File size: 14,915 Bytes
1d31989 1d3c9ee 1d31989 f4930a4 1d31989 1d3c9ee f4930a4 1d3c9ee 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 f4930a4 1d31989 e2ebde2 1d31989 1d3c9ee 1d31989 1d3c9ee 1d31989 |
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 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 |
{
"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\n",
"from src.data_api_calls import get_combined_data\n",
"from src.past_data_api_calls import get_past_combined_data"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Data is already up to date.\n",
"Data is already up to date.\n",
"Number of rows with missing values dropped: 7\n",
"Data is already up to date.\n",
"Number of rows with missing values dropped: 7\n"
]
}
],
"source": [
"week_data, predictions_O3, predictions_NO2 = get_data_and_predictions()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"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>2024-10-17</td>\n",
" <td>22.804605</td>\n",
" <td>22.769160</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>1</th>\n",
" <td>2024-10-18</td>\n",
" <td>23.268500</td>\n",
" <td>23.307332</td>\n",
" <td>21</td>\n",
" <td>155</td>\n",
" <td>42</td>\n",
" <td>39</td>\n",
" <td>10140</td>\n",
" <td>45</td>\n",
" <td>97</td>\n",
" <td>Friday</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2024-10-19</td>\n",
" <td>23.910064</td>\n",
" <td>23.171714</td>\n",
" <td>41</td>\n",
" <td>147</td>\n",
" <td>43</td>\n",
" <td>16</td>\n",
" <td>10141</td>\n",
" <td>228</td>\n",
" <td>89</td>\n",
" <td>Saturday</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2024-10-20</td>\n",
" <td>22.573238</td>\n",
" <td>23.537845</td>\n",
" <td>81</td>\n",
" <td>155</td>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>10160</td>\n",
" <td>415</td>\n",
" <td>83</td>\n",
" <td>Sunday</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2024-10-21</td>\n",
" <td>21.145700</td>\n",
" <td>24.020696</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>5</th>\n",
" <td>2024-10-22</td>\n",
" <td>21.776580</td>\n",
" <td>23.335886</td>\n",
" <td>53</td>\n",
" <td>114</td>\n",
" <td>57</td>\n",
" <td>49</td>\n",
" <td>10269</td>\n",
" <td>226</td>\n",
" <td>92</td>\n",
" <td>Tuesday</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>2024-10-23</td>\n",
" <td>21.974794</td>\n",
" <td>22.214689</td>\n",
" <td>36</td>\n",
" <td>112</td>\n",
" <td>12</td>\n",
" <td>0</td>\n",
" <td>10328</td>\n",
" <td>65</td>\n",
" <td>97</td>\n",
" <td>Wednesday</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>2024-10-24</td>\n",
" <td>25.512568</td>\n",
" <td>20.913710</td>\n",
" <td>56</td>\n",
" <td>104</td>\n",
" <td>62</td>\n",
" <td>0</td>\n",
" <td>10247</td>\n",
" <td>130</td>\n",
" <td>94</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 2024-10-17 22.804605 22.769160 51 169 43 \n",
"1 2024-10-18 23.268500 23.307332 21 155 42 \n",
"2 2024-10-19 23.910064 23.171714 41 147 43 \n",
"3 2024-10-20 22.573238 23.537845 81 155 0 \n",
"4 2024-10-21 21.145700 24.020696 58 144 27 \n",
"5 2024-10-22 21.776580 23.335886 53 114 57 \n",
"6 2024-10-23 21.974794 22.214689 36 112 12 \n",
"7 2024-10-24 25.512568 20.913710 56 104 62 \n",
"\n",
" percipitation pressure minimum_visibility humidity weekday \n",
"0 6 10100 371 86 Thursday \n",
"1 39 10140 45 97 Friday \n",
"2 16 10141 228 89 Saturday \n",
"3 5 10160 415 83 Sunday \n",
"4 43 10206 220 92 Monday \n",
"5 49 10269 226 92 Tuesday \n",
"6 0 10328 65 97 Wednesday \n",
"7 0 10247 130 94 Thursday "
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"week_data"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[10.33808859, 16.00098432, 19.64377496]])"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"predictions_O3"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[25.68519992, 25.76030745, 31.21057679]])"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"predictions_NO2"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from src.data_api_calls import get_combined_data"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"ename": "TypeError",
"evalue": "'<' not supported between instances of 'Timestamp' and 'str'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[2], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[43mget_combined_data\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m2024-10-10\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\data_api_calls.py:136\u001b[0m, in \u001b[0;36mget_combined_data\u001b[1;34m(input_date)\u001b[0m\n\u001b[0;32m 133\u001b[0m start_date \u001b[38;5;241m=\u001b[39m end_date \u001b[38;5;241m-\u001b[39m timedelta(\u001b[38;5;241m7\u001b[39m)\n\u001b[0;32m 135\u001b[0m update_weather_data(start_date, end_date)\n\u001b[1;32m--> 136\u001b[0m \u001b[43mupdate_pollution_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstart_date\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mend_date\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 138\u001b[0m weather_df \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mread_csv(WEATHER_DATA_FILE)\n\u001b[0;32m 140\u001b[0m weather_df\u001b[38;5;241m.\u001b[39minsert(\u001b[38;5;241m1\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNO2\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m)\n",
"File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\data_api_calls.py:123\u001b[0m, in \u001b[0;36mupdate_pollution_data\u001b[1;34m(start_date, end_date)\u001b[0m\n\u001b[0;32m 121\u001b[0m updated_data \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mconcat([existing_data, new_data], ignore_index\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m 122\u001b[0m updated_data\u001b[38;5;241m.\u001b[39mdrop_duplicates(subset\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdate\u001b[39m\u001b[38;5;124m\"\u001b[39m, keep\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlast\u001b[39m\u001b[38;5;124m\"\u001b[39m, inplace\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m--> 123\u001b[0m updated_data \u001b[38;5;241m=\u001b[39m \u001b[43mupdated_data\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msort_values\u001b[49m\u001b[43m(\u001b[49m\u001b[43mby\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mdate\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m 124\u001b[0m updated_data\u001b[38;5;241m.\u001b[39mto_csv(POLLUTION_DATA_FILE, index\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\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:7200\u001b[0m, in \u001b[0;36mDataFrame.sort_values\u001b[1;34m(self, by, axis, ascending, inplace, kind, na_position, ignore_index, key)\u001b[0m\n\u001b[0;32m 7197\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(ascending, (\u001b[38;5;28mtuple\u001b[39m, \u001b[38;5;28mlist\u001b[39m)):\n\u001b[0;32m 7198\u001b[0m ascending \u001b[38;5;241m=\u001b[39m ascending[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m-> 7200\u001b[0m indexer \u001b[38;5;241m=\u001b[39m \u001b[43mnargsort\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 7201\u001b[0m \u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkind\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkind\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mascending\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mascending\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mna_position\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mna_position\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkey\u001b[49m\n\u001b[0;32m 7202\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 7203\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 7204\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m inplace:\n",
"File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\core\\sorting.py:439\u001b[0m, in \u001b[0;36mnargsort\u001b[1;34m(items, kind, ascending, na_position, key, mask)\u001b[0m\n\u001b[0;32m 437\u001b[0m non_nans \u001b[38;5;241m=\u001b[39m non_nans[::\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\n\u001b[0;32m 438\u001b[0m non_nan_idx \u001b[38;5;241m=\u001b[39m non_nan_idx[::\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\n\u001b[1;32m--> 439\u001b[0m indexer \u001b[38;5;241m=\u001b[39m non_nan_idx[\u001b[43mnon_nans\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43margsort\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkind\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkind\u001b[49m\u001b[43m)\u001b[49m]\n\u001b[0;32m 440\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m ascending:\n\u001b[0;32m 441\u001b[0m indexer \u001b[38;5;241m=\u001b[39m indexer[::\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\n",
"\u001b[1;31mTypeError\u001b[0m: '<' not supported between instances of 'Timestamp' and 'str'"
]
}
],
"source": [
"get_combined_data(\"2024-10-10\")"
]
}
],
"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
}
|