EnergyLSTM/lstm_energy.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "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",
    "# all_data = pd.read_csv(dataPATH + r\"\\long_merge.csv\")\n",
    "all_data = pd.read_csv(dataPATH + r\"\\extended_energy_data.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "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>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>11.64</td>\n",
       "      <td>86.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2018-01-01 00:15:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11.49</td>\n",
       "      <td>45.88</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2018-01-01 00:30:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11.59</td>\n",
       "      <td>51.62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2018-01-01 00:45:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11.44</td>\n",
       "      <td>21.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2018-01-01 01:00:00</td>\n",
       "      <td>37.400002</td>\n",
       "      <td>19.5</td>\n",
       "      <td>11.12</td>\n",
       "      <td>6.45</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           11.64   \n",
       "1 2018-01-01 00:15:00        NaN     NaN           11.49   \n",
       "2 2018-01-01 00:30:00        NaN     NaN           11.59   \n",
       "3 2018-01-01 00:45:00        NaN     NaN           11.44   \n",
       "4 2018-01-01 01:00:00  37.400002    19.5           11.12   \n",
       "\n",
       "   solar_radiation_set_1  \n",
       "0                  86.70  \n",
       "1                  45.88  \n",
       "2                  51.62  \n",
       "3                  21.43  \n",
       "4                   6.45  "
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "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_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",
    "eed_15m.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "# energy_data = pd.read_csv(dataPATH + r\"\\extended_energy_data.csv\")\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",
    "\n",
    "energy_data['day_of_week'] = energy_data['date'].dt.weekday\n",
    "# Filter the data for the year 2019\n",
    "df_filtered = energy_data[ (energy_data.date.dt.date >date(2019, 1, 20)) & (energy_data.date.dt.date< date(2019, 7, 26))]\n",
    "\n",
    "# Check for NA values in the DataFrame\n",
    "if df_filtered.isna().any().any():\n",
    "    print(\"There are NA values in the DataFrame columns.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "testdataset_df = df_filtered[(df_filtered.date.dt.date <date(2019, 2, 20))]\n",
    "\n",
    "traindataset_df = df_filtered[ (df_filtered.date.dt.date >date(2019, 2, 21))]\n",
    "\n",
    "testdataset = testdataset_df.drop(columns=[\"date\"]).values\n",
    "\n",
    "traindataset = traindataset_df.drop(columns=[\"date\"]).values\n",
    "\n",
    "columns_with_na = traindataset_df.columns[traindataset_df.isna().any()].tolist()\n",
    "columns_with_na"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "traindataset = traindataset.astype('float32')\n",
    "testdataset = testdataset.astype('float32')\n",
    "\n",
    "mintest = np.min(testdataset[:,0:2])\n",
    "maxtest = np.max(testdataset[:,0:2])\n",
    "\n",
    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
    "traindataset = scaler.fit_transform(traindataset)\n",
    "testdataset = scaler.transform(testdataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/5\n",
      "225/229 [============================>.] - ETA: 0s - loss: 0.0130\n",
      "Epoch 1: val_loss improved from inf to 0.01885, saving model to lstm_energy_01.keras\n",
      "229/229 [==============================] - 8s 16ms/step - loss: 0.0129 - val_loss: 0.0189\n",
      "Epoch 2/5\n",
      "229/229 [==============================] - ETA: 0s - loss: 0.0058\n",
      "Epoch 2: val_loss did not improve from 0.01885\n",
      "229/229 [==============================] - 3s 11ms/step - loss: 0.0058 - val_loss: 0.0192\n",
      "Epoch 3/5\n",
      "225/229 [============================>.] - ETA: 0s - loss: 0.0052\n",
      "Epoch 3: val_loss improved from 0.01885 to 0.01818, saving model to lstm_energy_01.keras\n",
      "229/229 [==============================] - 3s 11ms/step - loss: 0.0052 - val_loss: 0.0182\n",
      "Epoch 4/5\n",
      "225/229 [============================>.] - ETA: 0s - loss: 0.0045\n",
      "Epoch 4: val_loss did not improve from 0.01818\n",
      "229/229 [==============================] - 3s 11ms/step - loss: 0.0045 - val_loss: 0.0190\n",
      "Epoch 5/5\n",
      "226/229 [============================>.] - ETA: 0s - loss: 0.0041\n",
      "Epoch 5: val_loss did not improve from 0.01818\n",
      "229/229 [==============================] - 3s 11ms/step - loss: 0.0041 - val_loss: 0.0186\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x25e69ac0370>"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train,test = traindataset,testdataset\n",
    "steps_in_past   = 3   \n",
    "time_step       = 4*6\n",
    "no_inputs       = 5\n",
    "no_outputs      = 2\n",
    "def create_dataset(dataset,time_step):\n",
    "    x = [[] for _ in range(no_inputs)] \n",
    "    Y = [[] for _ in range(no_outputs)]\n",
    "    for i in range(time_step * steps_in_past, len(dataset) - time_step * steps_in_past): # -time_step is to ensure that the Y value has enough values\n",
    "        for j in range(no_inputs):\n",
    "            x[j].append(dataset[(i-time_step*steps_in_past):i, j])\n",
    "        for j in range(no_outputs):\n",
    "            Y[j].append(dataset[i:i+time_step, j])    \n",
    "    x = [np.array(feature_list) for feature_list in x]\n",
    "    x = np.stack(x,axis=1)\n",
    "    Y = [np.array(feature_list) for feature_list in Y] \n",
    "    Y = np.stack(Y,axis=1)\n",
    "    Y = np.reshape(Y, (Y.shape[0], time_step*no_outputs))\n",
    "    return x, Y\n",
    "\n",
    "\n",
    "X_train, y_train = create_dataset(train, time_step)\n",
    "X_test, y_test = create_dataset(test, time_step)\n",
    "\n",
    "\n",
    "model = Sequential()\n",
    "model.add(LSTM(units=50, return_sequences=True, dropout= 0.2, input_shape=(X_train.shape[1], X_train.shape[2])))\n",
    "model.add(LSTM(units=50, dropout= 0.2, return_sequences=True))\n",
    "model.add(LSTM(units=time_step*no_outputs))\n",
    "model.add(Dense(units=time_step*no_outputs))\n",
    "\n",
    "model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "\n",
    "checkpoint_path = \"lstm_energy_01.keras\"\n",
    "checkpoint_callback = ModelCheckpoint(filepath=checkpoint_path, monitor='val_loss', verbose=1, save_best_only=True, mode='min')\n",
    "model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=5, batch_size=64, verbose=1, callbacks=[checkpoint_callback])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "86/86 [==============================] - 0s 3ms/step - loss: 0.0186\n",
      "86/86 [==============================] - 1s 3ms/step\n",
      "Loss:  0.01863059028983116\n"
     ]
    }
   ],
   "source": [
    "loss            = model.evaluate(X_test, y_test)\n",
    "test_predict1   = model.predict(X_test)\n",
    "print(\"Loss: \", loss)\n",
    "# Converting values back to the original scale\n",
    "scalerBack      = MinMaxScaler(feature_range=(mintest, maxtest))\n",
    "test_predict2   = scalerBack.fit_transform(test_predict1)\n",
    "y_test1         = scalerBack.fit_transform(y_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib qt\n",
    "\n",
    "# Create a 3x3 grid of subplots\n",
    "fig, axes = plt.subplots(3, 3, figsize=(10, 10))\n",
    "\n",
    "var = 100\n",
    "# Loop over the value index\n",
    "for i, ax in enumerate(axes.flat):\n",
    "    # Plot your data or perform any other operations\n",
    "    ax.plot(y_test[var+i,0:time_step], label='Original Testing Data', color='blue')\n",
    "    ax.plot(test_predict1[var+i,0:time_step], label='Predicted Testing Data', color='red',alpha=0.8)\n",
    "    # ax.set_title(f'Plot {i+1}')\n",
    "    ax.set_title('Testing Data - Predicted vs Actual')\n",
    "    ax.set_xlabel('Time [hours]')\n",
    "    ax.set_ylabel('Energy Consumption [kW]')     \n",
    "    ax.legend()\n",
    "\n",
    "# Adjust the spacing between subplots\n",
    "plt.tight_layout()\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Autoregressive prediction\n",
    "X_pred = testdataset.copy()\n",
    "for i in range(steps_in_past,steps_in_past*2):\n",
    "    xin = X_pred[i-steps_in_past:i].reshape((1, steps_in_past, no_outputs)) \n",
    "    X_pred[i] = model.predict(xin, verbose = 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Plot prediction vs actual for test data\n",
    "plt.figure()\n",
    "plt.plot(X_pred[steps_in_past:steps_in_past*2,0],':',label='LSTM')\n",
    "plt.plot(testdataset[steps_in_past:steps_in_past*2,0],'--',label='Actual')\n",
    "plt.legend()"
   ]
  },
  {
   "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
}