{ "cells": [ { "cell_type": "code", "execution_count": 2, "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\n" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
datezone_047_hw_valvertu_004_sat_sp_tnzone_047_tempzone_047_fan_spdrtu_004_fltrd_sa_flow_tnrtu_004_sa_temprtu_004_pa_static_stpt_tnrtu_004_oa_flow_tnrtu_004_oadmpr_pct...zone_047_heating_spUnnamed: 47_yhvac_Shp_hws_temparu_001_cwr_temparu_001_cws_fr_gpmaru_001_cws_temparu_001_hwr_temparu_001_hws_fr_gpmaru_001_hws_temp
02018-01-01 00:00:00100.069.067.520.09265.60466.10.060.00000028.0...NaNNaNNaN75.3NaNNaNNaNNaNNaNNaN
12018-01-01 00:01:00100.069.067.520.09265.60466.00.066572.09916228.0...NaNNaNNaN75.3NaNNaNNaNNaNNaNNaN
22018-01-01 00:02:00100.069.067.520.09708.24066.10.067628.83254228.0...NaNNaNNaN75.3NaNNaNNaNNaNNaNNaN
32018-01-01 00:03:00100.069.067.520.09611.63866.10.067710.29461728.0...NaNNaNNaN75.3NaNNaNNaNNaNNaNNaN
42018-01-01 00:04:00100.069.067.520.09215.11066.00.067139.18409028.0...NaNNaNNaN75.3NaNNaNNaNNaNNaNNaN
..................................................................
20721492020-12-31 23:58:00100.068.063.220.018884.83464.40.062938.32000023.4...71.069.023.145000123.856.2554.7156.4123.4261.6122.36
20721502020-12-31 23:58:00100.068.063.220.018884.83464.40.062938.32000023.4...71.069.023.145000123.856.2554.7156.4123.4261.6122.36
20721512020-12-31 23:59:00100.068.063.220.019345.50864.30.063154.39000023.4...71.069.023.145000123.856.2554.7156.4123.4261.6122.36
20721522020-12-31 23:59:00100.068.063.220.019345.50864.30.063154.39000023.4...71.069.023.145000123.856.2554.7156.4123.4261.6122.36
20721532021-01-01 00:00:00100.068.063.220.018650.23264.10.063076.27000022.9...71.069.023.788947123.856.2554.7156.4123.4261.6122.36
\n", "

2072154 rows × 30 columns

\n", "
" ], "text/plain": [ " date zone_047_hw_valve rtu_004_sat_sp_tn \\\n", "0 2018-01-01 00:00:00 100.0 69.0 \n", "1 2018-01-01 00:01:00 100.0 69.0 \n", "2 2018-01-01 00:02:00 100.0 69.0 \n", "3 2018-01-01 00:03:00 100.0 69.0 \n", "4 2018-01-01 00:04:00 100.0 69.0 \n", "... ... ... ... \n", "2072149 2020-12-31 23:58:00 100.0 68.0 \n", "2072150 2020-12-31 23:58:00 100.0 68.0 \n", "2072151 2020-12-31 23:59:00 100.0 68.0 \n", "2072152 2020-12-31 23:59:00 100.0 68.0 \n", "2072153 2021-01-01 00:00:00 100.0 68.0 \n", "\n", " zone_047_temp zone_047_fan_spd rtu_004_fltrd_sa_flow_tn \\\n", "0 67.5 20.0 9265.604 \n", "1 67.5 20.0 9265.604 \n", "2 67.5 20.0 9708.240 \n", "3 67.5 20.0 9611.638 \n", "4 67.5 20.0 9215.110 \n", "... ... ... ... \n", "2072149 63.2 20.0 18884.834 \n", "2072150 63.2 20.0 18884.834 \n", "2072151 63.2 20.0 19345.508 \n", "2072152 63.2 20.0 19345.508 \n", "2072153 63.2 20.0 18650.232 \n", "\n", " rtu_004_sa_temp rtu_004_pa_static_stpt_tn rtu_004_oa_flow_tn \\\n", "0 66.1 0.06 0.000000 \n", "1 66.0 0.06 6572.099162 \n", "2 66.1 0.06 7628.832542 \n", "3 66.1 0.06 7710.294617 \n", "4 66.0 0.06 7139.184090 \n", "... ... ... ... \n", "2072149 64.4 0.06 2938.320000 \n", "2072150 64.4 0.06 2938.320000 \n", "2072151 64.3 0.06 3154.390000 \n", "2072152 64.3 0.06 3154.390000 \n", "2072153 64.1 0.06 3076.270000 \n", "\n", " rtu_004_oadmpr_pct ... zone_047_heating_sp Unnamed: 47_y \\\n", "0 28.0 ... NaN NaN \n", "1 28.0 ... NaN NaN \n", "2 28.0 ... NaN NaN \n", "3 28.0 ... NaN NaN \n", "4 28.0 ... NaN NaN \n", "... ... ... ... ... \n", "2072149 23.4 ... 