPTy+yXiKR4Pjx41rtSxAErF27FkOGDMGgQYMAAGPGjEF0dDTOnTuHR48e4fHjx9i3bx9sbGzg6emJpKQkLF++HB9++CFMTEywadMmDB48GL179wYALF68GF26dMH+/fsxevRoXU+PiLRkLpcxMSCiaqssmy09b/9+rpZF+iCweRFVBJ0ThE8//RS//vor2rVrh4YNG5bq4LGxsXj06BF69eqlsVzdj2Hu3Llo3LgxbGxsxHWtWrVCZmYmYmJiUKdOHdy9exdBQUHiemNjY7Rs2RJRUVFMEIiIiKjSqoiaCqLi6Jwg/PHHH5g9ezbefffdUh88NjYWAJCVlYWRI0fi6tWrqFOnDsaMGYNOnTohLi4Ozs7OGtvUrFkTAPDvv//C2Lgg/Fq1ahUpc+3atVLHR0RERKRP5V1TQVQcnRMECwsL1KlTp0wOnpmZCQD4+OOPMX78eEybNg0//fQTxo4di/DwcCgUClhbW2tso56DIScnB9nZ2QAAExOTImVycnJKHJcgCMjKyirx9kT6oFAoxP/5/iXSnfozRERUHgzh91kQBEgkkpeW0zlBGDRoEMLCwtC8eXNYWFiUKDg1mayg/fLIkSPRp08fAECjRo1w9epVhIeHQy6XIzc3V2Mb9YW/ubm5OClbcWXMzEo+5KJSqURMTEyJtyfSh9TUVAAFNXMpKSn6DYaoElJ/hoi0kaNUsekP6cRQfp8L31gvjs4JwuDBg/Htt9+iffv2cHV1LXIhLpFIsGPHDq325eTkBADw9PTUWO7h4YGTJ08iICAAN27c0FiXkJAgbqtuWpSQkAB3d3eNMup9l4RMJoOHh0eJtyfSh7i4OERGRsLV1bVI0zwiejn1Z4joZTiBGZWEIfw+37p1S6tyOicIn332GWJjY+Hm5ga5XA5B0JxRtfDjF2ncuDEsLCxw8eJFtGzZUlx+48YN1KtXD/7+/jh06BAyMzNhaWkJADhz5gwsLCzQsGFDmJiYwNXVFWfPnhU7Kufl5SE6OhoDBw7U9dREEokE5ubmJd6eSB/UNWpyuZzvX6ISUH+GiF7k2QnM8lUCsnNV+PtWBicwo5cyhN9nbZoXASVIEH777TdMnToV77//vs5BFSaXyzFq1Chs2LABTk5O8PPzw9GjR/G///0P27dvR9OmTbFmzRp89NFHmDZtGh4+fIjPP/8cI0aMEKtHRowYgUWLFqF+/frw9fXF5s2boVAo0L9//1LHR0RERIZF30171BOYpWflITlDCQGABMA/9zLR3MP6ZZsTVQo6JwgmJiYlmi35ecaOHQszMzOsXr0a8fHxcHd3R2hoKAIDAwEAW7duxbx58zBgwADY2Nhg4MCBGDt2rLj9gAEDkJGRgTVr1iA1NRU+Pj4IDw/nJGlERERVTOGmPQ3rmsPOUlahyYKNhTEEQRCTAwCABLgbr0Dj+pyngKoGnROEN954A9988w0CAwMhlZbNh2D48OEYPnx4sevq16+Pbdu2vXD7kSNHYuTIkWUSCxH9J0uh5GzJVO0UNwko6V+OUkDUtSyo/v+qPFOhwq1HmXC2M4bMSIKGLiao61gx31M1rfJxJy4fggBIJICthRFyc3Px4N9kOFgZVUgMVHlUxu8UnRMEKysrHDhwAJ06dYKfn1+RkYwkEgkWL15cZgESkX5cuZ2IyAuPkK8SYCSVoF1TF/i4O+o7LKJyFxUVpe8QqBiKfFPEKwvmQhIECZ6qCtpyP8xWwFiSj4cPBbiYPoaRRFXuseQLUkhyXKASjCCBCmkKAekQcD6xYo5PVN50ThAiIiLEmY2vXLlSZL22nR+IyHBlKZRicgAUdMSLvPAIbi42rEmgKs/f37/IHDykfzlKAaeuFtQgKHIFCOl5kEiAWnY2MJIWXHu0cPeosDv4DxKVuPYoFyoBkErw/zUYXhVybKpc0tPTK92NhxJ1UiaiqitLocQ/d5KQo8yHsdF/zQjzVQKS0hRMEKjKs7a2hp2dnb7DoGL4q8xwKTYTxsYCUrME2FnKYC4vuJSRSoG6tewrrA+AnR3g1YBzIVDVpNW7edCgQbh9+7ZOO759+zYGDRpUoqCISD+u3E7EjqNX8b9Lj3HzQSqS0/+bWdZIKoGjLcf5JiL9cXU2w2stHRDsa4vX/R1ga/lfcuDnWvEdhE1lUtS0NWFyQFWOVjUI58+fx9OnT3XacWZmJv76668SBUVEFe/ZZkXGRlI425sjLjkL1hYmMJUZoV1TF5iZ6lzpSERUptQX5TVtTdDAyYx38InKgda/9m+//XZ5xkFEepaUphD7HACAnbUcVhYmaONXG43dHNi0iIgMjjpZIKKypVWCMH78+PKOg4j0zMFGDiOpRCNJMJUZwcfdkTUHRERE1QgTBCIDVdFzEJjLZWjX1KXI0KZMDoiIiKoX/vITGSB9zUHg4+4INxcbTo5GRJVWjpIjCxGVFhMEIgOj7zkIzOUyJgZEVCnFxmXjUmwmVKr/RjZydeboa0S6YmpNZGAKdxYG/puDgIiIipejVInJAQCoVMCl2EzkKDmzMZGumCAQGRh1Z+FncQ4CIqIXS3uaJyYHaipVwXIi0g0TBCIDo+4srE4S2FmYiOjlbCyMIS10VSOVFiwnIt1o9an55JNPMHbsWNStWxeffPLJC8tKJBIsXry4TIIjqq7YWZiISDemMin8XC2L9EFgR2Ui3WmVIJw9exZDhw4V/34RiUTywvVEpB12FiYi0o2rsxlqO5hyFCOiUtIqQfjtt9+K/ZuIiIjIkHB2ZaLSY2pNREREREQirWoQOnfujA0bNqBhw4bo1KnTS5sRmZubo379+pgwYQK8vLzKJFAiIiKi6ooTwFFF0ipBCAgIgIWFhfj3yxKEnJwcnDt3DiEhITh8+HDpoyQiIiKqBMrjQp4TwFFF0ypBWLJkifj30qVLi6zPy8uDsbHmrg4fPoy5c+eWLjoiIiKiSqI8LuSfNwFcbQdT1iRQuSnRO2vz5s344IMPxMfnz59H27ZtsXPnTnFZUFAQFi1aVPoIicggZCmUeBCfgSyFUt+hEBEZnPKayZkTwJE+6Dx7yLZt27BmzRoMHjxYXFavXj289tprWLp0KUxNTfHWW2+hZs2a6N69e5kGS0T6ceV2IiIvPEK+ShAnbvNxd9R3WEREBuNFF/KlGVVJPQHcs/vmBHBU3nSuQdizZw8++ugjzJw5U1xWq1YtzJ49G+PHj8f27dvLMj6iSqOq3mHPUijF5AAA8lUCIi88qnLnSURUGuU1k7N6Ajj1vjkBHFUEnd+18fHx8PX1LXZdkyZN8MUXX5Q6KKLKpirfYU9KU4jJgVq+SkBSmoITuRER/b/ynMmZE8BRRdM5QXBxccGff/6JoKCgIuuioqLg7OxcJoERVRbPu8Pu5mJTJS6gHWzkMJJKNJIEI6kEjrYcQYOI6FnleSHPCeCoIumcIAwYMAArVqyAUqlEly5d4ODggOTkZJw4cQLh4eGYOnVqecRJZLCq+h12c7kM7Zq6FKkhMTNl+1ciosJ4IU9Vgc6/8MOGDUN8fDy+/vprjf4GRkZGGDp0KIYPH16W8REZvOpwh93H3RFuLjZISlPAwUZeJRIfIiIiKl6JbgF+/PHHGDt2LC5cuIDU1FRYW1vDz88PdnZ2ZR0fkcGrLnfYzeUyJgZERETVgM5XMNeuXUPDhg1hZWWFdu3aaazLyMjAsmXLsHDhwjILkKgy4B12IiIiqip07j0zbNgwXLt2rcjyn376Cd27d8ehQ4fKIi6iSsdcLkNdJysmB0RERFSp6ZwgeHt7Y+jQobh69SoAICEhAePHj8ekSZNQu3ZtHDhwoMyDJCIiIjJUOUoVElJzSz1rMpGh0LmJ0aZNmzB58mQMGzYMQ4YMwfbt2yGRSDBnzhy88847kEgk5REnERERkcGJjcsuMveBq3PVGaSCqiedaxBMTEywbt06BAcHY/369WjUqBGOHTuGd999l8kBERERVRs5SpWYHACASgVcis1kTQJVelrVIERFRRVZ9tZbb+Hu3buIiYlBVFQUHB3/mzXW39+/7CIkIiIiMkBpT/PE5EBNpSpYzrkQqDLTKkF47733NGoHBEGARCKBIBSM+z558mTxsUQiQUxMjNYBxMfHIzg4uMjyJUuWoG/fvpg9ezb279+vsc7FxQW//fYbAEClUmH9+vXYv38/MjIy4O/vj88++wx169bVOgaispKlUOp9JCNFbj4exGdwNCUionJmY2EMqRQaSYJUWrCcqDLT6h381VdflVsA165dg6mpKY4fP66RhFhZWQEArl+/jg8//BCDBw8W1xkZGYl/b9y4Ebt378bSpUvh7OyMFStWYNSoUThy5AhMTJi9U8W5cjuxyFwIPu6OL9+wDGXkWSDi1EPIzZL0FgMRUXVhKpPCz9WySB8EU5nOLbiJDIpWCUJAQEC5BXDjxg00aNAANWvWLLJOEATcunULH3zwAWrUqFFkfW5uLrZt24Zp06ahQ4cOAIDVq1ejXbt2+Pnnn9GzZ89yi5voWVkKpZgcAEC+SkDkhUdwc7GpsLv4itx8pOTZwUnQXwxERBUpR6lC2tM82FgY6+2i3NXZDLUdTPUeB1FZKlEd2KVLl3D27Fnk5uaKzYwEQUBWVhbOnz+Pffv2ab2v69evw93dvdh19+/fR1ZWFtzc3Ipdf+3aNTx9+hRBQUHiMmtra3h7eyMqKooJAlWYpDSFmByo5asEJKUpKuziPDUjFwI0Bwqo6BiIiCqKIY0eZCqTavQ5MITEhag0dE4Qdu3ahYULF4qJwbOkUinatm2r0/5u3LgBOzs7DBo0CLGxsahfvz7GjBmD4OBg3LhxAwDw9ddf49SpU5BKpQgODsbkyZNhZWWFuLg4AECtWrU09lmzZk1xXUmokx0ibZmbCBBU+RpJgpFUAguTinsvyWUqSCAgPy8feXl5eomBqDJTKBT6DoG09LzRg2o7mOr9gtyQEhcyLAqFQu+/x+r+wi+jc4Kwc+dOBAcHY/ny5fjyyy+RmZmJmTNn4vfff8eMGTPQu3dvrfeVl5eHO3fuwMPDAzNmzIClpSWOHj2KDz74AOHh4bhx4wakUilq1qyJTZs24f79+1i+fDlu3ryJHTt2IDs7GwCK9DUwNTVFWlqarqcmUiqVOnW0JgKA2tY5+OdeFlQCIJUAjeubI/bOzXI/bo5ShfSsfAjKTNgZpyAzMwM5uTkVGgNRVZCamqrvEEhLhjp6kCEnLqR/sbGxSElJ0XcYWvXR1TlBePjwIWbMmAEbGxv4+Phgw4YNkMvl6NatG+7cuYOvvvpK66Y9xsbGOHv2LIyMjCCXywEAPj4+uHnzJsLCwrB582YMHDgQdnZ2AABPT0/UqFEDAwYMwOXLl8VtcnNzxb8BICcnB2ZmJc/WZTIZPDw8Srx9WUpPT9d7tknasbMDGrnmI+2pEjYWBU161H/LTYxesnXJ3Hr8FH/fTIVKBeTmFtRevO7vACNTq3I9LlV+5ubmsLa21ncYBiUuLg6RkZH6DoO0YKijBxlq4kKGwdXVFc7OznqN4datW1qV0/mTJJPJxIvx+vXr4969e1AqlZDJZGjRogXCw8N12p+FhUWRZa+88gpOnz4NqVQqJgfPrgMKvsjVTYsSEhJQr149sUxCQgK8vLx0iuNZEokE5ubmJd6+rKSmpmLr1q1icxGqPDLyLJCSZwcBEkggwM44BVbGT8v0GPmCFI9yamv0O5DADj/99BOMJJykh17M2NgY48ePh62trb5DMRjP3mgiw2aoowcZauJChkEul+v9+lLbSY11fsc2atQIJ06cQGBgIFxdXaFSqXDx4kW0bNlS53b/N2/exNtvv40vvvgCgYGB4vIrV67Aw8MDISEhSEhIwPbt28V1ly9fBgB4eHigbt26sLS0xNmzZ8UEIT09HVevXtUYFrWyysrKQl5eHgICAsRhX8nw5SgFnLqaBbNnuulIJXXQ1tscprKym208KSMfwu2ibaZbuHvAwYo1B/R8GRkZOHfuHLKyspggUKVliKMHGWriQqQrnROE4cOHY/z48UhPT8fixYvRuXNnhISEoGvXrjhy5AhatGih9b7c3d3h5uaG+fPnY968ebCzs8O+fftw4cIFHDx4EA8ePMDYsWOxfv169O7dG7GxsZg/fz569uwpjnw0ePBgrFy5Evb29nBxccGKFSvg7OyMrl276npqBsvKyqpITQoZroTUXMhk+UWWS00sYVeGVczmlir88yipyJ2qurXs+WNERNVC4dGDDIEhJi5EutI5QejSpQs2bdqE27dvAwDmz5+PqVOnYs+ePfD19cVnn32m9b6kUik2bdqEVatW4aOPPkJ6ejq8vb0RHh4OT09PeHp6Ys2aNdi8eTO2bNkCKysr9OrVCx999JG4j4kTJyIvLw+zZ8+GQqGAv78/wsLCIJNxWEfSj8JVzPkqAXn5KshNyvZHoqzuVHE4PiKqavT9vVZeiYu+z4uqjxI1iuvQoYM4MZmdnR22bdtW4gAcHR2xZMmS565//fXX8frrrz93vZGREaZPn47p06eXOAaisvTshXtqZh5SMpWws5Lh+N/JaOAkR+P6ZVfdXNo7VRyOj4iqmqr6vVZVz4sMU4l7zfz+++/4448/kJCQgClTpiAmJgaNGzeGi4tLWcZHVCm5OpvBwVqGH84loY6jHE9z8hEbn43bjwv+tfS0LrMv9pLeqeJwfERU1VTV77Wqel5kuHROELKzszFu3Dj88ccfsLS0xNOnTzFq1Ch88803uHr1Knbu3CmONERUnSlyVTCVSZGvEhCXkgPF/w9DejdBAYVSpfcvdg7HR0RVTVX9Xquq50WGS+cE4fPPP8c///yD7du3o2XLlvDx8QEALFu2DKNGjcLatWuxfv36Mg+UqLJR90XIVOSLyQEASCUSJKYp8SQ1F3Vq6G9YRbmJFDlKFYyNJDCSFoyuxOH4iApGeaLKSaUUoFTmQKUxihwgKDORklJ2o8hVtKp6XtVFZfxO0flK4NixY5gyZQpatWqF/Pz/RmqpWbMmxowZg/nz55dpgESVlbovwh8xqeIyuUwKiQSA+p+eqNuy5ihViEsp6CNha2HM4fioWjM3N4exsTHOnTun71CoFJ4WMw9NZGLZzkOjD1X1vKoLY2Njvc+BoAudE4T09PTn9jOwsbHhrL9Ez1D3Rdh3Kh7pT/MBCSCRAI7WMtSw0U+18LNtWa3NjWEhN0Jevgodm9jB2py1B1R92draYvz48fwdq4QUuflIzciFrZUJ5CZGRR6Xh8TERERERKBv375wdHQsl2MUVhHnReXD3Ny8Us07o/PVwCuvvIIjR46gbdu2Rdb99ttv7H9AVIi1uTE6N7XH37czoMgtGO60mbtVmd2p13XYu8JtWY2kEhhJjaDIVcG68tzcICoXtra2lepHnIArtxMReeER8lUCjKQStGvqAh/3irlgBwpGY6xdu3aFHY+oIuicIIwZMwbjx49HamoqOnbsCIlEgqioKERERGDPnj1YtWpVecRJVKmV18Q5JRn2rvA8DQD7HhBR5ZSlUIrJAVAw70zkhUdwc7GBubxqz4eUpVAiKU0BBxt5lT9XqnglmihtxYoVWLVqFX7//XcAwNKlS+Hg4IC5c+fitddeK/MgiaqCsp44p6TD3hWeYE0QBNTTY2dpIqKSSkpTiMmBWr5KQFKaokpfNOu71oSqPp0ThNu3b6NXr17o1asX7ty5g9TUVFhbW8PNzQ1SKTs3ElWU0gx7p67R+OdeJu7GK3A3Pgf3n+Rw4h0iqlQcbOQwkko0kgQjqQSOtlX3e6w615pQxdH5in7gwIE4dOgQAMDNzQ3NmzeHh4cHkwOiCqZuKvQsXZsKPXiSA8n/D6ekroHIUapeshURkWEwl8vQrqmLOFSz+m66mWnFNZlU5ObjQXwGshTKcj1OlkKJB/EZePQk87m1JkRlRedPkEwmg52dXXnEQkQ6KNxUSN0HQdv+DZx4h4iqAh93R7i52OilPX5GngUiTj2E3CypXJv6PNukSBAEpD/NhY2lqbi+qteaUMXTOUGYNGkSli9fjoyMDDRs2LDYMV3Zm5+oYpSm8zM7KxNRVWEul1V48xpFbj5S8uzgJJRvU5/CTYokEgkgFPQfk0gkeqk1oapP53fT3LlzkZ+fj+nTpz+3TExMTKmCIiLtlbTzc2lrIIiIqrPUjFwIhWa8LI8O0sV1xLaxMkW3wPqQmxpzFCMqFzonCAsXLiyPOIhIS7rOe/Ai5TX8KhFRVWdrZQIJNC/cy6Opz/M6YtdxsmKtAZUbnd9Zffr0KY84iKq8sriwL8m8By9T1sOvEhFVB3ITI9gZp0AqKd8O0uqO2IWHNWVyQOWJ7y6iClAWF/YlnfeAiIjKh5XxU/QNrgOZmW25NvXRZ0dsqp6YIFQC6enp+g6BSiFHKSDqWhaebUIadS0HZlJzmMokRcpmKlSwlBdc8Kv/NpVJkJSRj2xFTpH9P/g3GQ5WRuV6DlS18DuFqOzITYxQ28mq3I+jj47YVH0xQagEoqKi9B0ClYIi3xTxyppFlh+PT4Dc6L8L/ow8C6Tk2UGABEpVwUdTJs2DBALsjFNgbpSNxzm1NTrFSSDgfOJjGEk4dwERERGVDSYIlYC/vz+sra31HQaVUI5SwKmrmjUIUgnQvvErMDGWaJQxEwpGwfg3JQ8A4GxnDCOpBFJJHQR7myMhLQ/XHuVCJRTso6GLCeo6eunjtKgSS09P540HIiJ6rjJJEJ48eYKEhAQ0bNgQRkZs6lDWrK2tOTldJeevMivSB8Gpxn99EBJScyGT5QMAsnPzIZX+/3jXUhlMTQo+U1ITS/i9YgKvBmU3ihERERFRYTonCJmZmVi0aBF8fHwwaNAgHDt2DNOnT0d+fj4aNGiAbdu2oVatWuURK1Gl9bLhRJ+dtMzEWAqJBIBQ8DegOYEZRx0iIiKi8qTz7cdVq1bhp59+go2NDQBg5cqVaNiwIdavXw9jY2OsXLmyzIMkqgrUF/bF3fVXT1omlf7/ONrWMjjayAqaF3ECMyIiIqpAOtcg/Prrr5gxYwZ69uyJK1eu4NGjRwgJCUHnzp2Rl5eHOXPmlEecRFVe4VoGAGxKRERERBVO5wQhNTUVbm5uAIDff/8dxsbGaNOmDQDAxsYGOTlFh2EkIu0Ubj7EpkRERERU0XS+Leni4oLr168DAI4fP46mTZvC0tISQEHCUKdOnbKNkKiSyFGqkJCaixwlhxwlIiKiykvnGoR33nkHS5cuxa5du3Dnzh18/vnnAIDx48fj119/xezZs8s8SCJDVxYzJVcFOUqOsERERFTZ6ZwgDB06FA4ODoiKisL48ePRvXt3AIBMJsPcuXPx9ttvl3mQRIYsR6kSkwOgYCSiS7GZqO1gWq0ukpkkERERVQ0lmgehZ8+e6Nmzp8ay1atXl0lARJVN2tM8MTlQU6kKluu7D0FF3dFnkkREhiBLoURSmgIONnKYy2X6Doeo0ipRgnDp0iWcPXsWubm5EISCCZ0EQUBWVhbOnz+Pffv2lWmQRIbs2TkM1J6dt0BfKvKOviEnSURUPVy5nYjIC4+QrxJgJJWgXVMX+Lg76jssokpJ5yuYXbt2YeHChWJi8CypVIq2bduWSWBElYV6DoPCF+P6vHNe0Xf0DTVJIqLqIUuhFJMDAMhXCYi88AhuLjZVqiaBNSRUUXT+9d65cyeCg4OxfPlyfPnll8jMzMTMmTPx+++/Y8aMGejdu3d5xElk0F42U3JFq+g7+oaYJBFR9ZGUphCTA7V8lYCkNEWVuZBmDQlVJJ1/vR8+fIiBAwfCxsYGPj4+OH/+PORyObp164YPPvgAX331VXnESWTwXjRTckVT39F/Vnnf0Xd1NsNrLR3QprENXmvpwA7KRFRhHGzkMJJKNJYZSSVwtK0a30PPqyHJUij1HBlVVTpfychkMsjlcgBA/fr1ce/ePSiVBW/QFi1a4O7du2UaIBHpTn1HX50kVNQdfUNKkoio+jCXy9CuqYuYJKjvsJuZVo1mji+qISEqDzp/cho1aoQTJ04gMDAQrq6uUKlUuHjxIlq2bIm4uDidA4iPj0dwcHCR5UuWLEHfvn0RExODRYsW4cqVK7C3t8ewYcMwZMgQsZxKpcL69euxf/9+ZGRkwN/fH5999hnq1q2rcyxEVYmhNXsiIipPPu6OcHOxqZJt9NU1JM8mCVWphoQMj84JwvDhwzF+/Hikp6dj8eLF6Ny5M0JCQtC1a1ccOXIELVq00Gl/165dg6mpKY4fPw6J5L/qQSsrK6SkpGD48OHo1KkT5s2bhwsXLmDevHmwsLBAv379AAAbN27E7t27sXTpUjg7O2PFihUYNWoUjhw5AhMTjp5C1Zv6jj4RUXVgLpdVqcRATV1DUrgPQlWpISHDo/M7q0uXLti0aRNu374NAJg/fz6mTp2KPXv2wNfXF59++qlO+7tx4wYaNGiAmjVrFlm3Y8cOyGQyzJ8/H8bGxnB3d8e9e/ewefNm9OvXD7m5udi2bRumTZuGDh06ACiYj6Fdu3b4+eefi8zVQERERFQZVeUaEjI8JUo9O3ToIF6Q29nZYdu2bSUO4Pr163B3dy92XXR0NAICAmBs/F+YrVq1wpdffonExEQ8fvwYT58+RVBQkLje2toa3t7eiIqKYoJAREREVUZVrSEhw6NzgjBkyBAMGDCg2Ivvixcv4p133kFMTIzW+7tx4wbs7OwwaNAgxMbGon79+hgzZgyCg4MRFxcHT09PjfLqmoZ///1X7PNQq1atImVK0h9CTT3pm74pFOx8RETlR6FQGMR3HVFJZefkITk9B/bWplo1t9G1/Iuof6P5OaLKRBAEjSb9z6Pzp+PcuXOIiorCP//8g5CQEK0O8jx5eXm4c+cOPDw8MGPGDFhaWuLo0aP44IMPEB4eDoVCUaQfgampKQAgJycH2dnZAFBsmbS0tBLHpVQqdUpyyktqaqq+QyCiKiw2NhYpKSn6DoOoRO4m5OCfe1lQCYBUAjSub44GNU3LrPzLqH+j+TmiykabProlSp8HDx6M3bt34/r161i9ejVsbGxKshsYGxvj7NmzMDIyEodO9fHxwc2bNxEWFga5XI7c3FyNbXJycgAA5ubm4ja5ubni3+oyZmYl79kvk8ng4eFR4u3LSlxcHCIjI/UdBpVQjlLFEYTIoLm6usLZ2VnfYRDpLDsnD3/cuglrm/8udB6nS9Ch1SvF1gzoWl4b6t9ofo6oMrl165ZW5Ur0qejVqxd69uyJcePGoX///li/fj28vLxKVJtgYWFRZNkrr7yC06dPw9nZGQkJCRrr1I+dnJyQl5cnLqtXr55GGS8vL51jUZNIJDA3Ny/x9mXl2aSHKpfYuOwiswpz4jAyNHK53CC+64h0lZSRAYnUCMaF7r1k5UrgYFf0Pa1reW2of6P5OaLKRNtr9RLf1mzSpAkOHDgAKysrvPPOO/jhhx8gk+nWcebmzZto3rw5zp49q7H8ypUr8PDwgL+/P86fP4/8/Hxx3ZkzZ+Dq6goHBwc0bNgQlpaWGtunp6fj6tWr8Pf3L+mpEZVKjlIlJgcAoFIBl2IzkaNU6TcwIqIqQteZk6v6TMtEZa1U7R6cnZ2xe/duBAcHY+rUqQgLC9Npe3d3d7i5uWH+/PmIjo7G7du3sWTJEly4cAFjxoxBv379kJmZiVmzZuHWrVuIiIjA9u3bMXr0aAAFbagGDx6MlStX4tdff8W1a9cwefJkODs7o2vXrqU5NaISS3uaJyYHaipVwXIiIio9XWdO1qV8lkKJB/EZyFIoy+8EiAxcqWfYkMvlWLt2LUJDQ7Fx40adtpVKpdi0aRNWrVqFjz76COnp6fD29kZ4eLg4etHWrVuxaNEi9OnTBzVq1EBISAj69Okj7mPixInIy8vD7NmzoVAo4O/vj7CwMJ1rM4jKio2FMaRSaCQJUmnBciIiKhu6zgugTfkrtxOLTEbm4+5YXqdAZLB0vmL56quvip23YMKECfDy8sKJEyd02p+joyOWLFny3PV+fn7Yu3fvc9cbGRlh+vTpmD59uk7HJSovpjIp/Fwti/RBqOiOyuwkTURVna7zAryofJZCKSYHAJCvEhB54RHcXGw49wBVOzonCH5+fkU6z8bExKBRo0bo2rUrm/YQAXB1NkNtB1O9XaCzkzQRkW6S0hRicqCWrxKQlKZggkDVjtZXLdevX0e/fv0QHh6usTw9PR39+vXDG2+8gdjY2DIPkKiyMpVJUdPWRC81B+wkTUSkG3ZkJvqPVlcuDx8+xJAhQ5CYmAhXV1eNdTKZDCEhIUhNTcXAgQMRHx9fLoESkXbYSZqISHe6dnwmqsq0etdv3rwZtra2+Oabb2Bvb6+xzszMDMOGDUOPHj3w1ltv4csvv8Rnn31WLsES0cuxkzQRUcno2vGZqKrSqgbhzz//xKhRo4okB8+qUaMGRowYgf/9739lFhwR6U7dSVr6/59ufXWSJiKqjMzlMtR1sir35IDDqZIh0+qWYkJCAho0aPDScp6enoiLiyttTERUSvruJE1ERM/H4VTJ0GmVINjb2yMhIeGl5VJSUmBjY1PqoIio9NSdpImISis5ORkKhULfYRiUxMREjf+1pcjNx4//ewiV8N+IST/+7ybMjbIhNzEq0xj1QS6Xv7DFCVUOWiUI/v7+iIiIQI8ePV5Y7tChQ/D29i6TwIiIiEj/nj59itDQUAiC8PLC1VBERIRO5RX5pohX1iyyPPHmSciNcsoqLL2RSCSYNm0aLCws9B0KlYJWCcJ7772Hd999F0uXLsXkyZNhamqqsT43Nxdr1qzBqVOnsHnz5nIJlIiIiCqehYUFJkyYwBqEMqLIzUfEKc0aBKlEgr7BXatMDQKTg8pPqwTB19cXn3zyCRYvXozDhw8jKCgIderUQX5+Ph4/foyzZ88iJSUFkyZNQrt27co7ZiIiIqpAbDJStl7LNyvSB8GtAfsgkOHQetzDQYMGoWHDhggLC8Ovv/6KnJyCajALCwu0bdsWI0aMQJMmTcotUCJDlqNUsUMwERFphcOpkqHTaWD0Fi1aoEWLFgAKOiwZGxvD2tq6XAIjqixi47LFmYvVQ4q6OnPmTSIiej5zuYyJARmsEt/qtLe3Z3JA1V6OUiUmB0DB5GSXYjORo1S9eEMiIiIiA8W2EESlkPY0T2PGYqAgSUh7mqefgIiIiIhKiQkCUSnYWBiLMxarSaUFy4mIiIgqIyYIRKVgKpPCz9VSTBLUfRDYUZmIiIgqK97mJColV2cz1HYw5ShGREREVCUwQSAqA6YyKWramug7DCIiIqJS461OIiIiIiISMUEgMhA5ShUSUnM5RCoRERHpFZsYERkATrZGREREhoI1CER6xsnWiIiIyJCwBqESyMjI0HcIVI6SMvKRrcgpsvzBv8lwsDLSQ0RU1fE7hYiIXoQJggEzNzeHsbExzp07p+9QqBzlC1I8zqkNARJxmQQCzic+hpHE8GoR8gUplCoZZFKlQcZH2jE2Noa5ubm+wyAiIgPEBMGA2draYvz48cjKytJ3KFTObjzMQPS1ZKgEAVKJBC0b2sOzjpVO+0hMTERERAT69u0LR0dHg42TDIO5uTlsbW31HQYRERkgJggGztbWlj/i1UDt2kCAnxJJaQo42MhhLpeVeF+Ojo6oXbt2GUZXIEuhRMyfTyA3+6/zdMwDBQL83EoVLxERERkWJghEBsJcLjPoC+2kNAXyVYLGsnyVgKQ0hUHHTURERLrhKEZEpBUHGzmMpBKNZUZSCRxtORwrERFRVcIEgYi0Yi6XoV1TFzFJMJJK0K6pC8xMWRFJRERUlfCXnYi05uPuCDcXmzLpK0FERESGiQkCEenE0PtKEBERUemwiRFRJZKlUOJBfAayFEp9h0JERERVFGsQiCqJK7cTEXnhEfJVgtj+38e9fOY7ICIiourLoGoQYmNj0axZM0RERIjLZs+eDS8vL41/nTp1EterVCqsW7cO7dq1Q9OmTfH+++/jwYMH+gifqNxkKZRicgAUDC8aeeERaxKIiIiozBlMDYJSqcS0adOKzBp8/fp1fPjhhxg8eLC4zMjISPx748aN2L17N5YuXQpnZ2esWLECo0aNwpEjR2BiYlJh8ROVJ85BQERERBXFYGoQQkNDYWlpqbFMEATcunULPj4+qFGjhvjP3t4eAJCbm4tt27Zh4sSJ6NChAxo2bIjVq1cjLi4OP//8sz5Og6hccA4CIiIiqigGkSBERUVh7969WLp0qcby+/fvIysrC25ubsVud+3aNTx9+hRBQUHiMmtra3h7eyMqKqpcYyaqSJyDgIiIiCqK3q8u0tPTERISgtmzZ6NWrVoa627cuAEA+Prrr3Hq1ClIpVIEBwdj8uTJsLKyQlxcHAAU2a5mzZriupIQBKFIUycifXOrZY5a9q5ITs+BvbUpzEyNNd6nCoVC/J/vXyIiIipMEARIJJKXltN7gjB37lw0a9YMvXr1KrLuxo0bkEqlqFmzJjZt2oT79+9j+fLluHnzJnbs2IHs7GwAKNLXwNTUFGlpaSWOSalUIiYmpsTbE5W39MSiy1JTUwEUdPZPSUmp2ICIiIioUtCmj65eE4RDhw4hOjoaR44cKXb9mDFjMHDgQNjZ2QEAPD09UaNGDQwYMACXL1+GXC4HUNAXQf03AOTk5MDMrORts2UyGTw8PEq8PZE+xMXFITIyEq6urnB2dtZ3OERERGRgbt26pVU5vSYIBw8eRFJSEjp06KCxfM6cOfjhhx+wdetWMTlQe+WVVwAUXAypmxYlJCSgXr16YpmEhAR4eXmVOC6JRAJzc/MSb0+kD+okWS6X8/1LRERERWjTvAjQc4KwcuVKsd20WteuXTFx4kT07t0bISEhSEhIwPbt28X1ly9fBgB4eHigbt26sLS0xNmzZ8UEIT09HVevXtUYFpWIiIiIiLSj1wTBycmp2OUODg5wcnJCt27dMHbsWKxfvx69e/dGbGws5s+fj549e8Ld3R0AMHjwYKxcuRL29vZwcXHBihUr4OzsjK5du1bkqRCViSyFEklpCjjYyDm/AREREemF3jspv0jnzp2xZs0abN68GVu2bIGVlRV69eqFjz76SCwzceJE5OXlYfbs2VAoFPD390dYWBhkMl5cUeVy5XaiOFuyehhTH3dHfYdFRERE1YzBJQjXr1/XePz666/j9ddff255IyMjTJ8+HdOnTy/v0IjKTZZCKSYHQMEsyZEXHsHNxYY1CURERFShDGKiNKLqLilNISYHavkqAUlpiudsQURERFQ+mCAQGQAHG7k4S7KakVQCR9uSD9dLREREVBJMEIgMgLlchnZNXcQkQd0HwczU4FoBEhERURXHqw8iA+Hj7gg3F5uXjmLEkY6IiIioPDFBIDIg5nLZCy/6OdIRERERlTc2MSKqJJ430lGWQllhx7/5IAU376dU2DGJiIio4rEGgaiSeNFIR+Xd1OjK7UQcPnUbj55kAgBcHC3xRnt31l4QERFVQaxBIKok9DXSUZZCiRPnH+DRk0wIAiAIwKPETJw4/4A1CURERFUQEwSiSkJfIx0lpSmQpciD8EzlhSAATxV5nKeBiIioCmITI6JKRNuRjspSwXGMIZFATBIkEsBCbsx5GoiIiKogJghElczLRjoqj+N1bFEX6U9zNfogdGxRl/M0EBERVUH8dSeil1LXXDx6kgkIgEtNS87BQEREVEUxQSAirZjLZXilrp2+wyAiIqJyxk7KREREREQkYoJAREREREQiJghERERERCRigkBERERERCImCEREREREJGKCQEREREREIiYIREREREQkYoJAREREREQiTpRGVIllKZRISlPAwUau71CIiIioimCCQFRJXbmdiMgLj5CvEmAklaBRXSYJREREVHpsYkRUCWUplGJyAAD5KgHR15KRL/AjTURERKXDqwmiSigpTSEmB2oqQYBSJdNTRERERFRVMEEgqoQcbOQwkko0lkklEsikSj1FRERERFUFEwSiSshcLkO7pi5ikmAklaBlQ3sYSVR6joyIiIgqO3ZSJqqkfNwd4eZiI45ilJr8BL8KUsQlZcPWXglzOZsbERERke6YIBBVYuZymZgInHuYgUc5tXH8r3icvZGJdk1d4OPuqOcIiYiIqLJhEyOiKiBLoUT0tWQIKGhylK8SEHnhEbIU7JNAREREumGCQGTgshRKPIjPeOHFflKaAipBc1SjfJWApDRFeYdHREREVQybGBEZsMKToT2v2ZCDjRxSieaoRkZSCRxtzSoqVCIiIqoiWINAZKCKmwztec2GzOUytGxoDwkKyqqTCTNT3gMgIiIi3RhUghAbG4tmzZohIiJCXBYTE4PBgwejadOm6NSpE7766iuNbVQqFdatW4d27dqhadOmeP/99/HgwYOKDp2ozBU3GdqLmg151rGCi+ljdGnuhKE9vNlBmYiIiErEYBIEpVKJadOmISsrS1yWkpKC4cOHo169ejh48CDGjRuHlStX4uDBg2KZjRs3Yvfu3ViwYAH27NkDlUqFUaNGITc3Vx+nQVRmipsM7WXNhowkKjg7mHGIUyIiIioxg0kQQkNDYWlpqbFs3759kMlkmD9/Ptzd3dGvXz8MGzYMmzdvBgDk5uZi27ZtmDhxIjp06ICGDRti9erViIuLw88//6yP0yAqM8VNhsZmQ0RERFTeDOJKIyoqCnv37sWhQ4fQoUMHcXl0dDQCAgJgbPxfmK1atcKXX36JxMREPH78GE+fPkVQUJC43traGt7e3oiKikLPnj0r8jSIylzhydBYM0BERETlTe8JQnp6OkJCQjB79mzUqlVLY11cXBw8PT01ltWsWRMA8O+//yIuLg4AimxXs2ZNcR1RZffsZGhERERE5U3vCcLcuXPRrFkz9OrVq8g6hUIBExMTjWWmpqYAgJycHGRnZwNAsWXS0tJKHJMgCBp9IYgqA4VCIf7P9y8REREVJggCJIWGRS+OXhOEQ4cOITo6GkeOHCl2vVwuL9LZOCcnBwBgbm4OuVwOoKAvgvpvdRkzs5KP/65UKhETE1Pi7YmeJ0epQnpWPqzNjWAqK9suQKmpqQAKRgNLSUkp030TERFR1VD4xnpx9JogHDx4EElJSRr9DgBgzpw5+OGHH+Ds7IyEhASNderHTk5OyMvLE5fVq1dPo4yXl1eJ45LJZPDw8Cjx9kTFuXo3BedvxSFfJYGRVIIgX2d4N7Ars/3HxcUhMjISrq6ucHZ2LrP9EhERUdVw69YtrcrpNUFYuXKl2CxCrWvXrpg4cSJ69+6Nw4cPY8+ePcjPz4eRkREA4MyZM3B1dYWDgwOsrKxgaWmJs2fPiglCeno6rl69isGDB5c4LolEAnNz85KfGJW75OTkIu8dQ6bIzcfJ6IdQCf/Na3Ay+j7szVWQmxiVyTEyMzPF/9W1CVRALpfD3t5e32EQERHplTbNiwA9JwhOTk7FLndwcICTkxP69euHrVu3YtasWRg1ahQuXbqE7du3Y968eQAKqkgGDx6MlStXwt7eHi4uLlixYgWcnZ3RtWvXijwVqkBPnz5FaGgoBEF4eWEDocg3RbyyZpHliTdPQm6UU6bHenaiQSogkUgwbdo0WFhY6DsUIiIig6f3Tsov4uDggK1bt2LRokXo06cPatSogZCQEPTp00csM3HiROTl5WH27NlQKBTw9/dHWFgYZDKO+lJVWVhYYMKECZWuBiHilGYNglQiQd/grmVWg0DPJ5fLmRwQERFpSSJUptuwFeDy5csAAF9fXz1HQlXNlduJiLzwCPkqQZz0zMfdUd9hERERUTWh7XWuQdcgEFUlnPSMiIiIKgMmCEQViJOeERERkaEr24HYiYiIiIioUmOCQEREREREIiYIREREREQkYoJAREREREQiJghERERERCRigkBERERERCImCEREREREJGKCQEREREREIk6UVohSqYQgCOJU1EREREREVUFubi4kEslLyzFBKESbJ42IiIiIqLKRSCRaXetKBEEQKiAeIiIiIiKqBNgHgYiIiIiIREwQiIiIiIhIxASBiIiIiIhETBCIiIiIiEjEBIGIiIiIiERMEIiIiIiISMQEgYiIiIiIREwQiIiIiIhIxASBiIiIiIhETBCIiIiIiEjEBIGIiIiIiERMEIiIiIiISMQEgagKi4iIgJeXl77DICKqUKGhoejUqZO+w3gpLy8vRERE6DsMoiKYIBAREVGVMmLECBw4cEDfYRBVWsb6DoCIiIioLFlYWMDCwkLfYRBVWqxBIKogoaGh8PLyKvYfAJw+fRp9+vSBr68vevbsiYMHD8LLywsPHz4EACgUCqxZswadO3eGr68v3njjDfz0008ax/jll1/Qq1cv+Pr6YuDAgXj8+LHG+k6dOiEsLAwTJkxAs2bNEBgYiIULFyIvLw9KpRJBQUFYv369xjZ79uxB27ZtkZeXV47PDhGR9ry8vHDgwAEMGzYMfn5+aNu2rcZ3V+EmRvHx8Zg8eTJatmyJwMBAfPjhh7h79y4A4OHDh8/9bv72228BAMnJyRrbr1y5EkOGDEFoaKh4jJMnT2LAgAFo1qwZ2rZtiyVLlkChUIjr4+LiMGbMGDRr1gzBwcE4cuSIxjmFhoZi2LBh2Lx5M4KDg+Hr64vBgwfj9u3bAIDFixejS5cuGttkZGTAz88PJ0+eLJPnlUiNCQJRBRkxYgROnz4t/tu5cyfMzMwwYcIExMTEYPTo0QgKCsLhw4cxZswYLFu2TGP7KVOm4NChQ/j000/x3XffoUuXLpg0aRKOHz8OAPjrr78wYcIEdOvWDd999x369OmDzZs3F4lj7dq18Pf3x3fffYeQkBDs3LkT33//PWQyGXr37o3vvvtOo/yhQ4fQu3dvGBuzwpGIDMeyZcvQp08fHD16FIMHD0ZoaCiioqKKlMvKysJ7770HANi5cye+/vpr2NnZYcCAAYiPj0etWrU0vptPnTqFli1bwtPTE6+++ipUKhVGjx6Ne/fuYevWrdi2bRsuXLiAc+fOicf45ZdfMGbMGHTo0AERERGYN28efvjhB0yZMgUAkJeXh1GjRiElJQU7d+7E2rVrERYWViTW6OhonD9/Hps3b8bu3buRlJSEefPmAQD69u2LBw8eIDo6Wiz/ww8/wNraGu3atSvT55YIAhFVuOTkZKFLly7C5MmTBUEQhJCQEGHAgAEaZXbs2CF4enoKDx48EG7duiV4enoKv/32m0aZsWPHCv369RMEQRAmT54svPvuuxrrFy5cKHh6eoqPO3bsKIwZM0ajzBtvvCF8+umngiAIwvXr1wVPT0/hr7/+EgRBEO7cuSN4enoKN2/eLIOzJiIqG56ensLChQs1lrVs2VLYtGmTIAiCsG7dOqFjx46CIAjCvn37hMDAQEGpVIpl8/PzhY4dOwrr1q0rsu+FCxcKrVu3Fh4+fCgIgiD8+eefgqenp3D79m2xzJMnTwRfX19x+/79+wsTJkzQ2M8vv/wifn+eOnVK8PT0FO7duyeuv3r1quDp6SkcPHhQjNnLy0tITU0Vy2zfvl1o3Lix+LhPnz7i97UgCMLbb78tLFu2TJunjEgnrEEgqmC5ubkYN24c7OzssGTJEgDA1atX0bRpU41y/v7+4t/Xr18HALRo0aJImRs3bgAAbty4AV9fX431zZo1K3J8d3d3jcdWVlZQKpUAAE9PT/j6+uLQoUMACmoP/Pz84OHhoeNZEhGVrxd9lz3r6tWrSEtLg7+/P5o1a4ZmzZqhRYsWiIuLE5vvqO3atQt79+7Fhg0b4OLiIm5vY2MDNzc3sZyjoyNcXV3Fxzdu3EDz5s019hUQECCuu3HjBmxsbFCvXj1xfaNGjSCXyzW2cXR0hI2NzXPPqV+/fjh27Bhyc3Nx7949/P333+jXr9+LnyiiEmCbAaIKNnPmTPz777/Yv38/TE1NAQBGRkZQqVQ670sQBLHpj0QiKbIPmUxWZBsTE5Ni96PWr18/rF69GrNmzcKRI0cwatQoneMiIipvL/suU1OpVHB1dcUXX3xRZJ25ubn496lTp7B48WIsXbpU44aNNt/PzzsuABgbGxf7/axe96zizulZvXr1wrJly3DixAncuHEDfn5+RRIlorLAGgSiCrR+/Xr8+uuv+OKLL+Do6Cgub9iwIS5duqRR9u+//xb/VndkPn/+vEaZ6Oho8e5+w4YNNbYBgCtXrugcY8+ePZGTk4Pw8HAkJiaiZ8+eOu+DiMhQeHp64vHjx7CyskL9+vVRv3591K5dG6tWrRL7LFy/fh2TJ0/GBx98gF69emls37BhQ2RkZGjUNqSkpODevXviYy8vL/z1118a26n7Cri7u6NRo0bIyMjAzZs3xfV3795FZmamTudibW2NV199Fb/88gt++ukn9O3bV6ftibTFBIGoghw5cgQbN27EokWLUKNGDTx58kT8N2zYMFy+fBkrV65EbGwsfvnlF6xbtw5AQc2Au7s7OnbsiHnz5uHkyZOIjY0Vk40RI0YAKOgEfe3aNSxbtgyxsbH47rvvsHPnTp3jtLKywquvvoqNGzeic+fOsLa2LtPngYioIvXu3Rs2NjaYOHEiLl68iNu3b2PGjBk4deoUvLy88OTJE3z44YcICgrCe++9p/HdnJGRgcDAQDRp0gQhISG4cOECrl27hmnTpiE7OxsSiQQAMGrUKPz888/YuHEjYmNjceLECSxYsAAdO3aEu7t7kX1cvnwZISEhkEp1vwzr168ffvnlF9y/fx89evQo66eLCAATBKIKs2/fPuTn52Py5Mlo3bo12rZtK/5LS0vD+vXrcfLkSfTq1Qvr1q3D4MGDAfzXTOjzzz9Hly5dMGvWLPTu3RsnTpxAaGgoXnvtNQAF7Vm3bNmCs2fPonfv3ti+fTs+/PDDEsXat29fKBQK3p0iokrPysoKO3fuhJ2dHUaOHIn+/fsjPj4e27Ztg7u7OyIjI/H48WP88ssvCAoK0vhuXrRoEYCCIUidnZ0xbNgwDB06FH5+fqhdu7b4/dytWzd8/vnnOHbsGHr16oU5c+agR48eWLNmDQBAKpXiyy+/hJubG0aMGIHRo0ejR48esLe31/l8goKCYGdnhy5duvAGDpUbiVBcwzkiqlCXLl2CsbExvL29xWVHjhzBzJkz8ffff1f4EKMREREIDQ3Fr7/+WqI7XEREVUVycjIuXryItm3biglBbm4uAgMDMWfOHLz55psVGs/Tp0/Rtm1bbNiwAa1bt67QY1P1wU7KRAYgJiYGK1aswLJly9CoUSPcu3cPoaGh6NGjR4UmB//88w/u3Lkj1mAwOSCi6s7Y2BiTJ0/GO++8g3fffRdKpRJhYWEwMTFBcHBwhcWRlpaGM2fO4NixY3BxcUFQUFCFHZuqH9YgEBkAQRCwYcMGfPvtt4iPj4eDgwN69OiBiRMnFhkGrzzt2rULy5cvR4cOHbBy5cpiR0EiIqpuzpw5gzVr1uD69euQSqVo3rw5pk2bJg4gURGSk5PRtWtX2NvbY82aNRo1zkRljQkCERERERGJ2H6AiIiIiIhETBCIiIiIiEjEBIGIiIiIiERMEIiIiIiISMQEgYioGps0aRICAwOLLL98+TK8vLzQvHlzKJVKjXVXrlyBl5cXDh06VEFRls7Dhw/h5eWFiIgIfYdCRFQpMEEgIqrGgoKCkJqaijt37mgsj4yMhK2tLZ4+fYq///5bY110dDQAoE2bNhUWJxERVRwmCERE1Zh6sqW//vpLY/np06fx2muvoXbt2oiMjNRYFxUVBU9PT9SoUaPC4iQioorDBIGIqBqrX78+XFxcNBKEjIwMXLx4Ea1bt0ZQUBBOnz6tsc358+fRpk0b5OfnY/PmzejZsyf8/PzQtGlTvPPOOzhz5oxYNjQ0FK+++irWr1+PgIAAtG3bFmlpafDy8kJoaKjGfkNDQzUmnpoxYwaGDRuGgwcPolu3bvDx8cEbb7yBU6dOaWz3+PFjTJkyBQEBAWjSpAmGDh2Kq1evPvecBUHAJ598Aj8/vyLnRkREgLG+AyAiIv1q1aqVRoLw559/QhAEBAUFIT8/HxEREUhMTISjoyNu3bqFlJQUtGnTBitXrsQ333yDqVOnwsvLC/Hx8diwYQMmTZqEkydPwszMDEDBBfzvv/+O1atXIzU1FTY2NlrHduXKFSQkJGDixImwtLTE2rVrMWHCBJw6dQo2NjZITk7GO++8AzMzM3z66acwMzPDjh07MGjQIBw4cADu7u5F9rlw4UJ8//332LBhA9q2bVv6J5CIqIphgkBEVM0FBQXh4MGDSE5Ohr29PSIjI+Hn5wdra2u0bt0aEokEp0+fxptvvomoqCiYmJjA398fhw4dwuTJk/Hee++J+zI1NcWECRNw/fp1NG3aFACQl5eHjz/+GC1bttQ5toyMDERERKBevXoAAHNzcwwePBhnzpxBt27dsGPHDqSmpuKbb76Bi4sLACA4OBjdu3fH2rVrsW7dOo39rVq1Cnv37sX69esRHBxcwmeMiKhqY4JARFTNqfsh/P333+jcuTNOnz6Nfv36AQBsbW3RuHFj/PHHH3jzzTcRHR2N5s2bQy6XY9WqVQCA5ORk3LlzB/fu3cOJEycAALm5uRrHaNSoUYlis7e3F5MDAHB2dgYAZGdnAyio7WjUqBGcnJyQl5cHAJBKpQgODsZ3332nsa9du3bhypUrePPNN9GhQ4cSxUNEVB0wQSAiquYcHR3h6emJv/76Cw0aNMDjx4/Rrl07cX2bNm3EIU3Pnz+PgQMHAigYCnXevHm4fPkyzMzM4OHhgdq1awMoaOf/LAsLixLFpm6mpCaRSAAAKpUKAJCamop79+6hcePGxW6vTiQA4Nq1a2jbti2+//57DB06FN7e3iWKiYioqmOCQEREaNWqFS5evIhatWrB1tYWvr6+4rq2bdti06ZNOHPmDP7991+0adMGmZmZGDVqFLy8vHD06FG4ublBKpXi999/x08//aTVMfPz8zUeZ2Vl6Ry3lZUVAgICEBISUux6ExMT8e9JkyZhyJAh6NGjB2bPno39+/fDyMhI52MSEVV1HMWIiIjQunVr/PPPPzh79iyCgoIglf7389C0aVNYWFhg9+7dsLOzg7e3N+7cuYPU1FQMGTIEHh4eYnn1CEPqO/zPY2lpifj4eI1lhYda1UZAQABiY2Ph6uoKX19f8d/hw4dx4MABjQTA0dERcrkcn332Gf755x+Eh4frfDwiouqANQhERAR/f3/k5ubixIkTmDt3rsY6mUyGgIAA/Pbbb+jatSskEglcXV1haWmJTZs2wdjYGMbGxvjpp59w4MABAJpNe4rToUMHHD16FE2aNEH9+vURERGBe/fu6Rz3sGHDcPjwYQwbNgwjRoyAnZ0dfvjhB+zbtw+ffPJJsdu0b98er732GkJDQ9GtWzfUrVtX5+MSEVVlrEEgIiJYWlrC19cXSqWy2KE/27VrB6VSidatWwMoaNqzceNGCIKASZMmISQkBI8fP8bOnTthYWEhzrb8PJ988gk6duyIZcuWYeLEiTA3N8fUqVN1jtvJyQl79uyBi4sL5s6diw8//BCXLl3CokWLMGzYsOduN3PmTBgbG+PTTz/V+ZhERFWdRCjck4yIiIiIiKot1iAQEREREZGICQIREREREYmYIBARERERkYgJAhERERERiZggEBERERGRiAkCERERERGJmCAQEREREZGICQIREREREYmYIBARERERkYgJAhERERERiZggEBERERGRiAkCERERERGJ/g8I7MQHsVcLlAAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 900x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(9, 4))\n",
    "order = ['zgodny', 'niezgodny']\n",
    "\n",
    "sns.boxplot(data=stroop_df, x='condition', y='reaction_time_ms', order=order, color='lightgrey')\n",
    "sns.stripplot(data=stroop_df, x='condition', y='reaction_time_ms', order=order, alpha=0.6, size=4)\n",
    "\n",
    "plt.title('Czas reakcji w zadaniu Stroopa: warunek zgodny i niezgodny')\n",
    "plt.xlabel('Warunek')\n",
    "plt.ylabel('Czas reakcji [ms]')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000035",
   "metadata": {},
   "source": [
    "## Szybkie statystyki opisowe w Pythonie\n",
    "\n",
    "W praktyce często chcemy szybko zobaczyć podstawowe miary dla zmiennej ilościowej.\n",
    "\n",
    "W `pandas` służy do tego `describe()`, które standardowo pokazuje m.in.:\n",
    "\n",
    "- `count` (liczebność),\n",
    "- `mean` (średnia),\n",
    "- `std` (odchylenie standardowe z próby),\n",
    "- `min`, `max`,\n",
    "- kwartyle: `25%`, `50%` (mediana), `75%`.\n",
    "\n",
    "To dobry punkt startowy, ale pamiętaj: zawsze warto zestawić te liczby z wykresem."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "01000036",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    150.000000\n",
       "mean     540.077187\n",
       "std       68.842267\n",
       "min      384.992766\n",
       "25%      489.291144\n",
       "50%      526.826779\n",
       "75%      585.478804\n",
       "max      723.659793\n",
       "Name: reaction_time_ms, dtype: float64"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['reaction_time_ms'].describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000040",
   "metadata": {},
   "source": [
    "## Transformacje liniowe i standaryzacja\n",
    "\n",
    "Często zmieniamy skalę pomiaru (np. ms → s) albo dodajemy/odejmujemy stałą. To są przykłady **transformacji liniowych**:\n",
    "\n",
    "$$\n",
    "Y = aX + b\n",
    "$$\n",
    "\n",
    "Wtedy zachodzą proste zależności:\n",
    "\n",
    "- $\\mathrm{E}[Y] = a\\,\\mathrm{E}[X] + b$ (czyli średnia przesuwa się i/lub skaluje),\n",
    "- $\\mathrm{SD}(Y) = |a|\\,\\mathrm{SD}(X)$ (dodanie stałej nie zmienia SD).\n",
    "\n",
    "Szczególnym przypadkiem jest **standaryzacja**, gdzie odejmujemy średnią i dzielimy przez odchylenie standardowe. Otrzymany wynik standaryzowany $z$ jest bezjednostkowy i pozwala porównywać wyniki na różnych skalach.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "01000041",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>wariant</th>\n",
       "      <th>średnia</th>\n",
       "      <th>odchylenie standardowe (ddof=1)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ms</td>\n",
       "      <td>540.077187</td>\n",
       "      <td>68.842267</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>s (ms/1000)</td>\n",
       "      <td>0.540077</td>\n",
       "      <td>0.068842</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ms + 20</td>\n",
       "      <td>560.077187</td>\n",
       "      <td>68.842267</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       wariant     średnia  odchylenie standardowe (ddof=1)\n",
       "0           ms  540.077187                        68.842267\n",
       "1  s (ms/1000)    0.540077                         0.068842\n",
       "2      ms + 20  560.077187                        68.842267"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rt_ms = rt\n",
    "rt_s = rt_ms / 1000\n",
    "rt_ms_plus_20 = rt_ms + 20\n",
    "\n",
    "table = pd.DataFrame(\n",
    "    {\n",
    "        'wariant': ['ms', 's (ms/1000)', 'ms + 20'],\n",
    "        'średnia': [float(rt_ms.mean()), float(rt_s.mean()), float(rt_ms_plus_20.mean())],\n",
    "        'odchylenie standardowe (ddof=1)': [\n",
    "            float(rt_ms.std(ddof=1)),\n",
    "            float(rt_s.std(ddof=1)),\n",
    "            float(rt_ms_plus_20.std(ddof=1)),\n",
    "        ],\n",
    "    }\n",
    ")\n",
    "table"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "37bd4f48",
   "metadata": {},
   "source": [
    "### Interaktywna transformacja liniowa: $Y = aX + b$\n",
    "\n",
    "Poniższy widget pozwala zmieniać współczynniki $a$ (skala) i $b$ (przesunięcie) w transformacji liniowej:\n",
    "\n",
    "$$\n",
    "Y = aX + b\n",
    "$$\n",
    "\n",
    "Zwróć uwagę:\n",
    "\n",
    "- dodanie stałej $b$ przesuwa rozkład i średnią, ale nie zmienia odchylenia standardowego,\n",
    "- dla dodatniego $a$ odchylenie standardowe mnoży się przez $a$ (ogólnie: $\\mathrm{SD}(Y)=|a|\\,\\mathrm{SD}(X)$).\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "d18e2787",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "e48c3ce9a4eb4d4b81c6f8b25c4d9c4b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatSlider(value=1.0, continuous_update=False, description='a (skala):', max=3.0, min=0.1, rea…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b3ecf79192d64a1b98f7d47efa53c886",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Output()"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "if os.environ.get('JPY_SESSION_NAME') is None:\n",
    "    print('Ta sekcja korzysta z widgetów Jupyter i wymaga uruchomienia w notatniku. W trybie wsadowym (np. nbconvert) jest pomijana.')\n",
    "else:\n",
    "    import ipywidgets as widgets\n",
    "    from IPython.display import display\n",
    "\n",
    "    a_slider = widgets.FloatSlider(\n",
    "        value=1.0,\n",
    "        min=0.1,\n",
    "        max=3.0,\n",
    "        step=0.1,\n",
    "        description='a (skala):',\n",
    "        readout_format='.1f',\n",
    "        continuous_update=False,\n",
    "    )\n",
    "\n",
    "    b_slider = widgets.IntSlider(\n",
    "        value=0,\n",
    "        min=-300,\n",
    "        max=300,\n",
    "        step=10,\n",
    "        description='b [ms]:',\n",
    "        continuous_update=False,\n",
    "    )\n",
    "\n",
    "    transform_out = widgets.Output()\n",
    "\n",
    "    def draw_transform(_=None):\n",
    "        a = float(a_slider.value)\n",
    "        b = float(b_slider.value)\n",
    "\n",
    "        x_ms = np.asarray(rt, dtype=float)\n",
    "        y_ms = a * x_ms + b\n",
    "\n",
    "        mean_x = float(x_ms.mean())\n",
    "        sd_x = float(x_ms.std(ddof=1))\n",
    "\n",
    "        mean_y_emp = float(y_ms.mean())\n",
    "        sd_y_emp = float(y_ms.std(ddof=1))\n",
    "\n",
    "        mean_y_formula = a * mean_x + b\n",
    "        sd_y_formula = abs(a) * sd_x\n",
    "\n",
    "        summary = pd.DataFrame(\n",
    "            {\n",
    "                'miara': ['średnia', 'odchylenie standardowe (ddof=1)'],\n",
    "                'X (oryginalne)': [mean_x, sd_x],\n",
    "                'Y (z danych)': [mean_y_emp, sd_y_emp],\n",
    "                'Y (z wzoru)': [mean_y_formula, sd_y_formula],\n",
    "            }\n",
    "        )\n",
    "\n",
