Solving the eighth hometask

8th hometask/3th_task.ipynb

@@ -0,0 +1,190 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "a65a79c4",
+   "metadata": {},
+   "source": [
+    "#### *Задание 3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f3e1c980",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "427e6e7c",
+   "metadata": {},
+   "source": [
+    "Примените модель KMeans, построенную в предыдущем задании, к данным из тестового набора."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "dbdcad55",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.cluster import KMeans\n",
+    "import pickle"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "9bad59c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('models/kmeans.pkl', 'rb') as file_kmeans:\n",
+    "    kmeans = pickle.load(file = file_kmeans)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "59e842ce",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "sklearn.cluster._kmeans.KMeans"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(kmeans)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "d9d2c30d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_test_scaled = pd.read_pickle('data/x_test_scaled.pkl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a00946aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "labels_test = kmeans.predict(x_test_scaled)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "17828b71",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "2    63\n",
+       "1    41\n",
+       "0    23\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pd.value_counts(labels_test)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "00d51006",
+   "metadata": {},
+   "source": [
+    "Вычислите средние значения price и CRIM в разных кластерах на тестовых данных."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "7a9e1b0e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_test = pd.read_pickle('data/x_test.pkl')\n",
+    "y_test = pd.read_pickle('data/y_test.pkl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "6cacb8f0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Cluster #2:\tmean_price = 22.262,\tmean_CRIM = 0.275.\n",
+      "Cluster #1:\tmean_price = 16.034,\tmean_CRIM = 12.071.\n",
+      "Cluster #0:\tmean_price = 28.678,\tmean_CRIM = 0.068.\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i in list(pd.value_counts(labels_test).index):\n",
+    "    price = np.round(y_test.loc[labels_test == i, ['Price']].mean()[0], 3)\n",
+    "    crim = np.round(x_test.loc[labels_test == i, ['CRIM']].mean()[0], 3)\n",
+    "    print(f'Cluster #{i}:\\tmean_price = {price},\\tmean_CRIM = {crim}.')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6a3b82f0",
+   "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}