| 123 | 123 |
},
|
| 124 | 124 |
{
|
| 125 | 125 |
"cell_type": "code",
|
| 126 | |
"execution_count": 1,
|
|
126 |
"execution_count": null,
|
| 127 | 127 |
"metadata": {},
|
| 128 | 128 |
"outputs": [],
|
| 129 | 129 |
"source": [
|
|
| 140 | 140 |
},
|
| 141 | 141 |
{
|
| 142 | 142 |
"cell_type": "code",
|
| 143 | |
"execution_count": 2,
|
| 144 | |
"metadata": {},
|
| 145 | |
"outputs": [
|
| 146 | |
{
|
| 147 | |
"data": {
|
| 148 | |
"text/html": [
|
| 149 | |
"<div>\n",
|
| 150 | |
"<style scoped>\n",
|
| 151 | |
" .dataframe tbody tr th:only-of-type {\n",
|
| 152 | |
" vertical-align: middle;\n",
|
| 153 | |
" }\n",
|
| 154 | |
"\n",
|
| 155 | |
" .dataframe tbody tr th {\n",
|
| 156 | |
" vertical-align: top;\n",
|
| 157 | |
" }\n",
|
| 158 | |
"\n",
|
| 159 | |
" .dataframe thead th {\n",
|
| 160 | |
" text-align: right;\n",
|
| 161 | |
" }\n",
|
| 162 | |
"</style>\n",
|
| 163 | |
"<table border=\"1\" class=\"dataframe\">\n",
|
| 164 | |
" <thead>\n",
|
| 165 | |
" <tr style=\"text-align: right;\">\n",
|
| 166 | |
" <th></th>\n",
|
| 167 | |
" <th>天气</th>\n",
|
| 168 | |
" <th>温度</th>\n",
|
| 169 | |
" <th>湿度</th>\n",
|
| 170 | |
" <th>是否有风</th>\n",
|
| 171 | |
" <th>是否前往游乐场</th>\n",
|
| 172 | |
" </tr>\n",
|
| 173 | |
" </thead>\n",
|
| 174 | |
" <tbody>\n",
|
| 175 | |
" <tr>\n",
|
| 176 | |
" <td>0</td>\n",
|
| 177 | |
" <td>晴</td>\n",
|
| 178 | |
" <td>>26</td>\n",
|
| 179 | |
" <td>>75</td>\n",
|
| 180 | |
" <td>否</td>\n",
|
| 181 | |
" <td>0</td>\n",
|
| 182 | |
" </tr>\n",
|
| 183 | |
" <tr>\n",
|
| 184 | |
" <td>1</td>\n",
|
| 185 | |
" <td>晴</td>\n",
|
| 186 | |
" <td><=26</td>\n",
|
| 187 | |
" <td>>75</td>\n",
|
| 188 | |
" <td>是</td>\n",
|
| 189 | |
" <td>0</td>\n",
|
| 190 | |
" </tr>\n",
|
| 191 | |
" <tr>\n",
|
| 192 | |
" <td>2</td>\n",
|
| 193 | |
" <td>多云</td>\n",
|
| 194 | |
" <td>>26</td>\n",
|
| 195 | |
" <td>>75</td>\n",
|
| 196 | |
" <td>否</td>\n",
|
| 197 | |
" <td>1</td>\n",
|
| 198 | |
" </tr>\n",
|
| 199 | |
" <tr>\n",
|
| 200 | |
" <td>3</td>\n",
|
| 201 | |
" <td>雨</td>\n",
|
| 202 | |
" <td><=26</td>\n",
|
| 203 | |
" <td>>75</td>\n",
|
| 204 | |
" <td>否</td>\n",
|
| 205 | |
" <td>1</td>\n",
|
| 206 | |
" </tr>\n",
|
| 207 | |
" <tr>\n",
|
| 208 | |
" <td>4</td>\n",
|
| 209 | |
" <td>雨</td>\n",
|
| 210 | |
" <td><=26</td>\n",
|
| 211 | |
" <td>>75</td>\n",
|
| 212 | |
" <td>否</td>\n",
|
| 213 | |
" <td>1</td>\n",
|
| 214 | |
" </tr>\n",
|
| 215 | |
" <tr>\n",
|
| 216 | |
" <td>5</td>\n",
|
| 217 | |
" <td>雨</td>\n",
|
| 218 | |
" <td><=26</td>\n",
|
| 219 | |
" <td><=75</td>\n",
|
| 220 | |
" <td>是</td>\n",
|
| 221 | |
" <td>0</td>\n",
|
| 222 | |
" </tr>\n",
|
| 223 | |
" <tr>\n",
|
| 224 | |
" <td>6</td>\n",
|
| 225 | |
" <td>多云</td>\n",
|
| 226 | |
" <td><=26</td>\n",
|
| 227 | |
" <td><=75</td>\n",
|
| 228 | |
" <td>是</td>\n",
|
| 229 | |
" <td>1</td>\n",
|
| 230 | |
" </tr>\n",
|
| 231 | |
" <tr>\n",
|
| 232 | |
