{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 35,
   "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 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",
    "import tensorflow as tf\n",
    "import joblib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "merged = pd.read_csv(r'../data/long_merge.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "zones = [69, 68, 67, 66, 65, 64, 42, 41, 40, 39, 38, 37, 36]\n",
    "rtu = 1\n",
    "cols = []\n",
    "\n",
    "for zone in zones:\n",
    "    for column in merged.columns:\n",
    "        if (\n",
    "            f\"zone_0{zone}\" in column\n",
    "            and \"co2\" not in column\n",
    "            and \"hw_valve\" not in column\n",
    "            and \"cooling_sp\" not in column\n",
    "            and \"heating_sp\" not in column\n",
    "        ):\n",
    "            cols.append(column)\n",
    "\n",
    "\n",
    "# for rtu in rtus:\n",
    "#     for column in merged.columns:\n",
    "#         if f\"rtu_00{rtu}_fltrd_sa\" or f\"rtu_00{rtu}_sa_temp\" in column:\n",
    "#                 cols.append(column)\n",
    "\n",
    "cols = (\n",
    "    [\"date\"]\n",
    "    + cols\n",
    "    + [\n",
    "        f\"rtu_00{rtu}_fltrd_sa_flow_tn\",\n",
    "        f\"rtu_00{rtu}_sa_temp\", \n",
    "        \"air_temp_set_1\",\n",
    "        \"air_temp_set_2\",\n",
    "        \"dew_point_temperature_set_1d\",\n",
    "        \"relative_humidity_set_1\",\n",
    "        \"solar_radiation_set_1\",\n",
    "    ]\n",
    ")\n",
    "\n",
    "for zone in zones:\n",
    "    for column in merged.columns:\n",
    "        if f\"zone_0{zone}\" in column:\n",
    "            if \"cooling_sp\" in column or \"heating_sp\" in column:\n",
    "                cols.append(column)\n",
    "                \n",
    "input_dataset = merged[cols]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\arbal\\AppData\\Local\\Temp\\ipykernel_29192\\4293840618.py:1: 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",
      "  input_dataset['date'] = pd.to_datetime(input_dataset['date'], format = \"%Y-%m-%d %H:%M:%S\")\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "There are NA values in the DataFrame columns.\n"
     ]
    }
   ],
   "source": [
    "input_dataset['date'] = pd.to_datetime(input_dataset['date'], format = \"%Y-%m-%d %H:%M:%S\")\n",
    "df_filtered = input_dataset[ (input_dataset.date.dt.date >date(2019, 1, 1)) & (input_dataset.date.dt.date< date(2021, 1, 1))]\n",
    "\n",
    "if df_filtered.isna().any().any():\n",
    "    print(\"There are NA values in the DataFrame columns.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "testdataset_df = df_filtered[(df_filtered.date.dt.date >date(2020, 3, 1)) & (df_filtered.date.dt.date <date(2020,7, 1))]\n",
    "\n",
    "# traindataset_df = df_filtered[ (df_filtered.date.dt.date >date(2019, 11, 8))]\n",
    "\n",
    "traindataset_df = df_filtered[(df_filtered.date.dt.date >date(2019, 3, 1)) & (df_filtered.date.dt.date <date(2020, 3, 1)) | (df_filtered.date.dt.date >date(2020, 7, 1)) & (df_filtered.date.dt.date <date(2020, 12, 1))]\n",
    "testdataset = testdataset_df.drop(columns=[\"date\"]).values\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": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0 0\n"
     ]
    }
   ],
   "source": [
    "print(traindataset_df.isna().sum().sum(), testdataset_df.isna().sum().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1073512, 391818)"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(traindataset), len(testdataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['scaler_vav_1.pkl']"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "traindataset = traindataset.astype('float32')\n",
    "testdataset = testdataset.astype('float32')\n",
    "\n",
    "scaler = StandardScaler()\n",
    "traindataset = scaler.fit_transform(traindataset)\n",
    "testdataset = scaler.transform(testdataset)\n",
    "\n",
    "joblib.dump(scaler, 'scaler_vav_1.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "train,test = traindataset,testdataset\n",
    "\n",
    "def create_dataset(dataset,time_step):\n",
    "    x = []\n",
    "    Y = []\n",
    "    for i in range(len(dataset) - time_step - 1):\n",
    "        x.append(dataset[i:(i+time_step),:])\n",
    "        Y.append(dataset[i+time_step,0:26])\n",
    "    x= np.array(x)\n",
    "    Y = np.array(Y)\n",
    "    return x,Y\n",
    "time_step = 30\n",
    "X_train, y_train = create_dataset(train, time_step)\n",
    "X_test, y_test = create_dataset(test, time_step)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((1073481, 30, 55), (1073481, 26))"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape, y_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/3\n",
