Added moving averaged energy data

EnergyLSTM/EDA_lstm_energy.ipynb

@@ -0,0 +1,155 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\levim\\anaconda3\\envs\\experiments\\lib\\site-packages\\scipy\\__init__.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.24.3\n",
+      "  warnings.warn(f\"A NumPy version >={np_minversion} and <{np_maxversion}\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd \n",
+    "from datetime import datetime \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 keras.models import Sequential\n",
+    "from keras.layers import LSTM, Dense\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import MinMaxScaler,StandardScaler\n",
+    "from keras.callbacks import ModelCheckpoint\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\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Load selection of data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\levim\\AppData\\Local\\Temp\\ipykernel_27084\\3547628995.py:5: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  extended_energy_data['date'] = pd.to_datetime(extended_energy_data['date'])\n"
+     ]
+    }
+   ],
+   "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": 27,
+   "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 = 12*4 # Half a day\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()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(array([17591., 17652., 17713., 17775., 17836., 17897.]),\n",
+       " [Text(17591.0, 0, '2018-03'),\n",
+       "  Text(17652.0, 0, '2018-05'),\n",
+       "  Text(17713.0, 0, '2018-07'),\n",
+       "  Text(17775.0, 0, '2018-09'),\n",
+       "  Text(17836.0, 0, '2018-11'),\n",
+       "  Text(17897.0, 0, '2019-01')])"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%matplotlib qt\n",
+    "\n",
+    "start_date  = '2018-02-02'\n",
+    "end_date    = '2019-02-03'\n",
+    "\n",
+    "plt.plot(eed_15m['hvac_N'].loc[start_date:end_date])\n",
+    "plt.plot(eed_15m['moving_average'].loc[start_date:end_date])\n",
+    "plt.xticks(rotation=45)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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
+}

EnergyLSTM/lstm_energy.ipynb

@@ -2,9 +2,18 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 2,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\levim\\anaconda3\\envs\\experiments\\lib\\site-packages\\scipy\\__init__.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.24.3\n",
+      "  warnings.warn(f\"A NumPy version >={np_minversion} and <{np_maxversion}\"\n"
+     ]
+    }
+   ],
    "source": [
     "import pandas as pd \n",
     "from datetime import datetime \n",
@@ -25,113 +34,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\levim\\AppData\\Local\\Temp\\ipykernel_12184\\1569659483.py:5: SettingWithCopyWarning: \n",
-      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
-      "Try using .loc[row_indexer,col_indexer] = value instead\n",
-      "\n",
-      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
-      "  extended_energy_data['date'] = pd.to_datetime(extended_energy_data['date'])\n"
+     "ename": "NameError",
+     "evalue": "name 'all_data' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[1], line 3\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;66;03m# Prepar energy data set with extended features\u001b[39;00m\n\u001b[0;32m      2\u001b[0m feature_list \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdate\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhvac_N\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhvac_S\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mair_temp_set_1\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msolar_radiation_set_1\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[1;32m----> 3\u001b[0m extended_energy_data \u001b[38;5;241m=\u001b[39m \u001b[43mall_data\u001b[49m[feature_list]\n\u001b[0;32m      5\u001b[0m extended_energy_data[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdate\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mto_datetime(extended_energy_data[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdate\u001b[39m\u001b[38;5;124m'\u001b[39m])\n\u001b[0;32m      6\u001b[0m extended_energy_data\u001b[38;5;241m.\u001b[39mset_index(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdate\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;31mNameError\u001b[0m: name 'all_data' is not defined"
      ]
-    },
-    {
-     "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>hvac_N</th>\n",
-       "      <th>hvac_S</th>\n",
-       "      <th>air_temp_set_1</th>\n",
-       "      <th>solar_radiation_set_1</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>2018-01-01 00:00:00</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>11.5400</td>\n",
-       "      <td>51.4075</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>2018-01-01 01:00:00</td>\n",
-       "      <td>37.525001</td>\n",
-       "      <td>19.395</td>\n",
-       "      <td>10.8900</td>\n",
-       "      <td>2.1250</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>2018-01-01 02:00:00</td>\n",
-       "      <td>37.750001</td>\n",
-       "      <td>22.775</td>\n",
-       "      <td>10.7550</td>\n",
-       "      <td>0.0000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>2018-01-01 03:00:00</td>\n",
-       "      <td>37.550001</td>\n",
-       "      <td>18.920</td>\n",
-       "      <td>10.4775</td>\n",
-       "      <td>0.0000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>2018-01-01 04:00:00</td>\n",
-       "      <td>36.675001</td>\n",
-       "      <td>21.600</td>\n",
-       "      <td>9.9925</td>\n",
-       "      <td>0.0000</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                 date     hvac_N  hvac_S  air_temp_set_1  \\\n",
-       "0 2018-01-01 00:00:00        NaN     NaN         11.5400   \n",
-       "1 2018-01-01 01:00:00  37.525001  19.395         10.8900   \n",
-       "2 2018-01-01 02:00:00  37.750001  22.775         10.7550   \n",
-       "3 2018-01-01 03:00:00  37.550001  18.920         10.4775   \n",
-       "4 2018-01-01 04:00:00  36.675001  21.600          9.9925   \n",
-       "\n",
-       "   solar_radiation_set_1  \n",
-       "0                51.4075  \n",
-       "1                 2.1250  \n",
-       "2                 0.0000  \n",
-       "3                 0.0000  \n",
-       "4                 0.0000  "
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -142,11 +57,15 @@
     "extended_energy_data['date'] = pd.to_datetime(extended_energy_data['date'])\n",
     "extended_energy_data.set_index('date', inplace=True)\n",
     "\n",
-    "extended_energy_data = extended_energy_data.resample('60T').mean()\n",
-    "# extended_energy_data = extended_energy_data.interpolate(method='linear')\n",
+    "eed_15m = extended_energy_data.resample('15T').mean()\n",
+    "eed_15m = eed_15m.reset_index(drop=False)\n",
+    "\n",
+    "window_size = 12*4 # Half a day\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",
-    "extended_energy_data = extended_energy_data.reset_index(drop=False)\n",
-    "extended_energy_data.head()"
+    "eed_15m.head()"
    ]
   },
   {
@@ -156,7 +75,8 @@
    "outputs": [],
    "source": [
     "# energy_data = pd.read_csv(dataPATH + r\"\\hvac_data_1h.csv\")\n",
-    "energy_data = extended_energy_data\n",
+    "# energy_data = eed_15m\n",
+    "energy_data = eed_15m_avg\n",
     "\n",
     "# Convert the date column to datetime\n",
     "energy_data['date'] = pd.to_datetime(energy_data['date'], format = \"%Y-%m-%d %H:%M:%S\")\n",
@@ -261,7 +181,7 @@
    "source": [
     "train,test = traindataset,testdataset\n",
     "steps_in_past   = 3   \n",
-    "time_step       = 24\n",
+    "time_step       = 4*8\n",
     "no_inputs       = 5\n",
     "no_outputs      = 2\n",
     "def create_dataset(dataset,time_step):\n",