{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Импортируем библиотеки"
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import seaborn as sns\n",
"import random\n",
"import matplotlib.pyplot as plt\n",
"\n",
"from sklearn.model_selection import GridSearchCV, StratifiedKFold\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"from sklearn.svm import SVC\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.pipeline import Pipeline\n",
"from sklearn.datasets import make_classification"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Синтетические данные"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Создаём данные"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Т.к. в задании сказано мерить AUC, то речь должна идти о бинарной классификации. Т.к. мы хотим перебирать число признаков как параметр, то создаём данные, в которых 10 признаков, информативными являются только 4"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [],
"source": [
"X, y = make_classification(n_samples=2000, n_features=10, n_informative=4, n_classes=3, random_state=42)"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" x | \n",
" 0 | \n",
" 1 | \n",
" 2 | \n",
" 3 | \n",
" 4 | \n",
" 5 | \n",
" 6 | \n",
" 7 | \n",
" 8 | \n",
" y | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" -1.765310 | \n",
" -1.024146 | \n",
" -0.080752 | \n",
" -1.371603 | \n",
" -1.693012 | \n",
" 1.203602 | \n",
" 0.485726 | \n",
" -0.805957 | \n",
" -2.294698 | \n",
" -0.872444 | \n",
" 0.0 | \n",
"
\n",
" \n",
" | 1 | \n",
" -0.858258 | \n",
" 0.148367 | \n",
" -0.676983 | \n",
" -2.565923 | \n",
" -2.296268 | \n",
" -0.160094 | \n",
" 1.177521 | \n",
" -0.901972 | \n",
" -0.488819 | \n",
" -2.252863 | \n",
" 0.0 | \n",
"
\n",
" \n",
" | 2 | \n",
" -1.070693 | \n",
" -1.402868 | \n",
" -1.964698 | \n",
" -2.615374 | \n",
" -1.870387 | \n",
" -0.723574 | \n",
" -0.190782 | \n",
" -3.305596 | \n",
" 1.029794 | \n",
" -2.143583 | \n",
" 0.0 | \n",
"
\n",
" \n",
" | 3 | \n",
" 0.330069 | \n",
" 2.002894 | \n",
" -1.453344 | \n",
" 0.084383 | \n",
" 0.248392 | \n",
" -0.676807 | \n",
" -1.160034 | \n",
" 0.004808 | \n",
" 0.935594 | \n",
" -0.138064 | \n",
" 1.0 | \n",
"
\n",
" \n",
" | 4 | \n",
" 1.427064 | \n",
" 0.000755 | \n",
" 0.745855 | \n",
" 0.588909 | \n",
" 1.038847 | \n",
" -0.383004 | \n",
" -1.143316 | \n",
" -0.207470 | \n",
" 1.574944 | \n",
" 0.663299 | \n",
" 1.0 | \n",
"
\n",
" \n",
"
\n",
"