      "\u001b[1m8387/8387\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 0.0696\n",
      "Epoch 1: val_loss improved from inf to 0.65445, saving model to lstm_vav_01.keras\n",
      "\u001b[1m8387/8387\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m589s\u001b[0m 69ms/step - loss: 0.0696 - val_loss: 0.6544\n",
      "Epoch 2/3\n",
      "\u001b[1m 449/8387\u001b[0m \u001b[32m━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m7:16\u001b[0m 55ms/step - loss: 0.0033"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[54], line 11\u001b[0m\n\u001b[0;32m      9\u001b[0m checkpoint_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlstm_vav_01.keras\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m     10\u001b[0m checkpoint_callback \u001b[38;5;241m=\u001b[39m ModelCheckpoint(filepath\u001b[38;5;241m=\u001b[39mcheckpoint_path, monitor\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mval_loss\u001b[39m\u001b[38;5;124m'\u001b[39m, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m, save_best_only\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m, mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mmin\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m---> 11\u001b[0m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalidation_data\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mX_test\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_test\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mepochs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m128\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mverbose\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[43mcheckpoint_callback\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32md:\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\keras\\src\\utils\\traceback_utils.py:117\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    115\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m    116\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 117\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    118\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m    119\u001b[0m     filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n",
      "File \u001b[1;32md:\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\keras\\src\\backend\\tensorflow\\trainer.py:314\u001b[0m, in \u001b[0;36mTensorFlowTrainer.fit\u001b[1;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq)\u001b[0m\n\u001b[0;32m    312\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m step, iterator \u001b[38;5;129;01min\u001b[39;00m epoch_iterator\u001b[38;5;241m.\u001b[39menumerate_epoch():\n\u001b[0;32m    313\u001b[0m     callbacks\u001b[38;5;241m.\u001b[39mon_train_batch_begin(step)\n\u001b[1;32m--> 314\u001b[0m     logs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain_function\u001b[49m\u001b[43m(\u001b[49m\u001b[43miterator\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    315\u001b[0m     logs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_pythonify_logs(logs)\n\u001b[0;32m    316\u001b[0m     callbacks\u001b[38;5;241m.\u001b[39mon_train_batch_end(step, logs)\n",
      "File \u001b[1;32md:\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\tensorflow\\python\\util\\traceback_utils.py:150\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    148\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m    149\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 150\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    151\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m    152\u001b[0m   filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n",
      "File \u001b[1;32md:\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\polymorphic_function.py:833\u001b[0m, in \u001b[0;36mFunction.__call__\u001b[1;34m(self, *args, **kwds)\u001b[0m\n\u001b[0;32m    830\u001b[0m compiler \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mxla\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jit_compile \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnonXla\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    832\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m OptionalXlaContext(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jit_compile):\n\u001b[1;32m--> 833\u001b[0m   result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    835\u001b[0m new_tracing_count \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexperimental_get_tracing_count()\n\u001b[0;32m    836\u001b[0m without_tracing \u001b[38;5;241m=\u001b[39m (tracing_count \u001b[38;5;241m==\u001b[39m new_tracing_count)\n",
