diff --git a/机器学习竞赛实战_优胜解决方案/京东用户购买意向预测/.ipynb_checkpoints/4-模型预测及评估-checkpoint.ipynb b/机器学习竞赛实战_优胜解决方案/京东用户购买意向预测/.ipynb_checkpoints/4-模型预测及评估-checkpoint.ipynb
new file mode 100644
index 0000000..4686da3
--- /dev/null
+++ b/机器学习竞赛实战_优胜解决方案/京东用户购买意向预测/.ipynb_checkpoints/4-模型预测及评估-checkpoint.ipynb
@@ -0,0 +1,1055 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import lightgbm as lgb  # 模型\n",
+    "import pandas as pd  # 数据处理包\n",
+    "import numpy as np  # 数据处理包\n",
+    "from sklearn import metrics  # 混淆矩阵\n",
+    "from sklearn.model_selection import StratifiedKFold, GridSearchCV, train_test_split  # 分层五折验证包、寻找最优参函数、切分数据\n",
+    "from sklearn.metrics import accuracy_score, roc_curve, auc, confusion_matrix  # 准确率、roc计算、auc计算、混淆矩阵\n",
+    "import matplotlib.pyplot as plt  # 图形处理包\n",
+    "import itertools  # 处理混淆矩阵\n",
+    "import gc  # 处理缓存，有兴趣的可以搜搜怎么使用\n",
+    "import warnings  # 忽略普通警告，不打印太多东西\n",
+    "warnings.filterwarnings('ignore')\n",
+    "plt.rcParams['font.sans-serif']=['SimHei']  # 让图形可以显示中文\n",
+    "plt.rcParams['axes.unicode_minus']=False"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "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></th>\n",
+       "      <th>user_id</th>\n",
+       "      <th>sku_id</th>\n",
+       "      <th>cate</th>\n",
+       "      <th>action_before_3_1.0_x</th>\n",
+       "      <th>action_before_3_2.0_x</th>\n",
+       "      <th>action_before_3_3.0_x</th>\n",
+       "      <th>action_before_3_4.0_x</th>\n",
+       "      <th>action_before_3_5.0_x</th>\n",
+       "      <th>action_before_3_6.0_x</th>\n",
+       "      <th>action_before_3_1.0_y</th>\n",
+       "      <th>...</th>\n",
+       "      <th>cate_action_5_mean</th>\n",
+       "      <th>cate_action_6_mean</th>\n",
+       "      <th>has_bad_comment</th>\n",
+       "      <th>bad_comment_rate</th>\n",
+       "      <th>comment_num_0</th>\n",
+       "      <th>comment_num_1</th>\n",
+       "      <th>comment_num_2</th>\n",
+       "      <th>comment_num_3</th>\n",
+       "      <th>comment_num_4</th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>202633.0</td>\n",
+       "      <td>12564.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0260</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>218498.0</td>\n",
+       "      <td>149854.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0403</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>221842.0</td>\n",
+       "      <td>75877.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>79.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0245</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>222886.0</td>\n",
+       "      <td>154636.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0208</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>235240.0</td>\n",
+       "      <td>38222.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>30.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>55.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0166</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 237 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    user_id    sku_id  cate  action_before_3_1.0_x  action_before_3_2.0_x  \\\n",
+       "0  202633.0   12564.0   8.0                    1.0                    0.0   \n",
+       "1  218498.0  149854.0   8.0                    4.0                    0.0   \n",
+       "2  221842.0   75877.0   8.0                    3.0                    0.0   \n",
+       "3  222886.0  154636.0   8.0                   20.0                    1.0   \n",
+       "4  235240.0   38222.0   8.0                   30.0                    1.0   \n",
+       "\n",
+       "   action_before_3_3.0_x  action_before_3_4.0_x  action_before_3_5.0_x  \\\n",
+       "0                    0.0                    0.0                    0.0   \n",
+       "1                    0.0                    0.0                    0.0   \n",
+       "2                    0.0                    0.0                    0.0   \n",
+       "3                    0.0                    0.0                    0.0   \n",
+       "4                    0.0                    0.0                    0.0   \n",
+       "\n",
+       "   action_before_3_6.0_x  action_before_3_1.0_y  ...  cate_action_5_mean  \\\n",
+       "0                    2.0                    1.0  ...           20.866667   \n",
+       "1                    4.0                    2.0  ...           20.866667   \n",
+       "2                    5.0                   79.0  ...           20.866667   \n",
+       "3                   26.0                   10.0  ...           20.866667   \n",
+       "4                   28.0                   55.0  ...           20.866667   \n",
+       "\n",
+       "   cate_action_6_mean  has_bad_comment  bad_comment_rate  comment_num_0  \\\n",
+       "0              5167.6              1.0            0.0260            0.0   \n",
+       "1              5167.6              1.0            0.0403            0.0   \n",
+       "2              5167.6              1.0            0.0245            0.0   \n",
+       "3              5167.6              1.0            0.0208            0.0   \n",
+       "4              5167.6              1.0            0.0166            0.0   \n",
+       "\n",
+       "   comment_num_1  comment_num_2  comment_num_3  comment_num_4  label  \n",
+       "0            0.0            0.0            0.0            1.0    1.0  \n",
+       "1            0.0            0.0            0.0            1.0    1.0  \n",
+       "2            0.0            0.0            0.0            1.0    1.0  \n",
+       "3            0.0            0.0            0.0            1.0    1.0  \n",
+       "4            0.0            0.0            0.0            1.0    1.0  \n",
+       "\n",
+       "[5 rows x 237 columns]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = pd.read_csv('data/train_set.csv')  # 读取训练数据\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "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></th>\n",
+       "      <th>user_id</th>\n",
+       "      <th>sku_id</th>\n",
+       "      <th>cate</th>\n",
+       "      <th>action_before_3_1.0_x</th>\n",
+       "      <th>action_before_3_2.0_x</th>\n",
+       "      <th>action_before_3_3.0_x</th>\n",
+       "      <th>action_before_3_4.0_x</th>\n",
+       "      <th>action_before_3_5.0_x</th>\n",
+       "      <th>action_before_3_6.0_x</th>\n",
+       "      <th>action_before_3_1.0_y</th>\n",
+       "      <th>...</th>\n",
+       "      <th>cate_action_4_mean</th>\n",
+       "      <th>cate_action_5_mean</th>\n",
+       "      <th>cate_action_6_mean</th>\n",
+       "      <th>has_bad_comment</th>\n",
+       "      <th>bad_comment_rate</th>\n",
+       "      <th>comment_num_0</th>\n",
+       "      <th>comment_num_1</th>\n",
+       "      <th>comment_num_2</th>\n",
+       "      <th>comment_num_3</th>\n",
+       "      <th>comment_num_4</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>202633.0</td>\n",
+       "      <td>12564.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.4</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0260</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>218498.0</td>\n",
+       "      <td>149854.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.4</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0403</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>221842.0</td>\n",
+       "      <td>75877.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>79.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.4</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0245</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>222886.0</td>\n",
+       "      <td>154636.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.4</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0208</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>235240.0</td>\n",
+       "      <td>38222.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>30.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>55.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.4</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0166</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 236 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    user_id    sku_id  cate  action_before_3_1.0_x  action_before_3_2.0_x  \\\n",
+       "0  202633.0   12564.0   8.0                    1.0                    0.0   \n",
+       "1  218498.0  149854.0   8.0                    4.0                    0.0   \n",
+       "2  221842.0   75877.0   8.0                    3.0                    0.0   \n",
+       "3  222886.0  154636.0   8.0                   20.0                    1.0   \n",
+       "4  235240.0   38222.0   8.0                   30.0                    1.0   \n",
+       "\n",
+       "   action_before_3_3.0_x  action_before_3_4.0_x  action_before_3_5.0_x  \\\n",
+       "0                    0.0                    0.0                    0.0   \n",
+       "1                    0.0                    0.0                    0.0   \n",
+       "2                    0.0                    0.0                    0.0   \n",
+       "3                    0.0                    0.0                    0.0   \n",
+       "4                    0.0                    0.0                    0.0   \n",
+       "\n",
+       "   action_before_3_6.0_x  action_before_3_1.0_y  ...  cate_action_4_mean  \\\n",
+       "0                    2.0                    1.0  ...                 8.4   \n",
+       "1                    4.0                    2.0  ...                 8.4   \n",
+       "2                    5.0                   79.0  ...                 8.4   \n",
+       "3                   26.0                   10.0  ...                 8.4   \n",
+       "4                   28.0                   55.0  ...                 8.4   \n",
+       "\n",
+       "   cate_action_5_mean  cate_action_6_mean  has_bad_comment  bad_comment_rate  \\\n",
+       "0           20.866667              5167.6              1.0            0.0260   \n",
+       "1           20.866667              5167.6              1.0            0.0403   \n",
+       "2           20.866667              5167.6              1.0            0.0245   \n",
+       "3           20.866667              5167.6              1.0            0.0208   \n",
+       "4           20.866667              5167.6              1.0            0.0166   \n",
+       "\n",
+       "   comment_num_0  comment_num_1  comment_num_2  comment_num_3  comment_num_4  \n",
+       "0            0.0            0.0            0.0            0.0            1.0  \n",
+       "1            0.0            0.0            0.0            0.0            1.0  \n",
+       "2            0.0            0.0            0.0            0.0            1.0  \n",
+       "3            0.0            0.0            0.0            0.0            1.0  \n",
+       "4            0.0            0.0            0.0            0.0            1.0  \n",
+       "\n",
+       "[5 rows x 236 columns]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_x = data.loc[:,data.columns != 'label']  # 将训练数据集分成特征和标签\n",
+    "train_y = data.loc[:,data.columns == 'label']\n",
+    "train_x.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "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></th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   label\n",
+       "0    1.0\n",
