File size: 15,263 Bytes
eeaf86d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from data_loading import create_features_and_targets\n",
"from data_api_calls import get_data\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"dataset = pd.read_csv(\"dataset.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of rows with missing values dropped: 7\n"
]
},
{
"ename": "ValueError",
"evalue": "Found array with 0 sample(s) (shape=(0, 92)) while a minimum of 1 is required by StandardScaler.",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[11], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m X, y \u001b[38;5;241m=\u001b[39m \u001b[43mcreate_features_and_targets\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 2\u001b[0m \u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdataset\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3\u001b[0m \u001b[43m \u001b[49m\u001b[43mtarget_particle\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mNO2\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4\u001b[0m \u001b[43m \u001b[49m\u001b[43mlag_days\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m6\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5\u001b[0m \u001b[43m \u001b[49m\u001b[43msma_days\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m6\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6\u001b[0m \u001b[43m \u001b[49m\u001b[43mdays_ahead\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 7\u001b[0m \u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/Desktop/utrecht-pollution-prediction/data_loading.py:214\u001b[0m, in \u001b[0;36mcreate_features_and_targets\u001b[0;34m(data, target_particle, lag_days, sma_days, days_ahead)\u001b[0m\n\u001b[1;32m 211\u001b[0m target_scaler \u001b[38;5;241m=\u001b[39m StandardScaler()\n\u001b[1;32m 213\u001b[0m \u001b[38;5;66;03m# Fit the scalers on the training data\u001b[39;00m\n\u001b[0;32m--> 214\u001b[0m X_scaled \u001b[38;5;241m=\u001b[39m \u001b[43mfeature_scaler\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit_transform\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 215\u001b[0m y_scaled \u001b[38;5;241m=\u001b[39m target_scaler\u001b[38;5;241m.\u001b[39mfit_transform(y)\n\u001b[1;32m 217\u001b[0m \u001b[38;5;66;03m# Convert scaled data back to DataFrame for consistency\u001b[39;00m\n",
"File \u001b[0;32m~/anaconda3/envs/ml-industry/lib/python3.12/site-packages/sklearn/utils/_set_output.py:313\u001b[0m, in \u001b[0;36m_wrap_method_output.<locals>.wrapped\u001b[0;34m(self, X, *args, **kwargs)\u001b[0m\n\u001b[1;32m 311\u001b[0m \u001b[38;5;129m@wraps\u001b[39m(f)\n\u001b[1;32m 312\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mwrapped\u001b[39m(\u001b[38;5;28mself\u001b[39m, X, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m--> 313\u001b[0m data_to_wrap \u001b[38;5;241m=\u001b[39m \u001b[43mf\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\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[1;32m 314\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(data_to_wrap, \u001b[38;5;28mtuple\u001b[39m):\n\u001b[1;32m 315\u001b[0m \u001b[38;5;66;03m# only wrap the first output for cross decomposition\u001b[39;00m\n\u001b[1;32m 316\u001b[0m return_tuple \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m 317\u001b[0m _wrap_data_with_container(method, data_to_wrap[\u001b[38;5;241m0\u001b[39m], X, \u001b[38;5;28mself\u001b[39m),\n\u001b[1;32m 318\u001b[0m \u001b[38;5;241m*\u001b[39mdata_to_wrap[\u001b[38;5;241m1\u001b[39m:],\n\u001b[1;32m 319\u001b[0m )\n",
"File \u001b[0;32m~/anaconda3/envs/ml-industry/lib/python3.12/site-packages/sklearn/base.py:1098\u001b[0m, in \u001b[0;36mTransformerMixin.fit_transform\u001b[0;34m(self, X, y, **fit_params)\u001b[0m\n\u001b[1;32m 1083\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[1;32m 1084\u001b[0m (\n\u001b[1;32m 1085\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThis object (\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m) has a `transform`\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1093\u001b[0m \u001b[38;5;167;01mUserWarning\u001b[39;00m,\n\u001b[1;32m 1094\u001b[0m )\n\u001b[1;32m 1096\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m y \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 1097\u001b[0m \u001b[38;5;66;03m# fit method of arity 1 (unsupervised transformation)\u001b[39;00m\n\u001b[0;32m-> 1098\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\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[43mfit_params\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mtransform(X)\n\u001b[1;32m 1099\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1100\u001b[0m \u001b[38;5;66;03m# fit method of arity 2 (supervised transformation)\u001b[39;00m\n\u001b[1;32m 1101\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfit(X, y, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfit_params)\u001b[38;5;241m.\u001b[39mtransform(X)\n",
"File \u001b[0;32m~/anaconda3/envs/ml-industry/lib/python3.12/site-packages/sklearn/preprocessing/_data.py:878\u001b[0m, in \u001b[0;36mStandardScaler.fit\u001b[0;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[1;32m 876\u001b[0m \u001b[38;5;66;03m# Reset internal state before fitting\u001b[39;00m\n\u001b[1;32m 877\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reset()\n\u001b[0;32m--> 878\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpartial_fit\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[43msample_weight\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/anaconda3/envs/ml-industry/lib/python3.12/site-packages/sklearn/base.py:1473\u001b[0m, in \u001b[0;36m_fit_context.<locals>.decorator.<locals>.wrapper\u001b[0;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1466\u001b[0m estimator\u001b[38;5;241m.\u001b[39m_validate_params()\n\u001b[1;32m 1468\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[1;32m 1469\u001b[0m skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[1;32m 1470\u001b[0m prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[1;32m 1471\u001b[0m )\n\u001b[1;32m 1472\u001b[0m ):\n\u001b[0;32m-> 1473\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfit_method\u001b[49m\u001b[43m(\u001b[49m\u001b[43mestimator\u001b[49m\u001b[43m,\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",
"File \u001b[0;32m~/anaconda3/envs/ml-industry/lib/python3.12/site-packages/sklearn/preprocessing/_data.py:914\u001b[0m, in \u001b[0;36mStandardScaler.partial_fit\u001b[0;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[1;32m 882\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Online computation of mean and std on X for later scaling.\u001b[39;00m\n\u001b[1;32m 883\u001b[0m \n\u001b[1;32m 884\u001b[0m \u001b[38;5;124;03mAll of X is processed as a single batch. This is intended for cases\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 911\u001b[0m \u001b[38;5;124;03m Fitted scaler.\u001b[39;00m\n\u001b[1;32m 912\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 913\u001b[0m first_call \u001b[38;5;241m=\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mn_samples_seen_\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 914\u001b[0m X \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_validate_data\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 915\u001b[0m \u001b[43m \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 916\u001b[0m \u001b[43m \u001b[49m\u001b[43maccept_sparse\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcsr\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mcsc\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 917\u001b[0m \u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mFLOAT_DTYPES\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 918\u001b[0m \u001b[43m \u001b[49m\u001b[43mforce_all_finite\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mallow-nan\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 919\u001b[0m \u001b[43m \u001b[49m\u001b[43mreset\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfirst_call\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 920\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 921\u001b[0m n_features \u001b[38;5;241m=\u001b[39m X\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m1\u001b[39m]\n\u001b[1;32m 923\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m sample_weight \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
"File \u001b[0;32m~/anaconda3/envs/ml-industry/lib/python3.12/site-packages/sklearn/base.py:633\u001b[0m, in \u001b[0;36mBaseEstimator._validate_data\u001b[0;34m(self, X, y, reset, validate_separately, cast_to_ndarray, **check_params)\u001b[0m\n\u001b[1;32m 631\u001b[0m out \u001b[38;5;241m=\u001b[39m X, y\n\u001b[1;32m 632\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m no_val_X \u001b[38;5;129;01mand\u001b[39;00m no_val_y:\n\u001b[0;32m--> 633\u001b[0m out \u001b[38;5;241m=\u001b[39m \u001b[43mcheck_array\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minput_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mX\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;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[43mcheck_params\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 634\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m no_val_X \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m no_val_y:\n\u001b[1;32m 635\u001b[0m out \u001b[38;5;241m=\u001b[39m _check_y(y, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mcheck_params)\n",
"File \u001b[0;32m~/anaconda3/envs/ml-industry/lib/python3.12/site-packages/sklearn/utils/validation.py:1087\u001b[0m, in \u001b[0;36mcheck_array\u001b[0;34m(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_writeable, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator, input_name)\u001b[0m\n\u001b[1;32m 1085\u001b[0m n_samples \u001b[38;5;241m=\u001b[39m _num_samples(array)\n\u001b[1;32m 1086\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m n_samples \u001b[38;5;241m<\u001b[39m ensure_min_samples:\n\u001b[0;32m-> 1087\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 1088\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFound array with \u001b[39m\u001b[38;5;132;01m%d\u001b[39;00m\u001b[38;5;124m sample(s) (shape=\u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m) while a\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1089\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m minimum of \u001b[39m\u001b[38;5;132;01m%d\u001b[39;00m\u001b[38;5;124m is required\u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 1090\u001b[0m \u001b[38;5;241m%\u001b[39m (n_samples, array\u001b[38;5;241m.\u001b[39mshape, ensure_min_samples, context)\n\u001b[1;32m 1091\u001b[0m )\n\u001b[1;32m 1093\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m ensure_min_features \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m array\u001b[38;5;241m.\u001b[39mndim \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m2\u001b[39m:\n\u001b[1;32m 1094\u001b[0m n_features \u001b[38;5;241m=\u001b[39m array\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m1\u001b[39m]\n",
"\u001b[0;31mValueError\u001b[0m: Found array with 0 sample(s) (shape=(0, 92)) while a minimum of 1 is required by StandardScaler."
]
}
],
"source": [
"test_data = create_features_and_targets(\n",
" data=dataset,\n",
" target_particle=\"NO2\",\n",
" lag_days=7,\n",
" sma_days=7,\n",
" days_ahead=3,\n",
")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "ml-industry",
"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": "3.12.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|