      "File \u001b[1;32md:\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\polymorphic_function.py:878\u001b[0m, in \u001b[0;36mFunction._call\u001b[1;34m(self, *args, **kwds)\u001b[0m\n\u001b[0;32m    875\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lock\u001b[38;5;241m.\u001b[39mrelease()\n\u001b[0;32m    876\u001b[0m \u001b[38;5;66;03m# In this case we have not created variables on the first call. So we can\u001b[39;00m\n\u001b[0;32m    877\u001b[0m \u001b[38;5;66;03m# run the first trace but we should fail if variables are created.\u001b[39;00m\n\u001b[1;32m--> 878\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[43mtracing_compilation\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_function\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    879\u001b[0m \u001b[43m    \u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_variable_creation_config\u001b[49m\n\u001b[0;32m    880\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    881\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_created_variables:\n\u001b[0;32m    882\u001b[0m   \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCreating variables on a non-first call to a function\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    883\u001b[0m                    \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m decorated with tf.function.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
      "File \u001b[1;32md:\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\tracing_compilation.py:139\u001b[0m, in \u001b[0;36mcall_function\u001b[1;34m(args, kwargs, tracing_options)\u001b[0m\n\u001b[0;32m    137\u001b[0m bound_args \u001b[38;5;241m=\u001b[39m function\u001b[38;5;241m.\u001b[39mfunction_type\u001b[38;5;241m.\u001b[39mbind(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m    138\u001b[0m flat_inputs \u001b[38;5;241m=\u001b[39m function\u001b[38;5;241m.\u001b[39mfunction_type\u001b[38;5;241m.\u001b[39munpack_inputs(bound_args)\n\u001b[1;32m--> 139\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunction\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_flat\u001b[49m\u001b[43m(\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# pylint: disable=protected-access\u001b[39;49;00m\n\u001b[0;32m    140\u001b[0m \u001b[43m    \u001b[49m\u001b[43mflat_inputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcaptured_inputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfunction\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcaptured_inputs\u001b[49m\n\u001b[0;32m    141\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32md:\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\concrete_function.py:1322\u001b[0m, in \u001b[0;36mConcreteFunction._call_flat\u001b[1;34m(self, tensor_inputs, captured_inputs)\u001b[0m\n\u001b[0;32m   1318\u001b[0m possible_gradient_type \u001b[38;5;241m=\u001b[39m gradients_util\u001b[38;5;241m.\u001b[39mPossibleTapeGradientTypes(args)\n\u001b[0;32m   1319\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (possible_gradient_type \u001b[38;5;241m==\u001b[39m gradients_util\u001b[38;5;241m.\u001b[39mPOSSIBLE_GRADIENT_TYPES_NONE\n\u001b[0;32m   1320\u001b[0m     \u001b[38;5;129;01mand\u001b[39;00m executing_eagerly):\n\u001b[0;32m   1321\u001b[0m   \u001b[38;5;66;03m# No tape is watching; skip to running the function.\u001b[39;00m\n\u001b[1;32m-> 1322\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_inference_function\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_preflattened\u001b[49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1323\u001b[0m forward_backward \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_select_forward_and_backward_functions(\n\u001b[0;32m   1324\u001b[0m     args,\n\u001b[0;32m   1325\u001b[0m     possible_gradient_type,\n\u001b[0;32m   1326\u001b[0m     executing_eagerly)\n\u001b[0;32m   1327\u001b[0m forward_function, args_with_tangents \u001b[38;5;241m=\u001b[39m forward_backward\u001b[38;5;241m.\u001b[39mforward()\n",
      "File \u001b[1;32md:\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\atomic_function.py:216\u001b[0m, in \u001b[0;36mAtomicFunction.call_preflattened\u001b[1;34m(self, args)\u001b[0m\n\u001b[0;32m    214\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcall_preflattened\u001b[39m(\u001b[38;5;28mself\u001b[39m, args: Sequence[core\u001b[38;5;241m.\u001b[39mTensor]) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n\u001b[0;32m    215\u001b[0m \u001b[38;5;250m  \u001b[39m\u001b[38;5;124;03m\"\"\"Calls with flattened tensor inputs and returns the structured output.\"\"\"\u001b[39;00m\n\u001b[1;32m--> 216\u001b[0m   flat_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_flat\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    217\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfunction_type\u001b[38;5;241m.\u001b[39mpack_output(flat_outputs)\n",
      "File \u001b[1;32md:\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\tensorflow\\python\\eager\\polymorphic_function\\atomic_function.py:251\u001b[0m, in \u001b[0;36mAtomicFunction.call_flat\u001b[1;34m(self, *args)\u001b[0m\n\u001b[0;32m    249\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m record\u001b[38;5;241m.\u001b[39mstop_recording():\n\u001b[0;32m    250\u001b[0m   \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_bound_context\u001b[38;5;241m.\u001b[39mexecuting_eagerly():\n\u001b[1;32m--> 251\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_bound_context\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_function\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    252\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    253\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mlist\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    254\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfunction_type\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mflat_outputs\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    255\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    256\u001b[0m   \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m    257\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m make_call_op_in_graph(\n\u001b[0;32m    258\u001b[0m         \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m    259\u001b[0m         \u001b[38;5;28mlist\u001b[39m(args),\n\u001b[0;32m    260\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_bound_context\u001b[38;5;241m.\u001b[39mfunction_call_options\u001b[38;5;241m.\u001b[39mas_attrs(),\n\u001b[0;32m    261\u001b[0m     )\n",
      "File \u001b[1;32md:\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\tensorflow\\python\\eager\\context.py:1500\u001b[0m, in \u001b[0;36mContext.call_function\u001b[1;34m(self, name, tensor_inputs, num_outputs)\u001b[0m\n\u001b[0;32m   1498\u001b[0m cancellation_context \u001b[38;5;241m=\u001b[39m cancellation\u001b[38;5;241m.\u001b[39mcontext()\n\u001b[0;32m   1499\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m cancellation_context \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m-> 1500\u001b[0m   outputs \u001b[38;5;241m=\u001b[39m \u001b[43mexecute\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexecute\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1501\u001b[0m \u001b[43m      \u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mutf-8\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1502\u001b[0m \u001b[43m      \u001b[49m\u001b[43mnum_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnum_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1503\u001b[0m \u001b[43m      \u001b[49m\u001b[43minputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtensor_inputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1504\u001b[0m \u001b[43m      \u001b[49m\u001b[43mattrs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattrs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1505\u001b[0m \u001b[43m      \u001b[49m\u001b[43mctx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1506\u001b[0m \u001b[43m  \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1507\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m   1508\u001b[0m   outputs \u001b[38;5;241m=\u001b[39m execute\u001b[38;5;241m.\u001b[39mexecute_with_cancellation(\n\u001b[0;32m   1509\u001b[0m       name\u001b[38;5;241m.\u001b[39mdecode(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mutf-8\u001b[39m\u001b[38;5;124m\"\u001b[39m),\n\u001b[0;32m   1510\u001b[0m       num_outputs\u001b[38;5;241m=\u001b[39mnum_outputs,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1514\u001b[0m       cancellation_manager\u001b[38;5;241m=\u001b[39mcancellation_context,\n\u001b[0;32m   1515\u001b[0m   )\n",
      "File \u001b[1;32md:\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\tensorflow\\python\\eager\\execute.py:53\u001b[0m, in \u001b[0;36mquick_execute\u001b[1;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[0;32m     51\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m     52\u001b[0m   ctx\u001b[38;5;241m.\u001b[39mensure_initialized()\n\u001b[1;32m---> 53\u001b[0m   tensors \u001b[38;5;241m=\u001b[39m \u001b[43mpywrap_tfe\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mTFE_Py_Execute\u001b[49m\u001b[43m(\u001b[49m\u001b[43mctx\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_handle\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mop_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m     54\u001b[0m \u001b[43m                                      \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mattrs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnum_outputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     55\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m core\u001b[38;5;241m.\u001b[39m_NotOkStatusException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m     56\u001b[0m   \u001b[38;5;28;01mif\u001b[39;00m name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "\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=y_train.shape[1]))\n",