+       "1    1.0\n",
+       "2    1.0\n",
+       "3    1.0\n",
+       "4    1.0"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_y.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "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></th>\n",
+       "      <th>cate</th>\n",
+       "      <th>action_before_3_1.0_x</th>\n",
+       "      <th>action_before_3_2.0_x</th>\n",
+       "      <th>action_before_3_3.0_x</th>\n",
+       "      <th>action_before_3_4.0_x</th>\n",
+       "      <th>action_before_3_5.0_x</th>\n",
+       "      <th>action_before_3_6.0_x</th>\n",
+       "      <th>action_before_3_1.0_y</th>\n",
+       "      <th>action_before_3_2.0_y</th>\n",
+       "      <th>action_before_3_3.0_y</th>\n",
+       "      <th>...</th>\n",
+       "      <th>cate_action_4_mean</th>\n",
+       "      <th>cate_action_5_mean</th>\n",
+       "      <th>cate_action_6_mean</th>\n",
+       "      <th>has_bad_comment</th>\n",
+       "      <th>bad_comment_rate</th>\n",
+       "      <th>comment_num_0</th>\n",
+       "      <th>comment_num_1</th>\n",
+       "      <th>comment_num_2</th>\n",
+       "      <th>comment_num_3</th>\n",
+       "      <th>comment_num_4</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>8.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.4</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0260</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>8.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.4</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0403</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>8.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>79.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.4</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0245</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>8.0</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.4</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0208</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>8.0</td>\n",
+       "      <td>30.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>55.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>8.4</td>\n",
+       "      <td>20.866667</td>\n",
+       "      <td>5167.6</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0166</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 234 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   cate  action_before_3_1.0_x  action_before_3_2.0_x  action_before_3_3.0_x  \\\n",
+       "0   8.0                    1.0                    0.0                    0.0   \n",
+       "1   8.0                    4.0                    0.0                    0.0   \n",
+       "2   8.0                    3.0                    0.0                    0.0   \n",
+       "3   8.0                   20.0                    1.0                    0.0   \n",
+       "4   8.0                   30.0                    1.0                    0.0   \n",
+       "\n",
+       "   action_before_3_4.0_x  action_before_3_5.0_x  action_before_3_6.0_x  \\\n",
+       "0                    0.0                    0.0                    2.0   \n",
+       "1                    0.0                    0.0                    4.0   \n",
+       "2                    0.0                    0.0                    5.0   \n",
+       "3                    0.0                    0.0                   26.0   \n",
+       "4                    0.0                    0.0                   28.0   \n",
+       "\n",
+       "   action_before_3_1.0_y  action_before_3_2.0_y  action_before_3_3.0_y  ...  \\\n",
+       "0                    1.0                    0.0                    0.0  ...   \n",
+       "1                    2.0                    0.0                    0.0  ...   \n",
+       "2                   79.0                    0.0                    0.0  ...   \n",
+       "3                   10.0                    0.0                    0.0  ...   \n",
+       "4                   55.0                    0.0                    0.0  ...   \n",
+       "\n",
+       "   cate_action_4_mean  cate_action_5_mean  cate_action_6_mean  \\\n",
+       "0                 8.4           20.866667              5167.6   \n",
+       "1                 8.4           20.866667              5167.6   \n",
+       "2                 8.4           20.866667              5167.6   \n",
+       "3                 8.4           20.866667              5167.6   \n",
+       "4                 8.4           20.866667              5167.6   \n",
+       "\n",
+       "   has_bad_comment  bad_comment_rate  comment_num_0  comment_num_1  \\\n",
+       "0              1.0            0.0260            0.0            0.0   \n",
+       "1              1.0            0.0403            0.0            0.0   \n",
+       "2              1.0            0.0245            0.0            0.0   \n",
+       "3              1.0            0.0208            0.0            0.0   \n",
+       "4              1.0            0.0166            0.0            0.0   \n",
+       "\n",
+       "   comment_num_2  comment_num_3  comment_num_4  \n",
+       "0            0.0            0.0            1.0  \n",
+       "1            0.0            0.0            1.0  \n",
+       "2            0.0            0.0            1.0  \n",
+       "3            0.0            0.0            1.0  \n",
+       "4            0.0            0.0            1.0  \n",
+       "\n",
+       "[5 rows x 234 columns]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "del train_x['user_id']\n",
+    "del train_x['sku_id']\n",
+    "\n",
+    "train_x.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(14619, 234)"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_x.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "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></th>\n",
