{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "from src.predict import get_data_and_predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "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;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: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)"
     ]
    }
   ],
   "source": [
    "week_data, predictions_O3, predictions_NO2 = get_data_and_predictions()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "week_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv(\"dataset.csv\")\n",
    "target_particle = \"O3\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>date</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</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2024-10-16</td>\n",
       "      <td>22.602712</td>\n",
       "      <td>22.881288</td>\n",
       "      <td>61</td>\n",
       "      <td>151</td>\n",
       "      <td>40</td>\n",
       "      <td>0</td>\n",
       "      <td>10103</td>\n",
       "      <td>358</td>\n",
       "      <td>82</td>\n",
       "      <td>Wednesday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2024-10-17</td>\n",
       "      <td>23.104327</td>\n",
       "      <td>23.038638</td>\n",
       "      <td>51</td>\n",
       "      <td>169</td>\n",
       "      <td>43</td>\n",
       "      <td>6</td>\n",
       "      <td>10100</td>\n",
       "      <td>371</td>\n",
       "      <td>86</td>\n",
       "      <td>Thursday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2024-10-18</td>\n",
       "      <td>23.682857</td>\n",
       "      <td>23.716611</td>\n",
       "      <td>21</td>\n",
       "      <td>156</td>\n",
       "      <td>42</td>\n",
       "      <td>39</td>\n",
       "      <td>10140</td>\n",
       "      <td>64</td>\n",
       "      <td>97</td>\n",
       "      <td>Friday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2024-10-19</td>\n",
       "      <td>24.532039</td>\n",
       "      <td>23.604723</td>\n",
       "      <td>43</td>\n",
       "      <td>147</td>\n",
       "      <td>43</td>\n",
       "      <td>28</td>\n",
       "      <td>10140</td>\n",
       "      <td>236</td>\n",
       "      <td>92</td>\n",
       "      <td>Saturday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2024-10-20</td>\n",
       "      <td>23.019102</td>\n",
       "      <td>24.173377</td>\n",
       "      <td>68</td>\n",
       "      <td>145</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>10160</td>\n",
       "      <td>241</td>\n",
       "      <td>82</td>\n",
       "      <td>Sunday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2024-10-21</td>\n",
       "      <td>21.275629</td>\n",
       "      <td>25.058736</td>\n",
       "      <td>58</td>\n",
       "      <td>144</td>\n",
       "      <td>27</td>\n",
       "      <td>43</td>\n",
       "      <td>10206</td>\n",
       "      <td>220</td>\n",
       "      <td>92</td>\n",
       "      <td>Monday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2024-10-22</td>\n",
       "      <td>22.334375</td>\n",
       "      <td>24.594219</td>\n",
       "      <td>76</td>\n",
       "      <td>123</td>\n",
       "      <td>57</td>\n",
       "      <td>12</td>\n",
       "      <td>10265</td>\n",
       "      <td>100</td>\n",
       "      <td>87</td>\n",
       "      <td>Tuesday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2024-10-23</td>\n",
       "      <td>24.261733</td>\n",
       "      <td>23.560000</td>\n",
       "      <td>31</td>\n",
       "      <td>115</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>10328</td>\n",
       "      <td>105</td>\n",
       "      <td>95</td>\n",
       "      <td>Wednesday</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         date        NO2         O3  wind_speed  mean_temp  global_radiation  \\\n",
       "0  2024-10-16  22.602712  22.881288          61        151                40   \n",
       "1  2024-10-17  23.104327  23.038638          51        169                43   \n",
       "2  2024-10-18  23.682857  23.716611          21        156                42   \n",
       "3  2024-10-19  24.532039  23.604723          43        147                43   \n",
       "4  2024-10-20  23.019102  24.173377          68        145                 0   \n",
       "5  2024-10-21  21.275629  25.058736          58        144                27   \n",
       "6  2024-10-22  22.334375  24.594219          76        123                57   \n",
       "7  2024-10-23  24.261733  23.560000          31        115                 7   \n",
       "\n",
       "   percipitation  pressure  minimum_visibility  humidity    weekday  \n",
       "0              0     10103                 358        82  Wednesday  \n",
       "1              6     10100                 371        86   Thursday  \n",
       "2             39     10140                  64        97     Friday  \n",
       "3             28     10140                 236        92   Saturday  \n",
       "4              0     10160                 241        82     Sunday  \n",