    "\n",
    "model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "\n",
    "checkpoint_path = \"lstm_vav_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=3, batch_size=128, verbose=1, callbacks=[checkpoint_callback])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.load_weights(checkpoint_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m12244/12244\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m110s\u001b[0m 9ms/step\n"
     ]
    }
   ],
   "source": [
    "test_predict1 = model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{0: 'zone_069_temp',\n",
       " 1: 'zone_069_fan_spd',\n",
       " 2: 'zone_068_temp',\n",
       " 3: 'zone_068_fan_spd',\n",
       " 4: 'zone_067_temp',\n",
       " 5: 'zone_067_fan_spd',\n",
       " 6: 'zone_066_temp',\n",
       " 7: 'zone_066_fan_spd',\n",
       " 8: 'zone_065_temp',\n",
       " 9: 'zone_065_fan_spd',\n",
       " 10: 'zone_064_temp',\n",
       " 11: 'zone_064_fan_spd',\n",
       " 12: 'zone_042_temp',\n",
       " 13: 'zone_042_fan_spd',\n",
       " 14: 'zone_041_temp',\n",
       " 15: 'zone_041_fan_spd',\n",
       " 16: 'zone_040_temp',\n",
       " 17: 'zone_040_fan_spd',\n",
       " 18: 'zone_039_temp',\n",
       " 19: 'zone_039_fan_spd',\n",
       " 20: 'zone_038_temp',\n",
       " 21: 'zone_038_fan_spd',\n",
       " 22: 'zone_037_temp',\n",
       " 23: 'zone_037_fan_spd',\n",
       " 24: 'zone_036_temp',\n",
       " 25: 'zone_036_fan_spd',\n",
       " 26: 'rtu_001_fltrd_sa_flow_tn',\n",
       " 27: 'rtu_001_sa_temp',\n",
       " 28: 'air_temp_set_1',\n",
       " 29: 'air_temp_set_2',\n",
       " 30: 'dew_point_temperature_set_1d',\n",
       " 31: 'relative_humidity_set_1',\n",
       " 32: 'solar_radiation_set_1',\n",
       " 33: 'zone_069_cooling_sp',\n",
       " 34: 'zone_069_heating_sp',\n",
       " 35: 'zone_067_cooling_sp',\n",
       " 36: 'zone_067_heating_sp',\n",
       " 37: 'zone_066_cooling_sp',\n",
       " 38: 'zone_066_heating_sp',\n",
       " 39: 'zone_065_cooling_sp',\n",
       " 40: 'zone_065_heating_sp',\n",
       " 41: 'zone_064_cooling_sp',\n",
       " 42: 'zone_064_heating_sp',\n",
       " 43: 'zone_042_cooling_sp',\n",
       " 44: 'zone_042_heating_sp',\n",
       " 45: 'zone_041_cooling_sp',\n",
       " 46: 'zone_041_heating_sp',\n",
       " 47: 'zone_039_cooling_sp',\n",
       " 48: 'zone_039_heating_sp',\n",
       " 49: 'zone_038_cooling_sp',\n",
       " 50: 'zone_038_heating_sp',\n",
       " 51: 'zone_037_cooling_sp',\n",
       " 52: 'zone_037_heating_sp',\n",
       " 53: 'zone_036_cooling_sp',\n",
       " 54: 'zone_036_heating_sp'}"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idx_to_col = {i:col for i,col in enumerate(traindataset_df.drop(columns = ['date']).columns)}\n",
    "idx_to_col"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib qt\n",
    "plt.figure()\n",
    "var = 10\n",
    "plt.plot(y_test[:,var], label='Original Testing Data', color='blue')\n",
    "plt.plot(test_predict1[:,var], label='Predicted Testing Data', color='red',alpha=0.8)\n",
    "anomalies = np.where(abs(test_predict1[:,var] - y_test[:,var]) > 0.5)\n",
    "plt.scatter(anomalies,test_predict1[anomalies,var], color='black',marker =\"o\",s=100 )\n",
    "\n",
    "\n",
    "plt.title('Testing Data - Predicted vs Actual')\n",
    "plt.xlabel('Time')\n",
    "plt.ylabel('Value')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.mixture import GaussianMixture\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "\n",
    "# Generating random data for demonstration\n",
    "np.random.seed(0)\n",
    "X =  test_predict1 - y_test\n",
    "\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X = pca.fit_transform(X)\n",
    "\n",
    "\n",
    "# Creating the GMM instance with desired number of clusters\n",
    "gmm = GaussianMixture(n_components=2)\n",
    "\n",
    "# Fitting the model to the data\n",
    "gmm.fit(X)\n",
    "\n",
    "# Getting the cluster labels\n",
    "labels = gmm.predict(X)\n",
    "\n",
    "# Plotting the data points with colors representing different clusters\n",
    "plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis', alpha=0.5)\n",
    "plt.title('GMM Clustering')\n",
    "plt.xlabel('Feature 1')\n",
    "plt.ylabel('Feature 2')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['kmeans_vav_1.pkl']"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.cluster import KMeans\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "# Generating random data for demonstration\n",
    "np.random.seed(0)\n",
    "X = (test_predict1 - y_test)\n",
    "\n",
    "k = 2\n",
    "\n",
    "kmeans = KMeans(n_clusters=k)\n",
    "\n",
    "kmeans.fit(X)\n",
    "\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X = pca.fit_transform(X)\n",
    "\n",
    "\n",
    "\n",
    "# Getting the cluster centers and labels\n",
    "centroids = kmeans.cluster_centers_\n",
    "centroids = pca.transform(centroids)\n",
    "labels = kmeans.labels_\n",
    "\n",
    "# Plotting the data points and cluster centers\n",
    "plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis', alpha=0.5)\n",
    "plt.scatter(centroids[:, 0], centroids[:, 1], marker='x', c='red', s=200, linewidths=2)\n",
    "plt.title('KMeans Clustering')\n",
    "plt.xlabel('Feature 1')\n",
    "plt.ylabel('Feature 2')\n",
    "plt.show()\n",
    "\n",
    "joblib.dump(kmeans, 'kmeans_vav_1.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "k = 60\n",
    "X= test_predict1 - y_test\n",
    "processed_data = []\n",
    "feat_df = pd.DataFrame(columns=[\"mean\",\"std\",])\n",
    "for i in range(0,len(X), 60):\n",
    "    mean = X[i:i+k].mean(axis = 0)\n",
    "    std = X[i:i+k].std(axis = 0)\n",
    "    max = X[i:i+k].max(axis = 0)\n",
    "    min = X[i:i+k].min(axis = 0)\n",
    "    iqr = np.percentile(X[i:i+k], 75, axis=0) - np.percentile(X[i:i+k], 25,axis=0)\n",
    "    data = np.concatenate([mean, std, max, min, iqr])\n",
    "    processed_data.append([data])\n",
    "processed_data = np.concatenate(processed_data,axis=0) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = processed_data\n",
    "\n",
    "kmeans = KMeans(n_clusters=3, algorithm='elkan', max_iter=1000, n_init = 5)\n",
    "\n",
    "kmeans.fit(X)\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X = pca.fit_transform(X)\n",
    "\n",
    "\n",
    "# Getting the cluster centers and labels\n",
    "centroids = kmeans.cluster_centers_\n",
    "centroids = pca.transform(centroids)\n",
    "labels = kmeans.labels_\n",
    "\n",
    "# Plotting the data points and cluster centers\n",
    "plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis', alpha=0.5)\n",
    "plt.scatter(centroids[:, 0], centroids[:, 1], marker='x', c='red', s=200, linewidths=2)\n",
    "plt.title('KMeans Clustering')\n",
    "plt.xlabel('Feature 1')\n",
    "plt.ylabel('Feature 2')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.mixture import GaussianMixture\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "# Generating random data for demonstration\n",
    "np.random.seed(0)\n",
    "X = processed_data\n",
    "\n",
    "# Creating the GMM instance with desired number of clusters\n",
    "gmm = GaussianMixture(n_components=2, init_params='k-means++')\n",
    "\n",
    "# Fitting the model to the data\n",
    "gmm.fit(X)\n",
    "labels = gmm.predict(X)\n",
    "\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X = pca.fit_transform(X)\n",
    "\n",
    "\n",
    "# Getting the cluster labels\n",
    "\n",
    "# Plotting the data points with colors representing different clusters\n",
    "plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis', alpha=0.5)\n",
    "plt.title('GMM Clustering')\n",
    "plt.xlabel('Feature 1')\n",
    "plt.ylabel('Feature 2')\n",
    "plt.show()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.cluster import KMeans\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "# Generating random data for demonstration\n",
    "np.random.seed(0)\n",
    "X = test_predict1 - y_test \n",
    "\n",
    "kmeans = KMeans(n_clusters=2)\n",
    "\n",
    "kmeans.fit(X)\n",
    "\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X = pca.fit_transform(X)\n",
    "\n",
    "\n",
    "\n",
    "# Getting the cluster centers and labels\n",
    "centroids = kmeans.cluster_centers_\n",
    "centroids = pca.transform(centroids)\n",
    "labels = kmeans.labels_\n",
    "\n",
    "# Plotting the data points and cluster centers\n",
    "plt.figure()\n",
    "plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis', alpha=0.5)\n",
    "plt.scatter(centroids[:, 0], centroids[:, 1], marker='x', c='red', s=200, linewidths=2)\n",
    "plt.text(centroids[0,0], centroids[0,1], 'Normal', fontsize=12, color='red')\n",
    "plt.text(centroids[1,0], centroids[1,1], 'Anomaly', fontsize=12, color='red')\n",
    "plt.title('KMeans Clustering')\n",
    "plt.xlabel('Feature 1')\n",
    "plt.ylabel('Feature 2')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "329810"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(labels==0)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "tensorflow",
   "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
}