Setup docs page
This commit is contained in:
parent
dadbe24c82
commit
c39feeee53
33 changed files with 2724 additions and 379 deletions
|
|
@ -19,49 +19,16 @@
|
|||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[38;5;39m2022-06-20 14:33:17,570 | INFO | Starting parallel map (concurrency: 12, chunk size: 700)\u001b[0m\n"
|
||||
"84000it [00:09, 8647.60it/s] \n",
|
||||
"22399it [00:03, 6368.63it/s]\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "e6f76bf83615422cb4352dcb3af48a26",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
" 0%| | 0/84000 [00:00<?, ?it/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[38;5;39m2022-06-20 14:33:24,846 | INFO | Starting parallel map (concurrency: 12, chunk size: 187)\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "ab012f9276d74bdda15b00cfec6c8f56",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
" 0%| | 0/22399 [00:00<?, ?it/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import json\n",
|
||||
"from typing import Tuple\n",
|
||||
"from great_ai.utilities import clean, parallel_map\n",
|
||||
"from tqdm.cli import tqdm\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def preprocess(line: str) -> Tuple[str, str]:\n",
|
||||
|
|
@ -71,14 +38,14 @@
|
|||
"\n",
|
||||
"\n",
|
||||
"with open(\"mag/train.txt\", encoding=\"utf-8\") as f:\n",
|
||||
" training_data = parallel_map(preprocess, f.readlines())\n",
|
||||
" training_data = list(tqdm(parallel_map(preprocess, f.readlines())))\n",
|
||||
"\n",
|
||||
"X_train = [d[0] for d in training_data]\n",
|
||||
"y_train = [d[1] for d in training_data]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"with open(\"mag/test.txt\", encoding=\"utf-8\") as f:\n",
|
||||
" test_data = parallel_map(preprocess, f.readlines())\n",
|
||||
" test_data = list(tqdm(parallel_map(preprocess, f.readlines())))\n",
|
||||
"\n",
|
||||
"X_test = [d[0] for d in test_data]\n",
|
||||
"y_test = [d[1] for d in test_data]"
|
||||
|
|
@ -1070,10 +1037,10 @@
|
|||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>12</th>\n",
|
||||
" <td>1.172014</td>\n",
|
||||
" <td>0.033318</td>\n",
|
||||
" <td>0.625773</td>\n",
|
||||
" <td>0.013720</td>\n",
|
||||
" <td>1.227354</td>\n",
|
||||
" <td>0.011710</td>\n",
|
||||
" <td>0.652844</td>\n",
|
||||
" <td>0.040511</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1088,10 +1055,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>15</th>\n",
|
||||
" <td>1.201231</td>\n",
|
||||
" <td>0.016728</td>\n",
|
||||
" <td>0.613568</td>\n",
|
||||
" <td>0.013720</td>\n",
|
||||
" <td>1.279783</td>\n",
|
||||
" <td>0.037969</td>\n",
|
||||
" <td>0.634761</td>\n",
|
||||
" <td>0.068606</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1106,10 +1073,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>18</th>\n",
|
||||
" <td>1.211270</td>\n",
|
||||
" <td>0.036636</td>\n",
|
||||
" <td>0.670754</td>\n",
|
||||
" <td>0.076857</td>\n",
|
||||
" <td>1.332854</td>\n",
|
||||
" <td>0.171405</td>\n",
|
||||
" <td>0.743611</td>\n",
|
||||
" <td>0.109792</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1124,10 +1091,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>21</th>\n",
|
||||
" <td>1.165763</td>\n",
|
||||
" <td>0.061206</td>\n",
|
||||
" <td>0.549646</td>\n",
|
||||
" <td>0.046776</td>\n",
|
||||
" <td>1.253222</td>\n",
|
||||
" <td>0.072134</td>\n",
|
||||
" <td>0.612344</td>\n",
|
||||
" <td>0.016771</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1142,10 +1109,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>3</th>\n",
|
||||
" <td>1.277603</td>\n",
|
||||
" <td>0.127785</td>\n",
|
||||
" <td>0.650135</td>\n",
|
||||
" <td>0.023038</td>\n",
|
||||
" <td>1.472035</td>\n",
|
||||
" <td>0.080849</td>\n",
|
||||
" <td>0.654935</td>\n",
|
||||
" <td>0.044302</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1160,10 +1127,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>0</th>\n",
|
||||
" <td>1.118055</td>\n",
|
||||
" <td>0.058978</td>\n",
|
||||
" <td>0.622284</td>\n",
|
||||
" <td>0.014230</td>\n",
|
||||
" <td>1.380641</td>\n",
|
||||
" <td>0.054306</td>\n",
|
||||
" <td>0.739966</td>\n",
|
||||
" <td>0.053385</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1178,10 +1145,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>9</th>\n",
|
||||
" <td>1.166192</td>\n",
|
||||
" <td>0.044232</td>\n",
|
||||
" <td>0.619351</td>\n",
|
||||
" <td>0.024824</td>\n",
|
||||
" <td>1.284987</td>\n",
|
||||
" <td>0.113903</td>\n",
|
||||
" <td>0.696876</td>\n",
|
||||
" <td>0.003757</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1196,10 +1163,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>6</th>\n",
|
||||
" <td>1.233377</td>\n",
|
||||
" <td>0.063715</td>\n",
|
||||
" <td>0.666418</td>\n",
|
||||
" <td>0.061664</td>\n",
|
||||
" <td>1.291148</td>\n",
|
||||
" <td>0.101837</td>\n",
|
||||
" <td>0.686561</td>\n",
|
||||
" <td>0.083989</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1214,10 +1181,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>13</th>\n",
|
||||
" <td>1.245147</td>\n",
|
||||
" <td>0.089528</td>\n",
|
||||
" <td>0.645836</td>\n",
|
||||
" <td>0.006279</td>\n",
|
||||
" <td>1.268873</td>\n",
|
||||
" <td>0.042412</td>\n",
|
||||
" <td>0.645649</td>\n",
|
||||
" <td>0.022738</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1232,10 +1199,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>16</th>\n",
|
||||
" <td>1.145362</td>\n",
|
||||
" <td>0.071149</td>\n",
|
||||
" <td>0.637540</td>\n",
|
||||
" <td>0.028854</td>\n",
|
||||
" <td>1.147120</td>\n",
|
||||
" <td>0.009335</td>\n",
|
||||
" <td>0.599006</td>\n",
|
||||
" <td>0.045637</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1250,10 +1217,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>4</th>\n",
|
||||
" <td>1.179663</td>\n",
|
||||
" <td>0.046808</td>\n",
|
||||
" <td>0.598699</td>\n",
|
||||
" <td>0.035973</td>\n",
|
||||
" <td>1.186988</td>\n",
|
||||
" <td>0.057330</td>\n",
|
||||
" <td>0.642233</td>\n",
|
||||
" <td>0.078248</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1268,10 +1235,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1</th>\n",
|
||||
" <td>1.097773</td>\n",
|
||||
" <td>0.005871</td>\n",
|
||||
" <td>0.596514</td>\n",
|
||||
" <td>0.025899</td>\n",
|
||||
" <td>1.413231</td>\n",
|
||||
" <td>0.153288</td>\n",
|
||||
" <td>0.765960</td>\n",
|
||||
" <td>0.099535</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1286,10 +1253,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>19</th>\n",
|
||||
" <td>1.161582</td>\n",
|
||||
" <td>0.040011</td>\n",
|
||||
" <td>0.586831</td>\n",
|
||||
" <td>0.006144</td>\n",
|
||||
" <td>1.193013</td>\n",
|
||||
" <td>0.079000</td>\n",
|
||||
" <td>0.691768</td>\n",
|
||||
" <td>0.027448</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1304,10 +1271,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>22</th>\n",
|
||||
" <td>1.106277</td>\n",
|
||||
" <td>0.060809</td>\n",
|
||||
" <td>0.371986</td>\n",
|
||||
" <td>0.014114</td>\n",
|
||||
" <td>1.043618</td>\n",
|
||||
" <td>0.098733</td>\n",
|
||||
" <td>0.450375</td>\n",
|
||||
" <td>0.061660</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1322,10 +1289,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>7</th>\n",
|
||||
" <td>1.217713</td>\n",
|
||||
" <td>0.044787</td>\n",
|
||||
" <td>0.587896</td>\n",
|
||||
" <td>0.024613</td>\n",
|
||||
" <td>1.301459</td>\n",
|
||||
" <td>0.062143</td>\n",
|
||||
" <td>0.660748</td>\n",
|
||||
" <td>0.056054</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1340,10 +1307,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>10</th>\n",
|
||||
" <td>1.176654</td>\n",
|
||||
" <td>0.045971</td>\n",
|
||||
" <td>0.628005</td>\n",
|
||||
" <td>0.082375</td>\n",
|
||||
" <td>1.433934</td>\n",
|
||||
" <td>0.155240</td>\n",
|
||||
" <td>0.636608</td>\n",
|
||||
" <td>0.024064</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1358,10 +1325,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>14</th>\n",
|
||||
" <td>1.207308</td>\n",
|
||||
" <td>0.080923</td>\n",
|
||||
" <td>0.610284</td>\n",
|
||||
" <td>0.039157</td>\n",
|
||||
" <td>1.325535</td>\n",
|
||||
" <td>0.073539</td>\n",
|
||||
" <td>0.672542</td>\n",
|
||||
" <td>0.085835</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1376,10 +1343,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>17</th>\n",
|
||||
" <td>1.201498</td>\n",
|
||||
" <td>0.035161</td>\n",
|
||||
" <td>0.574234</td>\n",
|
||||
" <td>0.019247</td>\n",
|
||||
" <td>1.237677</td>\n",
|
||||
" <td>0.070063</td>\n",
|
||||
" <td>0.651091</td>\n",
|
||||
" <td>0.102538</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1394,10 +1361,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>2</th>\n",
|
||||
" <td>1.157947</td>\n",
|
||||
" <td>0.096841</td>\n",
|
||||
" <td>0.586462</td>\n",
|
||||
" <td>0.010952</td>\n",
|
||||
" <td>1.394873</td>\n",
|
||||
" <td>0.105286</td>\n",
|
||||
" <td>0.637073</td>\n",
|
||||
" <td>0.041708</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1412,10 +1379,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>5</th>\n",
|
||||
" <td>1.150511</td>\n",
|
||||
" <td>0.027807</td>\n",
|
||||
" <td>0.562870</td>\n",
|
||||
" <td>0.013724</td>\n",
|
||||
" <td>1.270732</td>\n",
|
||||
" <td>0.013414</td>\n",
|
||||
" <td>0.620984</td>\n",
|
||||
" <td>0.025393</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>True</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1430,10 +1397,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>20</th>\n",
|
||||
" <td>1.237030</td>\n",
|
||||
" <td>0.006805</td>\n",
|
||||
" <td>0.529591</td>\n",
|
||||
" <td>0.064449</td>\n",
|
||||
" <td>1.177219</td>\n",
|
||||
" <td>0.039633</td>\n",
|
||||
" <td>0.586308</td>\n",
|
||||
" <td>0.044247</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1448,10 +1415,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>8</th>\n",
|
||||
" <td>1.103937</td>\n",
|
||||
" <td>0.046513</td>\n",
|
||||
" <td>0.569367</td>\n",
|
||||
" <td>0.011001</td>\n",
|
||||
" <td>1.165583</td>\n",
|
||||
" <td>0.046999</td>\n",
|
||||
" <td>0.603675</td>\n",
|
||||
" <td>0.031774</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.05</td>\n",
|
||||
|
|
@ -1466,10 +1433,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>23</th>\n",
|
||||
" <td>1.080252</td>\n",
|
||||
" <td>0.040597</td>\n",
|
||||
" <td>0.326627</td>\n",
|
||||
" <td>0.002905</td>\n",
|
||||
" <td>0.907388</td>\n",
|
||||
" <td>0.121543</td>\n",
|
||||
" <td>0.354655</td>\n",
|
||||
" <td>0.023775</td>\n",
|
||||
" <td>1</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1484,10 +1451,10 @@
|
|||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>11</th>\n",
|
||||
" <td>1.275601</td>\n",
|
||||
" <td>0.087971</td>\n",
|
||||
" <td>0.580025</td>\n",
|
||||
" <td>0.034914</td>\n",
|
||||
" <td>1.210845</td>\n",
|
||||
" <td>0.041339</td>\n",
|
||||
" <td>0.653606</td>\n",
|
||||
" <td>0.028117</td>\n",
|
||||
" <td>0.5</td>\n",
|
||||
" <td>False</td>\n",
|
||||
" <td>0.1</td>\n",
|
||||
|
|
@ -1506,30 +1473,30 @@
|
|||
],
|
||||
"text/plain": [
|
||||
" mean_fit_time std_fit_time mean_score_time std_score_time \\\n",
|
||||
"12 1.172014 0.033318 0.625773 0.013720 \n",
|
||||
"15 1.201231 0.016728 0.613568 0.013720 \n",
|
||||
"18 1.211270 0.036636 0.670754 0.076857 \n",
|
||||
"21 1.165763 0.061206 0.549646 0.046776 \n",
|
||||
"3 1.277603 0.127785 0.650135 0.023038 \n",
|
||||
"0 1.118055 0.058978 0.622284 0.014230 \n",
|
||||
"9 1.166192 0.044232 0.619351 0.024824 \n",
|
||||
"6 1.233377 0.063715 0.666418 0.061664 \n",
|
||||
"13 1.245147 0.089528 0.645836 0.006279 \n",
|
||||
"16 1.145362 0.071149 0.637540 0.028854 \n",
|
||||
"4 1.179663 0.046808 0.598699 0.035973 \n",
|
||||
"1 1.097773 0.005871 0.596514 0.025899 \n",
|
||||
"19 1.161582 0.040011 0.586831 0.006144 \n",
|
||||
"22 1.106277 0.060809 0.371986 0.014114 \n",
|
||||
"7 1.217713 0.044787 0.587896 0.024613 \n",
|
||||
"10 1.176654 0.045971 0.628005 0.082375 \n",
|
||||
"14 1.207308 0.080923 0.610284 0.039157 \n",
|
||||
"17 1.201498 0.035161 0.574234 0.019247 \n",
|
||||
"2 1.157947 0.096841 0.586462 0.010952 \n",
|
||||
"5 1.150511 0.027807 0.562870 0.013724 \n",
|
||||
"20 1.237030 0.006805 0.529591 0.064449 \n",
|
||||
"8 1.103937 0.046513 0.569367 0.011001 \n",
|
||||
"23 1.080252 0.040597 0.326627 0.002905 \n",
|
||||
"11 1.275601 0.087971 0.580025 0.034914 \n",
|
||||
"12 1.227354 0.011710 0.652844 0.040511 \n",
|
||||
"15 1.279783 0.037969 0.634761 0.068606 \n",
|
||||
"18 1.332854 0.171405 0.743611 0.109792 \n",
|
||||
"21 1.253222 0.072134 0.612344 0.016771 \n",
|
||||
"3 1.472035 0.080849 0.654935 0.044302 \n",
|
||||
"0 1.380641 0.054306 0.739966 0.053385 \n",
|
||||
"9 1.284987 0.113903 0.696876 0.003757 \n",
|
||||
"6 1.291148 0.101837 0.686561 0.083989 \n",
|
||||
"13 1.268873 0.042412 0.645649 0.022738 \n",
|
||||
"16 1.147120 0.009335 0.599006 0.045637 \n",
|
||||
"4 1.186988 0.057330 0.642233 0.078248 \n",
|
||||
"1 1.413231 0.153288 0.765960 0.099535 \n",
|
||||
"19 1.193013 0.079000 0.691768 0.027448 \n",
|
||||
"22 1.043618 0.098733 0.450375 0.061660 \n",
|
||||
"7 1.301459 0.062143 0.660748 0.056054 \n",
|
||||
"10 1.433934 0.155240 0.636608 0.024064 \n",
|
||||
"14 1.325535 0.073539 0.672542 0.085835 \n",
|
||||
"17 1.237677 0.070063 0.651091 0.102538 \n",
|
||||
"2 1.394873 0.105286 0.637073 0.041708 \n",
|
||||
"5 1.270732 0.013414 0.620984 0.025393 \n",
|
||||
"20 1.177219 0.039633 0.586308 0.044247 \n",
|
||||
"8 1.165583 0.046999 0.603675 0.031774 \n",
|
||||
"23 0.907388 0.121543 0.354655 0.023775 \n",
|
||||
"11 1.210845 0.041339 0.653606 0.028117 \n",
|
||||
"\n",
|
||||
" param_classifier__alpha param_classifier__fit_prior \\\n",
|
||||
"12 1 True \n",
|
||||
|
|
@ -1726,7 +1693,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue