Merge branch 'mmj'

"asdasd#"

t
exit

data_api_calls.py

@@ -1,13 +1,15 @@
+import codecs
+import csv
 import http.client
-from datetime import date, timedelta
-import pandas as pd
-from io import StringIO
 import os
 import re
-import csv
-import urllib.request
 import sys
-import codecs
+import urllib.request
+from datetime import date, timedelta
+from io import StringIO
+
+import pandas as pd
+
 
 def pollution_data():
     particles = ["NO2", "O3"]
@@ -15,7 +17,7 @@ def pollution_data():
     all_dataframes = []
     today = date.today().isoformat() + "T09:00:00Z"
     yesterday = (date.today() - timedelta(1)).isoformat() + "T09:00:00Z"
-    latest_date = (date.today() - timedelta(7)).isoformat() + "T09:00:00Z"
+    latest_date = (date.today() - timedelta(8)).isoformat() + "T09:00:00Z"
     days_today = 0
     days_yesterday = 1
     while(today != latest_date):
@@ -50,7 +52,7 @@ def clean_values():
     O3 = []
     today = date.today().isoformat() + "T09:00:00Z"
     yesterday = (date.today() - timedelta(1)).isoformat() + "T09:00:00Z"
-    latest_date = (date.today() - timedelta(7)).isoformat() + "T09:00:00Z"
+    latest_date = (date.today() - timedelta(8)).isoformat() + "T09:00:00Z"
     days_today = 0
     while(today != latest_date):
         for particle in particles:
@@ -140,10 +142,10 @@ def scale():
     df['humidity'] = df['humidity'].astype(int)
     df['global_radiation'] = df['global_radiation'].astype(int)
 
-    df.to_csv('recorded_data.csv', index=False)
+    df.to_csv('dataset.csv', index=False)
 
 def insert_pollution(NO2, O3):
-    file_path = 'recorded_data.csv'
+    file_path = 'dataset.csv'
     df = pd.read_csv(file_path)
     start_index = 0
     while NO2:
@@ -157,7 +159,7 @@ def insert_pollution(NO2, O3):
 
 def weather_data():
   today = date.today().isoformat()
-  seven_days = (date.today() - timedelta(6)).isoformat()
+  seven_days = (date.today() - timedelta(7)).isoformat()
   try: 
     ResultBytes = urllib.request.urlopen(f"https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/Utrecht/{seven_days}/{today}?unitGroup=metric&elements=datetime%2Cwindspeed%2Ctemp%2Csolarradiation%2Cprecip%2Cpressure%2Cvisibility%2Chumidity&include=days&key=7Y6AY56M6RWVNHQ3SAVHNJWFS&maxStations=1&contentType=csv")
     

dataset.csv

@@ -1,8 +1,9 @@
 date,NO2,O3,wind_speed,mean_temp,global_radiation,percipitation,pressure,minimum_visibility,humidity,weekday
+2024-10-15,22.853627569528417,22.52299076212471,51,87,71,0,10194,290,86,Tuesday
 2024-10-16,22.4144459833795,22.78109803921569,61,151,40,0,10103,358,82,Wednesday
 2024-10-17,22.990465489566613,22.928154311649017,51,169,43,6,10100,371,86,Thursday
 2024-10-18,23.659013539651834,23.700536672629696,21,156,42,39,10140,64,97,Friday
 2024-10-19,24.727853658536585,23.52574561403509,43,147,43,28,10140,236,92,Saturday
 2024-10-20,22.700366666666664,24.317572254335257,68,145,0,0,10160,241,82,Sunday
 2024-10-21,19.763439153439155,25.661659574468086,66,142,27,39,10201,110,90,Monday
-2024-10-22,20.281666666666666,25.787520661157025,76,120,54,97,10266,128,87,Tuesday
+2024-10-22,20.281666666666666,25.787520661157025,76,121,54,97,10266,116,87,Tuesday

src/data_loading.py

@@ -162,17 +162,17 @@ def create_features_and_targets(
 
     # Create particle data (NO2 and O3) from the same time last year
     # Today last year
-    data["O3_last_year"] = data["O3"].shift(365)
-    data["NO2_last_year"] = data["NO2"].shift(365)
+    data["O3_last_year"] = 0 # data["O3_last_year"] = data["O3"].shift(365)
+    data["NO2_last_year"] = 0 # data["NO2_last_year"] = data["NO2"].shift(365)
 