+       "      <th>user_id</th>\n",
+       "      <th>sku_id</th>\n",
+       "      <th>cate</th>\n",
+       "      <th>action_before_3_1.0_x</th>\n",
+       "      <th>action_before_3_2.0_x</th>\n",
+       "      <th>action_before_3_3.0_x</th>\n",
+       "      <th>action_before_3_4.0_x</th>\n",
+       "      <th>action_before_3_5.0_x</th>\n",
+       "      <th>action_before_3_6.0_x</th>\n",
+       "      <th>action_before_3_1.0_y</th>\n",
+       "      <th>...</th>\n",
+       "      <th>cate_action_4_mean</th>\n",
+       "      <th>cate_action_5_mean</th>\n",
+       "      <th>cate_action_6_mean</th>\n",
+       "      <th>has_bad_comment</th>\n",
+       "      <th>bad_comment_rate</th>\n",
+       "      <th>comment_num_0</th>\n",
+       "      <th>comment_num_1</th>\n",
+       "      <th>comment_num_2</th>\n",
+       "      <th>comment_num_3</th>\n",
+       "      <th>comment_num_4</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>200005.0</td>\n",
+       "      <td>67444.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>73.400000</td>\n",
+       "      <td>169.366667</td>\n",
+       "      <td>48251.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0821</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>200005.0</td>\n",
+       "      <td>72967.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>30.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>73.400000</td>\n",
+       "      <td>169.366667</td>\n",
+       "      <td>48251.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0196</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>200007.0</td>\n",
+       "      <td>26229.0</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>20.766667</td>\n",
+       "      <td>56.700000</td>\n",
+       "      <td>12937.7</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0198</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>200007.0</td>\n",
+       "      <td>63315.0</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>20.766667</td>\n",
+       "      <td>56.700000</td>\n",
+       "      <td>12937.7</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0476</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>200007.0</td>\n",
+       "      <td>126404.0</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>20.766667</td>\n",
+       "      <td>56.700000</td>\n",
+       "      <td>12937.7</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 236 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    user_id    sku_id  cate  action_before_3_1.0_x  action_before_3_2.0_x  \\\n",
+       "0  200005.0   67444.0   4.0                    2.0                    0.0   \n",
+       "1  200005.0   72967.0   4.0                   26.0                    1.0   \n",
+       "2  200007.0   26229.0   9.0                    2.0                    0.0   \n",
+       "3  200007.0   63315.0   9.0                    4.0                    0.0   \n",
+       "4  200007.0  126404.0   9.0                    4.0                    0.0   \n",
+       "\n",
+       "   action_before_3_3.0_x  action_before_3_4.0_x  action_before_3_5.0_x  \\\n",
+       "0                    0.0                    0.0                    0.0   \n",
+       "1                    0.0                    1.0                    0.0   \n",
+       "2                    0.0                    0.0                    0.0   \n",
+       "3                    0.0                    0.0                    0.0   \n",
+       "4                    0.0                    0.0                    0.0   \n",
+       "\n",
+       "   action_before_3_6.0_x  action_before_3_1.0_y  ...  cate_action_4_mean  \\\n",
+       "0                    3.0                   26.0  ...           73.400000   \n",
+       "1                   30.0                    2.0  ...           73.400000   \n",
+       "2                    2.0                   12.0  ...           20.766667   \n",
+       "3                    3.0                   10.0  ...           20.766667   \n",
+       "4                    3.0                   10.0  ...           20.766667   \n",
+       "\n",
+       "   cate_action_5_mean  cate_action_6_mean  has_bad_comment  bad_comment_rate  \\\n",
+       "0          169.366667             48251.0              1.0            0.0821   \n",
+       "1          169.366667             48251.0              1.0            0.0196   \n",
+       "2           56.700000             12937.7              1.0            0.0198   \n",
+       "3           56.700000             12937.7              1.0            0.0476   \n",
+       "4           56.700000             12937.7              0.0            0.0000   \n",
+       "\n",
+       "   comment_num_0  comment_num_1  comment_num_2  comment_num_3  comment_num_4  \n",
+       "0            0.0            0.0            0.0            0.0            1.0  \n",
+       "1            0.0            0.0            0.0            0.0            1.0  \n",
+       "2            0.0            0.0            0.0            0.0            1.0  \n",
+       "3            0.0            0.0            0.0            0.0            1.0  \n",
+       "4            0.0            0.0            0.0            0.0            1.0  \n",
+       "\n",
+       "[5 rows x 236 columns]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = pd.read_csv('data/val_set.csv')  # 读取验证数据\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "val_x = data.loc[:,data.columns != 'label']  # 将验证数据集分成特征和标签\n",
+    "val_y = data.loc[:,data.columns == 'label']\n",
+    "val_x.head()"
+   ]
+  }
+ ],
+ "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
+}