case01-instacart_pac_kmeans.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e8a62fa2",
   "metadata": {},
   "source": [
    "案例：探究用户对物品类别的喜好细分\n",
    "\n",
    "\n",
    "  1.   用户  物品类别 \n",
    "\n",
    "  2.  user_id  aisle \n",
    "    \n",
    "    \n",
    "    \n",
    "\n",
    "* 需要将user_id和aisle放在同一个表中 - 合并\n",
    "* 找到user_id和aisle - 交叉表和透视表\n",
    "* 特征冗余过多 -> PCA降维"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "91dd01e4",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as  pd\n",
    "# 1.获取数据\n",
    "order_products = pd.read_csv(\"../../resource/instacart/order_products__prior.csv\")\n",
    "products = pd.read_csv(\"../../resource/instacart/products.csv\")\n",
    "orders = pd.read_csv(\"../../resource/instacart/orders.csv\")\n",
    "aisles = pd.read_csv(\"../../resource/instacart/aisles.csv\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7e79e753",
   "metadata": {},
   "outputs": [],
   "source": [
    "#2.处理数据\n",
    "#  1）合并表\n",
    "tab1 = pd.merge(aisles, products, on=[\"aisle_id\", \"aisle_id\"])\n",
    "tab2 = pd.merge(tab1, order_products, on=[\"product_id\", \"product_id\"])\n",
    "tab3 = pd.merge(tab2, orders, on=[\"order_id\", \"order_id\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "16d77bfa",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 2）.找到user和aisle 之间的关系 列user_id 行aisle\n",
    "table = pd.crosstab(tab3[\"user_id\"], tab3[\"aisle\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8ea3921c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "aisle    air fresheners candles  asian foods  baby accessories  \\\nuser_id                                                          \n1                             0            0                 0   \n2                             0            3                 0   \n3                             0            0                 0   \n4                             0            0                 0   \n5                             0            2                 0   \n\naisle    baby bath body care  baby food formula  bakery desserts  \\\nuser_id                                                            \n1                          0                  0                0   \n2                          0                  0                0   \n3                          0                  0                0   \n4                          0                  0                0   \n5                          0                  0                0   \n\naisle    baking ingredients  baking supplies decor  beauty  beers coolers  \\\nuser_id                                                                     \n1                         0                      0       0              0   \n2                         2                      0       0              0   \n3                         0                      0       0              0   \n4                         0                      0       0              0   \n5                         0                      0       0              0   \n\naisle    ...  spreads  tea  tofu meat alternatives  tortillas flat bread  \\\nuser_id  ...                                                               \n1        ...        1    0                       0                     0   \n2        ...        3    1                       1                     0   \n3        ...        4    1                       0                     0   \n4        ...        0    0                       0                     1   \n5        ...        0    0                       0                     0   \n\naisle    trail mix snack mix  trash bags liners  vitamins supplements  \\\nuser_id                                                                 \n1                          0                  0                     0   \n2                          0                  0                     0   \n3                          0                  0                     0   \n4                          0                  0                     0   \n5                          0                  0                     0   \n\naisle    water seltzer sparkling water  white wines  yogurt  \nuser_id                                                      \n1                                    0            0       1  \n2                                    2            0      42  \n3                                    2            0       0  \n4                                    1            0       0  \n5                                    0            0       3  \n\n[5 rows x 134 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th>aisle</th>\n      <th>air fresheners candles</th>\n      <th>asian foods</th>\n      <th>baby accessories</th>\n      <th>baby bath body care</th>\n      <th>baby food formula</th>\n      <th>bakery desserts</th>\n      <th>baking ingredients</th>\n      <th>baking supplies decor</th>\n      <th>beauty</th>\n      <th>beers coolers</th>\n      <th>...</th>\n      <th>spreads</th>\n      <th>tea</th>\n      <th>tofu meat alternatives</th>\n      <th>tortillas flat bread</th>\n      <th>trail mix snack mix</th>\n      <th>trash bags liners</th>\n      <th>vitamins supplements</th>\n      <th>water seltzer sparkling water</th>\n      <th>white wines</th>\n      <th>yogurt</th>\n    </tr>\n    <tr>\n      <th>user_id</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>1</th>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>0</td>\n      <td>3</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>3</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n      <td>42</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>4</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>3</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 134 columns</p>\n</div>"
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "table.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "b3592a87",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.decomposition import PCA\n",
    "# 3).PAC降维处理\n",
    "# 3.1)实例化一个转换器 n_components=0.95降维保留95%的数据，n_components=2 降为2维\n",
    "transform = PCA(n_components=0.95)\n",
    "# 3.2)调用fit_transform\n",
    "data_new = transform.fit_transform(table)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "86f08f17",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_new = data_new[:1000000]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "511695cd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 预估器流程\n",
    "from sklearn.cluster import KMeans\n",
    "estimator = KMeans(n_clusters=3)\n",
    "estimator.fit(data_new)\n",
    "y_predict = estimator.predict(data_new)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "2a6569fd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": "array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n       0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0,\n       0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,\n       0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,\n       1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0])"
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_predict[:100]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "71e5ce74",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 模型评估-轮廓系数 [-1,1] -1效果最不好  1效果最好\n",
    "from sklearn.metrics import silhouette_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "4366a569",
   "metadata": {},
   "outputs": [],
   "source": [
    "score = silhouette_score(data_new,y_predict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "371dce4f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5374100487431882\n"
     ]
    }
   ],
   "source": [
    "print(score)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "name": "torch1.7.1",
   "language": "python",
   "display_name": "Python 3[torch1.7,1]"
  },
  "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"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}