Added energy prediction LSTM

lstm_energy.ipynb

@@ -0,0 +1,384 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 98,
+   "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\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 102,
+   "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>86.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2018-01-01 00:01:00</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>11.64</td>\n",
+       "      <td>86.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2018-01-01 00:02:00</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>11.64</td>\n",
+       "      <td>86.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2018-01-01 00:03:00</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>11.64</td>\n",
+       "      <td>86.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2018-01-01 00:04:00</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>11.64</td>\n",
+       "      <td>86.7</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  date  hvac_N  hvac_S  air_temp_set_1  solar_radiation_set_1\n",
+       "0  2018-01-01 00:00:00     NaN     NaN           11.64                   86.7\n",
+       "1  2018-01-01 00:01:00     NaN     NaN           11.64                   86.7\n",
+       "2  2018-01-01 00:02:00     NaN     NaN           11.64                   86.7\n",
+       "3  2018-01-01 00:03:00     NaN     NaN           11.64                   86.7\n",
+       "4  2018-01-01 00:04:00     NaN     NaN           11.64                   86.7"
+      ]
+     },
+     "execution_count": 102,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "feature_list = ['date', 'hvac_N', 'hvac_S', 'air_temp_set_1', 'solar_radiation_set_1']\n",
+    "extended_energy_data = all_data[feature_list]\n",
+    "extended_energy_data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "energy_data = pd.read_csv(dataPATH + r\"\\hvac_data_1h.csv\")\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": null,
+   "metadata": {},
+   "outputs": [],
+   "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": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "traindataset = traindataset.astype('float32')\n",
+    "testdataset = testdataset.astype('float32')\n",
+    "\n",
+    "mintest = np.min(testdataset)\n",
+    "maxtest = np.max(testdataset)\n",
+    "\n",
+    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
+    "traindataset = scaler.fit_transform(traindataset)\n",
+    "testdataset = scaler.transform(testdataset)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 101,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/5\n",
+      "57/58 [============================>.] - ETA: 0s - loss: 0.0238\n",
+      "Epoch 1: val_loss improved from inf to 0.01717, saving model to lstm_energy_01.keras\n",
+      "58/58 [==============================] - 11s 62ms/step - loss: 0.0238 - val_loss: 0.0172\n",
+      "Epoch 2/5\n",
+      "56/58 [===========================>..] - ETA: 0s - loss: 0.0139\n",
+      "Epoch 2: val_loss improved from 0.01717 to 0.01117, saving model to lstm_energy_01.keras\n",
+      "58/58 [==============================] - 2s 42ms/step - loss: 0.0139 - val_loss: 0.0112\n",
+      "Epoch 3/5\n",
+      "57/58 [============================>.] - ETA: 0s - loss: 0.0116\n",
+      "Epoch 3: val_loss improved from 0.01117 to 0.00990, saving model to lstm_energy_01.keras\n",
+      "58/58 [==============================] - 2s 36ms/step - loss: 0.0116 - val_loss: 0.0099\n",
+      "Epoch 4/5\n",
+      "57/58 [============================>.] - ETA: 0s - loss: 0.0084\n",
+      "Epoch 4: val_loss improved from 0.00990 to 0.00889, saving model to lstm_energy_01.keras\n",
+      "58/58 [==============================] - 2s 40ms/step - loss: 0.0084 - val_loss: 0.0089\n",
+      "Epoch 5/5\n",
+      "57/58 [============================>.] - ETA: 0s - loss: 0.0066\n",
+      "Epoch 5: val_loss did not improve from 0.00889\n",
+      "58/58 [==============================] - 2s 37ms/step - loss: 0.0066 - val_loss: 0.0103\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x1f4931dc790>"
+      ]
+     },
+     "execution_count": 101,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train,test = traindataset,testdataset\n",
+    "days_in_past = 20\n",
+    "time_step = 1\n",
+    "def create_dataset(dataset,time_step):\n",
+    "    x = [[] for _ in range(3)] \n",
+    "    Y = [[] for _ in range(2)]\n",
+    "    for i in range(time_step * days_in_past, len(dataset) - time_step * days_in_past): # -time_step is to ensure that the Y value has enough values\n",
+    "        for j in range(3):\n",
+    "            x[j].append(dataset[(i-time_step*days_in_past):i, j])\n",
+    "        for j in range(2):\n",
+    "            Y[j].append([dataset[x + i, j] for x in range(0,time_step)])    \n",
+    "    x = [np.array(feature_list) for feature_list in x]\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*2))\n",
+    "    return np.stack(x,axis=2), 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, input_shape=(X_train.shape[1], X_train.shape[2])))\n",
+    "model.add(LSTM(units=50, return_sequences=True))\n",
+    "model.add(LSTM(units=30))\n",
+    "model.add(Dense(units=time_step*2))\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": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 95,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "22/22 [==============================] - 0s 8ms/step - loss: 0.0126\n",
+      "22/22 [==============================] - 1s 7ms/step\n",
+      "Loss:  0.01257658563554287\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": 96,
+   "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",
+    "# 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_test1[i,0:time_step], label='Original Testing Data', color='blue')\n",
+    "    ax.plot(test_predict2[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": [
+    "%matplotlib qt\n",
+    "index = 100\n",
+    "\n",
+    "\n",
+    "plt.plot(y_test[index,0:24], label='Original Testing Data', color='blue')\n",
+    "plt.plot(test_predict1[index,0:24], label='Predicted Testing Data', color='red',alpha=0.8)\n",
+    "\n",
+    "\n",
+    "plt.title('Testing Data - Predicted vs Actual')\n",
+    "plt.xlabel('Time [hours]')\n",
+    "plt.ylabel('Energy [kW]')\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_test[1, 0:24]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "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
+}