     # 7 days before today last year
     for i in range(1, lag_days + 1):
-        data[f"O3_last_year_{i}_days_before"] = data["O3"].shift(365 + i)
-        data[f"NO2_last_year_{i}_days_before"] = data["NO2"].shift(365 + i)
+        data[f"O3_last_year_{i}_days_before"] = 0 # data["O3"].shift(365 + i)
+        data[f"NO2_last_year_{i}_days_before"] = 0 # data["NO2"].shift(365 + i)
 
     # 3 days after today last year
-    data["O3_last_year_3_days_after"] = data["O3"].shift(365 - 3)
-    data["NO2_last_year_3_days_after"] = data["NO2"].shift(365 - 3)
+    data["O3_last_year_3_days_after"] = 0 # data["O3"].shift(365 - 3)
+    data["NO2_last_year_3_days_after"] = 0 # data["NO2"].shift(365 - 3)
 
     # Calculate the number of rows before dropping missing values
     rows_before = data.shape[0]
@@ -209,4 +209,4 @@ def create_features_and_targets(
         X_scaled, columns=feature_cols, index=x.index
     )
 
-    return X_scaled
+    return x

test.ipynb

@@ -13,7 +13,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -22,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -31,25 +31,6 @@
      "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": [
@@ -61,6 +42,126 @@
     "    days_ahead=3,\n",
     ")"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "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>NO2</th>\n",
+       "      <th>O3</th>\n",
+       "      <th>wind_speed</th>\n",
+       "      <th>mean_temp</th>\n",
+       "      <th>global_radiation</th>\n",
+       "      <th>percipitation</th>\n",
+       "      <th>pressure</th>\n",
+       "      <th>minimum_visibility</th>\n",
+       "      <th>humidity</th>\n",
+       "      <th>weekday_sin</th>\n",
+       "      <th>...</th>\n",
+       "      <th>O3_last_year_4_days_before</th>\n",
+       "      <th>NO2_last_year_4_days_before</th>\n",
+       "      <th>O3_last_year_5_days_before</th>\n",
+       "      <th>NO2_last_year_5_days_before</th>\n",
+       "      <th>O3_last_year_6_days_before</th>\n",
+       "      <th>NO2_last_year_6_days_before</th>\n",
+       "      <th>O3_last_year_7_days_before</th>\n",
+       "      <th>NO2_last_year_7_days_before</th>\n",
+       "      <th>O3_last_year_3_days_after</th>\n",
+       "      <th>NO2_last_year_3_days_after</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>20.281667</td>\n",
+       "      <td>25.787521</td>\n",
+       "      <td>76</td>\n",
+       "      <td>121</td>\n",
+       "      <td>54</td>\n",
+       "      <td>97</td>\n",
+       "      <td>10266</td>\n",
+       "      <td>116</td>\n",
+       "      <td>87</td>\n",
+       "      <td>0.781831</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1 rows × 103 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         NO2         O3  wind_speed  mean_temp  global_radiation  \\\n",
+       "0  20.281667  25.787521          76        121                54   \n",
+       "\n",
+       "   percipitation  pressure  minimum_visibility  humidity  weekday_sin  ...  \\\n",
+       "0             97     10266                 116        87     0.781831  ...   \n",
+       "\n",
+       "   O3_last_year_4_days_before  NO2_last_year_4_days_before  \\\n",
+       "0                           0                            0   \n",
+       "\n",
+       "   O3_last_year_5_days_before  NO2_last_year_5_days_before  \\\n",
+       "0                           0                            0   \n",
+       "\n",
+       "   O3_last_year_6_days_before  NO2_last_year_6_days_before  \\\n",
+       "0                           0                            0   \n",
+       "\n",
+       "   O3_last_year_7_days_before  NO2_last_year_7_days_before  \\\n",
+       "0                           0                            0   \n",
+       "\n",
+       "   O3_last_year_3_days_after  NO2_last_year_3_days_after  \n",
+       "0                          0                           0  \n",
+       "\n",
+       "[1 rows x 103 columns]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {