stupid api

pollution_data.csv

@@ -2,8 +2,8 @@ date,NO2,O3
 2024-10-17,22.804605103280675,22.769159859976643
 2024-10-18,23.2685,23.30733245729302
 2024-10-19,23.91006441223834,23.1717142857143
-2024-10-20,22.573237547892735,23.53784452296821
-2024-10-21,21.1457004830918,24.020695652173934
+2024-10-20,22.57323754789273,23.53784452296821
+2024-10-21,21.1457004830918,24.02069565217393
 2024-10-22,21.776579804560274,23.33588571428572
 2024-10-23,21.974793814433,22.21468879668051
 2024-10-24,25.51256756756757,20.91370967741937

scalers/feature_scaler_NO2.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6281e460d3a5a83a3d6a240aa76c26e45bd15089364b88d3a26fd638536a30b5
+oid sha256:4d2731707963125bbb452df55c91920c62eb745c7e78c0a79bdf7fab173b3369
 size 5791

src/data_api_calls.py

@@ -142,11 +142,19 @@ def get_combined_data():
     update_pollution_data()
 
     weather_df = pd.read_csv(WEATHER_DATA_FILE)
-    pollution_df = pd.read_csv(POLLUTION_DATA_FILE)
 
-    # Average NO2 and O3 values by date and add them to weather data
-    combined_df = pd.merge(weather_df, pollution_df, on="date", how="left")
-    combined_df.fillna(0, inplace=True)
+    weather_df.insert(1, "NO2", None)
+    weather_df.insert(2, "O3", None)
+    weather_df.insert(10, "weekday", None)
+    columns = list(weather_df.columns)
+    columns.insert(3, columns.pop(6))
+    weather_df = weather_df[columns]
+    columns.insert(5, columns.pop(9))
+    weather_df = weather_df[columns]
+    columns.insert(9, columns.pop(6))
+    weather_df = weather_df[columns]
+    
+    combined_df = weather_df
 
     # Apply scaling and renaming similar to the scale function from previous code
     combined_df = combined_df.rename(
@@ -177,5 +185,9 @@ def get_combined_data():
     combined_df["pressure"] = combined_df["pressure"].astype(int)
     combined_df["humidity"] = combined_df["humidity"].astype(int)
     combined_df["global_radiation"] = combined_df["global_radiation"].astype(int)
+    
+    pollution_df = pd.read_csv(POLLUTION_DATA_FILE)
+    combined_df["NO2"] = pollution_df["NO2"]
+    combined_df["O3"] = pollution_df["O3"]
 
     return combined_df

src/features_pipeline.py

@@ -3,7 +3,6 @@ import warnings
 import joblib
 import numpy as np
 import pandas as pd
-
 from src.past_data_api_calls import get_past_combined_data
 
 warnings.filterwarnings("ignore")

src/past_data_api_calls.py

@@ -15,8 +15,8 @@ PAST_POLLUTION_DATA_FILE = "pollution_data.csv"
 
 def get_past_weather_data():
     last_year_date = date.today() - timedelta(days=365)
-    start_date = (last_year_date - timedelta(days=7)).isoformat()
-    end_date = (last_year_date + timedelta(days=3)).isoformat()
+    start_date = (last_year_date - timedelta(days=8)).isoformat()
+    end_date = (last_year_date + timedelta(days=2)).isoformat()
 
     try:
         ResultBytes = urllib.request.urlopen(

src/predict.py

@@ -1,15 +1,14 @@
 import os
+from datetime import date, timedelta
 
 import joblib
-import streamlit as st
+import pandas as pd
 from dotenv import load_dotenv
 from huggingface_hub import hf_hub_download, login
-
 from src.data_api_calls import get_combined_data
 from src.features_pipeline import create_features
 
 
-@st.cache_resource()
 def load_model(particle):
     load_dotenv()
     login(token=os.getenv("HUGGINGFACE_DOWNLOAD_TOKEN"))
@@ -39,9 +38,33 @@ def get_data_and_predictions():
 
     week_data = get_combined_data()
 
-    o3_input_features = create_features(week_data, "O3")
-    no2_input_features = create_features(week_data, "NO2")
-    o3_predictions = run_model("O3", data=o3_input_features)
-    no2_predictions = run_model("NO2", data=no2_input_features)
+    o3_predictions = run_model("O3", data=week_data)
+    no2_predictions = run_model("NO2", data=week_data)
+
+    prediction_data = []
+    for i in range(3):
+        prediction_data.append(
+            {
+                "pollutant": "O3",
+                "date_predicted": date.today(),
+                "date": date.today() + timedelta(days=i + 1),
+                "prediction_value": o3_predictions[i],
+            }
+        )
+        prediction_data.append(
+            {
+                "pollutant": "NO2",
+                "date_predicted": date.today(),
+                "date": date.today() + timedelta(days=i + 1),
+                "prediction_value": no2_predictions[i],
+            }
+        )
+
+    predictions_df = pd.DataFrame(prediction_data)
+
+    if os.path.exists(PREDICTIONS_FILE):
+        predictions_df.to_csv(PREDICTIONS_FILE, mode="a", header=False, index=False)
+    else:
+        predictions_df.to_csv(PREDICTIONS_FILE, mode="w", header=True, index=False)
 
     return week_data, o3_predictions, no2_predictions

test.ipynb

@@ -15,43 +15,31 @@
     }
    ],
    "source": [
-    "from src.data_api_calls import get_combined_data\n",
-    "from src.past_data_api_calls import get_past_combined_data\n",
     "from src.predict import get_data_and_predictions"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "get_past_combined_data()"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
-     "ename": "OSError",
-     "evalue": "[Errno 22] Invalid argument: 'NO2_2023-10-18T09:00:00Z.csv'",
+     "ename": "ValueError",
+     "evalue": "Length of values (0) does not match length of index (11)",
      "output_type": "error",
      "traceback": [
       "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mOSError\u001b[0m                                   Traceback (most recent call last)",
+      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
       "Cell \u001b[1;32mIn[2], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m week_data, predictions_O3, predictions_NO2 \u001b[38;5;241m=\u001b[39m \u001b[43mget_data_and_predictions\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\predict.py:42\u001b[0m, in \u001b[0;36mget_data_and_predictions\u001b[1;34m()\u001b[0m\n\u001b[0;32m     38\u001b[0m PREDICTIONS_FILE \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpredictions_history.csv\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m     40\u001b[0m week_data \u001b[38;5;241m=\u001b[39m get_combined_data()\n\u001b[1;32m---> 42\u001b[0m o3_input_features \u001b[38;5;241m=\u001b[39m \u001b[43mcreate_features\u001b[49m\u001b[43m(\u001b[49m\u001b[43mweek_data\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mO3\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m     43\u001b[0m no2_input_features \u001b[38;5;241m=\u001b[39m create_features(week_data, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNO2\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m     44\u001b[0m o3_predictions \u001b[38;5;241m=\u001b[39m run_model(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mO3\u001b[39m\u001b[38;5;124m\"\u001b[39m, data\u001b[38;5;241m=\u001b[39mo3_input_features)\n",
-      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\features_pipeline.py:61\u001b[0m, in \u001b[0;36mcreate_features\u001b[1;34m(data, target_particle, lag_days, sma_days)\u001b[0m\n\u001b[0;32m     56\u001b[0m     data[\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfeature\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m_sma_\u001b[39m\u001b[38;5;132;01m{\u001b[39;00msma_days\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m     57\u001b[0m         data[feature]\u001b[38;5;241m.\u001b[39mrolling(window\u001b[38;5;241m=\u001b[39msma_days)\u001b[38;5;241m.\u001b[39mmean()\n\u001b[0;32m     58\u001b[0m     )\n\u001b[0;32m     60\u001b[0m \u001b[38;5;66;03m# Create particle data (NO2 and O3) from the same time last year\u001b[39;00m\n\u001b[1;32m---> 61\u001b[0m past_data \u001b[38;5;241m=\u001b[39m \u001b[43mget_past_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     63\u001b[0m \u001b[38;5;66;03m# Today last year\u001b[39;00m\n\u001b[0;32m     64\u001b[0m data[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mO3_last_year\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m past_data[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mO3\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39miloc[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m4\u001b[39m]\n",
-      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\past_data_api_calls.py:193\u001b[0m, in \u001b[0;36mget_past_data\u001b[1;34m()\u001b[0m\n\u001b[0;32m    191\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mget_past_data\u001b[39m():\n\u001b[0;32m    192\u001b[0m     weather_data()\n\u001b[1;32m--> 193\u001b[0m     \u001b[43mpollution_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    194\u001b[0m     NO2, O3 \u001b[38;5;241m=\u001b[39m clean_values()\n\u001b[0;32m    195\u001b[0m     df \u001b[38;5;241m=\u001b[39m add_columns()\n",
-      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\past_data_api_calls.py:46\u001b[0m, in \u001b[0;36mpollution_data\u001b[1;34m()\u001b[0m\n\u001b[0;32m     44\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m all_dataframes:\n\u001b[0;32m     45\u001b[0m     combined_data \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mconcat(all_dataframes, ignore_index\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m---> 46\u001b[0m     \u001b[43mcombined_data\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mparticle\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m_\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mtoday\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m.csv\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindex\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\util\\_decorators.py:333\u001b[0m, in \u001b[0;36mdeprecate_nonkeyword_arguments.<locals>.decorate.<locals>.wrapper\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    327\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m>\u001b[39m num_allow_args:\n\u001b[0;32m    328\u001b[0m     warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[0;32m    329\u001b[0m         msg\u001b[38;5;241m.\u001b[39mformat(arguments\u001b[38;5;241m=\u001b[39m_format_argument_list(allow_args)),\n\u001b[0;32m    330\u001b[0m         \u001b[38;5;167;01mFutureWarning\u001b[39;00m,\n\u001b[0;32m    331\u001b[0m         stacklevel\u001b[38;5;241m=\u001b[39mfind_stack_level(),\n\u001b[0;32m    332\u001b[0m     )\n\u001b[1;32m--> 333\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",
-      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\core\\generic.py:3967\u001b[0m, in \u001b[0;36mNDFrame.to_csv\u001b[1;34m(self, path_or_buf, sep, na_rep, float_format, columns, header, index, index_label, mode, encoding, compression, quoting, quotechar, lineterminator, chunksize, date_format, doublequote, escapechar, decimal, errors, storage_options)\u001b[0m\n\u001b[0;32m   3956\u001b[0m df \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m, ABCDataFrame) \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mto_frame()\n\u001b[0;32m   3958\u001b[0m formatter \u001b[38;5;241m=\u001b[39m DataFrameFormatter(\n\u001b[0;32m   3959\u001b[0m     frame\u001b[38;5;241m=\u001b[39mdf,\n\u001b[0;32m   3960\u001b[0m     header\u001b[38;5;241m=\u001b[39mheader,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   3964\u001b[0m     decimal\u001b[38;5;241m=\u001b[39mdecimal,\n\u001b[0;32m   3965\u001b[0m )\n\u001b[1;32m-> 3967\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mDataFrameRenderer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mformatter\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_csv\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   3968\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpath_or_buf\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3969\u001b[0m \u001b[43m    \u001b[49m\u001b[43mlineterminator\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlineterminator\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3970\u001b[0m \u001b[43m    \u001b[49m\u001b[43msep\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msep\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3971\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3972\u001b[0m \u001b[43m    \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3973\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcompression\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcompression\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3974\u001b[0m \u001b[43m    \u001b[49m\u001b[43mquoting\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mquoting\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3975\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcolumns\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3976\u001b[0m \u001b[43m    \u001b[49m\u001b[43mindex_label\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mindex_label\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3977\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3978\u001b[0m \u001b[43m    \u001b[49m\u001b[43mchunksize\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mchunksize\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3979\u001b[0m \u001b[43m    \u001b[49m\u001b[43mquotechar\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mquotechar\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3980\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdate_format\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdate_format\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3981\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdoublequote\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdoublequote\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3982\u001b[0m \u001b[43m    \u001b[49m\u001b[43mescapechar\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mescapechar\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3983\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstorage_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   3984\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\io\\formats\\format.py:1014\u001b[0m, in \u001b[0;36mDataFrameRenderer.to_csv\u001b[1;34m(self, path_or_buf, encoding, sep, columns, index_label, mode, compression, quoting, quotechar, lineterminator, chunksize, date_format, doublequote, escapechar, errors, storage_options)\u001b[0m\n\u001b[0;32m    993\u001b[0m     created_buffer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[0;32m    995\u001b[0m csv_formatter \u001b[38;5;241m=\u001b[39m CSVFormatter(\n\u001b[0;32m    996\u001b[0m     path_or_buf\u001b[38;5;241m=\u001b[39mpath_or_buf,\n\u001b[0;32m    997\u001b[0m     lineterminator\u001b[38;5;241m=\u001b[39mlineterminator,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1012\u001b[0m     formatter\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfmt,\n\u001b[0;32m   1013\u001b[0m )\n\u001b[1;32m-> 1014\u001b[0m \u001b[43mcsv_formatter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msave\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1016\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m created_buffer:\n\u001b[0;32m   1017\u001b[0m     \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(path_or_buf, StringIO)\n",
-      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\io\\formats\\csvs.py:251\u001b[0m, in \u001b[0;36mCSVFormatter.save\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    247\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    248\u001b[0m \u001b[38;5;124;03mCreate the writer & save.\u001b[39;00m\n\u001b[0;32m    249\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    250\u001b[0m \u001b[38;5;66;03m# apply compression and byte/text conversion\u001b[39;00m\n\u001b[1;32m--> 251\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[43mget_handle\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    252\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    253\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    254\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    255\u001b[0m \u001b[43m    \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    256\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcompression\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcompression\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    257\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstorage_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    258\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m handles:\n\u001b[0;32m    259\u001b[0m     \u001b[38;5;66;03m# Note: self.encoding is irrelevant here\u001b[39;00m\n\u001b[0;32m    260\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mwriter \u001b[38;5;241m=\u001b[39m csvlib\u001b[38;5;241m.\u001b[39mwriter(\n\u001b[0;32m    261\u001b[0m         handles\u001b[38;5;241m.\u001b[39mhandle,\n\u001b[0;32m    262\u001b[0m         lineterminator\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlineterminator,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    267\u001b[0m         quotechar\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mquotechar,\n\u001b[0;32m    268\u001b[0m     )\n\u001b[0;32m    270\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_save()\n",
-      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\io\\common.py:873\u001b[0m, in \u001b[0;36mget_handle\u001b[1;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[0;32m    868\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(handle, \u001b[38;5;28mstr\u001b[39m):\n\u001b[0;32m    869\u001b[0m     \u001b[38;5;66;03m# Check whether the filename is to be opened in binary mode.\u001b[39;00m\n\u001b[0;32m    870\u001b[0m     \u001b[38;5;66;03m# Binary mode does not support 'encoding' and 'newline'.\u001b[39;00m\n\u001b[0;32m    871\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mencoding \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ioargs\u001b[38;5;241m.\u001b[39mmode:\n\u001b[0;32m    872\u001b[0m         \u001b[38;5;66;03m# Encoding\u001b[39;00m\n\u001b[1;32m--> 873\u001b[0m         handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(\n\u001b[0;32m    874\u001b[0m             handle,\n\u001b[0;32m    875\u001b[0m             ioargs\u001b[38;5;241m.\u001b[39mmode,\n\u001b[0;32m    876\u001b[0m             encoding\u001b[38;5;241m=\u001b[39mioargs\u001b[38;5;241m.\u001b[39mencoding,\n\u001b[0;32m    877\u001b[0m             errors\u001b[38;5;241m=\u001b[39merrors,\n\u001b[0;32m    878\u001b[0m             newline\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m    879\u001b[0m         )\n\u001b[0;32m    880\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m    881\u001b[0m         \u001b[38;5;66;03m# Binary mode\u001b[39;00m\n\u001b[0;32m    882\u001b[0m         handle \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mopen\u001b[39m(handle, ioargs\u001b[38;5;241m.\u001b[39mmode)\n",
-      "\u001b[1;31mOSError\u001b[0m: [Errno 22] Invalid argument: 'NO2_2023-10-18T09:00:00Z.csv'"
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\predict.py:41\u001b[0m, in \u001b[0;36mget_data_and_predictions\u001b[1;34m()\u001b[0m\n\u001b[0;32m     37\u001b[0m PREDICTIONS_FILE \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpredictions_history.csv\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m     39\u001b[0m week_data \u001b[38;5;241m=\u001b[39m get_combined_data()\n\u001b[1;32m---> 41\u001b[0m o3_predictions \u001b[38;5;241m=\u001b[39m \u001b[43mrun_model\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mO3\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mweek_data\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     42\u001b[0m no2_predictions \u001b[38;5;241m=\u001b[39m run_model(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNO2\u001b[39m\u001b[38;5;124m\"\u001b[39m, data\u001b[38;5;241m=\u001b[39mweek_data)\n\u001b[0;32m     44\u001b[0m prediction_data \u001b[38;5;241m=\u001b[39m []\n",
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\predict.py:28\u001b[0m, in \u001b[0;36mrun_model\u001b[1;34m(particle, data)\u001b[0m\n\u001b[0;32m     27\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mrun_model\u001b[39m(particle, data):\n\u001b[1;32m---> 28\u001b[0m     input_data \u001b[38;5;241m=\u001b[39m \u001b[43mcreate_features\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtarget_particle\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparticle\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     29\u001b[0m     model \u001b[38;5;241m=\u001b[39m load_model(particle)\n\u001b[0;32m     30\u001b[0m     prediction \u001b[38;5;241m=\u001b[39m model\u001b[38;5;241m.\u001b[39mpredict(input_data)\n",
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\features_pipeline.py:60\u001b[0m, in \u001b[0;36mcreate_features\u001b[1;34m(data, target_particle, lag_days, sma_days)\u001b[0m\n\u001b[0;32m     55\u001b[0m     data[\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfeature\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m_sma_\u001b[39m\u001b[38;5;132;01m{\u001b[39;00msma_days\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m     56\u001b[0m         data[feature]\u001b[38;5;241m.\u001b[39mrolling(window\u001b[38;5;241m=\u001b[39msma_days)\u001b[38;5;241m.\u001b[39mmean()\n\u001b[0;32m     57\u001b[0m     )\n\u001b[0;32m     59\u001b[0m \u001b[38;5;66;03m# Create particle data (NO2 and O3) from the same time last year\u001b[39;00m\n\u001b[1;32m---> 60\u001b[0m past_data \u001b[38;5;241m=\u001b[39m \u001b[43mget_past_combined_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     62\u001b[0m \u001b[38;5;66;03m# Today last year\u001b[39;00m\n\u001b[0;32m     63\u001b[0m data[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mO3_last_year\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m past_data[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mO3\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39miloc[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m4\u001b[39m]\n",
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\past_data_api_calls.py:99\u001b[0m, in \u001b[0;36mget_past_combined_data\u001b[1;34m()\u001b[0m\n\u001b[0;32m     96\u001b[0m NO2_df, O3_df \u001b[38;5;241m=\u001b[39m get_past_pollution_data()\n\u001b[0;32m     98\u001b[0m combined_df \u001b[38;5;241m=\u001b[39m weather_df\n\u001b[1;32m---> 99\u001b[0m \u001b[43mcombined_df\u001b[49m\u001b[43m[\u001b[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 \u001b[38;5;241m=\u001b[39m NO2_df\n\u001b[0;32m    100\u001b[0m combined_df[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mO3\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m O3_df\n\u001b[0;32m    102\u001b[0m \u001b[38;5;66;03m# Apply scaling and renaming similar to the scale function from previous code\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\core\\frame.py:4311\u001b[0m, in \u001b[0;36mDataFrame.__setitem__\u001b[1;34m(self, key, value)\u001b[0m\n\u001b[0;32m   4308\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_setitem_array([key], value)\n\u001b[0;32m   4309\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m   4310\u001b[0m     \u001b[38;5;66;03m# set column\u001b[39;00m\n\u001b[1;32m-> 4311\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_set_item\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\core\\frame.py:4524\u001b[0m, in \u001b[0;36mDataFrame._set_item\u001b[1;34m(self, key, value)\u001b[0m\n\u001b[0;32m   4514\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_set_item\u001b[39m(\u001b[38;5;28mself\u001b[39m, key, value) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m   4515\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m   4516\u001b[0m \u001b[38;5;124;03m    Add series to DataFrame in specified column.\u001b[39;00m\n\u001b[0;32m   4517\u001b[0m \n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   4522\u001b[0m \u001b[38;5;124;03m    ensure homogeneity.\u001b[39;00m\n\u001b[0;32m   4523\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[1;32m-> 4524\u001b[0m     value, refs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sanitize_column\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   4526\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[0;32m   4527\u001b[0m         key \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns\n\u001b[0;32m   4528\u001b[0m         \u001b[38;5;129;01mand\u001b[39;00m value\u001b[38;5;241m.\u001b[39mndim \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m   4529\u001b[0m         \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(value\u001b[38;5;241m.\u001b[39mdtype, ExtensionDtype)\n\u001b[0;32m   4530\u001b[0m     ):\n\u001b[0;32m   4531\u001b[0m         \u001b[38;5;66;03m# broadcast across multiple columns if necessary\u001b[39;00m\n\u001b[0;32m   4532\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns\u001b[38;5;241m.\u001b[39mis_unique \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns, MultiIndex):\n",
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\core\\frame.py:5266\u001b[0m, in \u001b[0;36mDataFrame._sanitize_column\u001b[1;34m(self, value)\u001b[0m\n\u001b[0;32m   5263\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m _reindex_for_setitem(value, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mindex)\n\u001b[0;32m   5265\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_list_like(value):\n\u001b[1;32m-> 5266\u001b[0m     \u001b[43mcom\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequire_length_match\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mindex\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   5267\u001b[0m arr \u001b[38;5;241m=\u001b[39m sanitize_array(value, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mindex, copy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m, allow_2d\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m   5268\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[0;32m   5269\u001b[0m     \u001b[38;5;28misinstance\u001b[39m(value, Index)\n\u001b[0;32m   5270\u001b[0m     \u001b[38;5;129;01mand\u001b[39;00m value\u001b[38;5;241m.\u001b[39mdtype \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mobject\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   5273\u001b[0m     \u001b[38;5;66;03m# TODO: Remove kludge in sanitize_array for string mode when enforcing\u001b[39;00m\n\u001b[0;32m   5274\u001b[0m     \u001b[38;5;66;03m# this deprecation\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\core\\common.py:573\u001b[0m, in \u001b[0;36mrequire_length_match\u001b[1;34m(data, index)\u001b[0m\n\u001b[0;32m    569\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    570\u001b[0m \u001b[38;5;124;03mCheck the length of data matches the length of the index.\u001b[39;00m\n\u001b[0;32m    571\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    572\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(data) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;28mlen\u001b[39m(index):\n\u001b[1;32m--> 573\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m    574\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLength of values \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    575\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m(\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlen\u001b[39m(data)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m) \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    576\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdoes not match length of index \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    577\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m(\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlen\u001b[39m(index)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m)\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    578\u001b[0m     )\n",
+      "\u001b[1;31mValueError\u001b[0m: Length of values (0) does not match length of index (11)"
      ]
     }
    ],