1500 lines
308 KiB
Plaintext
1500 lines
308 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"id": "b4c54963-9622-4e66-9910-2ba3e5ba69af",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"import pandas as pd\n",
|
||
"from scipy import stats\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"\n",
|
||
"# Укажите путь к файлу xlsx\n",
|
||
"xlsx_file_path = \"example.xlsx\"\n",
|
||
"\n",
|
||
"# Прочитайте файл xlsx в DataFrame\n",
|
||
"df = pd.read_excel(xlsx_file_path)\n",
|
||
"\n",
|
||
"X = df['X']\n",
|
||
"Y = df['Y']\n",
|
||
"Z = df['Z']\n",
|
||
"D = df['D']"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"id": "8d13a687-0b28-421e-92a1-06a2ef6bda90",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"KS test for X (normal): statistic=0.08531409319640998, p-value=0.10260887852786338\n",
|
||
"KS test for Y (normal): statistic=0.08852268726983759, p-value=0.0818774378282563\n",
|
||
"KS test for Z (normal): statistic=0.03701671447372634, p-value=0.9373639241505186\n",
|
||
"KS test for D (normal): statistic=0.04950094422191759, p-value=0.6921286443105663\n",
|
||
"Гипотеза о нормальном распределении X не отвергается\n",
|
||
"Гипотеза о нормальном распределении Y не отвергается\n",
|
||
"Гипотеза о нормальном распределении Z не отвергается\n",
|
||
"Гипотеза о нормальном распределении D не отвергается\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Колмогоров-Смирнов тест для нормального распределения\n",
|
||
"ks_statistic_X, ks_pvalue_X = stats.kstest(X, 'norm', args=(X.mean(), X.std()))\n",
|
||
"ks_statistic_Y, ks_pvalue_Y = stats.kstest(Y, 'norm', args=(Y.mean(), Y.std()))\n",
|
||
"ks_statistic_Z, ks_pvalue_Z = stats.kstest(Z, 'norm', args=(Z.mean(), Z.std()))\n",
|
||
"ks_statistic_D, ks_pvalue_D = stats.kstest(D, 'norm', args=(D.mean(), D.std()))\n",
|
||
"\n",
|
||
"print(f\"KS test for X (normal): statistic={ks_statistic_X}, p-value={ks_pvalue_X}\")\n",
|
||
"print(f\"KS test for Y (normal): statistic={ks_statistic_Y}, p-value={ks_pvalue_Y}\")\n",
|
||
"\n",
|
||
"print(f\"KS test for Z (normal): statistic={ks_statistic_Z}, p-value={ks_pvalue_Z}\")\n",
|
||
"print(f\"KS test for D (normal): statistic={ks_statistic_D}, p-value={ks_pvalue_D}\")\n",
|
||
"# Выводы по результатам тестов\n",
|
||
"alpha = 0.05\n",
|
||
"if ks_pvalue_X < alpha:\n",
|
||
" print(\"Гипотеза о нормальном распределении X отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о нормальном распределении X не отвергается\")\n",
|
||
"\n",
|
||
"if ks_pvalue_Y < alpha:\n",
|
||
" print(\"Гипотеза о нормальном распределении Y отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о нормальном распределении Y не отвергается\")\n",
|
||
"\n",
|
||
"if ks_pvalue_Z < alpha:\n",
|
||
" print(\"Гипотеза о нормальном распределении Z отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о нормальном распределении Z не отвергается\")\n",
|
||
"\n",
|
||
"if ks_pvalue_D < alpha:\n",
|
||
" print(\"Гипотеза о нормальном распределении D отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о нормальном распределении D не отвергается\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 11,
|
||
"id": "dda26828-2972-4b58-8814-abeccc612ffd",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Chi-square test for X (Poisson): statistic=67.92056123161348, p-value=1.933614930324732e-09\n",
|
||
"Гипотеза о Пуассоновском распределении X отвергается\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Хи-квадрат тест для Пуассоновского распределения\n",
|
||
"observed_counts, bins = np.histogram(X, bins='auto')\n",
|
||
"expected_counts = len(X) * np.diff(stats.poisson.cdf(bins, mu=X.mean()))\n",
|
||
"\n",
|
||
"# Нормализация ожидаемых частот\n",
|
||
"expected_counts *= observed_counts.sum() / expected_counts.sum()\n",
|
||
"\n",
|
||
"chi2_statistic, chi2_pvalue = stats.chisquare(observed_counts, f_exp=expected_counts)\n",
|
||
"\n",
|
||
"print(f\"Chi-square test for X (Poisson): statistic={chi2_statistic}, p-value={chi2_pvalue}\")\n",
|
||
"\n",
|
||
"if chi2_pvalue < alpha:\n",
|
||
" print(\"Гипотеза о Пуассоновском распределении X отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о Пуассоновском распределении X не отвергается\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"id": "7dc6545e-684b-4f6d-9c4b-c9da5d49db57",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"KS test for Z (normal): statistic=0.03701671447372634, p-value=0.9373639241505186\n",
|
||
"Гипотеза о нормальном распределении Z не отвергается\n",
|
||
"KS test for D (normal): statistic=0.04950094422191759, p-value=0.6921286443105663\n",
|
||
"Гипотеза о нормальном распределении D не отвергается\n",
|
||
"KS test for Y (uniform): statistic=0.04778545860688088, p-value=0.732512122073677\n",
|
||
"Гипотеза о равномерном распределении Y не отвергается\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Тест Колмогорова-Смирнова для нормального распределения Z\n",
|
||
"ks_statistic_Z, ks_pvalue_Z = stats.kstest(Z, 'norm', args=(Z.mean(), Z.std()))\n",
|
||
"print(f\"KS test for Z (normal): statistic={ks_statistic_Z}, p-value={ks_pvalue_Z}\")\n",
|
||
"\n",
|
||
"if ks_pvalue_Z < alpha:\n",
|
||
" print(\"Гипотеза о нормальном распределении Z отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о нормальном распределении Z не отвергается\")\n",
|
||
"\n",
|
||
"# Тест Колмогорова-Смирнова для нормального распределения D\n",
|
||
"ks_statistic_D, ks_pvalue_D = stats.kstest(D, 'norm', args=(D.mean(), D.std()))\n",
|
||
"print(f\"KS test for D (normal): statistic={ks_statistic_D}, p-value={ks_pvalue_D}\")\n",
|
||
"\n",
|
||
"if ks_pvalue_D < alpha:\n",
|
||
" print(\"Гипотеза о нормальном распределении D отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о нормальном распределении D не отвергается\")\n",
|
||
"\n",
|
||
"# Тест Колмогорова-Смирнова для равномерного распределения Y\n",
|
||
"ks_statistic_Y, ks_pvalue_Y = stats.kstest(Y, 'uniform', args=(Y.min(), Y.max()-Y.min()))\n",
|
||
"print(f\"KS test for Y (uniform): statistic={ks_statistic_Y}, p-value={ks_pvalue_Y}\")\n",
|
||
"\n",
|
||
"if ks_pvalue_Y < alpha:\n",
|
||
" print(\"Гипотеза о равномерном распределении Y отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о равномерном распределении Y не отвергается\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 14,
|
||
"id": "12916750-f81f-42be-92dc-cd50dbc2e93a",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Chi-square test for X (Poisson): statistic=67.92056123161348, p-value=1.933614930324732e-09\n",
|
||
"Гипотеза о Пуассоновском распределении X отвергается\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Хи-квадрат тест для Пуассоновского распределения X\n",
|
||
"observed_counts, bins = np.histogram(X, bins='auto')\n",
|
||
"expected_counts = len(X) * np.diff(stats.poisson.cdf(bins, mu=X.mean()))\n",
|
||
"\n",
|
||
"# Нормализация ожидаемых частот\n",
|
||
"expected_counts *= observed_counts.sum() / expected_counts.sum()\n",
|
||
"\n",
|
||
"chi2_statistic, chi2_pvalue = stats.chisquare(observed_counts, f_exp=expected_counts)\n",
|
||
"\n",
|
||
"print(f\"Chi-square test for X (Poisson): statistic={chi2_statistic}, p-value={chi2_pvalue}\")\n",
|
||
"\n",
|
||
"alpha = 0.05\n",
|
||
"if chi2_pvalue < alpha:\n",
|
||
" print(\"Гипотеза о Пуассоновском распределении X отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о Пуассоновском распределении X не отвергается\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 21,
|
||
"id": "fa7778c3-c4e9-45b4-a2f2-3d5d902b12de",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"ename": "ValueError",
|
||
"evalue": "For each axis slice, the sum of the observed frequencies must agree with the sum of the expected frequencies to a relative tolerance of 1e-08, but the percent differences are:\n0.0015721607138329905",
|
||
"output_type": "error",
|
||
"traceback": [
|
||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
||
"\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)",
|
||
"\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_12128\\831602892.py\u001b[0m in \u001b[0;36m?\u001b[1;34m()\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0mexpected_freqs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpoisson\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpmf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmax\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m+\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlambda_X\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m*\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 6\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 7\u001b[0m \u001b[1;31m# Chi-square test\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 8\u001b[0m \u001b[0mobs_freqs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0m_\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhistogram\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mbins\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmax\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m+\u001b[0m\u001b[1;36m2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 9\u001b[1;33m \u001b[0mchi2_stat_X\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mp_value_X\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mchisquare\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobs_freqs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mexpected_freqs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 10\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 11\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mf'Chi-square test for X (Poisson): statistic={chi2_stat_X}, p-value={p_value_X}'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
|
||
"\u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\scipy\\stats\\_stats_py.py\u001b[0m in \u001b[0;36m?\u001b[1;34m(f_obs, f_exp, ddof, axis)\u001b[0m\n\u001b[0;32m 8208\u001b[0m ... axis=1)\n\u001b[0;32m 8209\u001b[0m \u001b[0mPower_divergenceResult\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstatistic\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0marray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m3.5\u001b[0m \u001b[1;33m,\u001b[0m \u001b[1;36m9.25\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpvalue\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0marray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0.62338763\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m0.09949846\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 8210\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 8211\u001b[0m \"\"\" # noqa: E501\n\u001b[1;32m-> 8212\u001b[1;33m return power_divergence(f_obs, f_exp=f_exp, ddof=ddof, axis=axis,\n\u001b[0m\u001b[0;32m 8213\u001b[0m lambda_=\"pearson\")\n",
|
||
