Spaces:
Sleeping
Sleeping
File size: 8,045 Bytes
6a833f6 b98571e 6a833f6 59b2cc9 6a833f6 59b2cc9 b98571e 6a833f6 59b2cc9 6a833f6 59b2cc9 6a833f6 b98571e 6a833f6 59b2cc9 6a833f6 b98571e 6a833f6 59b2cc9 6a833f6 59b2cc9 6a833f6 59b2cc9 b98571e 59b2cc9 ee469ba 59b2cc9 ee469ba 59b2cc9 b98571e 59b2cc9 ee469ba 59b2cc9 b98571e 59b2cc9 ee469ba b98571e ee469ba 59b2cc9 ee469ba 59b2cc9 b98571e 6a833f6 b98571e 6a833f6 ee469ba 6a833f6 ee469ba b98571e ee469ba b98571e ee469ba 6a833f6 ee469ba 59b2cc9 ee469ba 59b2cc9 ee469ba 59b2cc9 6a833f6 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd \n",
"from datetime import datetime \n",
"from datetime import timedelta\n",
"from datetime import date\n",
"import matplotlib.pyplot as plt\n",
"# import seaborn as sns\n",
"import numpy as np\n",
"import pandas as pd\n",
"from statsmodels.tsa.holtwinters import ExponentialSmoothing\n",
"\n",
"dataPATH = r\"C:\\Users\\levim\\OneDrive\\Documents\\MastersAI_ES\\TeamProject-5ARIP10\\smart-buildings\\Data\"\n",
"\n",
"### Load ALL data ###\n",
"# all_data = pd.read_csv(dataPATH + r\"\\long_merge.csv\")\n",
"all_data = pd.read_csv(dataPATH + r\"\\extended_energy_data.csv\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Load selection of data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Prepar energy data set with extended features\n",
"feature_list = ['date', 'hvac_N', 'hvac_S', 'air_temp_set_1', 'solar_radiation_set_1']\n",
"extended_energy_data = all_data[feature_list]\n",
"\n",
"extended_energy_data['date'] = pd.to_datetime(extended_energy_data['date'])\n",
"extended_energy_data.set_index('date', inplace=True)\n",
"\n",
"# eed = extended energy data\n",
"# Resampling back to 15 minutes and 1 hour\n",
"eed_15m = extended_energy_data.resample('15T').mean()\n",
"eed_1h = extended_energy_data.resample('60T').mean()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"vscode": {
"languageId": "ruby"
}
},
"outputs": [],
"source": [
"# Assuming you want to apply a moving average window of size 3 on the 'column_name' column\n",
"window_size = 4*4 # 4 hours\n",
"eed_15m_avg = eed_15m.copy()\n",
"eed_15m_avg['hvac_N'] = eed_15m['hvac_N'].rolling(window=window_size).mean()\n",
"eed_15m_avg['hvac_S'] = eed_15m['hvac_S'].rolling(window=window_size).mean()\n",
"\n",
"window_size = 4 # 4 hours\n",
"eed_1h_avg = eed_1h.copy()\n",
"eed_1h_avg['hvac_N'] = eed_1h['hvac_N'].rolling(window=window_size).mean()\n",
"eed_1h_avg['hvac_S'] = eed_1h['hvac_S'].rolling(window=window_size).mean()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%matplotlib qt\n",
"\n",
"start_date = '2018-06-02'\n",
"end_date = '2018-06-08'\n",
"\n",
"plt.plot(eed_15m['hvac_N'].loc[start_date:end_date])\n",
"plt.plot(eed_15m_avg['hvac_N'].loc[start_date:end_date])\n",
"plt.plot(eed_1h_avg['hvac_N'].loc[start_date:end_date])\n",
"plt.xticks(rotation=45)\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%matplotlib qt\n",
"\n",
"plt.figure(figsize=(20,10))\n",
"plt.plot(eed_1h['hvac_S'])\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Filling data gaps"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def fillgap(firstTS, secondTS, seasonal_periods):\n",
" \n",
" #PREPARATION\n",
" one = timedelta(hours=1)\n",
" secondTSr = secondTS[::-1].copy()\n",
" firstTSr = firstTS[::-1].copy()\n",
" indexr = pd.date_range(start=firstTS.index[0], end=secondTS.index[-1], freq='H')\n",
" firstTSr.index = indexr[-len(firstTSr):]\n",
" secondTSr.index = indexr[:len(secondTSr)]\n",
" \n",
" #FORWARD \n",
" es = ExponentialSmoothing(firstTS, seasonal_periods=seasonal_periods,seasonal='add', freq='H').fit()\n",
" forwardPrediction = es.predict(start=firstTS.index[-1]+one, end=secondTS.index[0]-one)\n",
" \n",
" #BACKWARD\n",
" es = ExponentialSmoothing(secondTSr, seasonal_periods=seasonal_periods,seasonal='add', freq='H').fit()\n",
" backwardPrediction = es.predict(start=secondTSr.index[-1]+one, end=firstTSr.index[0]-one)\n",
" \n",
" #INTERPOLATION\n",
" l = len(forwardPrediction)\n",
" interpolation = pd.Series([(backwardPrediction[i] * i + forwardPrediction[i] * (l -i) )/ l for i in range(l)], index=forwardPrediction.index.copy())\n",
" \n",
" return interpolation"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Function to split the data into multiple DataFrames based on the gaps\n",
"def split_dfs(data):\n",
"\n",
" # Prepare the DataFrame\n",
" df = data.copy()\n",
" df = df.reset_index()\n",
" df = df.dropna()\n",
" \n",
" # Set the maximum allowable gap (e.g., 1 hour)\n",
" max_gap = pd.Timedelta(hours=1)\n",
"\n",
" # Calculate the differences between consecutive timestamps\n",
" time_diff = df['date'].diff()\n",
"\n",
" # Identify gaps larger than the maximum allowable gap\n",
" gaps = time_diff > max_gap\n",
"\n",
" # Create a new column to identify different groups\n",
" df['group'] = gaps.cumsum()\n",
"\n",
" df.set_index('date', inplace=True)\n",
"\n",
" # Split the DataFrame into a list of DataFrames based on the groups\n",
" dfs = [group for _, group in df.groupby('group')]\n",
"\n",
" return dfs"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def interpolate_gaps(data, col):\n",
"\n",
" # Split the data into multiple DataFrames based on the gaps\n",
" dfs = split_dfs(data[[col]])\n",
"\n",
" # Interpolate the gaps between the DataFrames\n",
" ip_df = pd.DataFrame()\n",
" for ii in range(len(dfs)-1):\n",
" seasonal_periods = max(min([len(dfs[ii]), len(dfs[ii+1])]) // 2 - 10, 2)\n",
" \n",
" if seasonal_periods > 24*7: # Using more than 1 week of seasonal patterns is not necessary\n",
" seasonal_periods = 24*7\n",
" interpolation = fillgap(dfs[ii][col], dfs[ii+1][col], seasonal_periods)\n",
" else:\n",
" interpolation = fillgap(dfs[ii][col], dfs[ii+1][col], seasonal_periods)\n",
"\n",
" ip_df = pd.concat([ip_df,dfs[ii][col],interpolation])\n",
" \n",
" # Add the last DataFrame\n",
" ip_df = pd.concat([ip_df,dfs[-1][col]])\n",
"\n",
" return ip_df"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# interpolation of the whole data set\n",
"\n",
"ip_eed_1h = pd.DataFrame()\n",
"for ii in eed_1h.columns:\n",
" ip_df = interpolate_gaps(eed_1h['2018-1-2':], ii)\n",
" ip_eed_1h = pd.concat([ip_eed_1h, ip_df[0]], axis=1) # axis=1 for horizontal concat\n",
"ip_eed_1h.columns = list(eed_1h.columns)\n",
"\n",
"ip_eed_1h = ip_eed_1h.set_axis('date', axis=0)\n",
"ip_eed_1h.to_csv(dataPATH + r\"\\interpolated_energy_data.csv\")\n",
"\n",
"ip_eed_1h.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%matplotlib qt\n",
"# plt.plot(eed_1h['hvac_N'])\n",
"plt.plot(ip_df)\n",
"\n",
"plt.show()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "experiments",
"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": "3.8.15"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|