все еще на работает
This commit is contained in:
parent
003b2f8c7a
commit
fdbdb674e8
@ -521,19 +521,23 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"execution_count": 24,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"ename": "ValueError",
|
||||
"evalue": "brand_name is not a column in the dataframe",
|
||||
"evalue": "The least populated class in y has only 1 member, which is too few. The minimum number of groups for any class cannot be less than 2.",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[1;32mIn[22], line 46\u001b[0m\n\u001b[0;32m 42\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m df_train, df_val, df_test\n\u001b[0;32m 44\u001b[0m data \u001b[38;5;241m=\u001b[39m df[[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrating\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mprice\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mram_storage\u001b[39m\u001b[38;5;124m\"\u001b[39m]]\u001b[38;5;241m.\u001b[39mcopy()\n\u001b[1;32m---> 46\u001b[0m df_train, df_val, df_test \u001b[38;5;241m=\u001b[39m \u001b[43msplit_stratified_into_train_val_test\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 47\u001b[0m \u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstratify_colname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mbrand_name\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrac_train\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.60\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrac_val\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.20\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrac_test\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.20\u001b[39;49m\n\u001b[0;32m 48\u001b[0m \u001b[43m)\u001b[49m\n\u001b[0;32m 50\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mОбучающая выборка: \u001b[39m\u001b[38;5;124m\"\u001b[39m, df_train\u001b[38;5;241m.\u001b[39mshape)\n\u001b[0;32m 52\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mКонтрольная выборка: \u001b[39m\u001b[38;5;124m\"\u001b[39m, df_val\u001b[38;5;241m.\u001b[39mshape)\n",
|
||||
"Cell \u001b[1;32mIn[22], line 18\u001b[0m, in \u001b[0;36msplit_stratified_into_train_val_test\u001b[1;34m(df_input, stratify_colname, frac_train, frac_val, frac_test, random_state)\u001b[0m\n\u001b[0;32m 12\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m 13\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfractions \u001b[39m\u001b[38;5;132;01m%f\u001b[39;00m\u001b[38;5;124m, \u001b[39m\u001b[38;5;132;01m%f\u001b[39;00m\u001b[38;5;124m, \u001b[39m\u001b[38;5;132;01m%f\u001b[39;00m\u001b[38;5;124m do not add up to 1.0\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 14\u001b[0m \u001b[38;5;241m%\u001b[39m (frac_train, frac_val, frac_test)\n\u001b[0;32m 15\u001b[0m )\n\u001b[0;32m 17\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m stratify_colname \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m df_input\u001b[38;5;241m.\u001b[39mcolumns:\n\u001b[1;32m---> 18\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m is not a column in the dataframe\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m%\u001b[39m (stratify_colname))\n\u001b[0;32m 20\u001b[0m X \u001b[38;5;241m=\u001b[39m df_input \u001b[38;5;66;03m# Contains all columns.\u001b[39;00m\n\u001b[0;32m 21\u001b[0m y \u001b[38;5;241m=\u001b[39m df_input[\n\u001b[0;32m 22\u001b[0m [stratify_colname]\n\u001b[0;32m 23\u001b[0m ] \u001b[38;5;66;03m# Dataframe of just the column on which to stratify.\u001b[39;00m\n",
|
||||
"\u001b[1;31mValueError\u001b[0m: brand_name is not a column in the dataframe"
|
||||
"Cell \u001b[1;32mIn[24], line 46\u001b[0m\n\u001b[0;32m 42\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m df_train, df_val, df_test\n\u001b[0;32m 44\u001b[0m data \u001b[38;5;241m=\u001b[39m df[[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrating\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mprice\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mram_storage\u001b[39m\u001b[38;5;124m\"\u001b[39m]]\u001b[38;5;241m.\u001b[39mcopy()\n\u001b[1;32m---> 46\u001b[0m df_train, df_val, df_test \u001b[38;5;241m=\u001b[39m \u001b[43msplit_stratified_into_train_val_test\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 47\u001b[0m \u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstratify_colname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrating\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrac_train\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.60\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrac_val\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.20\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrac_test\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.20\u001b[39;49m\n\u001b[0;32m 48\u001b[0m \u001b[43m)\u001b[49m\n\u001b[0;32m 50\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mОбучающая выборка: \u001b[39m\u001b[38;5;124m\"\u001b[39m, df_train\u001b[38;5;241m.\u001b[39mshape)\n\u001b[0;32m 52\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mКонтрольная выборка: \u001b[39m\u001b[38;5;124m\"\u001b[39m, df_val\u001b[38;5;241m.\u001b[39mshape)\n",
|
||||
"Cell \u001b[1;32mIn[24], line 26\u001b[0m, in \u001b[0;36msplit_stratified_into_train_val_test\u001b[1;34m(df_input, stratify_colname, frac_train, frac_val, frac_test, random_state)\u001b[0m\n\u001b[0;32m 21\u001b[0m y \u001b[38;5;241m=\u001b[39m df_input[\n\u001b[0;32m 22\u001b[0m [stratify_colname]\n\u001b[0;32m 23\u001b[0m ] \u001b[38;5;66;03m# Dataframe of just the column on which to stratify.\u001b[39;00m\n\u001b[0;32m 25\u001b[0m \u001b[38;5;66;03m# Split original dataframe into train and temp dataframes.\u001b[39;00m\n\u001b[1;32m---> 26\u001b[0m df_train, df_temp, y_train, y_temp \u001b[38;5;241m=\u001b[39m \u001b[43mtrain_test_split\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 27\u001b[0m \u001b[43m \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstratify\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtest_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m1.0\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mfrac_train\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrandom_state\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrandom_state\u001b[49m\n\u001b[0;32m 28\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 30\u001b[0m \u001b[38;5;66;03m# Split the temp dataframe into val and test dataframes.\u001b[39;00m\n\u001b[0;32m 31\u001b[0m relative_frac_test \u001b[38;5;241m=\u001b[39m frac_test \u001b[38;5;241m/\u001b[39m (frac_val \u001b[38;5;241m+\u001b[39m frac_test)\n",
|
||||
"File \u001b[1;32md:\\Study\\3 курс 5 семестр\\AIM\\AIM-PIbd-31-Yakovlev-M-G\\kernel\\Lib\\site-packages\\sklearn\\utils\\_param_validation.py:213\u001b[0m, in \u001b[0;36mvalidate_params.<locals>.decorator.<locals>.wrapper\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m 207\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m 208\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[0;32m 209\u001b[0m skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[0;32m 210\u001b[0m prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[0;32m 211\u001b[0m )\n\u001b[0;32m 212\u001b[0m ):\n\u001b[1;32m--> 213\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 214\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m InvalidParameterError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m 215\u001b[0m \u001b[38;5;66;03m# When the function is just a wrapper around an estimator, we allow\u001b[39;00m\n\u001b[0;32m 216\u001b[0m \u001b[38;5;66;03m# the function to delegate validation to the estimator, but we replace\u001b[39;00m\n\u001b[0;32m 217\u001b[0m \u001b[38;5;66;03m# the name of the estimator by the name of the function in the error\u001b[39;00m\n\u001b[0;32m 218\u001b[0m \u001b[38;5;66;03m# message to avoid confusion.\u001b[39;00m\n\u001b[0;32m 219\u001b[0m msg \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msub(\n\u001b[0;32m 220\u001b[0m \u001b[38;5;124mr\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparameter of \u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124mw+ must be\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m 221\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparameter of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfunc\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__qualname__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m must be\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m 222\u001b[0m \u001b[38;5;28mstr\u001b[39m(e),\n\u001b[0;32m 223\u001b[0m )\n",
|
||||
"File \u001b[1;32md:\\Study\\3 курс 5 семестр\\AIM\\AIM-PIbd-31-Yakovlev-M-G\\kernel\\Lib\\site-packages\\sklearn\\model_selection\\_split.py:2806\u001b[0m, in \u001b[0;36mtrain_test_split\u001b[1;34m(test_size, train_size, random_state, shuffle, stratify, *arrays)\u001b[0m\n\u001b[0;32m 2802\u001b[0m CVClass \u001b[38;5;241m=\u001b[39m ShuffleSplit\n\u001b[0;32m 2804\u001b[0m cv \u001b[38;5;241m=\u001b[39m CVClass(test_size\u001b[38;5;241m=\u001b[39mn_test, train_size\u001b[38;5;241m=\u001b[39mn_train, random_state\u001b[38;5;241m=\u001b[39mrandom_state)\n\u001b[1;32m-> 2806\u001b[0m train, test \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mnext\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mcv\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msplit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43marrays\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstratify\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 2808\u001b[0m train, test \u001b[38;5;241m=\u001b[39m ensure_common_namespace_device(arrays[\u001b[38;5;241m0\u001b[39m], train, test)\n\u001b[0;32m 2810\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mlist\u001b[39m(\n\u001b[0;32m 2811\u001b[0m chain\u001b[38;5;241m.\u001b[39mfrom_iterable(\n\u001b[0;32m 2812\u001b[0m (_safe_indexing(a, train), _safe_indexing(a, test)) \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m arrays\n\u001b[0;32m 2813\u001b[0m )\n\u001b[0;32m 2814\u001b[0m )\n",
|
||||
"File \u001b[1;32md:\\Study\\3 курс 5 семестр\\AIM\\AIM-PIbd-31-Yakovlev-M-G\\kernel\\Lib\\site-packages\\sklearn\\model_selection\\_split.py:1843\u001b[0m, in \u001b[0;36mBaseShuffleSplit.split\u001b[1;34m(self, X, y, groups)\u001b[0m\n\u001b[0;32m 1813\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Generate indices to split data into training and test set.\u001b[39;00m\n\u001b[0;32m 1814\u001b[0m \n\u001b[0;32m 1815\u001b[0m \u001b[38;5;124;03mParameters\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 1840\u001b[0m \u001b[38;5;124;03mto an integer.\u001b[39;00m\n\u001b[0;32m 1841\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 1842\u001b[0m X, y, groups \u001b[38;5;241m=\u001b[39m indexable(X, y, groups)\n\u001b[1;32m-> 1843\u001b[0m \u001b[43m\u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mtrain\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtest\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_iter_indices\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgroups\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[0;32m 1844\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43;01myield\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mtrain\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtest\u001b[49m\n",
|
||||
"File \u001b[1;32md:\\Study\\3 курс 5 семестр\\AIM\\AIM-PIbd-31-Yakovlev-M-G\\kernel\\Lib\\site-packages\\sklearn\\model_selection\\_split.py:2252\u001b[0m, in \u001b[0;36mStratifiedShuffleSplit._iter_indices\u001b[1;34m(self, X, y, groups)\u001b[0m\n\u001b[0;32m 2250\u001b[0m class_counts \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mbincount(y_indices)\n\u001b[0;32m 2251\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m np\u001b[38;5;241m.\u001b[39mmin(class_counts) \u001b[38;5;241m<\u001b[39m \u001b[38;5;241m2\u001b[39m:\n\u001b[1;32m-> 2252\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m 2253\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe least populated class in y has only 1\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 2254\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m member, which is too few. The minimum\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 2255\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m number of groups for any class cannot\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 2256\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m be less than 2.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 2257\u001b[0m )\n\u001b[0;32m 2259\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m n_train \u001b[38;5;241m<\u001b[39m n_classes:\n\u001b[0;32m 2260\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m 2261\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe train_size = \u001b[39m\u001b[38;5;132;01m%d\u001b[39;00m\u001b[38;5;124m should be greater or \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 2262\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mequal to the number of classes = \u001b[39m\u001b[38;5;132;01m%d\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m%\u001b[39m (n_train, n_classes)\n\u001b[0;32m 2263\u001b[0m )\n",
|
||||
"\u001b[1;31mValueError\u001b[0m: The least populated class in y has only 1 member, which is too few. The minimum number of groups for any class cannot be less than 2."
|
||||
]
|
||||
}
|
||||
],
|
||||
|
||||
Loading…
Reference in New Issue
Block a user