       "5             43     10206                 220        92     Monday  \n",
       "6             12     10265                 100        87    Tuesday  \n",
       "7              0     10328                 105        95  Wednesday  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of rows with missing values dropped: 7\n"
     ]
    }
   ],
   "source": [
    "input_data = create_features(\n",
    "    data=data,\n",
    "    target_particle=target_particle,\n",
    "    lag_days=7,\n",
    "    sma_days=7,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>-0.126371</td>\n",
       "      <td>-0.855455</td>\n",
       "      <td>-0.206181</td>\n",
       "      <td>0.082314</td>\n",
       "      <td>-1.330268</td>\n",
       "      <td>-0.493936</td>\n",
       "      <td>1.783274</td>\n",
       "      <td>2.813837</td>\n",
       "      <td>1.547919</td>\n",
       "      <td>1.37753</td>\n",
       "      <td>...</td>\n",
       "      <td>-1.036205</td>\n",
       "      <td>-0.802392</td>\n",
       "      <td>-0.883032</td>\n",
       "      <td>-0.968984</td>\n",
       "      <td>0.333776</td>\n",
       "      <td>-1.446199</td>\n",
       "      <td>-1.180992</td>\n",
       "      <td>-0.54567</td>\n",
       "      <td>-1.15814</td>\n",
       "      <td>-0.358079</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 87 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        NO2        O3  wind_speed  mean_temp  global_radiation  percipitation  \\\n",
       "0 -0.126371 -0.855455   -0.206181   0.082314         -1.330268      -0.493936   \n",
       "\n",
       "   pressure  minimum_visibility  humidity  weekday_sin  ...  \\\n",
       "0  1.783274            2.813837  1.547919      1.37753  ...   \n",
       "\n",
       "   O3_last_year_4_days_before  NO2_last_year_4_days_before  \\\n",
       "0                   -1.036205                    -0.802392   \n",
       "\n",
       "   O3_last_year_5_days_before  NO2_last_year_5_days_before  \\\n",
       "0                   -0.883032                    -0.968984   \n",
       "\n",
       "   O3_last_year_6_days_before  NO2_last_year_6_days_before  \\\n",
       "0                    0.333776                    -1.446199   \n",
       "\n",
       "   O3_last_year_7_days_before  NO2_last_year_7_days_before  \\\n",
       "0                   -1.180992                     -0.54567   \n",
       "\n",
       "   O3_last_year_3_days_after  NO2_last_year_3_days_after  \n",
       "0                   -1.15814                   -0.358079  \n",
       "\n",
       "[1 rows x 87 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "input_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#prediction = run_model(particle=\"O3\", data=df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>date</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</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2023-10-16</td>\n",
       "      <td>17.958784</td>\n",
       "      <td>32.611400</td>\n",
       "      <td>31</td>\n",
       "      <td>90</td>\n",
       "      <td>68</td>\n",
       "      <td>9</td>\n",
       "      <td>1022</td>\n",
       "      <td>348</td>\n",
       "      <td>88</td>\n",
       "      <td>Monday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2023-10-17</td>\n",
       "      <td>10.842703</td>\n",
       "      <td>39.812600</td>\n",
       "      <td>61</td>\n",
       "      <td>85</td>\n",
       "      <td>75</td>\n",
       "      <td>0</td>\n",
       "      <td>1019</td>\n",
       "      <td>348</td>\n",
       "      <td>84</td>\n",
       "      <td>Tuesday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2023-10-18</td>\n",
       "      <td>17.970267</td>\n",
       "      <td>31.779024</td>\n",
       "      <td>71</td>\n",
       "      <td>90</td>\n",
       "      <td>71</td>\n",
       "      <td>23</td>\n",
       "      <td>1006</td>\n",
       "      <td>238</td>\n",
       "      <td>77</td>\n",
       "      <td>Wednesday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2023-10-19</td>\n",
       "      <td>17.233056</td>\n",
       "      <td>18.715600</td>\n",
       "      <td>61</td>\n",
       "      <td>145</td>\n",
       "      <td>39</td>\n",
       "      <td>114</td>\n",
       "      <td>990</td>\n",
       "      <td>212</td>\n",
       "      <td>94</td>\n",
       "      <td>Thursday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2023-10-20</td>\n",
       "      <td>15.023600</td>\n",
       "      <td>22.040000</td>\n",
       "      <td>71</td>\n",
       "      <td>119</td>\n",
       "      <td>7</td>\n",
       "      <td>204</td>\n",
       "      <td>981</td>\n",
       "      <td>104</td>\n",
       "      <td>97</td>\n",
       "      <td>Friday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2023-10-21</td>\n",
       "      <td>8.723378</td>\n",
       "      <td>48.334400</td>\n",
       "      <td>61</td>\n",
       "      <td>131</td>\n",
       "      <td>39</td>\n",
       "      <td>35</td>\n",
       "      <td>989</td>\n",
       "      <td>277</td>\n",