"\u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\scipy\\stats\\_stats_py.py\u001b[0m in \u001b[0;36m?\u001b[1;34m(f_obs, f_exp, ddof, axis, lambda_)\u001b[0m\n\u001b[0;32m 8005\u001b[0m \u001b[1;34mf\"frequencies must agree with the sum of the \"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 8006\u001b[0m \u001b[1;34mf\"expected frequencies to a relative tolerance \"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 8007\u001b[0m \u001b[1;34mf\"of {rtol}, but the percent differences are:\\n\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 8008\u001b[0m f\"{relative_diff}\")\n\u001b[1;32m-> 8009\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmsg\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 8010\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 8011\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 8012\u001b[0m \u001b[1;31m# Ignore 'invalid' errors so the edge case of a data set with length 0\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
|
||
"\u001b[1;31mValueError\u001b[0m: For each axis slice, the sum of the observed frequencies must agree with the sum of the expected frequencies to a relative tolerance of 1e-08, but the percent differences are:\n0.0015721607138329905"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import chisquare\n",
|
||
"from scipy.stats import poisson\n",
|
||
"# Define the expected frequencies for Poisson distribution\n",
|
||
"lambda_X = X.mean()\n",
|
||
"expected_freqs = poisson.pmf(range(int(X.max())+1), lambda_X) * len(X)\n",
|
||
"\n",
|
||
"# Chi-square test\n",
|
||
"obs_freqs, _ = np.histogram(X, bins=range(int(X.max())+2))\n",
|
||
"chi2_stat_X, p_value_X = chisquare(obs_freqs, expected_freqs)\n",
|
||
"\n",
|
||
"print(f'Chi-square test for X (Poisson): statistic={chi2_stat_X}, p-value={p_value_X}')\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 15,
|
||
"id": "4e2815a6-f3b9-4628-b551-e98b65f34e42",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"t-test for equality of means: statistic=30.6366470045653, p-value=9.554335422627212e-107\n",
|
||
"Гипотеза о равенстве средних X и Y отвергается\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"t_statistic, t_pvalue = stats.ttest_ind(X, Y)\n",
|
||
"print(f\"t-test for equality of means: statistic={t_statistic}, p-value={t_pvalue}\")\n",
|
||
"\n",
|
||
"if t_pvalue < alpha:\n",
|
||
" print(\"Гипотеза о равенстве средних X и Y отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о равенстве средних X и Y не отвергается\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 16,
|
||
"id": "1d895585-9c7e-4910-afdf-cd259132289e",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Выборки нельзя объединить\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"if t_pvalue >= alpha:\n",
|
||
" combined = np.concatenate([X, Y])\n",
|
||
" combined_mean = np.mean(combined)\n",
|
||
" combined_std = np.std(combined)\n",
|
||
" print(f\"Объединенная выборка: среднее={combined_mean}, стандартное отклонение={combined_std}\")\n",
|
||
"else:\n",
|
||
" print(\"Выборки нельзя объединить\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 23,
|
||
"id": "1ab79d2d-c581-4ea0-80b0-2984ff12b5b5",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"T-test for equality of means X and Y: statistic=30.6366470045653, p-value=9.554335422627212e-107\n",
|
||
"Гипотеза о равенстве распределений X и Y (критерий знаков) отвергается\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import ttest_ind\n",
|
||
"\n",
|
||
"t_stat, p_value_ttest = ttest_ind(X, Y)\n",
|
||
"\n",
|
||
"print(f'T-test for equality of means X and Y: statistic={t_stat}, p-value={p_value_ttest}')\n",
|
||
"\n",
|
||
"\n",
|
||
"if p_value_ttest < alpha:\n",
|
||
" print(\"Гипотеза о равенстве распределений X и Y (критерий знаков) отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о равенстве распределений X и Y (критерий знаков) не отвергается\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 27,
|
||
"id": "3d683033-3432-42b0-b99d-5bc4602c1d28",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Mann-Whitney U test for X and Y: statistic=39604.0, p-value=1.4768098049370635e-64\n",
|
||
"Гипотеза о равенстве распределений X и Y (mannwhitneyu) отвергается\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import mannwhitneyu\n",
|
||
"\n",
|
||
"u_stat, p_value_mannwhitney = mannwhitneyu(X, Y)\n",
|
||
"\n",
|
||
"print(f'Mann-Whitney U test for X and Y: statistic={u_stat}, p-value={p_value_mannwhitney}')\n",
|
||
"if p_value_mannwhitney < alpha:\n",
|
||
" print(\"Гипотеза о равенстве распределений X и Y (mannwhitneyu) отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о равенстве распределений X и Y (mannwhitneyu) не отвергается\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 26,
|
||
"id": "393bd722-dee4-4692-86b2-94d3c926ef5c",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Sign test for X and Y: statistic=0.985, p-value=1.659679419208622e-54\n",
|
||
"Гипотеза о равенстве распределений X и Y (критерий знаков) отвергается\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import binomtest\n",
|
||
"\n",
|
||
"diff = X - Y\n",
|
||
"n_positive = sum(diff > 0)\n",
|
||
"n_total = len(diff)\n",
|
||
"\n",
|
||
"# Binomial test for the sign test\n",
|
||
"sign_test_result = binomtest(n_positive, n_total, p=0.5)\n",
|
||
"\n",
|
||
"print(f'Sign test for X and Y: statistic={sign_test_result.statistic}, p-value={sign_test_result.pvalue}')\n",
|
||
"\n",
|
||
"if sign_test_result.pvalue < alpha:\n",
|
||
" print(\"Гипотеза о равенстве распределений X и Y (критерий знаков) отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о равенстве распределений X и Y (критерий знаков) не отвергается\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "9d15fbd5-61f7-4ce8-8c26-442f3fe7a5a9",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "69bb743a-0e18-475b-9c99-12fb4c878c1e",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"id": "e9621a70-9dd7-49e9-a90a-da9051cc1e39",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Строка со значениями столбца D= 2.29106893237,2.26403892097,6.2446633167,4.93176295377,7.09973553507,5.84190076275,2.91330742621,2.57308785442,5.6869144632,3.93707283059,3.93264067442,1.23962711663,5.92816588081,0.581310339931,2.49878223168,4.42584857266,3.49898148888,6.21364616744,3.25898170282,1.94131808365,2.96677343358,0.659741263411,3.86031145306,9.3666796951,8.24459611291,4.09220004134,5.37452862445,3.13882468173,4.11122173603,0.821461514186,1.68323605285,4.19761005136,3.95725973395,2.8609219217,2.68274392059,2.4003848785,4.26325289,2.5649356191,3.43856907433,-0.538190802425,1.75420235677,7.71678561833,0.798787047917,2.4360008161,4.73973356807,6.82361363062,4.39184490587,4.3084153142,6.386130936,6.62243894369,6.45107547269,1.5908026934,4.21369497931,4.22386242803,2.04668932594,6.16359705613,3.00290165295,5.36868575955,5.45289249694,5.25748441637,0.854327294099,2.98104069695,-0.906781451662,6.01869463603,6.39252059987,5.32627669441,3.08171241758,1.55856342896,4.25735001619,4.58761357451,4.06579591448,5.16454770286,5.68891593981,3.57863598436,4.56023660632,3.25232371118,5.77108364008,2.03424375966,4.12033429679,5.30654271053,3.60168565262,4.00852550948,3.87609131575,4.92368031545,2.47706932781,4.12559834465,3.83740051376,6.19007173018,5.54866779539,3.85911984464,5.78379334795,2.6106290677,3.70107333278,4.4480199468,2.80946277543,3.91595268754,3.69526841579,5.08263234991,2.83853013513,4.56256981337,-0.0990200850857,5.49396138122,3.81375229905,6.02800623977,5.04723833063,5.19108977244,4.93166811013,3.94996447786,2.09122440706,5.58352321149,1.76235444754,0.687902390455,9.40034597862,3.90031851624,4.66853453111,3.95885204015,4.67091515234,2.65800659385,2.46596735383,6.01718943957,2.23501287594,4.34057052755,4.47605810844,3.6169140101,5.07961062785,3.9313569109,3.10307345473,3.14798092339,3.99360992117,3.15387309597,5.08153540746,4.93200276959,3.13595577552,4.7898447788,3.58858222531,0.849263712182,2.72882701337,5.25185003134,4.97964627689,1.82587131482,4.98551578131,0.291661479713,4.71002970446,3.6719721177,3.39311964905,2.44986199694,3.07573083838,2.81492940053,4.87307626853,3.9604570183,1.13029273173,4.82053698751,1.32654701727,7.84993225841,4.12777568255,3.40927235632,5.79027259845,0.802078248036,4.12200287544,2.44315413193,5.95786851881,2.24412800208,6.70453282764,2.86035816443,5.82231338817,4.2488210453,2.2595308785,5.09681669192,2.3652351624,4.42603453088,3.42992742979,4.91407089281,4.69591396749,3.31654416171,8.03286461231,6.06914894206,2.95791637169,2.91747025301,4.30917748622,3.2359712866,5.16293255691,6.20587331612,0.193329476264,3.47222227364,4.01633869097,4.4995946619,4.46669620218,-3.16290716318,5.92328009802,5.53693447068,2.82024823135,4.24260693696,3.15279329672,-0.575154108122,4.4948177318,2.6877013137,3.38441889758,1.29226692427,5.42852280974,4.86122623556\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"column_values = df[\"D\"].tolist()\n",
|
||
"\n",
|
||
"# Объедините значения в одну строку, разделяя их пробелами\n",
|
||
"column_as_string = ','.join(map(str, column_values))\n",
|
||
"print(\"Строка со значениями столбца\", \"D=\",column_as_string)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "f5d4c355-9485-4f89-8390-8f12cf45642a",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"max Z: 9.40034597862\n",
|
||
"min Z: -3.16290716318\n",
|
||
"12.5632531418\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"\n",
|
||
"X = np.array([5,7,7,10,12,14,6,13,13,11,11,7,15,12,12,12,7,11,10,11,11,11,10,3,12,6,10,10,7,11,8,12,3,7,12,7,4,13,11,7,9,15,9,9,12,11,10,9,11,3,12,8,9,13,14,9,14,8,8,8,8,11,13,8,11,16,5,17,7,20,8,10,8,8,7,12,16,13,11,9,7,11,13,13,6,12,7,7,8,8,6,15,11,14,7,11,6,5,7,6,15,8,10,7,10,12,8,13,13,15,11,11,9,14,9,11,8,14,14,7,10,15,10,10,7,7,9,13,11,15,11,13,16,9,5,10,6,9,3,10,11,5,5,13,13,9,12,12,11,9,10,10,8,5,8,8,10,9,12,5,11,16,13,11,11,13,12,10,7,13,2,17,6,6,13,9,7,12,18,8,8,12,15,12,17,8,6,16,6,11,10,8,14,7,6,9,10,10,6,9])\n",
|
||
"\n",
|
||
"max_X = np.max(column_values)\n",
|
||
"min_X = np.min(column_values)\n",
|
||
"print(f\"max Z: {max_X}\")\n",
|
||
"print(f\"min Z: {min_X}\")\n",
|
||
"\n",
|
||
"print(max_X - min_X)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"id": "2a0963ac-bc8b-4067-9d73-e7763d9166bf",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import statsmodels.api as sm\n",
|
||
"\n",
|
||
"# Ваши данные\n",
|
||
"Y = df[\"Y\"]\n",
|
||
"\n",
|
||
"# Построение гистограммы\n",
|
||
"plt.hist(Y, bins=30, edgecolor='k', alpha=0.7)\n",
|
||
"plt.title('Histogram of Y')\n",
|
||
"plt.xlabel('Value')\n",
|
||
"plt.ylabel('Frequency')\n",
|
||
"plt.show()\n",
|
||
"\n",
|
||
"# Построение QQ-графика для нормального распределения\n",
|
||
"sm.qqplot(np.array(Y), line ='s')\n",
|
||
"plt.title('QQ plot')\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 32,
|
||
"id": "845241c8-3e21-4eea-b63a-9d3af2641a75",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Основные числовые характеристики:\n",
|
||
" X Y Z D\n",
|
||
"count 200.000000 200.000000 200.000000 200.000000\n",
|
||
"mean 9.990000 1.973704 1.075743 3.886346\n",
|
||
"std 3.242293 1.783375 3.886138 1.859615\n",
|
||
"min 2.000000 -0.960908 -8.928492 -3.162907\n",
|
||
"25% 8.000000 0.314313 -1.393858 2.813563\n",
|
||
"50% 10.000000 1.942471 1.158932 3.959655\n",
|
||
"75% 12.000000 3.583925 3.856398 5.080092\n",
|
||
"max 20.000000 4.976185 11.438908 9.400346\n",
|
||
"\n",
|
||
"Мода:\n",
|
||
" X Y Z D\n",
|
||
"0 11.0 -0.960908 -8.928492 -3.162907\n",
|
||
"1 NaN -0.922780 -8.137045 -0.906781\n",
|
||
"2 NaN -0.915775 -6.631962 -0.575154\n",
|
||
"3 NaN -0.905167 -6.595189 -0.538191\n",
|
||
"4 NaN -0.878380 -6.265933 -0.099020\n",
|
||
".. ... ... ... ...\n",
|
||
"195 NaN 4.794342 8.613534 7.849932\n",
|
||
"196 NaN 4.863656 8.757429 8.032865\n",
|
||
"197 NaN 4.887727 9.249164 8.244596\n",
|
||
"198 NaN 4.939905 10.436217 9.366680\n",
|
||
"199 NaN 4.976185 11.438908 9.400346\n",
|
||
"\n",
|
||
"[200 rows x 4 columns]\n",
|
||
"\n",
|
||
"Коэффициенты асимметрии:\n",
|
||
"X 0.169883\n",
|
||
"Y 0.048440\n",
|
||
"Z -0.057667\n",
|
||
"D -0.218358\n",
|
||
"dtype: float64\n",
|
||
"\n",
|
||
"Коэффициенты эксцесса:\n",
|
||
"X -0.133848\n",
|
||
"Y -1.278495\n",
|
||
"Z -0.325102\n",
|
||
"D 1.058480\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"\n",
|
||
"# Основные числовые характеристики для каждой выборки\n",
|
||
"stats = df.describe()\n",
|
||
"\n",
|
||
"# Мода для каждой выборки\n",
|
||
"modes = df.mode(axis=0)\n",
|
||
"\n",
|
||
"# Коэффициенты асимметрии для каждой выборки\n",
|
||
"skewness = df.skew()\n",
|
||
"\n",
|
||
"# Коэффициенты эксцесса для каждой выборки\n",
|
||
"kurtosis = df.kurtosis()\n",
|
||
"\n",
|
||
"# Вывод результатов\n",
|
||
"print(\"Основные числовые характеристики:\")\n",
|
||
"print(stats)\n",
|
||
"print(\"\\nМода:\")\n",
|
||
"print(modes)\n",
|
||
"print(\"\\nКоэффициенты асимметрии:\")\n",
|
||
"print(skewness)\n",
|
||
"print(\"\\nКоэффициенты эксцесса:\")\n",
|
||
"print(kurtosis)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 33,
|
||
"id": "ae5b504b-0ed0-4324-a9bf-c4d86e846c99",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Дисперсия:\n",
|
||
"X 10.512462\n",
|
||
"Y 3.180425\n",
|
||
"Z 15.102067\n",
|
||
"D 3.458169\n",
|
||
"dtype: float64\n",
|
||
"\n",
|
||
"Медиана:\n",
|
||
"X 10.000000\n",
|
||
"Y 1.942471\n",
|
||
"Z 1.158932\n",
|
||
"D 3.959655\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Используем describe() для получения основных статистических характеристик\n",
|
||
"stats = df.describe()\n",
|
||
"\n",
|
||
"# Извлекаем значения дисперсии и медианы из результата describe()\n",
|
||
"variance = df.var()\n",
|
||
"median = df.median()\n",
|
||
"\n",
|
||
"print(\"Дисперсия:\")\n",
|
||
"print(variance)\n",
|
||
"print(\"\\nМедиана:\")\n",
|
||
"print(median)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 38,
|
||
"id": "6f33dfdc-1541-4257-bded-804fc7aa92d5",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Мода для массива X: ModeResult(mode=11, count=27)\n",
|
||
"Мода для массива Y: ModeResult(mode=-0.960907783569, count=1)\n",
|
||
"Мода для массива Z: ModeResult(mode=-8.92849226343, count=1)\n",
|
||
"Мода для массива D: ModeResult(mode=-3.16290716318, count=1)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import mode\n",
|
||
"\n",
|
||
"mode_X = mode(df[\"X\"])\n",
|
||
"print(\"Мода для массива X:\", mode_X)\n",
|
||
"mode_Y = mode(df[\"Y\"])\n",
|
||
"print(\"Мода для массива Y:\", mode_Y)\n",
|
||
"mode_Z = mode(df[\"Z\"])\n",
|
||
"print(\"Мода для массива Z:\", mode_Z)\n",
|
||
"mode_D = mode(df[\"D\"])\n",
|
||
"print(\"Мода для массива D:\", mode_D)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 40,
|
||
"id": "a63946f5-ca2b-4f6e-a75c-ead8046719e9",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Размах для массива X: 18\n",
|
||
"Размах для массива Y: 5.937092332969\n",
|
||
"Размах для массива Z: 20.367399974130002\n",
|
||
"Размах для массива D: 12.5632531418\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"range_x = df[\"X\"].max() - df[\"X\"].min()\n",
|
||
"range_y = df[\"Y\"].max() - df[\"Y\"].min()\n",
|
||
"range_z = df[\"Z\"].max() - df[\"Z\"].min()\n",
|
||
"range_d = df[\"D\"].max() - df[\"D\"].min()\n",
|
||
"\n",
|
||
"print(\"Размах для массива X:\", range_x)\n",
|
||
"print(\"Размах для массива Y:\", range_y)\n",
|
||
"print(\"Размах для массива Z:\", range_z)\n",
|
||
"print(\"Размах для массива D:\", range_d)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 18,
|
||
"id": "65bab523-1fa1-4565-8175-c0377cdbb3de",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Доверительный интервал для параметра lambda: (0.0, 6.0)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import poisson\n",
|
||
"\n",
|
||
"# Генерируем случайные данные из распределения Пуассона\n",
|
||
"data = df[\"Y\"]\n",
|
||
"\n",
|
||
"# Вычисляем доверительный интервал для параметра lambda\n",
|
||
"confidence_level = 0.97\n",
|
||
"mu = np.mean(data)\n",
|
||
"confidence_interval_lambda = poisson.interval(confidence_level, mu)\n",
|
||
"\n",
|
||
"print(\"Доверительный интервал для параметра lambda:\", confidence_interval_lambda)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 20,
|
||
"id": "f845203f-e203-469d-b691-605f2ad9157f",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Доверительный интервал для среднего: (0.4809137886503132, 1.670572952477344)\n",
|
||
"Доверительный интервал для дисперсии: (1377.9540180739787, -1377.9540180739787)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import norm\n",
|
||
"import numpy as np\n",
|
||
"\n",
|
||
"# Генерируем случайные данные из нормального распределения\n",
|
||
"data = df[\"Z\"]\n",
|
||
"\n",
|
||
"# Вычисляем доверительные интервалы для среднего и дисперсии\n",
|
||
"confidence_level = 0.97\n",
|
||
"mean, std_dev = np.mean(data), np.std(data)\n",
|
||
"confidence_interval_mean = norm.interval(confidence_level, loc=mean, scale=std_dev/np.sqrt(len(data)))\n",
|
||
"confidence_interval_variance = ((len(data) - 1) * std_dev ** 2 / norm.ppf((1 + confidence_level) / 2), (len(data) - 1) * std_dev ** 2 / norm.ppf((1 - confidence_level) / 2))\n",
|
||
"\n",
|
||
"print(\"Доверительный интервал для среднего:\", confidence_interval_mean)\n",
|
||
"print(\"Доверительный интервал для дисперсии:\", confidence_interval_variance)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 26,
|
||
"id": "4e66b1b2-bb67-487b-aa5a-119e52372024",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Доверительный интервал для среднего (нормальное распределение): (3.8814008005067353, 3.891291378730957)\n",
|
||
"Доверительный интервал для стандартного отклонения (нормальное распределение): (1.854670068863352, 1.8645606470875733)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"from scipy import stats\n",
|
||
"\n",
|
||
"# Пример данных для нормального распределения\n",
|
||
"data_normal = df[\"D\"]\n",
|
||
"\n",
|
||
"# Уровень доверия\n",
|
||
"alpha_normal = 1 - 0.97\n",
|
||
"\n",
|
||
"# Доверительный интервал для среднего\n",
|
||
"ci_mean_normal = stats.norm.interval(alpha_normal, loc=np.mean(data_normal), scale=stats.sem(data_normal))\n",
|
||
"\n",
|
||
"# Доверительный интервал для стандартного отклонения\n",
|
||
"ci_std_normal = stats.norm.interval(alpha_normal, loc=np.std(data_normal, ddof=1), scale=stats.sem(data_normal))\n",
|
||
"\n",
|
||
"print(\"Доверительный интервал для среднего (нормальное распределение):\", ci_mean_normal)\n",
|
||
"print(\"Доверительный интервал для стандартного отклонения (нормальное распределение):\", ci_std_normal)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 28,
|
||
"id": "cff25e40-88e2-4c3d-a07c-3308d7b80e0a",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Доверительный интервал для λ (распределение Пуассона): (1.7000475201301464, 2.24736008127113)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import statsmodels.api as sm\n",
|
||
"\n",
|
||
"# Пример данных для распределения Пуассона\n",
|
||
"data_poisson = df[\"Y\"]\n",
|
||
"\n",
|
||
"# Уровень доверия\n",
|
||
"alpha_poisson = 1 - 0.97\n",
|
||
"\n",
|
||
"# Доверительный интервал для λ распределения Пуассона\n",
|
||
"ci_low, ci_upp = sm.stats.DescrStatsW(data_poisson).zconfint_mean(alpha=alpha_poisson)\n",
|
||
"\n",
|
||
"print(\"Доверительный интервал для λ (распределение Пуассона):\", (ci_low, ci_upp))\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 40,
|
||
"id": "0f465489-bda9-46fa-a992-98c8c9359c08",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Для нормального распределения:\n",
|
||
"Критерий χ²:\n",
|
||
"Статистика: 2793.7065606649576\n",
|
||
"p-значение: 0.0\n",
|
||
"Гипотеза о нормальном распределении отвергается\n",
|
||
"\n",
|
||
"Критерий Колмогорова-Смирнова:\n",
|
||
"Статистика: 0.40797473115516536\n",
|
||
"p-значение: 1.3210039910263899e-30\n",
|
||
"Гипотеза о нормальном распределении отвергается\n",
|
||
"\n",
|
||
"Для распределения Пуассона:\n",
|
||
"Критерий χ²:\n",
|
||
"Статистика: 97.10526315789474\n",
|
||
"p-значение: 0.5350796372889958\n",
|
||
"Гипотеза о распределении Пуассона не отвергается\n",
|
||
"\n",
|
||
"Критерий Колмогорова-Смирнова:\n",
|
||
"Статистика: 0.24762088352106568\n",
|
||
"p-значение: 6.908752326169566e-06\n",
|
||
"Гипотеза о распределении Пуассона отвергается\n",
|
||
"\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import normaltest, kstest, chisquare\n",
|
||
"import numpy as np\n",
|
||
"\n",
|
||
"# Генерация случайных данных из нормального распределения\n",
|
||
"data_normal = df[\"Z\"]\n",
|
||
"\n",
|
||
"# Проверка гипотезы о нормальном распределении с помощью критерия χ²\n",
|
||
"chi2_stat_normal, chi2_p_value_normal = chisquare(data_normal, f_exp=np.mean(data_normal))\n",
|
||
"\n",
|
||
"# Проверка гипотезы о нормальном распределении с помощью критерия Колмогорова-Смирнова\n",
|
||
"ks_stat_normal, ks_p_value_normal = kstest(data_normal, 'norm')\n",
|
||
"\n",
|
||
"print(\"Для нормального распределения:\")\n",
|
||
"print(\"Критерий χ²:\")\n",
|
||
"print(\"Статистика:\", chi2_stat_normal)\n",
|
||
"print(\"p-значение:\", chi2_p_value_normal)\n",
|
||
"if chi2_p_value_normal < 0.05:\n",
|
||
" print(\"Гипотеза о нормальном распределении отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о нормальном распределении не отвергается\")\n",
|
||
"print()\n",
|
||
"\n",
|
||
"print(\"Критерий Колмогорова-Смирнова:\")\n",
|
||
"print(\"Статистика:\", ks_stat_normal)\n",
|
||
"print(\"p-значение:\", ks_p_value_normal)\n",
|
||
"if ks_p_value_normal < 0.05:\n",
|
||
" print(\"Гипотеза о нормальном распределении отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о нормальном распределении не отвергается\")\n",
|
||
"print()\n",
|
||
"\n",
|
||
"# Генерация случайных данных из распределения Пуассона\n",
|
||
"data_poisson = np.random.poisson(lam=3, size=100)\n",
|
||
"\n",
|
||
"# Проверка гипотезы о распределении с помощью критерия χ²\n",
|
||
"chi2_stat_poisson, chi2_p_value_poisson = chisquare(data_poisson, f_exp=np.mean(data_poisson))\n",
|
||
"\n",
|
||
"# Проверка гипотезы о распределении с помощью критерия Колмогорова-Смирнова\n",
|
||
"ks_stat_poisson, ks_p_value_poisson = kstest(data_poisson, 'poisson', args=(np.mean(data_poisson),))\n",
|
||
"\n",
|
||
"print(\"Для распределения Пуассона:\")\n",
|
||
"print(\"Критерий χ²:\")\n",
|
||
"print(\"Статистика:\", chi2_stat_poisson)\n",
|
||
"print(\"p-значение:\", chi2_p_value_poisson)\n",
|
||
"if chi2_p_value_poisson < 0.05:\n",
|
||