    "        with transform_out:\n",
    "            transform_out.clear_output(wait=True)\n",
    "\n",
    "            fig, axes = plt.subplots(1, 2, figsize=(12, 4))\n",
    "\n",
    "            axes[0].hist(\n",
    "                x_ms,\n",
    "                bins=20,\n",
    "                density=True,\n",
    "                color='lightgrey',\n",
    "                edgecolor='white',\n",
    "            )\n",
    "            axes[0].axvline(mean_x, color='C3', linewidth=2, label='średnia')\n",
    "            axes[0].set_title('X: dane wyjściowe')\n",
    "            axes[0].set_xlabel('Czas reakcji [ms]')\n",
    "            axes[0].set_ylabel('Gęstość')\n",
    "            axes[0].legend()\n",
    "\n",
    "            axes[1].hist(\n",
    "                y_ms,\n",
    "                bins=20,\n",
    "                density=True,\n",
    "                color='lightgrey',\n",
    "                edgecolor='white',\n",
    "            )\n",
    "            axes[1].axvline(mean_y_emp, color='C3', linewidth=2, label='średnia')\n",
    "            axes[1].set_title(f'Y = {a:.1f}·X + {b:.0f}')\n",
    "            axes[1].set_xlabel('Wartość po transformacji [ms]')\n",
    "            axes[1].set_ylabel('Gęstość')\n",
    "            axes[1].legend()\n",
    "\n",
    "            fig.tight_layout()\n",
    "            plt.show()\n",
    "\n",
    "            display(summary)\n",
    "\n",
    "    for control in [a_slider, b_slider]:\n",
    "        control.observe(draw_transform, names='value')\n",
    "\n",
    "    display(widgets.HBox([a_slider, b_slider]), transform_out)\n",
    "    draw_transform()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000043",
   "metadata": {},
   "source": [
    "## Ćwiczenia\n",
    "\n",
    "1) Opis rozkładu (czasy reakcji w zadaniu Sternberga):\n",
    "\n",
    "- Na podstawie histogramu i wykres pudełkowego opisz rozkład `reaction_time_ms` w 4 krokach: centrum, rozproszenie, kształt, odstające.\n",
    "\n",
    "2) Histogram (wpływ wyboru przedziałów):\n",
    "\n",
    "- Zmień `bin_width` (np. 20 i 50) i porównaj, jak zmienia się wrażenie „kształtu” rozkładu.\n",
    "\n",
    "3) Centrum:\n",
    "\n",
    "- Policz średnią, medianę i średnią obciętą (np. 20%) dla `reaction_time_ms`.\n",
    "- Która miara jest najbardziej odporna na obserwacje odstające? Uzasadnij krótko.\n",
    "\n",
    "4) Zmienność:\n",
    "\n",
    "- Policz odchylenie standardowe i IQR.\n",
    "- Zinterpretuj: co oznacza większe odchylenie standardowe w kontekście czasu reakcji?\n",
    "\n",
    "5) Percentyle:\n",
    "\n",
    "- Znajdź 90. percentyl czasu reakcji.\n",
    "- Sprawdź rangę centylową dla 450 ms.\n",
    "\n",
    "6) Transformacje:\n",
    "\n",
    "- Zweryfikuj na danych, że po dodaniu stałej (np. `+ 20`) odchylenie standardowe się nie zmienia.\n",
    "\n",
    "7) Porównanie dwóch warunków (efekt Stroopa, opisowo):\n",
    "\n",
    "- Na podstawie wykresu pudełkowego opisz różnice między warunkiem `zgodny` i `niezgodny` w `stroop_df`.\n",
    "- Uzupełnij opis o dwie liczby: medianę i IQR w każdym warunku.\n",
    "\n",
    "8) Dwie strategie (kształt rozkładu):\n",
    "\n",
    "- Obejrzyj histogram `strategie_df` dla różnych liczb przedziałów (np. 15, 30, 45).\n",
    "- Czy rozkład wygląda na jedno- czy dwumodalny? Jak zmienia się wrażenie, gdy zmieniasz ustawienia histogramu?\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01000044",
   "metadata": {},
   "source": [
    "## Podsumowanie\n",
    "\n",
    "- Statystyka opisowa porządkuje dane i pomaga je interpretować.\n",
    "- Zaczynamy od prezentacji i agregacji danych (tabela częstości, histogram, wykres punktowy), a miary liczbowe traktujemy jako uzupełnienie.\n",
    "- Rozkład opisujemy przez: miarę tendencji centralnej, miarę rozproszenia, kształt i obserwacje odstające.\n",
    "- Średnia jest wrażliwa na odstające; mediana i miary oparte na kwartylach są bardziej odporne.\n",
    "- Wariancja ma jednostkę \"do kwadratu\", a odchylenie standardowe tę samą co dane — dlatego SD jest łatwiejsze do interpretacji.\n",
    "- Transformacje liniowe zmieniają średnią i SD w przewidywalny sposób; wynik standaryzowany $z$ pozwala porównywać wyniki na różnych skalach."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.14.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}