       "      <td>88</td>\n",
       "      <td>Saturday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>2023-10-22</td>\n",
       "      <td>20.634267</td>\n",
       "      <td>15.586000</td>\n",
       "      <td>71</td>\n",
       "      <td>121</td>\n",
       "      <td>55</td>\n",
       "      <td>39</td>\n",
       "      <td>1003</td>\n",
       "      <td>323</td>\n",
       "      <td>87</td>\n",
       "      <td>Sunday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>2023-10-23</td>\n",
       "      <td>15.115600</td>\n",
       "      <td>24.628085</td>\n",
       "      <td>50</td>\n",
       "      <td>99</td>\n",
       "      <td>43</td>\n",
       "      <td>5</td>\n",
       "      <td>1011</td>\n",
       "      <td>59</td>\n",
       "      <td>95</td>\n",
       "      <td>Monday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2023-10-24</td>\n",
       "      <td>22.885676</td>\n",
       "      <td>27.117600</td>\n",
       "      <td>61</td>\n",
       "      <td>116</td>\n",
       "      <td>32</td>\n",
       "      <td>65</td>\n",
       "      <td>1001</td>\n",
       "      <td>231</td>\n",
       "      <td>92</td>\n",
       "      <td>Tuesday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>2023-10-25</td>\n",
       "      <td>21.531757</td>\n",
       "      <td>13.321600</td>\n",
       "      <td>50</td>\n",
       "      <td>93</td>\n",
       "      <td>14</td>\n",
       "      <td>153</td>\n",
       "      <td>996</td>\n",
       "      <td>157</td>\n",
       "      <td>96</td>\n",
       "      <td>Wednesday</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>2023-10-26</td>\n",
       "      <td>23.072267</td>\n",
       "      <td>16.154167</td>\n",
       "      <td>31</td>\n",
       "      <td>94</td>\n",
       "      <td>36</td>\n",
       "      <td>1</td>\n",
       "      <td>995</td>\n",
       "      <td>48</td>\n",
       "      <td>97</td>\n",
       "      <td>Thursday</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         date        NO2         O3  wind_speed  mean_temp  global_radiation  \\\n",
       "0  2023-10-16  17.958784  32.611400          31         90                68   \n",
       "1  2023-10-17  10.842703  39.812600          61         85                75   \n",
       "2  2023-10-18  17.970267  31.779024          71         90                71   \n",
       "3  2023-10-19  17.233056  18.715600          61        145                39   \n",
       "4  2023-10-20  15.023600  22.040000          71        119                 7   \n",
       "5  2023-10-21   8.723378  48.334400          61        131                39   \n",
       "6  2023-10-22  20.634267  15.586000          71        121                55   \n",
       "7  2023-10-23  15.115600  24.628085          50         99                43   \n",
       "8  2023-10-24  22.885676  27.117600          61        116                32   \n",
       "9  2023-10-25  21.531757  13.321600          50         93                14   \n",
       "10 2023-10-26  23.072267  16.154167          31         94                36   \n",
       "\n",
       "    percipitation  pressure  minimum_visibility  humidity    weekday  \n",
       "0               9      1022                 348        88     Monday  \n",
       "1               0      1019                 348        84    Tuesday  \n",
       "2              23      1006                 238        77  Wednesday  \n",
       "3             114       990                 212        94   Thursday  \n",
       "4             204       981                 104        97     Friday  \n",
       "5              35       989                 277        88   Saturday  \n",
       "6              39      1003                 323        87     Sunday  \n",
       "7               5      1011                  59        95     Monday  \n",
       "8              65      1001                 231        92    Tuesday  \n",
       "9             153       996                 157        96  Wednesday  \n",
       "10              1       995                  48        97   Thursday  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "get_past_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2024-10-23 19:40:20.321 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
      "2024-10-23 19:40:20.322 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
      "2024-10-23 19:40:20.323 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of rows with missing values dropped: 7\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2024-10-23 19:40:34.183 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
      "2024-10-23 19:40:34.184 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n"
     ]
    }
   ],
   "source": [
    "prediction=run_model(particle=target_particle, data=data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[19.90814701,  8.8039613 , 26.57711386]])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prediction"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.11.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}