" print(\"Гипотеза о распределении Пуассона отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о распределении Пуассона не отвергается\")\n",
|
||
"print()\n",
|
||
"\n",
|
||
"print(\"Критерий Колмогорова-Смирнова:\")\n",
|
||
"print(\"Статистика:\", ks_stat_poisson)\n",
|
||
"print(\"p-значение:\", ks_p_value_poisson)\n",
|
||
"if ks_p_value_poisson < 0.05:\n",
|
||
" print(\"Гипотеза о распределении Пуассона отвергается\")\n",
|
||
"else:\n",
|
||
" print(\"Гипотеза о распределении Пуассона не отвергается\")\n",
|
||
"print()\n",
|
||
"\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 24,
|
||
"id": "039d794e-24dd-4021-af5f-ba8af18c126e",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Доверительный интервал для среднего значения нормального распределения (Z): (0.4737185524940215, 1.6662814475059786)\n",
|
||
"Доверительный интервал для среднего значения нормального распределения (D): (3.1477413862442116, 3.7522586137557887)\n",
|
||
"Доверительный интервал для дисперсии нормального распределения (Z): (12.278109551840211, 18.9936876420616)\n",
|
||
"Доверительный интервал для дисперсии нормального распределения (D): (3.154904970936425, 4.88049722193371)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"from scipy.stats import norm, chi2, poisson\n",
|
||
"\n",
|
||
"# Данные\n",
|
||
"mean_X = 1.07\n",
|
||
"variance_X = 15.1\n",
|
||
"\n",
|
||
"mean_Y = 3.45\n",
|
||
"variance_Y = 3.88\n",
|
||
"\n",
|
||
"# Количество наблюдений\n",
|
||
"n = 200\n",
|
||
"\n",
|
||
"# Уровень доверия\n",
|
||
"gamma = 0.97\n",
|
||
"\n",
|
||
"# Доверительный интервал для среднего значения нормального распределения\n",
|
||
"z_score = norm.ppf((1 + gamma) / 2)\n",
|
||
"margin_of_error_X = z_score * np.sqrt(variance_X / n)\n",
|
||
"confidence_interval_mean_X = (mean_X - margin_of_error_X, mean_X + margin_of_error_X)\n",
|
||
"\n",
|
||
"margin_of_error_Y = z_score * np.sqrt(variance_Y / n)\n",
|
||
"confidence_interval_mean_Y = (mean_Y - margin_of_error_Y, mean_Y + margin_of_error_Y)\n",
|
||
"\n",
|
||
"# Доверительный интервал для дисперсии нормального распределения\n",
|
||
"lower_chi2_X = chi2.ppf((1 - gamma) / 2, n - 1)\n",
|
||
"upper_chi2_X = chi2.ppf((1 + gamma) / 2, n - 1)\n",
|
||
"confidence_interval_variance_X = ((n - 1) * variance_X / upper_chi2_X, (n - 1) * variance_X / lower_chi2_X)\n",
|
||
"confidence_interval_variance_Y = ((n - 1) * variance_Y / upper_chi2_X, (n - 1) * variance_Y / lower_chi2_X)\n",
|
||
"# Оценка параметра λ (лямбда) распределения Пуассона\n",
|
||
"lambda_estimate_Y = mean_Y\n",
|
||
"\n",
|
||
"# Доверительный интервал для параметра λ (лямбда) распределения Пуассона\n",
|
||
"margin_of_error_lambda_Y = z_score * np.sqrt(variance_Y / n)\n",
|
||
"confidence_interval_lambda_Y = (lambda_estimate_Y - margin_of_error_lambda_Y, lambda_estimate_Y + margin_of_error_lambda_Y)\n",
|
||
"\n",
|
||
"print(\"Доверительный интервал для среднего значения нормального распределения (Z):\", confidence_interval_mean_X)\n",
|
||
"print(\"Доверительный интервал для среднего значения нормального распределения (D):\", confidence_interval_mean_Y)\n",
|
||
"print(\"Доверительный интервал для дисперсии нормального распределения (Z):\", confidence_interval_variance_X)\n",
|
||
"print(\"Доверительный интервал для дисперсии нормального распределения (D):\", confidence_interval_variance_Y)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 43,
|
||
"id": "56b72908-81f9-4d91-bd23-baae0acb67b1",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Доверительный интервал для параметра λ (лямбда) распределения Пуассона (D): (3.600990708651492, 4.1717012913485085)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"from scipy.stats import norm\n",
|
||
"\n",
|
||
"# Данные\n",
|
||
"mean_D = 3.886346\n",
|
||
"variance_D = 3.458169\n",
|
||
"\n",
|
||
"# Количество наблюдений\n",
|
||
"n = 200\n",
|
||
"\n",
|
||
"# Уровень доверия\n",
|
||
"gamma = 0.97\n",
|
||
"\n",
|
||
"# Оценка параметра λ (лямбда) распределения Пуассона\n",
|
||
"lambda_estimate_D = mean_D\n",
|
||
"\n",
|
||
"# Доверительный интервал для параметра λ (лямбда) распределения Пуассона\n",
|
||
"margin_of_error_lambda_D = norm.ppf((1 + gamma) / 2) * np.sqrt(variance_D / n)\n",
|
||
"confidence_interval_lambda_D = (lambda_estimate_D - margin_of_error_lambda_D, lambda_estimate_D + margin_of_error_lambda_D)\n",
|
||
"\n",
|
||
"print(\"Доверительный интервал для параметра λ (лямбда) распределения Пуассона (D):\", confidence_interval_lambda_D)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 43,
|
||
"id": "544987ab-1968-4756-b841-d0bc53cf371d",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Результаты теста на нормальность (Хи-квадрат):\n",
|
||
"Хи-квадрат статистика: 7.227123057931748\n",
|
||
"p-значение: 0.026955672296074838\n",
|
||
"Отвергаем нулевую гипотезу (случайная величина не имеет нормальное распределение)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy import stats\n",
|
||
"\n",
|
||
"# Загрузим данные\n",
|
||
"data_X = df['D']\n",
|
||
"\n",
|
||
"# Проведем тест на нормальность с помощью критерия хи-квадрат\n",
|
||
"chi_square, p_chi = stats.normaltest(data_X)\n",
|
||
"\n",
|
||
"# Определим уровень значимости\n",
|
||
"alpha = 0.05\n",
|
||
"\n",
|
||
"# Выведем результаты теста\n",
|
||
"print(\"Результаты теста на нормальность (Хи-квадрат):\")\n",
|
||
"print(\"Хи-квадрат статистика:\", chi_square)\n",
|
||
"print(\"p-значение:\", p_chi)\n",
|
||
"\n",
|
||
"# Сравним p-значение с уровнем значимости\n",
|
||
"if p_chi < alpha:\n",
|
||
" print(\"Отвергаем нулевую гипотезу (случайная величина не имеет нормальное распределение)\")\n",
|
||
"else:\n",
|
||
" print(\"Не отвергаем нулевую гипотезу (случайная величина имеет нормальное распределение)\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 44,
|
||
"id": "c5c37f26-076a-4bdd-8cbd-d230c74cb494",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Результаты теста Колмогорова-Смирнова:\n",
|
||
"Статистика Колмогорова-Смирнова: 0.04950094422191759\n",
|
||
"p-значение: 0.6921286443105663\n",
|
||
"Не отвергаем нулевую гипотезу (случайная величина имеет нормальное распределение)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy import stats\n",
|
||
"\n",
|
||
"# Загрузим данные\n",
|
||
"data_X = df['D']\n",
|
||
"\n",
|
||
"# Проведем тест Колмогорова-Смирнова на нормальность\n",
|
||
"ks_statistic, p_ks = stats.kstest(data_X, 'norm', args=(data_X.mean(), data_X.std()))\n",
|
||
"\n",
|
||
"# Определим уровень значимости\n",
|
||
"alpha = 0.05\n",
|
||
"\n",
|
||
"# Выведем результаты теста\n",
|
||
"print(\"Результаты теста Колмогорова-Смирнова:\")\n",
|
||
"print(\"Статистика Колмогорова-Смирнова:\", ks_statistic)\n",
|
||
"print(\"p-значение:\", p_ks)\n",
|
||
"\n",
|
||
"# Сравним p-значение с уровнем значимости\n",
|
||
"if p_ks < alpha:\n",
|
||
" print(\"Отвергаем нулевую гипотезу (случайная величина не имеет нормальное распределение)\")\n",
|
||
"else:\n",
|
||
" print(\"Не отвергаем нулевую гипотезу (случайная величина имеет нормальное распределение)\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 61,
|
||
"id": "04e8c235-5a08-407b-9606-d97583e8426b",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Результаты t-теста:\n",
|
||
"t-статистика: 30.6366470045653\n",
|
||
"p-значение: 9.554335422627212e-107\n",
|
||
"\n",
|
||
"Результаты U-теста Манна-Уитни:\n",
|
||
"U-статистика: 39604.0\n",
|
||
"p-значение: 1.4768098049370635e-64\n",
|
||
"\n",
|
||
"Отвергаем нулевую гипотезу (параметры идентичны)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy import stats\n",
|
||
"\n",
|
||
"# Загрузим данные\n",
|
||
"data_X = df['X']\n",
|
||
"data_Y = df['Y']\n",
|
||
"\n",
|
||
"# Проведем тесты\n",
|
||
"t_statistic, p_t = stats.ttest_ind(data_X, data_Y)\n",
|
||
"u_statistic, p_u = stats.mannwhitneyu(data_X, data_Y)\n",
|
||
"\n",
|
||
"# Определим уровень значимости\n",
|
||
"alpha = 0.05\n",
|
||
"\n",
|
||
"# Выведем результаты тестов\n",
|
||
"print(\"Результаты t-теста:\")\n",
|
||
"print(\"t-статистика:\", t_statistic)\n",
|
||
"print(\"p-значение:\", p_t)\n",
|
||
"\n",
|
||
"print(\"\\nРезультаты U-теста Манна-Уитни:\")\n",
|
||
"print(\"U-статистика:\", u_statistic)\n",
|
||
"print(\"p-значение:\", p_u)\n",
|
||
"\n",
|
||
"# Сравним p-значения с уровнем значимости\n",
|
||
"if p_t < alpha:\n",
|
||
" print(\"\\nОтвергаем нулевую гипотезу (параметры идентичны)\")\n",
|
||
"else:\n",
|
||
" print(\"\\nНе отвергаем нулевую гипотезу (параметры различны)\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 62,
|
||
"id": "d64c7870-21a7-4854-bc1b-c2e6b12b00c9",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Тест Фишера (для равенства дисперсий):\n",
|
||
"Статистика теста: 50.53439589307273\n",
|
||
"p-value: 5.4580629443683286e-12\n",
|
||
"Отвергаем гипотезу о равенстве дисперсий (p-value < alpha)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import levene\n",
|
||
"\n",
|
||
"def check_equal_variances(data1, data2, alpha=0.05):\n",
|
||
" # Проверяем гипотезу о равенстве дисперсий с помощью теста Фишера\n",
|
||
" stat, p_value = levene(data1, data2)\n",
|
||
" \n",
|
||
" # Выводим результаты теста\n",
|
||
" print(\"Тест Фишера (для равенства дисперсий):\")\n",
|
||
" print(\"Статистика теста:\", stat)\n",
|
||
" print(\"p-value:\", p_value)\n",
|
||
" \n",
|
||
" # Сравниваем p-value с уровнем значимости\n",
|
||
" if p_value < alpha:\n",
|
||
" print(\"Отвергаем гипотезу о равенстве дисперсий (p-value < alpha)\")\n",
|
||
" else:\n",
|
||
" print(\"Не отвергаем гипотезу о равенстве дисперсий (p-value >= alpha)\")\n",
|
||
"\n",
|
||
"# Пример использования\n",
|
||
"data1 = df['X']\n",
|
||
"data2 = df['Y']\n",
|
||
"check_equal_variances(data1, data2)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "6744264b-5b63-4d8b-a937-66847504c323",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "b96eddf5-38cb-49e8-a20c-555407030c43",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 14,
|
||
"id": "e576602a-0ce3-4ffd-a8e1-c63058e9f05f",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"import matplotlib.pyplot as plt\n",
|
||
"\n",
|
||
"# Ваши данные\n",
|
||
"Z = [-0.446584790913,6.86355998091,-1.76549845667,5.03261621241,2.83657823695,6.06844310176,6.13086503711,4.17390545601,9.24916448539,-0.668637990896,-0.869061479559,1.2073522402,-2.59905331132,-3.15066996361,4.02603956288,-0.665513707286,-0.377684709386,-2.93039363693,4.72056537216,1.54982053201,5.98095784994,2.9929446293,0.612329479455,-6.0333756427,5.3457555361,-2.07350827026,2.39601300347,-1.87484187283,3.62588309108,-2.36085162266,1.73519617398,6.20173937204,4.15508334629,4.87722785335,-1.32340512765,3.8812159451,-3.10211663662,-5.19518153501,-0.754185890619,1.33735774207,-3.03086014735,-6.59518865247,-0.0254148054433,4.71219967908,-1.36632919482,-3.42555874305,2.17886985096,0.999733463673,3.55042506167,1.46306069171,3.89874897496,3.10189036997,2.51554468804,-6.23670951284,-0.245339464639,2.76444728454,6.20781237816,-1.47644507541,-0.326347021775,5.24313328217,2.11947271,2.37226182866,-3.46526085438,-5.52929531389,1.97220243579,3.46245202858,4.84235670059,-1.23933963676,2.52057481149,-3.00212447839,1.01018142082,-8.92849226343,-1.20749752954,2.78835380984,-6.10788648726,4.96482421185,1.39783588053,1.43471543386,0.108448798888,2.41109062292,1.86552796086,2.70011301324,-1.26749119379,5.48339911606,-6.63196208972,-3.65267252051,1.23120361376,-0.812317415883,5.35009949318,-0.206368872157,0.0621515314538,-4.43688663449,-0.484832607861,-0.21889229213,-1.07761966901,0.999879814614,0.934924542726,3.88878652167,5.13533831695,3.51653737604,7.07288832585,-2.91857230865,2.75097807206,-4.22942642976,7.06802251868,4.42472519565,-2.12882388479,3.02644722611,0.276600891445,8.61353400882,-2.38378393337,-0.301650838815,-3.12053854458,6.70014649829,3.20443817138,-8.13704475284,2.29492465761,-5.77033086202,6.70240591701,1.27619637614,0.121054514359,0.476461293517,5.77845530964,-0.00886636038868,-2.57060370512,-0.946499440958,-0.260366692556,-5.28553951728,3.45387946052,-5.60934099704,-6.2113232549,-6.26593335795,2.84569941765,1.1621565758,2.58092233426,1.15570798649,4.97641233382,4.67773082083,-0.175952263047,3.92783781409,-4.42600849076,0.798322329752,-3.25618449742,-0.21042582753,8.52487591151,3.15413018799,-2.90445422243,11.4389077107,3.84812593057,2.74841304152,3.28887366301,0.413641831907,5.84333440683,1.81270008983,-3.27684147132,-5.55995520912,-2.8902012445,0.127438016975,-2.68727936377,1.60533019764,-2.84242889149,-3.40727990249,5.48637822522,5.67721879508,2.28348393701,4.82906495104,0.865144277335,-4.11226219478,0.816534973486,5.98258079178,3.00456216818,6.96201245375,5.38320423149,3.64206813965,-3.25667030846,2.28922188272,10.4362170536,-0.00846385757209,1.44867516102,-5.02054399297,-0.679656172104,0.313740873016,-2.46767358101,8.4406691847,5.81084876898,2.5584796121,-0.61910348737,-1.60200738241,0.711265765542,0.062322878034,5.35252488596,-1.32395121384,4.43881843719,3.0418197787,3.69401512845,8.33910525837,8.75742938344,0.266181712928,0.179777088018,-4.24193710422]\n",
|
||
"X = [5,7,7,10,12,14,6,13,13,11,11,7,15,12,12,12,7,11,10,11,11,11,10,3,12,6,10,10,7,11,8,12,3,7,12,7,4,13,11,7,9,15,9,9,12,11,10,9,11,3,12,8,9,13,14,9,14,8,8,8,8,11,13,8,11,16,5,17,7,20,8,10,8,8,7,12,16,13,11,9,7,11,13,13,6,12,7,7,8,8,6,15,11,14,7,11,6,5,7,6,15,8,10,7,10,12,8,13,13,15,11,11,9,14,9,11,8,14,14,7,10,15,10,10,7,7,9,13,11,15,11,13,16,9,5,10,6,9,3,10,11,5,5,13,13,9,12,12,11,9,10,10,8,5,8,8,10,9,12,5,11,16,13,11,11,13,12,10,7,13,2,17,6,6,13,9,7,12,18,8,8,12,15,12,17,8,6,16,6,11,10,8,14,7,6,9,10,10,6,9]\n",
|
||
"Y = [4.41093280453,4.76071247375,-0.393406324096,0.710337606411,2.94606113427,3.70952523734,-0.486096917133,3.77529027862,-0.589344166252,3.11478162602,0.24661990083,-0.915774529541,0.399703831113,2.91793978566,-0.69544654109,3.27267215749,4.47216168913,4.65865652207,0.247328807254,3.51624463673,1.69539925023,4.29129601289,-0.905167045048,3.66880449721,2.66826478729,1.72408658984,-0.474366150145,4.30017803344,0.723794246009,2.17190233136,4.02755895643,0.286811556882,4.18262938414,-0.220165994296,3.352863608,4.9761845494,4.59798194177,1.15493570586,4.64232315781,2.21887426496,-0.689892280671,-0.633472220449,3.29695650974,3.19299683095,3.22126149067,1.05417370797,4.8877269806,4.17488377742,3.79297334692,0.915615946838,3.68066085636,4.86365613995,4.05814383861,-0.215404184641,0.327884892456,3.04987972974,1.43842296028,4.60185394116,2.85330341951,-0.635336415703,1.59737359502,-0.167871526532,-0.0497738748602,1.14150547377,0.785188184305,1.35533529388,-0.922779683276,2.09561901957,4.29288768076,-0.151515060316,0.825609684893,2.99285074846,4.2611558854,-0.59464253544,1.54872087441,4.93990509012,4.79434164053,2.83087395818,2.53291065201,0.732676975238,1.73556553328,-0.713525006439,4.73682716786,4.18726205307,2.17803334454,4.71912436028,2.45093367292,2.1558538494,0.458287929479,4.71724401256,-0.878379838021,0.074387093037,4.68066009183,2.49795497609,1.02438203961,2.94726228088,1.68902213695,4.46007425031,1.93315589528,1.73326355448,2.23665281743,1.9517866833,3.47314680793,4.3177191615,0.20553857212,0.925922986957,2.99658172896,2.22553897893,0.380133519451,4.15676544423,4.18811755188,1.33351877297,4.77177697621,-0.768488835042,1.62410297311,3.81314513178,0.519835192383,3.87721432052,0.106483747667,0.532779693303,0.276857852209,2.08602624583,-0.742484487326,-0.819921224123,2.78360002012,4.38803114419,0.289857551121,1.470156411,2.92259484645,2.98859348375,3.46937648281,1.32120634383,1.34329769078,0.291254178334,-0.206497437231,0.204807702742,3.88345342089,0.245187883964,2.9095507131,0.371257415716,0.87264115291,1.04479290003,-0.0373568247459,0.0375370978293,3.12442127277,3.25161886846,0.581664284246,2.57768736997,4.67163737726,2.85890831369,1.88587397739,0.321999440891,-0.560951533272,0.0617857884422,-0.0466454210008,2.56269508285,3.80097691441,3.17453655958,4.7658451795,3.70753202886,-0.960907783569,2.08376568345,1.77041943087,-0.284687765208,1.34331018195,4.43162773046,1.32704280133,0.773023056715,-0.611673082162,3.57393195051,-0.223048153453,3.77743206482,1.40714290351,1.60962559327,-0.164117394868,4.03214654483,2.0065413409,2.98261145275,1.3603013495,-0.281928262179,-0.0251685620926,0.0971406083006,-0.871778773962,1.34066293226,1.96239295378,0.778269017198,1.67100071132,-0.119244135182,3.61390351274,2.06318939885,2.06748559444,0.41777138974,4.26936239329,1.22065940708,4.2935752377,4.67286242059,3.36957711741,0.240759403929,2.49367238667,2.20328875046]\n",
|
||
"D = [2.29106893237,2.26403892097,6.2446633167,4.93176295377,7.09973553507,5.84190076275,2.91330742621,2.57308785442,5.6869144632,3.93707283059,3.93264067442,1.23962711663,5.92816588081,0.581310339931,2.49878223168,4.42584857266,3.49898148888,6.21364616744,3.25898170282,1.94131808365,2.96677343358,0.659741263411,3.86031145306,9.3666796951,8.24459611291,4.09220004134,5.37452862445,3.13882468173,4.11122173603,0.821461514186,1.68323605285,4.19761005136,3.95725973395,2.8609219217,2.68274392059,2.4003848785,4.26325289,2.5649356191,3.43856907433,-0.538190802425,1.75420235677,7.71678561833,0.798787047917,2.4360008161,4.73973356807,6.82361363062,4.39184490587,4.3084153142,6.386130936,6.62243894369,6.45107547269,1.5908026934,4.21369497931,4.22386242803,2.04668932594,6.16359705613,3.00290165295,5.36868575955,5.45289249694,5.25748441637,0.854327294099,2.98104069695,-0.906781451662,6.01869463603,6.39252059987,5.32627669441,3.08171241758,1.55856342896,4.25735001619,4.58761357451,4.06579591448,5.16454770286,5.68891593981,3.57863598436,4.56023660632,3.25232371118,5.77108364008,2.03424375966,4.12033429679,5.30654271053,3.60168565262,4.00852550948,3.87609131575,4.92368031545,2.47706932781,4.12559834465,3.83740051376,6.19007173018,5.54866779539,3.85911984464,5.78379334795,2.6106290677,3.70107333278,4.4480199468,2.80946277543,3.91595268754,3.69526841579,5.08263234991,2.83853013513,4.56256981337,-0.0990200850857,5.49396138122,3.81375229905,6.02800623977,5.04723833063,5.19108977244,4.93166811013,3.94996447786,2.09122440706,5.58352321149,1.76235444754,0.687902390455,9.40034597862,3.90031851624,4.66853453111,3.95885204015,4.67091515234,2.65800659385,2.46596735383,6.01718943957,2.23501287594,4.34057052755,4.47605810844,3.6169140101,5.07961062785,3.9313569109,3.10307345473,3.14798092339,3.99360992117,3.15387309597,5.08153540746,4.93200276959,3.13595577552,4.7898447788,3.58858222531,0.849263712182,2.72882701337,5.25185003134,4.97964627689,1.82587131482,4.98551578131,0.291661479713,4.71002970446,3.6719721177,3.39311964905,2.44986199694,3.07573083838,2.81492940053,4.87307626853,3.9604570183,1.13029273173,4.82053698751,1.32654701727,7.84993225841,4.12777568255,3.40927235632,5.79027259845,0.802078248036,4.12200287544,2.44315413193,5.95786851881,2.24412800208,6.70453282764,2.86035816443,5.82231338817,4.2488210453,2.2595308785,5.09681669192,2.3652351624,4.42603453088,3.42992742979,4.91407089281,4.69591396749,3.31654416171,8.03286461231,6.06914894206,2.95791637169,2.91747025301,4.30917748622,3.2359712866,5.16293255691,6.20587331612,0.193329476264,3.47222227364,4.01633869097,4.4995946619,4.46669620218,-3.16290716318,5.92328009802,5.53693447068,2.82024823135,4.24260693696,3.15279329672,-0.575154108122,4.4948177318,2.6877013137,3.38441889758,1.29226692427,5.42852280974,4.86122623556]\n",
|
||
"\n",
|
||
"# Построение гистограммы\n",
|
||
"plt.hist(D, bins=20, color='skyblue', edgecolor='black')\n",
|
||
"plt.title('Histogram of D')\n",
|
||
"plt.xlabel('Value')\n",
|
||
"plt.ylabel('Frequency')\n",
|
||
"plt.show()\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"id": "3aca64d7-8567-4041-a15c-b3b9ae2194bc",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<function matplotlib.pyplot.show(close=None, block=None)>"
|
||
]
|
||
},
|
||
"execution_count": 8,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAjUAAAG1CAYAAAABTQXdAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAABaWUlEQVR4nO3deZzNdd/H8deZfYyZYTAzZDDW7Pu+DEWklBZthOoqtxRSWVoslUSSK4TqyhLRoohKUfadsWRfZkTMNDTMmGG2c373H+eacxlmOGfMds68n4+Hx+38zu/3PR/HfTVv39VkGIaBiIiIiJNzK+wCRERERPKCQo2IiIi4BIUaERERcQkKNSIiIuISFGpERETEJSjUiIiIiEtQqBERERGXoFAjIiIiLkGhRkRERFyCQo2IiIi4hCITatavX0+PHj2oUKECJpOJpUuXZnnfMAxGjx5N+fLl8fX1pXPnzhw7dqxwihUREZEip8iEmuTkZBo2bMiMGTOyfX/SpEl89NFHzJo1i23btuHn50fXrl1JSUkp4EpFRESkKDIVxQMtTSYT33//PT179gSsvTQVKlTg5Zdf5pVXXgEgISGBkJAQ5s6dy2OPPWZXuxaLhbNnz+Lv74/JZMqv8kVERCQPGYbBpUuXqFChAm5uOffHeBRgTbkWHR1NbGwsnTt3tl0LDAykZcuWbNmyJcdQk5qaSmpqqu31mTNnqFOnTr7XKyIiInnv9OnTVKxYMcf3nSLUxMbGAhASEpLlekhIiO297EyYMIFx48Zdd/306dMEBATkbZEiIiKSLxITEwkLC8Pf3/+G9zlFqMmtUaNGMWzYMNvrzC8lICBAoUZERMTJ3GzqSJGZKHwjoaGhAPz9999Zrv/999+297Lj7e1tCzAKMiIiIq7NKUJNeHg4oaGh/Pbbb7ZriYmJbNu2jdatWxdiZSIiIlJUFJnhp6SkJI4fP257HR0dzZ49ewgKCqJSpUoMHTqUd955hxo1ahAeHs6bb75JhQoVbCukREREpHgrMqFm586ddOrUyfY6cy5Mv379mDt3LsOHDyc5OZnnnnuOixcv0q5dO1auXImPj09hlSwiIiJFSJHcpya/JCYmEhgYSEJCgubXiIiIOAl7f347xZwaERERkZtRqBERERGXoFAjIiIiLkGhRkRERFxCkVn9JCIiIsWH2WKwPTqeuEspBPv70CI8CHe3WztsWqFGREREspUfwQNg5f4Yxi0/SExCiu1a+UAfxvSoQ7d65XPdrkKNiIiIXCe/gsfK/TEMXBDJtfvJxCakMHBBJDP7NMl1+5pTIyIiIllkBo+rAw38L3is3B+Tq3bNFoNxyw9eF2gA27Vxyw9ituRuCz2FGhEREbHJz+CxPTr+uqB0bfsxCSlsj453uG1QqBEREZGr5GfwiLuUc7u5ue9aCjUiIiJik5/BI9jfvvMa7b3vWgo1IiIiYpOfwaNFeBDlA33Iaf2UCetk5BbhQQ63DQo1IiIicpX8DB7ubibG9Khja+fadgHG9KiT62XjCjUiIiJik9/Bo1u98szs04TQwKw9PaGBPre0nBvAZBhG7tZNOSF7jy4XEREp7vJrn5pMjmzsZ+/Pb4UaERERyVZ+7SjsKHt/fmtHYREREcmWu5uJ1tXKFHYZdtOcGhEREXEJCjUiIiLiEhRqRERExCUo1IiIiIhLUKgRERERl6BQIyIiIi5BoUZERERcgkKNiIiIuASFGhEREXEJCjUiIiLiEhRqREREpOBZLPDVV/D005BHx1Aq1IiIiEjBWr0aWrSAxx6DOXPgl1/ypFkdaCkiIiIFIzISRo6EVausr0uWhFdfhXbt8qR5hRoRERHJX8ePwxtvWIebADw9YeBAeP11CA7Os49RqBEREZH8ERsLb78Nn3wCGRlgMkHv3vDWWxAenucfp1AjIiIieSsxEd5/H6ZMgcuXrdfuvhsmTICGDfPtYxVqREREJG+kpsLMmfDOO/DPP9ZrLVvCxIkQEZHvH69QIyIiIrfGbIaFC2H0aPjzT+u1WrWsPTM9e1qHnQqAQo2IiIiLM1sMtkfHE3cphWB/H1qEB+HulgdBwzDgp59g1Cj44w/rtQoVYNw46N8fPAo2ZijUiIiIuLCV+2MYt/wgMQkptmvlA30Y06MO3eqVz33DW7bAiBGwYYP1dalS1uXaL74IJUrcWtG5pM33REREXNTK/TEMXBCZJdAAxCakMHBBJCv3xzje6MGD1iGlNm2sgcbHB4YPh6goa8gppEADCjUiIiIuyWwxGLf8INkdQJB5bdzyg5gtdh5RcPo0PPMM1K8Py5aBm5v19bFj1onApUvnVem5plAjIiLigrZHx1/XQ3M1A4hJSGF7dPyNG4qPt/bE1KgBn39uPbPpgQdg/3747DOoWDFvC78FmlMjIiLihG42+TfuUs6B5mo53nf5Mnz0kbUX5uJF67UOHeC996B161usPn8o1IiIiDgZeyb/Bvv72NXWdfdlZFgPmRw7Fs6etV6rX98aZu6+u8CWZ+eG0ww/mc1m3nzzTcLDw/H19aVatWq8/fbbGHl0XLmIiIgzsHfyb4vwIMoH+pBTBDFhDUItwoOsFwwDliyBevXgueesgaZyZZg/H3bvhu7di3SgAScKNRMnTmTmzJlMnz6dQ4cOMXHiRCZNmsS0adMKuzQREZEC4cjkX3c3E2N61AG4Lthkvh7To451yGrtWmjVCh5+GI4cgbJlYepU6++ffBLc3fPlz5PXnCbUbN68mfvvv5977rmHKlWq8PDDD3PXXXexffv2wi5NRESkQDg6+bdbvfLM7NOE0MCsQ0yhgT7M7NOEbuY465BSp06wfTv4+cGbb8KJEzBkCHh75+cfJ885zZyaNm3a8Mknn3D06FFq1qzJ3r172bhxI1OmTMnxmdTUVFJTU22vExMTC6JUERGRW5LTJODcTP7tVq88XeqEZm2PBNzHvApffmkddvLwgAEDrIEmJCS//lj5zmlCzciRI0lMTOT222/H3d0ds9nM+PHj6d27d47PTJgwgXHjxhVglSIiIrfmRpOAczv5193NROtqZSAuDt4ZB7NmQXq69c3HHoO334bq1fPsz1BYnGb46euvv2bhwoV8+eWXREZGMm/ePCZPnsy8efNyfGbUqFEkJCTYfp0+fboAKxYREXHMzSYBX0hOdWzyb6ZLl6znMVWrBtOmWQPNXXfBrl2waJFLBBoAk+Eky4fCwsIYOXIkgwYNsl175513WLBgAYcPH7arjcTERAIDA0lISCAgICC/ShUREXGY2WLQbuLvOc6ZMWGdC/PmPXUY9GUkQJYJw5lBZ2afJv870yktDWbPtvbEnDtnvdasmXV59p135sufIz/Y+/PbaYafLl++jJtb1o4ld3d3LBZLIVUkIiKSe9fOm7EYhl2TgEv7eTGzT5PrhqhCr96nxmKBxYutc2Sioqw3VK8O775rXeFUxJdm55bThJoePXowfvx4KlWqRN26ddm9ezdTpkzh6aefLuzSREREHJLdvJlSvp52PRt3KYX7G912/eTf8CDcTcDKlTBqFOzZY30gNBTGjLGe0+Rp32c4K6cJNdOmTePNN9/k+eefJy4ujgoVKjBgwABGjx5d2KWJiIjYLXPezLVzPy5eSbfr+cxJwLbJv5m2b4eRI2HNGuvrgADrmU1Dh1qXahcDTjOnJi9oTo2IiBSmm82buZHMOTUbR9yR5YwnjhyB11+37gYM4OUFL7wAr70GZcpk25azcbk5NSIiIs7uZpvn5eS6HYDBeozBuHHwn/+A2WydJ9O3r/Va5cp5V7QTUagREREpIPZunlfK1zPLcFSWScAXL8KkSdZjDK5csd7Qo4d1EnC9enlftBNRqBERESkg9m6eN+OJJrj9dwdh2yTgtFSYPNkaXi5csN7Ypg1MnAjt2uVj1c5DoUZERKSAZJ6cHZuQku2hlJnzZlpVK/O/YSazGebNhdGj4a+/rNfq1IEJE6w9NC66PDs3nGZHYREREWfn0MnZhgHLlkGDBvD009ZAExYGc+bAvn1w330KNNdQqBERESlANz05u1552LDBOqTUsyccPAilS1uHno4ehf79wd29UGov6jT8JCIiUsCyPTk7PAj3gwegx3OwYoX1Rl9f6z4zw4dDqVKFWbJTUKgREREpBFk2z/vzT3hqGHzxhXXYyd0d/vUv6zyaChUKt1AnolAjIiJSWM6ft65mmjHDevgkWM9meucdqFWrcGtzQgo1IiIiBS05GT78EN5/HxITrdc6dbIuz27evHBrc2IKNSIiIgUlPR0++wzeegtiY63XGjWC996Du+7SaqZbpFAjIiKS3ywW+PZb6xlNx49br1Wtah1mevRRcNNi5LygUCMiIpJPzBaDIwu+p8J74yh1aJ/1YnAwvPkmPPec9fBJyTMKNSIiIvlg89e/4P7667Q8vguAJC9fFrV/hCrjX6dLyxqFXJ1rUqgRERHJS8ePE/Piy7RZ+QMAaW4eLGx8N9NbP0q8Xyn4/igz/UpaN9mTPKVQIyIikhdiY+HttzE++YTyGRlYMLG0bkemtOvNX6VCbbeZgHHLD9KlTuj/zneSPKFQIyIicisSE61Ls6dMgcuXMQFrqjZlUkQ/DgVXve52A4hJSGF7dPz/Nt+TPKFQIyIikhupqTBzJowfb91ED6BFCzY++wpPHS9x08fjLqXkc4HFj9aQiYiIOMJshvnzrTv+vvSSNdDUqgVLlsDWrbh3usOuZoL9fW5+kzhEoUZERMQehgE//giNG0O/ftbzmipUgE8/hf374cEHwWSiRXgQ5QN9yGm2jAkoH2g9wFLylkKNiIjIzWzZAhERcO+98Mcf1hOz33sPjh2zHjzp4YHZYrDlxD+s2HeWx5pXArgu2GS+HtOjjiYJ5wPNqREREcnJoUPw2muwdKn1tY8PvPgijBwJQf/raVm5P4Zxyw8Sk/C/eTKlSngCcPFyuu1aaKAPY3rU0XLufKJQIyIicq3Tp2HsWJg713rEgZsbPPWU9VrFilluXbk/hoELIjGuaSLhcjoG8FLnGlQp60ewv3XIST00+UehRkREJFN8vHVY6aOPrKubAHr2hHffhdq1bbeZLQbbo+OJTbjC2z8eui7QgHXptglYvOM0G0fcoTBTABRqRERELl+GadOsgebiReu1Dh2sr1u3znJrdkNNOdGeNAVLoUZERIqvjAyYM8c6rHT2rPVa/frWMHP33WAy2Xpl4i6lcPL8ZaauPpptz8yNaE+agqFQIyIixY9hwPffWycBHzlivVa5Mrz9NjzxBLi7A471ytyI9qQpGAo1IiJSvKxda129tG2b9XWZMvDmm/B//wfe3rbbcpoA7AgT1hVP2pOmYCjUiIhI8bB3rzXMrFxpfe3nB8OGwSuvQEBAllvNFoNxyw/ecqAB7UlTkBRqRETEtUVHW3tivvzSOuzk4QEDBlivhYRk+8j26PhbHnLSnjQFT6FGRERcU1wcvPMOzJoF6f/dAO+xx6zzZqpXz/Exs8Vg0/HzufrIID9P3ry3LqEB2pOmMCjUiIiIa7l0CaZMgcmTISnJeq1LF5gwAZo2ve72a1c3Ldp+ithEx3ppMqPLuw/UV89MIVKoERER15CWBrNnW3tizp2zXmvaFCZOhDvvtN2WFyHmWhpqKhoUakRExLlZLLB4sXWOTFSU9Vr16jB+PDz8sPWIg//KiyXaJtDxB0WUQo2IiDgnw4Bff7WuaNqzx3otNBTGjIFnngFPzyy358USbVCvTFGmUCMiIs5n+3ZrmFmzxvo6IACGD4ehQ61Lta9ithhsPfEPI5f8ccuB5oVO1XipSy31yhRRCjUiIuI8jh6F11+Hb7+1vvbyghdegFGjMAeV+e9cmYuU9fMGE/x26G+W7jlLfHJannx82+rlFGiKMIUaEREp+s6ehXHj4D//AbMZw2Ti9L0PEzdsFKkVw/hty98s3bM7z8LLtbQzsHNQqBERkaLr4kWYNAmmToUrVwDYcHtr3m7Tm6PlqsDKs8DZfC1BOwM7D4UaEREpelJSYPp0ePdduHABgAuNmvFc3V7sqFi3QEvRxGDnoVAjIiJFh9kM8+dbVzCdPm29VqcO6e+M584/ShB/OT3fSwgN8ObxFpW0XNsJKdSIiEihM5stHPt0IRXef4eAqKMAXA6pwM6nhrC2ZTe+2RPDpZT8CTQKMa5DoUZERArV1vlLKfHmGzQ4dQCAiz4lmd76Eb5oci+phhdsPZ0vn1vK15MZvZvQqmoZhRgX4XbzW4qOM2fO0KdPH8qUKYOvry/169dn586dhV2WiIjkxv79/B3RhVb9HqDBqQNc8fBmRqtedBjwGZ+1eJBUD698+VjTf3+991B92lYvq0DjQpymp+bChQu0bduWTp068fPPP1OuXDmOHTtG6dKlC7s0ERGxQ+aZS5eOHKfhZx8SvPRrQgyDDJMbXzW8i3+3eZw4/zL5Xocm/roupwk1EydOJCwsjDlz5tiuhYeHF2JFIiJir5X7Y5i6eAsP/zKfJ3f/iLc5A4Afa7Xlg/ZPElWmYr5+fpCfJw80uo3OdUI1Z8aFOU2o+eGHH+jatSu9evVi3bp13HbbbTz//PM8++yzOT6TmppKamqq7XViYmJBlCoiIlf5ZesJ/hg+jq+3LSEg7TIAmys1YGJEP/ZWqJWnn5UZXu64PQRMcD4pVZN/ixGnCTVRUVHMnDmTYcOG8dprr7Fjxw4GDx6Ml5cX/fr1y/aZCRMmMG7cuAKuVESkeMscZvr7fCIZn3xKh69m0TXZutfMgeCqTIzox/rwJmC69ZBRuoQHHz3WhPjLaQovgskwjFs936tAeHl50axZMzZv3my7NnjwYHbs2MGWLVuyfSa7npqwsDASEhIICAjI95pFRIqDzBATm3CFTcfPs/pALG33rOWVDfMJvxADwKnAECZ36Mvy2u0xTLe+RiUztszs00RzY4qBxMREAgMDb/rz22l6asqXL0+dOnWyXKtduzZLlizJ8Rlvb2+8vb3zuzQRkWJr5f4Yxi0/SExCCgBtTu5h/rq5NIg9DsC5EqWY1uZRFjXqRrq7Z559rib7SnacJtS0bduWI0eOZLl29OhRKleuXEgViYgUT5k9M78eiGHO5j8BqBt7nBHr5tHh5G4Akrx8+aTFg/yn2f0ke5fIk8/VZF+5GacJNS+99BJt2rTh3Xff5ZFHHmH79u188sknfPLJJ4VdmohIsXFtz0zlC2d5Zf0X9Di8AYA0Nw8WNr6b6a0f5R+/Urn+nKF3VqdyGT/ik9MIKulNaIDmy8jNOc2cGoAVK1YwatQojh07Rnh4OMOGDbvh6qdr2TsmJyIi11u5P4aBCyIxgHJJF3hx82Ie37sST4sZCyaW1u3IlHa9+atUaK4/o3QJTyY8WF/DSpKFvT+/nSrU3CqFGhGR3DFbDNq+9ztJ5+J5btsS/rVzKSXSrQsx1lRtyqSIfhwKrprr9kv5evJU2yq8cEcN9cbIdVxuorCIiBSsq1c1Ld8eTfffvmLQlq8oc8W659ee8jV5r2N/tlZqkKv2h95ZnfByJbUUW/KMQo2IiFznp30xvLFsPxcvXaHnwbW8tWEhFRPjADgRVJFJHfryS83WudprRkNMkl8UakRExMZsMRiyeDcr9p6lU9ROhq+bR+1zJwGILRnE1LZP8E2DLpjd3B1uW0NMkt8UakREBLPFYPrvx5m17ji1Tx7gq7VzafnXAQASvP2Y2aoXc5veS4qnj91tBvp40KVOCG1rlNPqJSkQCjUiIsXcyv0xjPzuD8qcimLq+nl0PbYVgFR3T+Y07cHMVr1I8PW3u72n2lTmrrrlFWKkwCnUiIgUU5m9M4u+28zITV/S64/VuBsWzCY3vqnfmaltnyA2oKzd7ZXXLr9SyBRqRESKEbPFYOuJf1iw7SR790bRd/1XrI1cgU9GGgC/1GjFpA79OFE2zO42A309+Lh3U1pVLaOeGSlUCjUiIsVE5jBTSsIl+u9awXtbvyEwNRmAbWH1mBjRj8jbajvUpgmY+FAD2la3v0dHJL8o1IiIuLCrz2mavzGKXvtWMXTTl4QmxQNwqFwVJkb0Y23VZg4vz9bSbClqFGpERFxU5l4z8UmpdD26hV/Xz6da/F8A/BUQzAft+7CsTgQWB5dna2m2FFUKNSIiLiRzzszkXw+z+3QCrU7tY8TaeTSOOQJAvG8A01s/yoLG3Unz8LS7XR9PNx5vHqZVTVKkORxqIiMj8fT0pH79+gAsW7aMOXPmUKdOHcaOHYuXl1eeFykiIjeXOWfm4uV0asdFMXftPDpG7wLgsqc3nzZ/gE9bPEiSdwm72/T2cOP5jtXUKyNOweFQM2DAAEaOHEn9+vWJioriscce44EHHuCbb77h8uXLTJ06NR/KFBGRq2X2yGyJOo/FgNiEFL7bfYaKF2MZs2EB9x9chxsG6W7uLGrYjWltHuNcydIOfYaftzu737wLLw+3fPpTiOQth0PN0aNHadSoEQDffPMNHTp04Msvv2TTpk089thjCjUiIvnsp30xDF+yj6TUDNu1oMsJjNm8mN67f8bLYr3+Q+0OfNC+D3+WrpCrz/mgV0MFGnEqDocawzCwWCwArF69mnvvvReAsLAwzp8/n7fViYhIFhN+Osjs9dG2136pl/nXjqU8u+N7SqZdAWB9lcZMiujH/tDqufoMbaInzsrhUNOsWTPeeecdOnfuzLp165g5cyYA0dHRhISE5HmBIiJiHW769+qjtkDjaU7n8T0rGbx5MWUvJwCwL7Q6EyP6s6lKI4faLuHpRvf65XVGkzg9h0PN1KlT6d27N0uXLuX111+nenXrvwS+/fZb2rRpk+cFiogUR5lzZjadOMfOkxfYc/oiaWYDk2Ghx6H1vLxhAZUvxgIQXbo8k9v35afb22KYHBsuGnpndV68s6ZCjLgEk2EYRl40lJKSgru7O56e9i8RLGiJiYkEBgaSkJBAQEBAYZcjIpLF1UcYrDl8jpQMy//eNAw6REcyYt086sZFARDnV5p/t32crxrcRYa7Y/9G1RCTOBN7f37nap+aixcv8u2333LixAleffVVgoKCOHjwICEhIdx22225LlpEpLi5esffRTtOk5Juue6eBjFHGbl2Lm1O7QMg0asEs1s+xOfN7ueKl4/dn6W9ZsTVORxq9u3bx5133kmpUqU4efIkzz77LEFBQXz33XecOnWK+fPn50edIiIux7bjb3Jatu+Hx5/hlfXzuefIJgBS3T2Y3+RePm7ViwslAu3+HD8vd57rUFV7zYjLczjUDBs2jKeeeopJkybh7+9vu969e3eeeOKJPC1ORMRVjf/xIJ9uiM72veBL/zB00yIe2fcrHoYFCya+q3cHH7brzZnAYIc+R3NmpDhxONTs2LGD2bNnX3f9tttuIzY2Nk+KEhFxZeN/PMCnG05edz0gJYkB25bw9M4f8M1IBWB1tea8H9GPI+WqOPQZOmxSiiOHQ423tzeJiYnXXT969CjlypXLk6JERFxR5rLsawONd0YafXetYNDWrymVkgTAzttq817H/uysWNeuth9oWJ4KQSUwYaJ1tTK0qlpGvTNS7Dgcau677z7eeustvv76awBMJhOnTp1ixIgRPPTQQ3leoIiIs8qcBBybcIWNx8+zfO9Z0sz/W3DqZjHz0P7fGbrxS267dA6Ao2UqMSmiH6urtwCTfaHk4yca071B7nYNFnElDi/pTkhI4OGHH2bnzp1cunSJChUqEBsbS+vWrfnpp5/w8/PLr1pvmZZ0i0hBWbk/hnHLDxKTkHL9m4ZBl+PbeHXdfGr+cwqAs/5l+bBdb5bUuwOLm7tdn6EhJiku8m1Jd2BgIKtWrWLjxo3s27ePpKQkmjRpQufOnW+pYBERV7FyfwwDF0SS3b8Ym/11gJFr59LszCEALvqUZEarR5jf5B5SPb1v2raPhxudbg+mT6vKGmISuUau9qkBaNeuHe3atcvLWkREnFrm5nkjlvxxXaCpee4kw9fNo/OJHQBc8fDm82b3MbvlQyT6lMyxTQ8TNKlcmubhQbSpVlZBRuQG7Ao1H330kd0NDh48ONfFiIg4q5yGm25LiOOljQt5cP/vuGGQYXLj6wZ3MbXt48T5l8mxPT9vd55tF67l2CIOsGtOTXh4uH2NmUxERUXdclH5RXNqRCQ//LQvhue/jMxyrdSVRAZt+Zq+kSvwNmcA8GOttnzQ/kmiylTMsa1OtcryXIfq2vFX5Cp5OqcmOjr7DaJERIqjq1c1bTh2ju92n7W955uWwtM7lzFg2xIC0i4DsLlSAyZG9GNvhVo5tmkCpj3WmHsbaRWTSG7lek6NiEhxY7YYTPvtGJ9tjCIp1ZzlPQ9zBo/u+5UhmxYRnHwBgAPBVZkY0Y/14U1uujx7hpZli9wyu0LNsGHDePvtt/Hz82PYsGE3vHfKlCl5UpiISFHy074Yhn29J+vJ2YDJsND98CZe3vAFVS9Ye2xOBYYwuUNfltduj2Fyu2G7ft7ufNCroZZli+QBu0LN7t27SU9Pt/1eRKQ4yemcpjYn9zBy3VwaxB4H4FyJUkxr8yiLGnUj3d3zhm16e5gYGFFNE4FF8pDDm+85M00UFhF7ZS7Pfv+XQ+z5K+vRMHVjjzNi3Tw6nLT+Iy/Jy5dPWjzIf5rdT7J3iRu26+ftzqzeTWlTvazCjIid8m3zvaeffpp///vfWU7oBkhOTubFF1/k888/d7xaEZEiInPezKx1J64baqp84SyvrP+CHoc3AJDm5sHCxnczvfWj/ONXyq72P+jVkPY1dU6eSH5wuKfG3d2dmJgYgoODs1w/f/48oaGhZGRk5GmBeUk9NSJyrcwemS1R5zkWl8Tvh+NIN2f9z2K5pAu8uHkxj+9diafFjAUTy+pEMKV9H06XCrXrc3SkgUju5XlPTWJiIoZhYBgGly5dwsfHx/ae2Wzmp59+ui7oiIgUVTfqkclUMvUyz21bwjM7l+GXbt1Ub03VpkyK6Meh4Kp2fc7d9UJ1pIFIAbE71JQqVQqTyYTJZKJmzZrXvW8ymRg3blyeFicikh9W7o9h2Nd7uZxmzvZ9r4x0+uz+iUFbvqLMFet8mj3la/Jex/5srdTArs/QqiaRgmd3qFmzZg2GYXDHHXewZMkSgoKCbO95eXlRuXJlKlTQHgsiUrRkDi9tOnGOsxdTuJJu5pcDf2d7r5vFzP0H1/HyhgVUTIwD4ERQRSZ16MsvNVvfdK8Z0KomkcJkd6iJiIgArLsLh4WF4eZ2470XREQK20/7Yhi+ZB9JqTeZ62cYdIrayfB186h97iQAsSWDmNr2Cb5p0AWzm3uOj3q4QefaIVQP9qd1tTIaZhIpRA6vfqpcuTIXL15k+/btxMXFYbFkHYvu27dvnhUnIpJbOe0tc63GZw4zct1cWp7eD0CCtx8zW/VibtN7SfH0ueGz99QP4aPHmyrEiBQRDoea5cuX07t3b5KSkggICMB0VXesyWRSqBGRQmW2GAz+MpIf98fe8L5q508zfP08uh7bCkCquydzmvZgZqteJPj63/DZkt7uTHqogY41ECliHA41L7/8Mk8//TTvvvsuJUrceJOp/PTee+8xatQohgwZwtSpUwutDhEpPFfPlzlz4QoxCSns+vMC5htsVBGaeJ6hm76k1x+rcTcsmE1ufFvvTqa2e4KYgBvvH+PtYeL5jtV54Y4a6p0RKYIcDjVnzpxh8ODBhRpoduzYwezZs2nQwL5VCCLi/K7eT8ZiQGxCCj/+EUNqDsuxrxV45RIDt35D/8gV+GSkAfBLjVa836Evx8tWuuGznu4mBnXU5F+Ros7hUNO1a1d27txJ1ar27dGQ15KSkujduzeffvop77zzTqHUICIFx579ZG7EJz2F/rtWMHDrNwSmJgOwrWJdJnbsT+RttW/4rJ+3O8+2C1eYEXESDoeae+65h1dffZWDBw9Sv359PD2zHtp233335Vlx2Rk0aBD33HMPnTt3vmmoSU1NJTU11fY6MTHxBneLSFGR2Sszf+tJVh/6G7PjWQZ3i5le+1YxdNOXhCbFA3CoXBUmRfRjTdVmOS7PfrBRBdrXCiY0wIcW4UEKMyJOxOFQ8+yzzwLw1ltvXfeeyWTCbM5+M6u8sHjxYiIjI9mxY4dd90+YMEEbAoo4icwgs2DbSdYcPperXhkADIOuR7cwfP18qsX/BcBfAcF80L4Py+pEYLnB8uyPn2isyb8iTszhUHPtEu6Ccvr0aYYMGcKqVauyHNFwI6NGjWLYsGG214mJiYSFheVXiSKSSyv3xzDyuz+4eDn9ltppdWofI9bOo3HMEQDifQOY3vpRFjTuTpqHZ47P6VwmEdfg8IGWhWXp0qU88MADuLv/719ZZrMZk8mEm5sbqampWd7Ljg60FCl6Vu6P4f8WRN5SG7Xjohi+bh6donYBcNnTm8+a9eTTlg9yydsvy70Nb/One4PbSExJx4RJG+aJOIE8P9DyasnJyaxbt45Tp06RlpaW5b3BgwfnpsmbuvPOO/njjz+yXHvqqae4/fbbGTFixE0DjYgUPWaLwdgfDuT6+YoXY3l5wwLuP7gONwzS3dxZ1LAb09o8xrmSpa+7/9n2VXj9nrq3UrKIFGEOh5rdu3fTvXt3Ll++THJyMkFBQZw/f54SJUoQHBycb6HG39+fevXqZbnm5+dHmTJlrrsuIs5ha9Q/xCam3vzGawRdTuDFzYvpvftnvCzWIxCW396eyR2e5M/S18+J0WZ5IsWDw6HmpZdeokePHsyaNYvAwEC2bt2Kp6cnffr0YciQIflRo4i4oJX7Yxi8aLdDz/ilXuZfO5by7I7vKZl2BYD1VRozKaIf+0OrZ7nXx8ONTrcH06dVZQ0viRQTDs+pKVWqFNu2baNWrVqUKlWKLVu2ULt2bbZt20a/fv04fPhwftV6yzSnRqRwXb1UO6eTsrPjaU7n8T0rGbx5MWUvJwCwL7Q6EyP6s6lKIwA8TNC4cmlahAfRplpZBRkRF5Jvc2o8PT1tJ3QHBwdz6tQpateuTWBgIKdPn859xSLi0uw+MfsqJsNCj0MbeHnDF1S+aD3LKbp0eT6M6IvnIw/TKKgkjTXZV0T+y+FQ07hxY3bs2EGNGjWIiIhg9OjRnD9/ni+++EJzW0QkWxN+Osjs9Tc/MdvGMOgQHcnw9fOp9/cJAM75lWJ6+96UGfx/fNi1rgKMiFzH4VDz7rvvcunSJQDGjx9P3759GThwIDVq1ODzzz/P8wJFxLmt2HPWoUDTIOYoI9fOpc2pfQAk+/gR+ei/8Bj2EqPrVVKYEZEcOc0+NXlBc2pECo7ZYvDRb8f492/H7Lo/PP4Mr6yfzz1HNgGQ6u7B1y3u44mls3APvvHp2SLi2vJ1nxoRkZw4egBl8KV/GLppEY/s+xUPw4IFE9/Vu4MP2/Xm9YHdFGhExG4Oh5rw8HBMORwEBxAVFXVLBYmIc8oMMzPWHCfdcvMO4ICUJAZsW8LTO3/AN8O6V83qas15P6IfR8pVYUCHcLo30LEFImI/h0PN0KFDs7xOT09n9+7drFy5kldffTWv6hIRJ7JyfwzDvt7L5bSbH2jrnZFG310reH7rN5ROsc7P23lbbd7r2J+dFetS0tudj7VRnojkgsOhJqcN9mbMmMHOnTtvuSARcS4/7Yvh+S9vfnaTm8XMQ/t/Z+jGL7nt0jkAjpapxPsRfVlVvSWYTAy9szov3llTk4FFJFfybKJwVFQUjRo1IjExMS+ayxeaKCySd8wWg3+vPspHvx+/8Y2GQefj23l1/TxqnT8FwFn/snzYrjdL6t2Bxc1dp2SLyA0V+EThb7/9lqCgoLxqTkSKsJ/2xTDs6z03nQjc7K8DjFg7j+ZnDgJw0ackM1o9wvwm95Dq6Y23u4nP+jWnTfWy6p0RkVuWq833rp4obBgGsbGxnDt3jo8//jhPixORoseejfRqnjvJq+vn0+X4dgCueHjzebP7mN3yIRJ9Stru+/fjjWlfU6ubRCRvOBxqevbsmeW1m5sb5cqVo2PHjtx+++15VZeIFDKzxWB7dDyxCVc4n5RK/OU0dkT9w85TCTk+c1tCHC9tXMiD+3/HDYMMkxtfN7iLqW0fJ86/jO0+DTeJSH7Q5nsicp2f9sXwxrL9xCen2XV/qSuJDNryNX0jV+Bttp7t9GOttnzQ/kmiylS03dckLJCXu96uc5pExCH5NqfmzJkzLFmyhKNHj+Ll5UWtWrV45JFHKF269C0VLCKFK7Nn5pP1J1hz5Jxdz/impfD0zmUM2LaEgLTLAGyu1ICJEf3YW6GW7T4fTzem9GqoZdoikq8cCjUff/wxw4YNIy0tzZaUEhMTGTZsGJ999hmPP/44hmGwZ88eGjdunC8Fi0jeW7k/hnHLDxKTkGLX/R7mDB7d9ytDNi0iOPkCAAeDw3kvoj/rw5vAf+fdeXuYGBhRTcu0RaRA2B1qfvzxRwYPHszQoUN5+eWXKV/eOhYeExPD+++/T79+/QgLC+Pjjz/m9ttvV6gRcRIr98cwcEEkdo1DGwb3HN7Iyxu+oOqFswCcCgxhcocnWV67A4bJzXbr4E7VGdJFYUZECo7doeb9999n5MiRvPPOO1muly9fnilTplCiRAm6dOlCaGgoEyZMyPNCRSTvmC0GW0/8w6YT5/jPxpN2BZo2J/cwYt08GsZaD6g8XyKQj9o8xqJG3Uh398xy74AO4QzrWiu7ZkRE8o3dE4UDAgLYsWMHtWpl/x+qI0eOULt2bU6ePEmlSpXytMi8oonCUpxlzpn59UAMi3acJiX95odNAtSNPc6IdfPocHI3AElevnza/AE+a96TZO8SWe7V3BkRyQ95PlHYbDbj6emZ4/uenp74+voW2UAjUpw5OmcGoNKFGF7Z8AX3HVoPQJqbBwsb38301o/yj1+p6+7XcJOIFDa7Q03dunVZtmwZL730UrbvL126lLp16+ZZYSJya67umZmz+U+7nyuXdIEXNy/m8b0r8bSYsWBiWZ0IprTvw+lSodk+8/ETjdU7IyKFzu5QM2jQIAYOHIi3tzfPPfccHh7WRzMyMpg9ezZvvPGGdhQWKUSZ82S2RJ3nWFwSm0/8w6WUDLufL5l6mWe3f8e/dizFL93ao7M2vCmTIvpxMKRqts9oEz0RKUrsDjX9+vXjjz/+4IUXXmDUqFFUq1YNwzCIiooiKSmJwYMH079//3wsVURysnJ/DCO/+4OLl9MdftYrI50+u39i0JavKHPFeiDtnvI1ea9jf7ZWamC7r2FFf6qUKYnJZOK20r60qVZWm+iJSJHi8I7CW7duZdGiRRw7Zl0BUaNGDR5//HFatWqVLwXmJU0UFlf0074Ynv8y0uHn3Cxm7j+4jpc3LKBiYhwAJ4IqMqlDX36p2dq210yQnyfv3F9Pw0siUmjybUfhVq1aOUWAESkOVuw5ywuLdzv2kGHQMWonI9bNo/a5kwDElgxiatsn+KZBF8xu7rZbh95ZgxfvrKHeGBFxCg6HGhEpXJlzZyb/epjdp3M+XDI7jc8cZuS6ubQ8vR+ARG8/Pm7Vi7lN7yXF0yfLvQM6hDO0S808q1tEJL8p1Ig4kdzOnal2/jTD18+j67GtAKS6ezKnaQ9mtupFgq9/lns13CQizkqhRsRJ5GbuTGjieYZu+pJef6zG3bBgNrnxbb07mdruCWICygFQwsuNu+uF0q5GMKEBPrQID9Jwk4g4JYUakSIsc6+ZlfvPMm/LKbufC7xyiYFbv6F/5Ap8MtIA+KVGK97v0JfjZf+3QeZLnWvwwh2aMyMiriFXoSYjI4O1a9dy4sQJnnjiCfz9/Tl79iwBAQGULFkyr2sUKZZyswuwd3oqT+1azsCt3xCYmgzAtop1mdixP5G31bbdp/1lRMQVORxq/vzzT7p168apU6dITU2lS5cu+Pv7M3HiRFJTU5k1a1Z+1Cni8jJ7ZWITrrDp+Hm+jTxj97PuFjO99q1i6KYvCU2KB+BQuSpMiujHmqrNKOnjTrfq5age7E/ramW0v4yIuCSHQ82QIUNo1qwZe/fupUyZMrbrDzzwAM8++2yeFifiqq4OMPHJaZyKv8x3u884tAMwAIZB16NbGL5+PtXi/wLgr4BgprTvjemJJ7ivdnme0zwZESkmHA41GzZsYPPmzXh5eWW5XqVKFc6csf9fliLF1U/7Ynhj2X7ik9NuqZ1Wp/YxYu08GsccASDeN4DprR9lQePuPHVHTUZ1r5MX5YqIOA2HQ43FYsFsNl93/a+//sLf3z+bJ0QErL0zQxbvZsW+mFtqp3ZcFMPXzaNT1C4ALnt681mznnza8kGMgACmPtRAy7FFpFhyONTcddddTJ06lU8++QQAk8lEUlISY8aMoXv37nleoIgrWLk/hhFL9pFwxcHhpatUvBjLsI0L6XlgLW4YpLu5s6hhN6a1eYzLQWV5rkNVrWQSkWLN4bOf/vrrL7p27YphGBw7doxmzZpx7NgxypYty/r16wkODs6vWm+Zzn6SwpDbs5kyBV1O4MXNi+m9+2e8LNZQtPz29kzu8CR/lq7A4E7VGdKlpsKMiLisfDv7qWLFiuzdu5fFixezb98+kpKSeOaZZ+jduze+vr63VLSIM7t28m+pEl5sPn6O73afzVV7JdKu8K8dS3lu+3eUTLsCwPoqjZkU0Y/9odUB61EGw7rWyrM/g4iIM8vVPjUeHh706dMnr2sRcUpmi8H0348zZ1M0F684dnxBdjzN6Ty+ZyUvbv6KcpcvArAvtDoTI/qzqUojQEcZiIhkx65Q88MPP9jd4H333ZfrYkScTW7PYsqOybDQ49AGXt7wBZUvxgIQXbo8k9v35afb22KY3ADtAiwikhO7Qk3Pnj3tasxkMmW7MkrEFa3cH8P/Lcj9XBkbw6BDdCTD18+n3t8nADjnV4p/t32CxQ3uIsPd+j/T8oE+jOlRR7sAi4jkwK5QY7FY8rsOEadithiM/eHgLbfTIOYoI9bNpe2f+wC45OXLrJYP8027B7m7ZTVGBfkRVNJbB02KiNhBB1qK5ML0348Rm2j/mUzXCo8/wyvr53PPkU0AZHh4cvjBJ/lzwFDaVa7AMAUYERGH5SrU/Pbbb3z44YccOnQIgNq1azN06FA6d+6cp8WJFCWZq5t+PRDDnM1/5qqN4Ev/MHTTIh7Z9ysehgXDZMJ4si8eb42jXuXK1MvjmkVEihOHQ83HH3/MkCFDePjhhxkyZAgAW7dupXv37nz44YcMGjQoz4sUKWy5OTH7agEpSQzYtoSnd/6Ab0YqAH936EzI9CmY6tfPy1JFRIothzffq1ixIiNHjuSFF17Icn3GjBm8++67+Xb+04QJE/juu+84fPgwvr6+tGnThokTJ1Krlv17dGjzPcmNW9k8zzsjjScjVzBoyzeUTrkEwN6w2qS8/S4t+/XMwypFRFyXvT+/3Rxt+OLFi3Tr1u2663fddRcJCQmONme3devWMWjQILZu3cqqVatIT0/nrrvuIjk5Od8+U+SnfWd5YZHjgcbNYqbXvlX8/skA3ljzOaVTLnGiXCWWj5tBvej9CjQiIvnA4eGn++67j++//55XX301y/Vly5Zx77335llh11q5cmWW13PnziU4OJhdu3bRoUOHfPtcKb5W7o/h+S93O/aQYdD5+HbGbl1IxbNRAFwOKc/Zl0YRPmwg1Tw1N19EJL84/F/YOnXqMH78eNauXUvr1q0B65yaTZs28fLLL/PRRx/Z7h08eHDeVXqNzF6hoKCgHO9JTU0lNTXV9joxMTHf6hHXkpsl283+OsCItfNofua/z5UuDa+9RolBg6iuI0RERPKdw3NqwsPD7WvYZCIqKipXRd2MxWLhvvvu4+LFi2zcuDHH+8aOHcu4ceOuu645NXIz/159lA9XH7Pr3prnTvLq+vl0Ob4dALOPD+5Dh8KIEVCqVP4VKSJSTNg7p8bhUFMUDBw4kJ9//pmNGzdSsWLFHO/LrqcmLCxMoUauk7lcO+5SCtHnkpn6280DTYXEOIZtWMiD+3/HDYMMkxtnH3yCSh9NhAo6k0lEJK/k2yndhe2FF15gxYoVrF+//oaBBsDb2xtvb+8CqkyclaPLtUtdSWTQlq/pG/kj3mbrmU8/1WyD3/sTiLhP87tERAqLw6HGMAy+/fZb1qxZQ1xc3HVHKHz33Xd5Vty1n/viiy/y/fffs3btWruHwURuxJHl2r5pKTy9cxkDti0hIO0yAJsrNeA/9zxHr+cfJEJnMomIFCqHQ83QoUOZPXs2nTp1IiQkBJOpYLZyHzRoEF9++SXLli3D39+f2FjrKcaBgYH4ahKm5IJ1ufbNVzd5mDN4dN+vDNm0iODkCwAcDA4ncuAIqvV5iE+qltGRBiIiRYDDc2qCgoJYsGAB3bt3z6+aspVTeJozZw79+/e3qw1tvieZ7Dph2zC45/BGXt7wBVUvnAXgVGAIkzs8SbUX/sWQu+zf+FFERHIv3+bUBAYGUrVq1VsqLjeccD6zFFFpGRZe+37/De9pc3IPI9bNo2GsdcLw+RKBTGvzGF826kaZ0iX5sHPNgihVREQc4HCoyVwm/fnnn2vYR5yK2WIw/ffjfLL+BMlp5mzvqRt7nBHr5tHhpHVYKsnLl0+bP8BnzXuS7F0CgLH31dVwk4hIEeRwqHnkkUdYtGgRwcHBVKlSBU9PzyzvR0bm7owckfy0cn8MI7/7g4uX07N9v9KFGF7Z8AX3HVoPQJqbBwsb38301o/yj18pANxMMP3xJnTThGARkSLJ4VDTr18/du3aRZ8+fQp0orBIbt1o/kzZ5Au8uHkxT+xZiafFjAUTy+pEMKV9H06XCs1y7/THG9O9gQKNiEhR5XCo+fHHH/nll19o165dftQjkqfMFoNxy68/7qBk6mWe3f4d/9qxFL906/40a8ObMimiHwdDss4ZKx/ow5geddRDIyJSxDkcasLCwrRySJzG9uj4LJvqeWWk03vPT7yw+SvKXLGeBbanfE3e69ifrZUa2O4bemd1wsuVJNjfhxbhQZpDIyLiBBwONR988AHDhw9n1qxZVKlSJR9KEsk7cZesgcbNYub+g+sYtnEhYQl/A3Ai6DYmdejHLzVbw3+HUcv4eTH+gXrqlRERcUIOh5o+ffpw+fJlqlWrRokSJa6bKBwfH59nxYncqrJ+XnQ8sYMR6+ZR+9xJAGJLBjG17RN806ALZjd3271Bfp5sGXUnXh5uhVStiIjcCodDzdSpU/OhDJG8k3k45cHvfqHRjPeY++cfACR6+/Fxq17MbXovKZ4+WZ4xAe8+UF+BRkTEieVq9ZNIUZMZZFYdjGXvqq08+8t/eOboFgBS3T2Z07QHM1v1IsHX/7pnS5fwZMKD9TXkJCLi5G7plO6UlBTS0tKyXNMkYilomadsG6f/YuimL3n9j9W4GxbMJje+rXcnU9s9QUxAueueK+XryVNtq/DCHTU0EVhExAU4HGqSk5MZMWIEX3/9Nf/8889175vN2e/UKpIfVu6PYeSn6/i/rd/QP3IFPhnWkP1LjVa836Evx8tWyvHZGU80oW2NsgVVqoiI5DOHQ83w4cNZs2YNM2fO5Mknn2TGjBmcOXOG2bNn89577+VHjSLZSruUzJFhb7Ju/WICU5MB2FaxLhMj+hNZsfZNnz+fnJrfJYqISAFyONQsX76c+fPn07FjR5566inat29P9erVqVy5MgsXLqR37975UafI/2RksH/8VMpNmciQxPMAHCpXhUkR/VhTtZltefbNBPv73PwmERFxGg6Hmvj4eNsp3QEBAbYl3O3atWPgwIF5W53I1QwDvv+epFdGUC/6OAB/BZRjSvs+LK3TEctVy7NvxASEBlo31RMREdfhcKipWrUq0dHRVKpUidtvv52vv/6aFi1asHz5ckqVKpUPJYoA69bBiBGwbRslgXjfAKa3fpQFjbuT5uF508czZfbhjOlRR5ODRURcjMOh5qmnnmLv3r1EREQwcuRIevTowfTp00lPT2fKlCn5UaMUZ3v3wqhR8PPPAJh9SzCjUQ8+bfkgl7z9HG4uVOc4iYi4LJNhGMatNHDy5EkiIyOpXr06DRo0uPkDhSgxMZHAwEASEhK09Lyoi46G0aNh4ULrsJOHBzz3HCsf+Bf/t/qsQ00F+XnyQKPb6FwnVOc4iYg4IXt/ft/SPjUAVapU0RlQknfOnYN33oGZMyE93Xrt0Uet16pXJ/DEP8DNQ02Ajwe9mlZUkBERKUbs3hN+y5YtrFixIsu1+fPnEx4eTnBwMM899xypqVoiK7mUlARvvQXVqsFHH1kDTefOsHMnLF4M1asD0LRyaYL8vG7YVJCfJzvf6MKbPerSuloZBRoRkWLC7p6at956i44dO3LvvfcC8Mcff/DMM8/Qv39/ateuzfvvv0+FChUYO3ZsftUqrigtDT75BN5+G+LiADCaNuXQ4Nc41qAlwf4+NM2wsOvPC6w6GMvSPWeJT07LtqnM6KIznEREiie7Q82ePXt4++23ba8XL15My5Yt+fTTTwEICwtjzJgxCjViF3OGmRPT/8NtH7yL319/AnClcjg/PjqICSXq8c/BDDi4BwA3E1jsmPmlScAiIsWb3aHmwoULhISE2F6vW7eOu+++2/a6efPmnD59Om+rE9djGOz8ZDH+b42m1lnrXjPn/ErxUdsnWNTgLjJMHnAlI8sj9gSaID9P1r3aST00IiLFmN0/AUJCQoiOjgYgLS2NyMhIWrVqZXv/0qVLeHrav1+IFEM7dvBP6w40+78nqHX2OJe8fJncvg8Rz33KF427k+Ge+3nr8cnp7PrzQh4WKyIizsbunyLdu3dn5MiRTJw4kaVLl1KiRAnat29ve3/fvn1Uq1YtX4oU52Y+fISLLw2nzMofKAOkunvwReN7mNH6ES6UCMyzz4m7lJJnbYmIiPOxO9S8/fbbPPjgg0RERFCyZEnmzZuHl9f/VqF8/vnn3HXXXflSpDgXs8Vge3Q8CVF/ctu/36f2z19TxmLBgonv63ViSrs+nAkMzvPP1VlOIiLFm92hpmzZsqxfv56EhARKliyJu3vWc3a++eYbSpYsmecFinNZuT+GD77eTs9VC3l65w/4ZliX+a+u1pz3I/pxpFyVPP9MneUkIiKQi833AgOzHy4ICtIPlOIms0cm7lIKwf4+JMQnsmvEO3y95RtKp1wCYFeF23mvY392hNXLlxp0lpOIiGS65R2FpXhauT+GccsPEpOQgpvFzIMH1jBs40K6JZ4D4GiZSrwf0ZdV1VuCKf/ChpZxi4hIJoUacdjK/TEMXBCJYRh0Pr6dV9fPo9b5UwCc9S/Lh+16s6TeHVjc3G/Skn2u3adGZzmJiEh2FGrEIWaLwbjlB2n61wFGrJ1H8zMHAbjoU5IZrR5hfpN7SPX0drjdGwWXppVLs+vPC7ZhLgUZERHJjkKNOOSPXzbx1uev0eX4dgCueHgzp1kPZrV8mEQfxyaKB/l58ua9dQkN8LlpcGldrUye/jlERMT1KNSIfU6dgtGjaTh/PibDIMPkxtcN7mJq28eJ83cscFx9RtPVc2EUXERE5FYo1MiN/fMPvPsuzJgBqamYgJ9qtmFyh75ElamYqyY1uVdERPKDQo1kLzkZpk6FSZMgMdF6rWNHzBPe4+01ScQm5Lx777XzY0IDvHm8RSWqlPXTnBgREck3CjWSVXo6/Oc/MG4cxMZarzVsiPndCWyv2Zy4pFQea36ZqauPYgKuPmsyM6ZMf7wxpf28NbFXREQKlEKNWBkGfPMNvPEGHDtmvRYeDu+8w8p6EYz78TAx67fZbi9Vwnp46cXL6bZrGlYSEZHCpFAj8NtvMHIk7NwJQGrpMpx98RUqjXqJVcfjrXvSXPNIwuV0DOClzjU0rCQiIkWCQk1xtnu3Ncz8+isAyV6+fNL8AT5r3pPk1BKETtlASoblukAD1mEnE7B4x2k2jrhDYUZERAqdQk1xdOKEdZhp8WIALB6ezG/YjWmtH+Ufv1K222ITU2/YjAHEJKSwPTpey7FFRKTQKdQUJ3//DW+/DbNnQ0YGmExYHn+CXhW6sss99weSxl3KeSWUiIhIQXEr7AKkACQmwujRUK2adb+ZjAzo1g0iI9n21r9vKdAABPv75FGhIiIiuaeeGleWmgqzZsE778D589ZrLVrAe+9Bp04AxO05k+vmTVhXPLUIv7VQJCIikhecrqdmxowZVKlSBR8fH1q2bMn27dsLu6Six2yGL76A22+HoUOtgaZmTfj2W9i61RZoIPe9LJnTgsf0qKNJwiIiUiQ4Vaj56quvGDZsGGPGjCEyMpKGDRvStWtX4uLiCru0osEw4KefoEkT6NsXTp6E8uXhk0/gwAF46CEwZQ0gLcKDKB/oQ06xxIR1T5rQgKzhJzTQh5l9mmhPGhERKTJMhmFkt2K3SGrZsiXNmzdn+vTpAFgsFsLCwnjxxRcZOXLkTZ9PTEwkMDCQhIQEAgIC8rvcgrV1K4wYAevXW18HBlqXaw8eDCVK2G4zWwy2R8dn2e131cFYBi6IBLLfIXhmnyZ0qRN63XPqoRERkYJg789vp5lTk5aWxq5duxg1apTtmpubG507d2bLli3ZPpOamkpq6v+WJSdmnmHkSg4fhtdeg++/t7729rYGmZEjISjrXJeV+2MYt/wgMVed21T+v7sAz+zT5Lr3rt0hWMu2RUSkKHOaUHP+/HnMZjMhISFZroeEhHD48OFsn5kwYQLjxo0riPIK3l9/wdixMGcOWCzg5gb9+1uvhYVdd/vK/THZ7gwcm5DCwAWRzOzThI0j7lBvjIiIOC2nmlPjqFGjRpGQkGD7dfr06cIu6dZduGAdZqpRw3rwpMUC998Pf/xhfZ1NoDFbDMYtP5jjzsAA45YfBKy9Mfc3uo3W1coo0IiIiFNxmp6asmXL4u7uzt9//53l+t9//01oaGi2z3h7e+Pt7V0Q5eW/K1fgo4+sy7EvXrRea9/e+rpNmxs+uj06Psuw0rW0M7CIiLgCp+mp8fLyomnTpvz222+2axaLhd9++43WrVsXYmX5LCMDPvvM2jMzcqQ10NSrBytWwLp1Nw00YP+Ov9oZWEREnJnT9NQADBs2jH79+tGsWTNatGjB1KlTSU5O5qmnnirs0vKeYcDSpdZJwJlzhipVsh5z0Ls3uLvb3ZS9e9FoZ2AREXFmThVqHn30Uc6dO8fo0aOJjY2lUaNGrFy58rrJw05v3Tprr8zWrdbXZcrA66/DwIHg43jwyNyLJjYhJdt5NdoZWEREXIFT7VNzq4r8PjV798KoUfDzz9bXJUrAsGHwyivWfWduQebqJ8h5LxptpCciIkWRvT+/nWZOjUuLjoYnn4TGja2BxsPD2itz4oR1uOkWAw1At3rlmdmnCaGB2hlYRERck1MNP7mcc+esh03OnAnp6dZrjz5qvVa9ep5/XLd65bUzsIiIuCyFmsKQlARTpsDkyXDpkvVa587W5dlNm+brR7u7mbRsW0REXJJCTUFKS7MeLvn225B5CGfTptYw07nzLTef3blO6oUREZHiQqGmIFgs8NVX8MYbEBVlvVa9unWYqVcv6xEHN2BPWLnRuU6aLyMiIsWBQk1+Mgz49Vfriqbdu63XQkJgzBj417/A0/OmTdgTVuw510nBRkREXJ1WP+WXHTusQ0rdulkDjb+/ddjp+HHryiY7A83ABZHXHXGQGVZW7o+x+1wns6XYrNwXEZFiSj01ee3oUesw0zffWF97ecGgQdadgcuWtbuZm4UVE9aw4u/jqXOdREREUKjJOzExMG6c9ZwmsxlMJuveM2+9BZUrO9ycvYdQbjnxj13t6VwnERFxdQo1tyohASZNgg8/tJ6kDXDvvfDuu1C/fq6btT+E2DespHOdRETE1WlOTW6lpMAHH0DVqtYAc+UKtG4N69fD8uW3FGjA/hDSumpZygf6kNPCbRPWicU610lERFydQo2jzGaYOxdq1rSeyRQfD3XqWE/U3rQJ2rfPk4/JPITyZmGlVbUyjOlRx3bt2nsAxvSoo/1qRETE5SnU2Msw4IcfoGFDeOopOH0aKlaEzz+Hffvg/vut82jyiLubye6wonOdREREdEq3fTZtghEjrP8XoHRp62qmQYPA19euJnK7268jm+ppR2EREXFF9v78Vqi5kf37reFl+XLra19fGDLEGnBKlbL7c291t1+FFRERKc4UarJhd6g5dcq66++8edZhJ3d3eOYZ67UKFRz6zJx2+82MJBoeEhERuTF7f35rTs3VkpPh5Zetk4DnzrUGmoceggMHYPZshwONdvsVEREpOAo1V/Pysg41paZCx46wdSt8+y3UqpWr5uzdQG97dHzu6hUREREbbb53NU9PmDHDumy7a9dbXs1k7wZ62u1XRETk1inUXKtLlzxryt4N9LTbr4iIyK3T8FM+sncDPe32KyIicusUavKRIxvoiYiIyK1RqMln2u1XRESkYGhOTQHoVq88XeqEagM9ERGRfKRQU0Dc3Uy0rlamsMsQERFxWRp+EhEREZegUCMiIiIuQaFGREREXIJCjYiIiLgEhRoRERFxCQo1IiIi4hIUakRERMQlKNSIiIiIS1CoEREREZegUCMiIiIuQaFGREREXIJCjYiIiLgEhRoRERFxCQo1IiIi4hIUakRERMQlKNSIiIiIS1CoEREREZegUCMiIiIuwSlCzcmTJ3nmmWcIDw/H19eXatWqMWbMGNLS0gq7NBERESkiPAq7AHscPnwYi8XC7NmzqV69Ovv37+fZZ58lOTmZyZMnF3Z5IiIiUgSYDMMwCruI3Hj//feZOXMmUVFRdj+TmJhIYGAgCQkJBAQE5GN1IiIiklfs/fntFD012UlISCAoKOiG96SmppKammp7nZiYmN9liYiISCFxijk11zp+/DjTpk1jwIABN7xvwoQJBAYG2n6FhYUVUIUiIiJS0Ao11IwcORKTyXTDX4cPH87yzJkzZ+jWrRu9evXi2WefvWH7o0aNIiEhwfbr9OnT+fnHERERkUJUqHNqzp07xz///HPDe6pWrYqXlxcAZ8+epWPHjrRq1Yq5c+fi5uZYJtOcGhEREefjFHNqypUrR7ly5ey698yZM3Tq1ImmTZsyZ84chwONiIiIuDanmCh85swZOnbsSOXKlZk8eTLnzp2zvRcaGlqIlYmIiEhR4RShZtWqVRw/fpzjx49TsWLFLO856Yp0ERERyWNOMYbTv39/DMPI9peIiIgIOEmoEREREbkZhRoRERFxCQo1IiIi4hIUakRERMQlKNSIiIiIS1CoEREREZegUCMiIiIuQaFGREREXIJCjYiIiLgEhRoRERFxCQo1IiIi4hIUakRERMQlKNSIiIiIS1CoEREREZegUCMiIiIuQaFGREREXIJCjYiIiLgEhRoRERFxCQo1IiIi4hI8CruAosRsMdgeHU/cpRSC/X1oER6Eu5upsMsSEREROyjU/NfK/TGMW36QmIQU27XygT6M6VGHbvXKF2JlIiIiYg8NP2ENNAMXRGYJNACxCSkMXBDJyv0xhVSZiIiI2KvYhxqzxWDc8oMY2byXeW3c8oOYLdndISIiIkVFsQ8126Pjr+uhuZoBxCSksD06vuCKEhEREYcV+1ATdynnQJOb+0RERKRwFPtQE+zvk6f3iYiISOEo9qGmRXgQ5QN9yGnhtgnrKqgW4UEFWZaIiIg4qNiHGnc3E2N61AG4Lthkvh7To472qxERESniin2oAehWrzwz+zQhNDDrEFNooA8z+zTRPjUiIiJOQJvv/Ve3euXpUidUOwqLiIg4KYWaq7i7mWhdrUxhlyEiIiK5oOEnERERcQkKNSIiIuISFGpERETEJSjUiIiIiEtQqBERERGXoFAjIiIiLkGhRkRERFyCQo2IiIi4BIUaERERcQnFakdhwzAASExMLORKRERExF6ZP7czf47npFiFmkuXLgEQFhZWyJWIiIiIoy5dukRgYGCO75uMm8UeF2KxWDh79iz+/v6YTMXroMrExETCwsI4ffo0AQEBhV2Oy9P3XfD0nRcsfd8Frzh/54ZhcOnSJSpUqICbW84zZ4pVT42bmxsVK1Ys7DIKVUBAQLH7H0Nh0vdd8PSdFyx93wWvuH7nN+qhyaSJwiIiIuISFGpERETEJSjUFBPe3t6MGTMGb2/vwi6lWND3XfD0nRcsfd8FT9/5zRWricIiIiLiutRTIyIiIi5BoUZERERcgkKNiIiIuASFGhEREXEJCjXFzMmTJ3nmmWcIDw/H19eXatWqMWbMGNLS0gq7NJc1fvx42rRpQ4kSJShVqlRhl+OSZsyYQZUqVfDx8aFly5Zs3769sEtyWevXr6dHjx5UqFABk8nE0qVLC7sklzZhwgSaN2+Ov78/wcHB9OzZkyNHjhR2WUWWQk0xc/jwYSwWC7Nnz+bAgQN8+OGHzJo1i9dee62wS3NZaWlp9OrVi4EDBxZ2KS7pq6++YtiwYYwZM4bIyEgaNmxI165diYuLK+zSXFJycjINGzZkxowZhV1KsbBu3ToGDRrE1q1bWbVqFenp6dx1110kJycXdmlFkpZ0C++//z4zZ84kKiqqsEtxaXPnzmXo0KFcvHixsEtxKS1btqR58+ZMnz4dsJ7xFhYWxosvvsjIkSMLuTrXZjKZ+P777+nZs2dhl1JsnDt3juDgYNatW0eHDh0Ku5wiRz01QkJCAkFBQYVdhojD0tLS2LVrF507d7Zdc3Nzo3PnzmzZsqUQKxPJHwkJCQD6b3YOFGqKuePHjzNt2jQGDBhQ2KWIOOz8+fOYzWZCQkKyXA8JCSE2NraQqhLJHxaLhaFDh9K2bVvq1atX2OUUSQo1LmLkyJGYTKYb/jp8+HCWZ86cOUO3bt3o1asXzz77bCFV7pxy832LiNyKQYMGsX//fhYvXlzYpRRZHoVdgOSNl19+mf79+9/wnqpVq9p+f/bsWTp16kSbNm345JNP8rk61+Po9y35o2zZsri7u/P3339nuf73338TGhpaSFWJ5L0XXniBFStWsH79eipWrFjY5RRZCjUuoly5cpQrV86ue8+cOUOnTp1o2rQpc+bMwc1NHXaOcuT7lvzj5eVF06ZN+e2332yTVS0WC7/99hsvvPBC4RYnkgcMw+DFF1/k+++/Z+3atYSHhxd2SUWaQk0xc+bMGTp27EjlypWZPHky586ds72nf9nmj1OnThEfH8+pU6cwm83s2bMHgOrVq1OyZMnCLc4FDBs2jH79+tGsWTNatGjB1KlTSU5O5qmnnirs0lxSUlISx48ft72Ojo5mz549BAUFUalSpUKszDUNGjSIL7/8kmXLluHv72+bKxYYGIivr28hV1cEGVKszJkzxwCy/SX5o1+/ftl+32vWrCns0lzGtGnTjEqVKhleXl5GixYtjK1btxZ2SS5rzZo12f7/c79+/Qq7NJeU03+v58yZU9ilFUnap0ZERERcgiZTiIiIiEtQqBERERGXoFAjIiIiLkGhRkRERFyCQo2IiIi4BIUaERERcQkKNSIiIuISFGpERETEJSjUiLiItWvXYjKZuHjxYmGX4hCTycTSpUvzrL0qVaowderUPGuvsJw8eRKTyWQ7VsNZ/35FCpJCjYgTMJlMN/w1duzYwi7xpsaOHUujRo2uux4TE8Pdd99doLXEx8czdOhQKleujJeXFxUqVODpp5/m1KlTBVpHpv79+9sO5MwUFhZGTEwM9erVK5SaRJyRDrQUcQIxMTG233/11VeMHj2aI0eO2K6VLFmSnTt3FkZppKWl4eXllevnC/og1fj4eFq1aoWXlxezZs2ibt26nDx5kjfeeIPmzZuzZcsWqlatWqA1Zcfd3V2HzIo4SD01Ik4gNDTU9iswMBCTyZTl2tWnfe/atYtmzZpRokQJ2rRpkyX8ACxbtowmTZrg4+ND1apVGTduHBkZGbb3T506xf3330/JkiUJCAjgkUce4e+//7a9n9nj8tlnnxEeHo6Pjw8AFy9e5F//+hflypUjICCAO+64g7179wIwd+5cxo0bx969e229S3PnzgWuH37666+/ePzxxwkKCsLPz49mzZqxbds2AE6cOMH9999PSEgIJUuWpHnz5qxevdqh7/L111/n7NmzrF69mrvvvptKlSrRoUMHfvnlFzw9PRk0aJDt3uyGsho1apSlZ2zKlCnUr18fPz8/wsLCeP7550lKSrK9P3fuXEqVKsUvv/xC7dq1KVmyJN26dbMF1bFjxzJv3jyWLVtm+27Wrl173fBTdjZu3Ej79u3x9fUlLCyMwYMHk5ycbHv/448/pkaNGvj4+BASEsLDDz/s0Hcl4mwUakRczOuvv84HH3zAzp078fDw4Omnn7a9t2HDBvr27cuQIUM4ePAgs2fPZu7cuYwfPx4Ai8XC/fffT3x8POvWrWPVqlVERUXx6KOPZvmM48ePs2TJEr777jvbD91evXoRFxfHzz//zK5du2jSpAl33nkn8fHxPProo7z88svUrVuXmJgYYmJirmsTICkpiYiICM6cOcMPP/zA3r17GT58OBaLxfZ+9+7d+e2339i9ezfdunWjR48edg8bWSwWFi9eTO/eva/rBfH19eX555/nl19+IT4+3u7v283NjY8++ogDBw4wb948fv/9d4YPH57lnsuXLzN58mS++OIL1q9fz6lTp3jllVcAeOWVV3jkkUdsQScmJoY2bdrc9HNPnDhBt27deOihh9i3bx9fffUVGzdu5IUXXgBg586dDB48mLfeeosjR46wcuVKOnToYPefS8QpFfYx4SLimDlz5hiBgYHXXV+zZo0BGKtXr7Zd+/HHHw3AuHLlimEYhnHnnXca7777bpbnvvjiC6N8+fKGYRjGr7/+ari7uxunTp2yvX/gwAEDMLZv324YhmGMGTPG8PT0NOLi4mz3bNiwwQgICDBSUlKytF2tWjVj9uzZtucaNmx4Xd2A8f333xuGYRizZ882/P39jX/++cfOb8Mw6tata0ybNs32unLlysaHH36Y7b2xsbEGkOP73333nQEY27Zty7Gthg0bGmPGjMmxnm+++cYoU6aM7fWcOXMMwDh+/Ljt2owZM4yQkBDb6379+hn3339/lnaio6MNwNi9e7dhGP/7+71w4YJhGIbxzDPPGM8991yWZzZs2GC4ubkZV65cMZYsWWIEBAQYiYmJOdYq4mo0p0bExTRo0MD2+/LlywMQFxdHpUqV2Lt3L5s2bbL1zACYzWZSUlK4fPkyhw4dIiwsjLCwMNv7derUoVSpUhw6dIjmzZsDULlyZcqVK2e7Z+/evSQlJVGmTJkstVy5coUTJ07YXfuePXto3LgxQUFB2b6flJTE2LFj+fHHH4mJiSEjI4MrV644PMHXMIwbvu/IHKHVq1czYcIEDh8+TGJiIhkZGbbvs0SJEgCUKFGCatWq2Z4pX748cXFxDtV8rb1797Jv3z4WLlxou2YYBhaLhejoaLp06ULlypWpWrUq3bp1o1u3bjzwwAO2mkRckUKNiIvx9PS0/d5kMgFkGb4ZN24cDz744HXPZc6NsYefn1+W10lJSZQvX561a9ded2+pUqXsbtfX1/eG77/yyiusWrWKyZMnU716dXx9fXn44YdJS0uzq/1y5crZAlp2Dh06hIeHB+Hh4YB1aOnaAJSenm77/cmTJ7n33nsZOHAg48ePJygoiI0bN/LMM8+QlpZmCxBX/52A9e/lZsHqZpKSkhgwYACDBw++7r1KlSrh5eVFZGQka9eu5ddff2X06NGMHTuWHTt2OPR3IuJMFGpEipEmTZpw5MgRqlevnu37tWvX5vTp05w+fdrWW3Pw4EEuXrxInTp1bthubGwsHh4eVKlSJdt7vLy8MJvNN6yvQYMGfPbZZ8THx2fbW7Np0yb69+/PAw88AFh/sJ88efKGbV7Nzc2NRx55hIULF/LWW29lmVdz5coVPv74Yx544AECAwMBawi6euVZYmIi0dHRtte7du3CYrHwwQcf4OZmnaL49ddf211PJnu+m2s1adKEgwcP5vh3CeDh4UHnzp3p3LkzY8aMoVSpUvz+++/ZhloRV6CJwiLFyOjRo5k/fz7jxo3jwIEDHDp0iMWLF/PGG28A0LlzZ+rXr0/v3r2JjIxk+/bt9O3bl4iICJo1a5Zju507d6Z169b07NmTX3/9lZMnT7J582Zef/1121LzKlWqEB0dzZ49ezh//jypqanXtfP4448TGhpKz5492bRpE1FRUSxZsoQtW7YAUKNGDdvk5L179/LEE0/YeqHsNX78eEJDQ+nSpQs///wzp0+fZv369XTt2hU3Nzf+/e9/2+694447+OKLL9iwYQN//PEH/fr1w93d3fZ+9erVSU9PZ9q0aURFRfHFF18wa9Ysh+rJ/G727dvHkSNHOH/+fJbeoJyMGDGCzZs388ILL7Bnzx6OHTvGsmXLbBOFV6xYwUcffcSePXv4888/mT9/PhaLhVq1ajlcn4izUKgRKUa6du3KihUr+PXXX2nevDmtWrXiww8/pHLlyoB1WGTZsmWULl2aDh060LlzZ6pWrcpXX311w3ZNJhM//fQTHTp04KmnnqJmzZo89thj/Pnnn4SEhADw0EMP0a1bNzp16kS5cuVYtGjRde14eXnx66+/EhwcTPfu3alfvz7vvfeeLUhMmTKF0qVL06ZNG3r06EHXrl1p0qSJQ99B2bJl2bp1K506dWLAgAGEh4cTERGB2Wxmz549tnlIAKNGjSIiIoJ7772Xe+65h549e2aZG9OwYUOmTJnCxIkTqVevHgsXLmTChAkO1QPw7LPPUqtWLZo1a0a5cuXYtGnTTZ9p0KAB69at4+jRo7Rv357GjRszevRoKlSoAFiH/b777jvuuOMOateuzaxZs1i0aBF169Z1uD4RZ2EybnVgV0TEyf3nP//h+eef56uvvrpuZ18RcR7qqRGRYu+ZZ55h8eLFHDp0iCtXrhR2OSKSS+qpEREREZegnhoRERFxCQo1IiIi4hIUakRERMQlKNSIiIiIS1CoEREREZegUCMiIiIuQaFGREREXIJCjYiIiLgEhRoRERFxCf8PJ1qNYYTRM2IAAAAASUVORK5CYII=",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"from statsmodels.graphics.gofplots import qqplot\n",
|
||
"from matplotlib import pyplot\n",
|
||
"qqplot(df[\"X\"], line='s')\n",
|
||
"qqplot(df[\"Y\"], line='s')\n",
|
||
"qqplot(df[\"Z\"], line='s')\n",
|
||
"qqplot(df[\"D\"], line='s')\n",
|
||
"pyplot.show"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 16,
|
||
"id": "0edc209a-7eff-4b7f-8b72-7388dd8e9a68",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"\n",
|
||
"# Параметры равномерного распределения\n",
|
||
"a = 0 # Нижний предел интервала\n",
|
||
"b = 10 # Верхний предел интервала\n",
|
||
"\n",
|
||
"# Генерируем 1000 случайных чисел из равномерного распределения\n",
|
||
"data = np.random.uniform(a, b, 1000)\n",
|
||
"\n",
|
||
"# Построение гистограммы\n",
|
||
"plt.hist(data, bins=30, density=True, color='skyblue', edgecolor='black')\n",
|
||
"\n",
|
||
"# Построение графика плотности вероятности\n",
|
||
"x = np.linspace(a, b, 1000)\n",
|
||
"plt.plot(x, np.ones_like(x) / (b - a), color='red', lw=2, label='PDF')\n",
|
||
"\n",
|
||
"plt.title('Continuous Uniform Distribution')\n",
|
||
"plt.xlabel('Value')\n",
|
||
"plt.ylabel('Density')\n",
|
||
"plt.legend()\n",
|
||
"plt.show()\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 17,
|
||
"id": "9e27516d-3e0c-4140-8a64-1ac251308050",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 640x480 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"\n",
|
||
"# Смоделируем данные с нормальным распределением\n",
|
||
"mean = 0 # Среднее значение\n",
|
||
"std_dev = 1 # Стандартное отклонение\n",
|
||
"data = np.random.normal(loc=mean, scale=std_dev, size=1000)\n",
|
||
"\n",
|
||
"# Построим гистограмму\n",
|
||
"plt.hist(data, bins=30, color='skyblue', edgecolor='black')\n",
|
||
"plt.title('Histogram of Normal Data')\n",
|
||
"plt.xlabel('Value')\n",
|
||
"plt.ylabel('Frequency')\n",
|
||
"plt.show()\n",
|
||
"\n",
|
||
"\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "65f4eeea-c2fd-49dd-892e-cdeb0692c898",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "ca2d8c11-a9ad-490c-b9d8-891eac98e625",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 45,
|
||
"id": "428a63c3-b1ab-49a5-aafd-4d0a7ded8f59",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Критерий Уилкоксона:\n",
|
||
"Статистика: 15.0\n",
|
||
"p-значение: 1.7998606112922388e-34\n",
|
||
"Отвергаем гипотезу о равенстве медиан\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import wilcoxon\n",
|
||
"\n",
|
||
"X = df[\"X\"]\n",
|
||
"Y = df[\"Y\"]\n",
|
||
"# Проверка однородности массивов X и Y с помощью критерия Уилкоксона\n",
|
||
"statistic, p_value = wilcoxon(X, Y)\n",
|
||
"\n",
|
||
"print(\"Критерий Уилкоксона:\")\n",
|
||
"print(\"Статистика:\", statistic)\n",
|
||
"print(\"p-значение:\", p_value)\n",
|
||
"if p_value < 0.05:\n",
|
||
" print(\"Отвергаем гипотезу о равенстве медиан\")\n",
|
||
"else:\n",
|
||
" print(\"Не можем отвергнуть гипотезу о равенстве медиан\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 46,
|
||
"id": "0045955c-ba0e-4d97-93a0-9d1ee2a2427c",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Критерий Манна-Уитни:\n",
|
||
"Статистика: 39604.0\n",
|
||
"p-значение: 1.4768098049370635e-64\n",
|
||
"Отвергаем гипотезу о равенстве распределений\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import mannwhitneyu\n",
|
||
"\n",
|
||
"# Проверка однородности массивов X и Y с помощью критерия Манна-Уитни\n",
|
||
"statistic, p_value = mannwhitneyu(X, Y)\n",
|
||
"\n",
|
||
"print(\"Критерий Манна-Уитни:\")\n",
|
||
"print(\"Статистика:\", statistic)\n",
|
||
"print(\"p-значение:\", p_value)\n",
|
||
"if p_value < 0.05:\n",
|
||
" print(\"Отвергаем гипотезу о равенстве распределений\")\n",
|
||
"else:\n",
|
||
" print(\"Не можем отвергнуть гипотезу о равенстве распределений\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 47,
|
||
"id": "d7b1e5f2-5a84-4e29-808a-ade7baf3e498",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Критерий Уилкоксона:\n",
|
||
"Статистика: 16.95637977171405\n",
|
||
"p-значение: 1.7266008845117972e-64\n",
|
||
"Отвергаем гипотезу о равенстве распределений\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from scipy.stats import ranksums\n",
|
||
"\n",
|
||
"# Проверка однородности массивов X и Y с помощью критерия Уилкоксона\n",
|
||
"statistic, p_value = ranksums(X, Y)\n",
|
||
"\n",
|
||
"print(\"Критерий Уилкоксона:\")\n",
|
||
"print(\"Статистика:\", statistic)\n",
|
||
"print(\"p-значение:\", p_value)\n",
|
||
"if p_value < 0.05:\n",
|
||
" print(\"Отвергаем гипотезу о равенстве распределений\")\n",
|
||
"else:\n",
|
||
" print(\"Не можем отвергнуть гипотезу о равенстве распределений\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "d5777af6-31d9-4f90-a955-e0c14f85eb7b",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Python 3",
|
||
"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": "3.9.13"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|