" <td>7</td>\n",
|
| 233 | |
" <td>晴</td>\n",
|
| 234 | |
" <td><=26</td>\n",
|
| 235 | |
" <td>>75</td>\n",
|
| 236 | |
" <td>否</td>\n",
|
| 237 | |
" <td>0</td>\n",
|
| 238 | |
" </tr>\n",
|
| 239 | |
" <tr>\n",
|
| 240 | |
" <td>8</td>\n",
|
| 241 | |
" <td>晴</td>\n",
|
| 242 | |
" <td><=26</td>\n",
|
| 243 | |
" <td><=75</td>\n",
|
| 244 | |
" <td>否</td>\n",
|
| 245 | |
" <td>1</td>\n",
|
| 246 | |
" </tr>\n",
|
| 247 | |
" <tr>\n",
|
| 248 | |
" <td>9</td>\n",
|
| 249 | |
" <td>雨</td>\n",
|
| 250 | |
" <td><=26</td>\n",
|
| 251 | |
" <td>>75</td>\n",
|
| 252 | |
" <td>否</td>\n",
|
| 253 | |
" <td>1</td>\n",
|
| 254 | |
" </tr>\n",
|
| 255 | |
" <tr>\n",
|
| 256 | |
" <td>10</td>\n",
|
| 257 | |
" <td>晴</td>\n",
|
| 258 | |
" <td><=26</td>\n",
|
| 259 | |
" <td><=75</td>\n",
|
| 260 | |
" <td>是</td>\n",
|
| 261 | |
" <td>1</td>\n",
|
| 262 | |
" </tr>\n",
|
| 263 | |
" <tr>\n",
|
| 264 | |
" <td>11</td>\n",
|
| 265 | |
" <td>多云</td>\n",
|
| 266 | |
" <td><=26</td>\n",
|
| 267 | |
" <td>>75</td>\n",
|
| 268 | |
" <td>是</td>\n",
|
| 269 | |
" <td>1</td>\n",
|
| 270 | |
" </tr>\n",
|
| 271 | |
" <tr>\n",
|
| 272 | |
" <td>12</td>\n",
|
| 273 | |
" <td>多云</td>\n",
|
| 274 | |
" <td>>26</td>\n",
|
| 275 | |
" <td><=75</td>\n",
|
| 276 | |
" <td>否</td>\n",
|
| 277 | |
" <td>1</td>\n",
|
| 278 | |
" </tr>\n",
|
| 279 | |
" <tr>\n",
|
| 280 | |
" <td>13</td>\n",
|
| 281 | |
" <td>雨</td>\n",
|
| 282 | |
" <td><=26</td>\n",
|
| 283 | |
" <td>>75</td>\n",
|
| 284 | |
" <td>是</td>\n",
|
| 285 | |
" <td>0</td>\n",
|
| 286 | |
" </tr>\n",
|
| 287 | |
" </tbody>\n",
|
| 288 | |
"</table>\n",
|
| 289 | |
"</div>"
|
| 290 | |
],
|
| 291 | |
"text/plain": [
|
| 292 | |
" 天气 温度 湿度 是否有风 是否前往游乐场\n",
|
| 293 | |
"0 晴 >26 >75 否 0\n",
|
| 294 | |
"1 晴 <=26 >75 是 0\n",
|
| 295 | |
"2 多云 >26 >75 否 1\n",
|
| 296 | |
"3 雨 <=26 >75 否 1\n",
|
| 297 | |
"4 雨 <=26 >75 否 1\n",
|
| 298 | |
"5 雨 <=26 <=75 是 0\n",
|
| 299 | |
"6 多云 <=26 <=75 是 1\n",
|
| 300 | |
"7 晴 <=26 >75 否 0\n",
|
| 301 | |
"8 晴 <=26 <=75 否 1\n",
|
| 302 | |
"9 雨 <=26 >75 否 1\n",
|
| 303 | |
"10 晴 <=26 <=75 是 1\n",
|
| 304 | |
"11 多云 <=26 >75 是 1\n",
|
| 305 | |
"12 多云 >26 <=75 否 1\n",
|
| 306 | |
"13 雨 <=26 >75 是 0"
|
| 307 | |
]
|
| 308 | |
},
|
| 309 | |
"execution_count": 2,
|
| 310 | |
"metadata": {},
|
| 311 | |
"output_type": "execute_result"
|
| 312 | |
}
|
| 313 | |
],
|
|
143 |
"execution_count": null,
|
|
144 |
"metadata": {},
|
|
145 |
"outputs": [],
|
| 314 | 146 |
"source": [
|
| 315 | 147 |
"# 原始数据\n",
|
| 316 | 148 |
"datasets = [\n",
|
|
| 889 | 721 |
"outputs": [],
|
| 890 | 722 |
"source": [
|
| 891 | 723 |
"# 读取英文短文\n",
|
| 892 | |
"en_essay = read_file('essay3_en.txt')\n",
|
|
724 |
"en_essay = read_file('essay1_en.txt')\n",
|
| 893 | 725 |
"# 读取中文短文\n",
|
| 894 | |
"ch_essay = read_file('essay3_ch.txt')\n"
|
|
726 |
"ch_essay = read_file('essay1_ch.txt')\n"
|
| 895 | 727 |
]
|
| 896 | 728 |
},
|
| 897 | 729 |
{
|