71.0 69.0 \n", "2072150 23.4 ... 71.0 69.0 \n", "2072151 23.4 ... 71.0 69.0 \n", "2072152 23.4 ... 71.0 69.0 \n", "2072153 22.9 ... 71.0 69.0 \n", "\n", " hvac_S hp_hws_temp aru_001_cwr_temp aru_001_cws_fr_gpm \\\n", "0 NaN 75.3 NaN NaN \n", "1 NaN 75.3 NaN NaN \n", "2 NaN 75.3 NaN NaN \n", "3 NaN 75.3 NaN NaN \n", "4 NaN 75.3 NaN NaN \n", "... ... ... ... ... \n", "2072149 23.145000 123.8 56.25 54.71 \n", "2072150 23.145000 123.8 56.25 54.71 \n", "2072151 23.145000 123.8 56.25 54.71 \n", "2072152 23.145000 123.8 56.25 54.71 \n", "2072153 23.788947 123.8 56.25 54.71 \n", "\n", " aru_001_cws_temp aru_001_hwr_temp aru_001_hws_fr_gpm \\\n", "0 NaN NaN NaN \n", "1 NaN NaN NaN \n", "2 NaN NaN NaN \n", "3 NaN NaN NaN \n", "4 NaN NaN NaN \n", "... ... ... ... \n", "2072149 56.4 123.42 61.6 \n", "2072150 56.4 123.42 61.6 \n", "2072151 56.4 123.42 61.6 \n", "2072152 56.4 123.42 61.6 \n", "2072153 56.4 123.42 61.6 \n", "\n", " aru_001_hws_temp \n", "0 NaN \n", "1 NaN \n", "2 NaN \n", "3 NaN \n", "4 NaN \n", "... ... \n", "2072149 122.36 \n", "2072150 122.36 \n", "2072151 122.36 \n", "2072152 122.36 \n", "2072153 122.36 \n", "\n", "[2072154 rows x 30 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "merged = pd.read_csv(r'C:\\Users\\jerin\\Downloads\\lbnlbldg59\\lbnlbldg59\\lbnlbldg59.processed\\LBNLBLDG59\\clean_Bldg59_2018to2020\\clean data\\long_merge.csv')\n", "\n", "zone = \"47\"\n", "\n", "if zone in [\"36\", \"37\", \"38\", \"39\", \"40\", \"41\", \"42\", \"64\", \"65\", \"66\", \"67\", \"68\", \"69\", \"70\"]:\n", " rtu = \"rtu_001\"\n", " wing = \"hvac_N\"\n", "elif zone in [\"18\", \"25\", \"26\", \"45\", \"48\", \"55\", \"56\", \"61\"]:\n", " rtu = \"rtu_003\"\n", " wing = \"hvac_S\"\n", "elif zone in [\"16\", \"17\", \"21\", \"22\", \"23\", \"24\", \"46\", \"47\", \"51\", \"52\", \"53\", \"54\"]:\n", " rtu = \"rtu_004\"\n", " wing = \"hvac_S\"\n", "else:\n", " rtu = \"rtu_002\"\n", " wing = \"hvac_N\"\n", "#merged is the dataframe\n", "sorted = merged[[\"date\"]+[col for col in merged.columns if zone in col or rtu in col or wing in col]+[\"hp_hws_temp\", \"aru_001_cwr_temp\" , \"aru_001_cws_fr_gpm\" ,\"aru_001_cws_temp\",\"aru_001_hwr_temp\" ,\"aru_001_hws_fr_gpm\" ,\"aru_001_hws_temp\"]]\n", "sorted" ] }, { "cell_type": "code", "execution_count": 100, "metadata": {}, "outputs": [], "source": [ "correlation_matrix = sorted.loc[:, sorted.columns != 'date'].corr()\n", "plt.figure(figsize=(15, 10))\n", "sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt=\".2f\", linewidths=0.5)\n", "plt.title('Pearson Correlation Coefficients')\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 102, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "zone_047_fan_spd ---- 0.3838842710385038 ---- zone_047_temp\n", "rtu_004_sa_temp ---- 0.5636316174287519 ---- zone_047_temp\n", "rtu_004_ra_temp ---- 0.32776265464886917 ---- zone_047_temp\n", "rtu_004_oa_temp ---- 0.3911499150089511 ---- zone_047_temp\n", "rtu_004_ma_temp ---- 0.3800818291020465 ---- zone_047_temp\n", "hvac_S ---- 0.3163506114497974 ---- zone_047_hw_valve\n", "hvac_S ---- 0.42500326788919984 ---- rtu_004_fltrd_sa_flow_tn\n", "hvac_S ---- 0.4794994590105312 ---- rtu_004_oa_temp\n", "hvac_S ---- 0.37653522078249596 ---- rtu_004_ma_temp\n", "hvac_S ---- 0.45054590590454646 ---- rtu_004_sf_vfd_spd_fbk_tn\n", "hvac_S ---- 0.3910776435479394 ---- rtu_004_rf_vfd_spd_fbk_tn\n", "aru_001_cwr_temp ---- 0.4337890009515319 ---- zone_047_temp\n", "aru_001_cwr_temp ---- 0.5103744910713975 ---- hvac_S\n", "aru_001_cws_fr_gpm ---- 0.5251959795850137 ---- zone_047_temp\n", "aru_001_cws_fr_gpm ---- 0.4816297584385553 ---- hvac_S\n", "aru_001_cws_temp ---- 0.576461860142355 ---- zone_047_temp\n", "aru_001_cws_temp ---- 0.5060071970556257 ---- hvac_S\n" ] } ], "source": [ "highly_correlated_cols = set()\n", "for i in range(len(correlation_matrix.columns)):\n", " for j in range(i):\n", " if abs(correlation_matrix.iloc[i, j]) > 0.3:\n", " colname_i = correlation_matrix.columns[i]\n", " colname_j = correlation_matrix.columns[j]\n", " if (colname_i != colname_j) and (colname_i==\"zone_047_temp\" or colname_j==\"zone_047_temp\" or colname_i==\"hvac_S\" or colname_j==\"hvac_S\"):\n", " print(colname_i,\"----\",abs(correlation_matrix.iloc[i, j]),\"----\",colname_j)\n", " highly_correlated_cols.add(colname_i)\n", " highly_correlated_cols.add(colname_j)\n", " \n", " " ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "date 0\n", "zone_047_hw_valve 0\n", "rtu_004_sat_sp_tn 0\n", "zone_047_temp 0\n", "zone_047_fan_spd 0\n", "rtu_004_fltrd_sa_flow_tn 0\n", "rtu_004_sa_temp 0\n", "rtu_004_pa_static_stpt_tn 0\n", "rtu_004_oa_flow_tn 0\n", "rtu_004_oadmpr_pct 0\n", "rtu_004_econ_stpt_tn 0\n", "rtu_004_ra_temp 0\n", "rtu_004_oa_temp 0\n", "rtu_004_ma_temp 0\n", "rtu_004_sf_vfd_spd_fbk_tn 0\n", "rtu_004_rf_vfd_spd_fbk_tn 0\n", "rtu_004_fltrd_gnd_lvl_plenum_press_tn 0\n", "rtu_004_fltrd_lvl2_plenum_press_tn 0\n", "zone_047_cooling_sp 0\n", "Unnamed: 47_x 0\n", "zone_047_heating_sp 0\n", "Unnamed: 47_y 0\n", "hvac_S 0\n", "hp_hws_temp 0\n", "aru_001_cwr_temp 667858\n", "aru_001_cws_fr_gpm 667858\n", "aru_001_cws_temp 667858\n", "aru_001_hwr_temp 0\n", "aru_001_hws_fr_gpm 0\n", "aru_001_hws_temp 0\n", "dtype: int64" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "final_df = sorted.copy()\n", "final_df['date'] = pd.to_datetime(final_df['date'], format = \"%Y-%m-%d %H:%M:%S\")\n", "final_df = final_df[ (final_df.date.dt.date >date(2020, 1, 1)) & (final_df.date.dt.date< date(2020, 12, 30))]\n", "final_df.isna().sum()" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [], "source": [ "%matplotlib qt\n", "for i in final_df.columns[11:14]:\n", " plt.plot(final_df['date'],final_df[i])\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\jerin\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\keras\\src\\layers\\rnn\\rnn.py:205: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", " super().__init__(**kwargs)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/2\n", "\u001b[1m12174/12174\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m811s\u001b[0m 66ms/step - loss: 0.0019 - val_loss: 9.6280e-04\n", "Epoch 2/2\n", "\u001b[1m12174/12174\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m814s\u001b[0m 67ms/step - loss: 7.9909e-04 - val_loss: 7.6609e-04\n", "\u001b[1m24348/24348\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m120s\u001b[0m 5ms/step\n", "\u001b[1m10434/10434\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m58s\u001b[0m 6ms/step\n" ] } ], "source": [ "\n", "dataset = final_df[['rtu_004_oa_temp','rtu_004_ra_temp','hp_hws_temp','rtu_004_ma_temp','rtu_004_sa_temp']].values\n", "\n", "# dataset = final_df[['hvac_S','rtu_004_ra_temp','rtu_004_oa_temp','rtu_004_ma_temp','rtu_004_fltrd_sa_flow_tn',\n", "# 'rtu_004_sf_vfd_spd_fbk_tn','rtu_004_rf_vfd_spd_fbk_tn','zone_047_temp']].values\n", "# dataset = final_df[['rtu_004_fltrd_sa_flow_tn','rtu_004_sf_vfd_spd_fbk_tn','rtu_004_rf_vfd_spd_fbk_tn',\n", "# 'rtu_004_oa_temp','rtu_004_ma_temp','zone_047_fan_spd','zone_047_hw_valve','rtu_004_sa_temp','zone_047_temp']].values\n", "dataset = dataset.astype('float32')\n", "\n", "\n", "scaler = MinMaxScaler(feature_range=(0, 1))\n", "dataset = scaler.fit_transform(dataset)\n", "train_size = int(len(dataset)* 0.30)\n", "test_size = len(dataset) - train_size\n", "test,train = dataset[0:train_size,:],dataset[train_size:len(dataset),:]\n", "\n", "def create_dataset(dataset,time_step):\n", " # x1,x2,x3,x4,x5,x6,x7, Y = [],[],[],[],[],[],[],[]\n", " x1,x2,x3,Y = [],[],[],[]\n", " for i in range(len(dataset)-time_step-1):\n", " x1.append(dataset[i:(i+time_step), 0])\n", " x2.append(dataset[i:(i+time_step), 1])\n", " x3.append(dataset[i:(i+time_step), 2])\n", " # x4.append(dataset[i:(i+time_step), 3])\n", " # x5.append(dataset[i:(i+time_step), 4])\n", " # x6.append(dataset[i:(i+time_step), 5])\n", " # x7.append(dataset[i:(i+time_step), 6])\n", " Y.append([dataset[i + time_step, 3],dataset[i + time_step, 4]])\n", " # x1,x2,x3,x4,x5,x6,x7,Y = np.array(x1),np.array(x2),np.array(x3), np.array(x4),np.array(x5),np.array(x6),np.array(x7),np.array(Y)\n", " x1,x2,x3,Y = np.array(x1),np.array(x2),np.array(x3),np.array(Y)\n", " # Y = np.reshape(Y,(len(Y),1))\n", " return np.stack([x1,x2,x3],axis=2),Y\n", "\n", "\n", "\n", "\n", "time_step = 60\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))\n", "model.add(Dense(units=2))\n", "\n", "model.compile(optimizer='adam', loss='mean_squared_error')\n", "\n", "model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=5, batch_size=64, verbose=1)\n", "\n", "train_predict = model.predict(X_train)\n", "test_predict = model.predict(X_test)\n" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [], "source": [ "%matplotlib qt\n", "\n", "# plt.plot(y_test[:,0], label='Original Testing Data', color='blue')\n", "# plt.plot(test_predict[:,0], label='Predicted Testing Data', color='red')\n", "plt.plot(y_test[:,1], label='Original Testing Data', color='green')\n", "plt.plot(test_predict[:,1], label='Predicted Testing Data', color='orange')\n", "anomalies = np.where(abs(test_predict[:,1] - y_test[:,0]) > 0.5)[0]\n", "plt.scatter(anomalies,test_predict[anomalies,1], color='black',marker =\"o\",s=100 )\n", "plt.title('Testing Data - Predicted vs Actual')\n", "plt.xlabel('Time')\n", "plt.ylabel('Value')\n", "plt.legend()\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "LSTM autoencoder" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "----------------------------" ] }, { "cell_type": "code", "execution_count": 246, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\jerin\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\keras\\src\\layers\\rnn\\rnn.py:205: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", " super().__init__(**kwargs)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\u001b[1m11487/24348\u001b[0m \u001b[32m━━━━━━━━━\u001b[0m\u001b[37m━━━━━━━━━━━\u001b[0m \u001b[1m2:07\u001b[0m 10ms/step" ] }, { "ename": "", "evalue": "", "output_type": "error", "traceback": [ "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n", "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n", "\u001b[1;31mClick here for more info. \n", "\u001b[1;31mView Jupyter log for further details." ] } ], "source": [ "\n", "# dataset = final_df[['zone_047_temp','hvac_S','rtu_004_sa_temp']].values\n", "\n", "# dataset = final_df[['hvac_S','rtu_004_ra_temp','rtu_004_oa_temp','rtu_004_ma_temp','rtu_004_fltrd_sa_flow_tn',\n", "# 'rtu_004_sf_vfd_spd_fbk_tn','rtu_004_rf_vfd_spd_fbk_tn','zone_047_temp']].values\n", "dataset = final_df[['rtu_004_fltrd_sa_flow_tn','rtu_004_sf_vfd_spd_fbk_tn','rtu_004_rf_vfd_spd_fbk_tn',\n", " 'rtu_004_oa_temp','rtu_004_ma_temp','zone_047_fan_spd','zone_047_hw_valve','rtu_004_ra_temp','rtu_004_sa_temp','zone_047_temp']].values\n", "dataset = dataset.astype('float32')\n", "\n", "\n", "scaler = MinMaxScaler(feature_range=(0, 1))\n", "dataset = scaler.fit_transform(dataset)\n", "test_size = int(len(dataset)* 0.30)\n", "test, train = dataset[0:test_size,:],dataset[test_size:len(dataset),:]\n", "\n", "def create_dataset(dataset,time_step):\n", " x1,x2,x3,x4,x5,x6,x7,x8,x9, Y = [],[],[],[],[],[],[],[],[],[]\n", "\n", " for i in range(0,len(dataset)-time_step-1):\n", " x1.append(dataset[i:(i+time_step), 0])\n", " x2.append(dataset[i:(i+time_step), 1])\n", " x3.append(dataset[i:(i+time_step), 2])\n", " x4.append(dataset[i:(i+time_step), 3])\n", " x5.append(dataset[i:(i+time_step), 4])\n", " x6.append(dataset[i:(i+time_step), 5])\n", " x7.append(dataset[i:(i+time_step), 6])\n", " x8.append(dataset[i:(i+time_step), 7])\n", " x9.append(dataset[i:(i+time_step), 8])\n", " Y.append(dataset[i:(i+time_step), 8])\n", " x1,x2,x3,x4,x5,x6,x7,x8,x9,Y = np.array(x1),np.array(x2),np.array(x3), np.array(x4),np.array(x5),np.array(x6),np.array(x7),np.array(x8),np.array(x9),np.array(Y)\n", " \n", " # Y = np.reshape(Y,(len(Y),1))\n", " return np.stack([x1,x2,x3,x4,x5,x6,x7,x8,x9],axis=2),Y\n", "\n", "\n", "\n", "\n", "time_step = 60\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=30))\n", "# model.add(Dense(units=time_step))\n", "\n", "model.compile(optimizer='adam', loss='mean_squared_error')\n", "\n", "# model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=2, batch_size=64, verbose=1)\n", "\n", "train_predict = model.predict(X_train)\n", "# test_predict = model.predict(X_test)\n" ] }, { "cell_type": "code", "execution_count": 244, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(779111, 60, 9)" ] }, "execution_count": 244, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X_train.shape" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "mo" ] }, { "cell_type": "code", "execution_count": 241, "metadata": {}, "outputs": [], "source": [ "%matplotlib qt\n", "time = 10\n", "mse = (y_test[time] - test_predict[0])**2\n", "anomalies = np.where(mse > 0.0001)[0]\n", "plt.plot(y_test[time], label='Original Data')\n", "plt.plot(test_predict[time], label='predicted Data')\n", "plt.scatter(anomalies,test_predict[time,anomalies], color='red', label='Anomalies')\n", "plt.legend()\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 242, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
Model: \"sequential_19\"\n",
       "
\n" ], "text/plain": [ "\u001b[1mModel: \"sequential_19\"\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ lstm_39 (LSTM)                  │ (None, 60, 50)         │        12,000 │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ lstm_40 (LSTM)                  │ (None, 30)             │         9,720 │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_26 (Dense)                │ (None, 60)             │         1,860 │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "
\n" ], "text/plain": [ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", "│ lstm_39 (\u001b[38;5;33mLSTM\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m60\u001b[0m, \u001b[38;5;34m50\u001b[0m) │ \u001b[38;5;34m12,000\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ lstm_40 (\u001b[38;5;33mLSTM\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m30\u001b[0m) │ \u001b[38;5;34m9,720\u001b[0m │\n", "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", "│ dense_26 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m60\u001b[0m) │ \u001b[38;5;34m1,860\u001b[0m │\n", "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Total params: 70,742 (276.34 KB)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m70,742\u001b[0m (276.34 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Trainable params: 23,580 (92.11 KB)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m23,580\u001b[0m (92.11 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Non-trainable params: 0 (0.00 B)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Optimizer params: 47,162 (184.23 KB)\n",
       "
\n" ], "text/plain": [ "\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m47,162\u001b[0m (184.23 KB)\n" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "model.summary()" ] }, { "cell_type": "code", "execution_count": 238, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([-0.00162351, -0.00127119, -0.00132501, -0.00043088, -0.00357354,\n", " -0.00349951, -0.00703096, -0.00679523, 0.00243503, 0.00075096,\n", " 0.015773 , 0.01411158, 0.01689583, 0.01593572, 0.00665802,\n", " 0.0068891 , -0.001706 , -0.00310844, -0.00871575, -0.00967073,\n", " -0.00820547, -0.00687617, 0.00930512, 0.00670969, 0.00769156,\n", " 0.01000088, -0.00052458, 0.00010484, -0.00573552, -0.00811213,\n", " -0.01016176, -0.01063424, -0.01580012, -0.01502603, -0.01243931,\n", " -0.01488668, 0.00733459, 0.00564003, 0.01374102, 0.01534522,\n", " 0.00324941, 0.00375515, -0.0078848 , -0.00780392, -0.01223874,\n", " -0.01329106, -0.00772917, -0.00823385, 0.01035273, 0.01039612,\n", " 0.01731664, 0.01493615, 0.00356281, 0.00522107, -0.00680918,\n", " -0.00461727, -0.00997645, -0.01072395, -0.00542653, -0.00710839],\n", " dtype=float32)" ] }, "execution_count": 238, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_predict[0]-y_test[0]" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "base", "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 }