From 65a50dfd422f68ccf35e75e82f3521a70ddf8a2d Mon Sep 17 00:00:00 2001
From: benjas <909336740@qq.com>
Date: Mon, 8 Feb 2021 22:27:45 +0800
Subject: [PATCH] Update. some methods

---
 .../4-模型预测及评估.ipynb             | 244 ++++++++++++++++++
 1 file changed, 244 insertions(+)

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/4-模型预测及评估.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/4-模型预测及评估.ipynb
index c442ea5..b6ee0ca 100644
--- 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/4-模型预测及评估.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/4-模型预测及评估.ipynb
@@ -21,6 +21,250 @@
     "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_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>200001.0</td>\n",
+       "      <td>20308.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</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>...</td>\n",
+       "      <td>214.800000</td>\n",
+       "      <td>665.166667</td>\n",
+       "      <td>185387.233333</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0132</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>200001.0</td>\n",
+       "      <td>38604.0</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</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>...</td>\n",
+       "      <td>59.033333</td>\n",
+       "      <td>106.600000</td>\n",
+       "      <td>37389.133333</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0250</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>200001.0</td>\n",
+       "      <td>164215.0</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</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>...</td>\n",
+       "      <td>214.800000</td>\n",
+       "      <td>665.166667</td>\n",
+       "      <td>185387.233333</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0386</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>200002.0</td>\n",
+       "      <td>2866.0</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>10.0</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>59.033333</td>\n",
+       "      <td>106.600000</td>\n",
+       "      <td>37389.133333</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>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>200002.0</td>\n",
+       "      <td>3673.0</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>0.0</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>30.0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>59.033333</td>\n",
+       "      <td>106.600000</td>\n",
+       "      <td>37389.133333</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0436</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  200001.0   20308.0   8.0                    0.0                    0.0   \n",
+       "1  200001.0   38604.0   9.0                    0.0                    0.0   \n",
+       "2  200001.0  164215.0   8.0                    0.0                    0.0   \n",
+       "3  200002.0    2866.0   9.0                    2.0                    0.0   \n",
+       "4  200002.0    3673.0   9.0                    0.0                    0.0   \n",
+       "\n",
+       "   action_before_3_3.0_x  action_before_3_4.0_x  action_before_3_5.0_x  \\\n",
+       "0                    1.0                    0.0                    0.0   \n",
+       "1                    1.0                    0.0                    0.0   \n",
+       "2                    1.0                    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                    0.0                    0.0  ...          214.800000   \n",
+       "1                    0.0                    0.0  ...           59.033333   \n",
+       "2                    0.0                    0.0  ...          214.800000   \n",
+       "3                   10.0                   28.0  ...           59.033333   \n",
+       "4                    4.0                   30.0  ...           59.033333   \n",
+       "\n",
+       "   cate_action_5_mean  cate_action_6_mean  has_bad_comment  bad_comment_rate  \\\n",
+       "0          665.166667       185387.233333              1.0            0.0132   \n",
+       "1          106.600000        37389.133333              1.0            0.0250   \n",
+       "2          665.166667       185387.233333              1.0            0.0386   \n",
+       "3          106.600000        37389.133333              0.0            0.0000   \n",
+       "4          106.600000        37389.133333              1.0            0.0436   \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            0.0  \n",
+       "4            0.0            0.0            0.0            0.0            1.0  \n",
+       "\n",
+       "[5 rows x 236 columns]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = pd.read_csv('data/test_set.csv')  # 读取训练数据\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(270139, 236)"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.shape"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 2,