{ "cells": [ { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "from sklearn.decomposition import PCA\n", "from sklearn.cluster import KMeans\n", "from sklearn.metrics import silhouette_score" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "# 1.获取数据\n", "order_product = pd.read_csv(\"./data/instacart/order_products__prior.csv\")\n", "products = pd.read_csv(\"./data/instacart/products.csv\")\n", "orders = pd.read_csv(\"./data/instacart/orders.csv\")\n", "aisles = pd.read_csv(\"./data/instacart/aisles.csv\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 2.数据基本处理 数据集合并 交叉表\n", "\n", "# 3.特征工程 PCA\n", "\n", "# 4.机器学习 聚类\n", "\n", "# 5.模型评估 轮廓系数" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "# 2.数据基本处理 数据集合并 交叉表\n", "data = pd.merge(left=order_product, right=orders, on=['order_id'], how='inner')" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "data = pd.merge(left=data, right=products, on=['product_id'], how='inner')" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "data = pd.merge(left=data, right=aisles, on=['aisle_id'], how='inner')" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
order_idproduct_idadd_to_cart_orderreordereduser_ideval_setorder_numberorder_doworder_hour_of_daydays_since_prior_orderproduct_nameaisle_iddepartment_idaisle
023312011202279prior3598.0Organic Egg Whites8616eggs
1263312050153404prior20167.0Organic Egg Whites8616eggs
21203312013023750prior116810.0Organic Egg Whites8616eggs
3327331205158707prior21698.0Organic Egg Whites8616eggs
439033120281166654prior480129.0Organic Egg Whites8616eggs
\n", "
" ], "text/plain": [ " order_id product_id add_to_cart_order reordered user_id eval_set \\\n", "0 2 33120 1 1 202279 prior \n", "1 26 33120 5 0 153404 prior \n", "2 120 33120 13 0 23750 prior \n", "3 327 33120 5 1 58707 prior \n", "4 390 33120 28 1 166654 prior \n", "\n", " order_number order_dow order_hour_of_day days_since_prior_order \\\n", "0 3 5 9 8.0 \n", "1 2 0 16 7.0 \n", "2 11 6 8 10.0 \n", "3 21 6 9 8.0 \n", "4 48 0 12 9.0 \n", "\n", " product_name aisle_id department_id aisle \n", "0 Organic Egg Whites 86 16 eggs \n", "1 Organic Egg Whites 86 16 eggs \n", "2 Organic Egg Whites 86 16 eggs \n", "3 Organic Egg Whites 86 16 eggs \n", "4 Organic Egg Whites 86 16 eggs " ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data.head()" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "# 建立交叉表\n", "data = pd.crosstab(data['user_id'], data['aisle'])" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "# 3.特征工程 PCA\n", "transfer = PCA(n_components=0.9)\n", "data = transfer.fit_transform(data)" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "KMeans(algorithm='auto', copy_x=True, init='k-means++', max_iter=300,\n", " n_clusters=8, n_init=10, n_jobs=None, precompute_distances='auto',\n", " random_state=None, tol=0.0001, verbose=0)" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 4.机器学习 聚类\n", "x = data[:1000, :]\n", "# 4.1 创建模型\n", "estimator = KMeans(n_clusters=8)\n", "# 4.2 训练模型\n", "estimator.fit(x)" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.3313898637995612" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 5.模型评估 轮廓系数\n", "y_predict = estimator.predict(x)\n", "silhouette_score(x, y_predict) # 平均轮廓系数" ] }, { "cell_type": "code", "execution_count": null, "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": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }