{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "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"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>zone_047_hw_valve</th>\n",
       "      <th>rtu_004_sat_sp_tn</th>\n",
       "      <th>zone_047_temp</th>\n",
       "      <th>zone_047_fan_spd</th>\n",
       "      <th>rtu_004_fltrd_sa_flow_tn</th>\n",
       "      <th>rtu_004_sa_temp</th>\n",
       "      <th>rtu_004_pa_static_stpt_tn</th>\n",
       "      <th>rtu_004_oa_flow_tn</th>\n",
       "      <th>rtu_004_oadmpr_pct</th>\n",
       "      <th>...</th>\n",
       "      <th>zone_047_heating_sp</th>\n",
       "      <th>Unnamed: 47_y</th>\n",
       "      <th>hvac_S</th>\n",
       "      <th>hp_hws_temp</th>\n",
       "      <th>aru_001_cwr_temp</th>\n",
       "      <th>aru_001_cws_fr_gpm</th>\n",
       "      <th>aru_001_cws_temp</th>\n",
       "      <th>aru_001_hwr_temp</th>\n",
       "      <th>aru_001_hws_fr_gpm</th>\n",
       "      <th>aru_001_hws_temp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2018-01-01 00:00:00</td>\n",
       "      <td>100.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>67.5</td>\n",
       "      <td>20.0</td>\n",
       "      <td>9265.604</td>\n",
       "      <td>66.1</td>\n",
       "      <td>0.06</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>28.0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>75.3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2018-01-01 00:01:00</td>\n",
       "      <td>100.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>67.5</td>\n",
       "      <td>20.0</td>\n",
       "      <td>9265.604</td>\n",
       "      <td>66.0</td>\n",
       "      <td>0.06</td>\n",
       "      <td>6572.099162</td>\n",
       "      <td>28.0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>75.3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2018-01-01 00:02:00</td>\n",
       "      <td>100.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>67.5</td>\n",
       "      <td>20.0</td>\n",
       "      <td>9708.240</td>\n",
       "      <td>66.1</td>\n",
       "      <td>0.06</td>\n",
       "      <td>7628.832542</td>\n",
       "      <td>28.0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>75.3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2018-01-01 00:03:00</td>\n",
       "      <td>100.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>67.5</td>\n",
       "      <td>20.0</td>\n",
       "      <td>9611.638</td>\n",
       "      <td>66.1</td>\n",
       "      <td>0.06</td>\n",
       "      <td>7710.294617</td>\n",
       "      <td>28.0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>75.3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2018-01-01 00:04:00</td>\n",
       "      <td>100.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>67.5</td>\n",
       "      <td>20.0</td>\n",
       "      <td>9215.110</td>\n",
       "      <td>66.0</td>\n",
       "      <td>0.06</td>\n",
       "      <td>7139.184090</td>\n",
       "      <td>28.0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>75.3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2072149</th>\n",
       "      <td>2020-12-31 23:58:00</td>\n",
       "      <td>100.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>63.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>18884.834</td>\n",
       "      <td>64.4</td>\n",
       "      <td>0.06</td>\n",
       "      <td>2938.320000</td>\n",
       "      <td>23.4</td>\n",
       "      <td>...</td>\n",
       "      <td>71.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>23.145000</td>\n",
       "      <td>123.8</td>\n",
       "      <td>56.25</td>\n",
       "      <td>54.71</td>\n",
       "      <td>56.4</td>\n",
       "      <td>123.42</td>\n",
       "      <td>61.6</td>\n",
       "      <td>122.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2072150</th>\n",
       "      <td>2020-12-31 23:58:00</td>\n",
       "      <td>100.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>63.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>18884.834</td>\n",
       "      <td>64.4</td>\n",
       "      <td>0.06</td>\n",
       "      <td>2938.320000</td>\n",
       "      <td>23.4</td>\n",
       "      <td>...</td>\n",
       "      <td>71.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>23.145000</td>\n",
       "      <td>123.8</td>\n",
       "      <td>56.25</td>\n",
       "      <td>54.71</td>\n",
       "      <td>56.4</td>\n",
       "      <td>123.42</td>\n",
       "      <td>61.6</td>\n",
       "      <td>122.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2072151</th>\n",
       "      <td>2020-12-31 23:59:00</td>\n",
       "      <td>100.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>63.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>19345.508</td>\n",
       "      <td>64.3</td>\n",
       "      <td>0.06</td>\n",
       "      <td>3154.390000</td>\n",
       "      <td>23.4</td>\n",
       "      <td>...</td>\n",
       "      <td>71.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>23.145000</td>\n",
       "      <td>123.8</td>\n",
       "      <td>56.25</td>\n",
       "      <td>54.71</td>\n",
       "      <td>56.4</td>\n",
       "      <td>123.42</td>\n",
       "      <td>61.6</td>\n",
       "      <td>122.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2072152</th>\n",
       "      <td>2020-12-31 23:59:00</td>\n",
       "      <td>100.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>63.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>19345.508</td>\n",
       "      <td>64.3</td>\n",
       "      <td>0.06</td>\n",
       "      <td>3154.390000</td>\n",
       "      <td>23.4</td>\n",
       "      <td>...</td>\n",
       "      <td>71.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>23.145000</td>\n",
       "      <td>123.8</td>\n",
       "      <td>56.25</td>\n",
       "      <td>54.71</td>\n",
       "      <td>56.4</td>\n",
       "      <td>123.42</td>\n",
       "      <td>61.6</td>\n",
       "      <td>122.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2072153</th>\n",
       "      <td>2021-01-01 00:00:00</td>\n",
       "      <td>100.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>63.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>18650.232</td>\n",
       "      <td>64.1</td>\n",
       "      <td>0.06</td>\n",
       "      <td>3076.270000</td>\n",
       "      <td>22.9</td>\n",
       "      <td>...</td>\n",
       "      <td>71.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>23.788947</td>\n",
       "      <td>123.8</td>\n",
       "      <td>56.25</td>\n",
       "      <td>54.71</td>\n",
       "      <td>56.4</td>\n",
       "      <td>123.42</td>\n",
       "      <td>61.6</td>\n",
       "      <td>122.36</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2072154 rows × 30 columns</p>\n",
       "</div>"
      ],
      "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": 2,
     "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": 3,
   "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                            394570\n",
       "zone_047_heating_sp                           0\n",
       "Unnamed: 47_y                            394570\n",
       "hvac_S                                    13035\n",
       "hp_hws_temp                                   0\n",
       "aru_001_cwr_temp                         524350\n",
       "aru_001_cws_fr_gpm                       524350\n",
       "aru_001_cws_temp                         524350\n",
       "aru_001_hwr_temp                         299165\n",
       "aru_001_hws_fr_gpm                       299165\n",
       "aru_001_hws_temp                         299165\n",
       "dtype: int64"
      ]
     },
     "execution_count": 3,
     "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(2019, 4, 1)) & (final_df.date.dt.date< date(2020, 2, 15))]\n",
    "final_df.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "testdataset_df = final_df[(final_df.date.dt.date <date(2019, 11, 8))]\n",
    "\n",
    "traindataset_df = final_df[ (final_df.date.dt.date >date(2019, 11, 8))]\n",
    "\n",
    "testdataset = testdataset_df[['rtu_004_oa_temp','rtu_004_ra_temp','hp_hws_temp','rtu_004_oa_flow_tn','rtu_004_oadmpr_pct',\n",
    "                    'rtu_004_sat_sp_tn','rtu_004_rf_vfd_spd_fbk_tn','rtu_004_ma_temp','rtu_004_sa_temp','rtu_004_fltrd_sa_flow_tn',\n",
    "                    'rtu_004_sf_vfd_spd_fbk_tn']].values\n",
    "\n",
    "\n",
    "traindataset = traindataset_df[['rtu_004_oa_temp','rtu_004_ra_temp','hp_hws_temp','rtu_004_oa_flow_tn','rtu_004_oadmpr_pct',\n",
    "                    'rtu_004_sat_sp_tn','rtu_004_rf_vfd_spd_fbk_tn','rtu_004_ma_temp','rtu_004_sa_temp','rtu_004_fltrd_sa_flow_tn',\n",
    "                    'rtu_004_sf_vfd_spd_fbk_tn']].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "traindataset = traindataset.astype('float32')\n",
    "testdataset = testdataset.astype('float32')\n",
    "\n",
    "\n",
    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
    "traindataset = scaler.fit_transform(traindataset)\n",
    "testdataset = scaler.transform(testdataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n"
     ]
    },
    {
     "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[1m2745/3220\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m6s\u001b[0m 14ms/step - loss: 0.0100"
     ]
    },
    {
     "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[6], line 38\u001b[0m\n\u001b[0;32m     36\u001b[0m checkpoint_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlstm2.keras\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m     37\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---> 38\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;43m10\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;43m64\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;32mc:\\Users\\jerin\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\keras\\src\\utils\\traceback_utils.py:118\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    116\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m    117\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 118\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    119\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    120\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;32mc:\\Users\\jerin\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\keras\\src\\backend\\tensorflow\\trainer.py:323\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    321\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    322\u001b[0m     callbacks\u001b[38;5;241m.\u001b[39mon_train_batch_begin(step)\n\u001b[1;32m--> 323\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    324\u001b[0m     callbacks\u001b[38;5;241m.\u001b[39mon_train_batch_end(\n\u001b[0;32m    325\u001b[0m         step, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_pythonify_logs(logs)\n\u001b[0;32m    326\u001b[0m     )\n\u001b[0;32m    327\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstop_training:\n",
      "File \u001b[1;32mc:\\Users\\jerin\\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;32mc:\\Users\\jerin\\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;32mc:\\Users\\jerin\\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;32mc:\\Users\\jerin\\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;32mc:\\Users\\jerin\\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;32mc:\\Users\\jerin\\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;32mc:\\Users\\jerin\\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;32mc:\\Users\\jerin\\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;32mc:\\Users\\jerin\\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": [
    "train,test = traindataset,testdataset\n",
    "\n",
    "def create_dataset(dataset,time_step):\n",
    "    x1,x2,x3,x4,x5,x6,x7,x8,x9,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",
    "        x8.append(dataset[i:(i+time_step), 7])\n",
    "        # x9.append(dataset[i:(i+time_step), 8])\n",
    "        Y.append([dataset[i + time_step, 7]])\n",
    "    x1,x2,x3,x4,x5,x6,x7,x8 =  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)\n",
    "    Y = np.reshape(Y,(len(Y),1))\n",
    "    return np.stack([x1,x2,x3,x4,x5,x6,x7,x8],axis=2),Y\n",
    "\n",
    "\n",
    "\n",
    "\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",
    "\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=1))\n",
    "\n",
    "model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "\n",
    "checkpoint_path = \"lstm2.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=10, batch_size=64, verbose=1, callbacks=[checkpoint_callback])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/5\n",
      "\u001b[1m3218/3220\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 1.8977e-04\n",
      "Epoch 1: val_loss improved from inf to 0.01131, saving model to lstm2.keras\n",
      "\u001b[1m3220/3220\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m94s\u001b[0m 29ms/step - loss: 1.8977e-04 - val_loss: 0.0113\n",
      "Epoch 2/5\n",
      "\u001b[1m3219/3220\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 1.7357e-04\n",
      "Epoch 2: val_loss did not improve from 0.01131\n",
      "\u001b[1m3220/3220\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m91s\u001b[0m 28ms/step - loss: 1.7358e-04 - val_loss: 0.0123\n",
      "Epoch 3/5\n",
      "\u001b[1m3219/3220\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 1.6701e-04\n",
      "Epoch 3: val_loss did not improve from 0.01131\n",
      "\u001b[1m3220/3220\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m92s\u001b[0m 28ms/step - loss: 1.6701e-04 - val_loss: 0.0127\n",
      "Epoch 4/5\n",
      "\u001b[1m3220/3220\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 1.7043e-04\n",
      "Epoch 4: val_loss did not improve from 0.01131\n",
      "\u001b[1m3220/3220\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m91s\u001b[0m 28ms/step - loss: 1.7043e-04 - val_loss: 0.0131\n",
      "Epoch 5/5\n",
      "\u001b[1m3218/3220\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 1.6319e-04\n",
      "Epoch 5: val_loss did not improve from 0.01131\n",
      "\u001b[1m3220/3220\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m104s\u001b[0m 32ms/step - loss: 1.6319e-04 - val_loss: 0.0134\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.src.callbacks.history.History at 0x2a05f486ed0>"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "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": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m9900/9900\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m34s\u001b[0m 3ms/step\n"
     ]
    }
   ],
   "source": [
    "# train_predict = model.predict(X_train)\n",
    "test_predict = model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib qt\n",
    "#'rtu_004_ma_temp','rtu_004_sa_temp'\n",
    "var = 0\n",
    "plt.plot(testdataset_df['date'][31:],y_test, label='Original Testing Data', color='blue')\n",
    "plt.plot(testdataset_df['date'][31:],test_predict, label='Predicted Testing Data', color='red',alpha=0.8)\n",
    "# anomalies = np.where(abs(test_predict[:,var] - y_test[:,var]) > 0.38)[0]\n",
    "# plt.scatter(anomalies,test_predict[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": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
     ]
    }
   ],
   "source": [
    "from tensorflow.keras.models import load_model\n",
    "# model.save(\"MA_temp_model.h5\") \n",
    "# loaded_model = load_model(\"MA_temp_model.h5\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "ENERGY DATA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 267,
   "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>air_temp_set_1</th>\n",
       "      <th>air_temp_set_2</th>\n",
       "      <th>dew_point_temperature_set_1d</th>\n",
       "      <th>relative_humidity_set_1</th>\n",
       "      <th>solar_radiation_set_1</th>\n",
       "      <th>wifi_third_south</th>\n",
       "      <th>wifi_fourth_south</th>\n",
       "      <th>hvac_N</th>\n",
       "      <th>hvac_S</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2018-01-01 00:00:00</td>\n",
       "      <td>11.64</td>\n",
       "      <td>11.51</td>\n",
       "      <td>8.1</td>\n",
       "      <td>79.07</td>\n",
       "      <td>86.7</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2018-01-01 00:01:00</td>\n",
       "      <td>11.64</td>\n",
       "      <td>11.51</td>\n",
       "      <td>8.1</td>\n",
       "      <td>79.07</td>\n",
       "      <td>86.7</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  date  air_temp_set_1  air_temp_set_2  \\\n",
       "0  2018-01-01 00:00:00           11.64           11.51   \n",
       "1  2018-01-01 00:01:00           11.64           11.51   \n",
       "\n",
       "   dew_point_temperature_set_1d  relative_humidity_set_1  \\\n",
       "0                           8.1                    79.07   \n",
       "1                           8.1                    79.07   \n",
       "\n",
       "   solar_radiation_set_1  wifi_third_south  wifi_fourth_south  hvac_N  hvac_S  \n",
       "0                   86.7               NaN                NaN     NaN     NaN  \n",
       "1                   86.7               NaN                NaN     NaN     NaN  "
      ]
     },
     "execution_count": 267,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "zone =  [\"18\", \"25\", \"26\", \"45\", \"48\", \"55\", \"56\", \"61\",\"16\", \"17\", \"21\", \"23\", \"24\", \"46\", \"47\", \"51\", \"52\", \"53\", \"54\"]\n",
    "rtu = [\"rtu_001\",\"rtu_002\",\"rtu_003\",\"rtu_004\"]\n",
    "wing = [\"hvac_N\",\"hvac_S\"]\n",
    "env = [\"air_temp_set_1\",\"air_temp_set_2\",\"dew_point_temperature_set_1d\",\"relative_humidity_set_1\",\"solar_radiation_set_1\"]\n",
    "wifi=[\"wifi_third_south\",\"wifi_fourth_south\"]\n",
    "# any(sub in col for sub in zone) or\n",
    "energy_data = merged[[\"date\"]+[col for col in merged.columns if \n",
    "                               any(sub in col for sub in env) or any(sub in col for sub in wifi)]+wing]\n",
    "df_filtered = energy_data[[col for col in energy_data.columns if 'Unnamed' not in col]]\n",
    "df_filtered = df_filtered[[col for col in df_filtered.columns if 'co2' not in col]]\n",
    "df_filtered = df_filtered[[col for col in df_filtered.columns if 'templogger' not in col]]\n",
    "# df_filtered = df_filtered.dropna()\n",
    "df_filtered.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 268,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "There are NA values in the DataFrame columns.\n"
     ]
    }
   ],
   "source": [
    "df_filtered['date'] = pd.to_datetime(df_filtered['date'], format = \"%Y-%m-%d %H:%M:%S\")\n",
    "df_filtered = df_filtered[ (df_filtered.date.dt.date >date(2019, 4, 1)) & (df_filtered.date.dt.date< date(2020, 2, 15))]\n",
    "# df_filtered.isna().sum()\n",
    "if df_filtered.isna().any().any():\n",
    "    print(\"There are NA values in the DataFrame columns.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 269,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 269,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "testdataset_df = df_filtered[(df_filtered.date.dt.date <date(2019, 8, 21))]\n",
    "\n",
    "traindataset_df = df_filtered[ (df_filtered.date.dt.date >date(2019, 11, 8))]\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": 270,
   "metadata": {},
   "outputs": [],
   "source": [
    "traindataset = traindataset.astype('float32')\n",
    "testdataset = testdataset.astype('float32')\n",
    "\n",
    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
    "traindataset = scaler.fit_transform(traindataset)\n",
    "testdataset = scaler.transform(testdataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 271,
   "metadata": {},
   "outputs": [],
   "source": [
    "train,test = traindataset,testdataset\n",
    "\n",
    "def create_dataset(dataset,time_step):\n",
    "    x = [[] for _ in range(9)] \n",
    "    Y = []\n",
    "    for i in range(len(dataset) - time_step - 1):\n",
    "        for j in range(9):\n",
    "            x[j].append(dataset[i:(i + time_step), j])\n",
    "        Y.append([dataset[i + time_step, 7],dataset[i + time_step, 8]])\n",
    "    x= [np.array(feature_list) for feature_list in x]\n",
    "    Y = np.reshape(Y,(len(Y),2))\n",
    "    return np.stack(x,axis=2),Y\n",
    "\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",
    "\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=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=3, batch_size=64, verbose=1, callbacks=[checkpoint_callback])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 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=10, batch_size=64, verbose=1, callbacks=[checkpoint_callback])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 272,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m6345/6345\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m42s\u001b[0m 6ms/step\n"
     ]
    }
   ],
   "source": [
    "from tensorflow.keras.models import load_model\n",
    "checkpoint_path = \"lstm_energy_01.keras\"\n",
    "model = load_model(checkpoint_path)\n",
    "test_predict1 = model.predict(X_test)\n",
    "# train_predict1 = model.predict(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 273,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib qt\n",
    "var = 1\n",
    "plt.plot(testdataset_df['date'][31:],y_test[:,1], label='Original Testing Data', color='blue')\n",
    "plt.plot(testdataset_df['date'][31:],test_predict1[:,1], label='Predicted Testing Data', color='red',alpha=0.8)\n",
    "# anomalies = np.where(abs(test_predict[:,var] - y_test[:,var]) > 0.38)[0]\n",
    "# plt.scatter(anomalies,test_predict[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": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
     ]
    }
   ],
   "source": [
    "# from tensorflow.keras.models import load_model\n",
    "# model.save(\"energy_model_01.h5\") "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x152fd38cd10>]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%matplotlib qt\n",
    "plt.plot(df_filtered['date'],df_filtered['hvac_S'])\n",
    "plt.plot(df_filtered['date'],df_filtered['rtu_003_sf_vfd_spd_fbk_tn'])\n",
    "plt.plot(df_filtered['date'],df_filtered['zone_025_temp'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x1fe7e211d90>]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plt.plot(merged['hvac_S'])\n",
    "plt.plot(testdataset_df['hvac_S'])\n",
    "plt.plot(traindataset_df['hvac_S'],'r')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x1fe8ecf5bd0>]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plt.plot(merged['hvac_N'])\n",
    "plt.plot(testdataset_df['hvac_N'])\n",
    "plt.plot(traindataset_df['hvac_N'],'r')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# merged.columns.to_list()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.16.1\n"
     ]
    }
   ],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "LSTM 2.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 325,
   "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>hp_hws_temp</th>\n",
       "      <th>rtu_001_sat_sp_tn</th>\n",
       "      <th>rtu_002_sat_sp_tn</th>\n",
       "      <th>rtu_003_sat_sp_tn</th>\n",
       "      <th>rtu_004_sat_sp_tn</th>\n",
       "      <th>rtu_001_fltrd_sa_flow_tn</th>\n",
       "      <th>rtu_002_fltrd_sa_flow_tn</th>\n",
       "      <th>rtu_003_fltrd_sa_flow_tn</th>\n",
       "      <th>rtu_004_fltrd_sa_flow_tn</th>\n",
       "      <th>...</th>\n",
       "      <th>rtu_002_fltrd_lvl2_plenum_press_tn</th>\n",
       "      <th>rtu_003_fltrd_lvl2_plenum_press_tn</th>\n",
       "      <th>rtu_004_fltrd_lvl2_plenum_press_tn</th>\n",
       "      <th>wifi_third_south</th>\n",
       "      <th>wifi_fourth_south</th>\n",
       "      <th>air_temp_set_1</th>\n",
       "      <th>air_temp_set_2</th>\n",
       "      <th>dew_point_temperature_set_1d</th>\n",
       "      <th>relative_humidity_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>75.3</td>\n",
       "      <td>68.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>65.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>14131.449</td>\n",
       "      <td>13998.757</td>\n",
       "      <td>13558.539</td>\n",
       "      <td>9265.604</td>\n",
       "      <td>...</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.050</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11.64</td>\n",
       "      <td>11.51</td>\n",
       "      <td>8.1</td>\n",
       "      <td>79.07</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>75.3</td>\n",
       "      <td>68.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>65.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>14164.429</td>\n",
       "      <td>14065.259</td>\n",
       "      <td>13592.909</td>\n",
       "      <td>9265.604</td>\n",
       "      <td>...</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.04</td>\n",
       "      <td>0.046</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11.64</td>\n",
       "      <td>11.51</td>\n",
       "      <td>8.1</td>\n",
       "      <td>79.07</td>\n",
       "      <td>86.7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 65 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                  date  hp_hws_temp  rtu_001_sat_sp_tn  rtu_002_sat_sp_tn  \\\n",
       "0  2018-01-01 00:00:00         75.3               68.0               70.0   \n",
       "1  2018-01-01 00:01:00         75.3               68.0               70.0   \n",
       "\n",
       "   rtu_003_sat_sp_tn  rtu_004_sat_sp_tn  rtu_001_fltrd_sa_flow_tn  \\\n",
       "0               65.0               69.0                 14131.449   \n",
       "1               65.0               69.0                 14164.429   \n",
       "\n",
       "   rtu_002_fltrd_sa_flow_tn  rtu_003_fltrd_sa_flow_tn  \\\n",
       "0                 13998.757                 13558.539   \n",
       "1                 14065.259                 13592.909   \n",
       "\n",
       "   rtu_004_fltrd_sa_flow_tn  ...  rtu_002_fltrd_lvl2_plenum_press_tn  \\\n",
       "0                  9265.604  ...                                0.05   \n",
       "1                  9265.604  ...                                0.05   \n",
       "\n",
       "   rtu_003_fltrd_lvl2_plenum_press_tn  rtu_004_fltrd_lvl2_plenum_press_tn  \\\n",
       "0                                0.05                               0.050   \n",
       "1                                0.04                               0.046   \n",
       "\n",
       "   wifi_third_south  wifi_fourth_south  air_temp_set_1  air_temp_set_2  \\\n",
       "0               NaN                NaN           11.64           11.51   \n",
       "1               NaN                NaN           11.64           11.51   \n",
       "\n",
       "   dew_point_temperature_set_1d  relative_humidity_set_1  \\\n",
       "0                           8.1                    79.07   \n",
       "1                           8.1                    79.07   \n",
       "\n",
       "   solar_radiation_set_1  \n",
       "0                   86.7  \n",
       "1                   86.7  \n",
       "\n",
       "[2 rows x 65 columns]"
      ]
     },
     "execution_count": 325,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rtu = [\"rtu_003\",\"rtu_004\",\"rtu_001\",\"rtu_002\"]\n",
    "# wing = [\"hvac_N\",\"hvac_S\"]\n",
    "env = [\"air_temp_set_1\",\"air_temp_set_2\",\"dew_point_temperature_set_1d\",\"relative_humidity_set_1\",\"solar_radiation_set_1\"]\n",
    "wifi=[\"wifi_third_south\",\"wifi_fourth_south\"]\n",
    "# any(sub in col for sub in zone) or\n",
    "energy_data = merged[[\"date\",\"hp_hws_temp\"]+[col for col in merged.columns if \n",
    "                               any(sub in col for sub in rtu) or any(sub in col for sub in wifi)]+env]\n",
    "df_filtered = energy_data[[col for col in energy_data.columns if 'Unnamed' not in col]]\n",
    "df_filtered = df_filtered[[col for col in df_filtered.columns if 'co2' not in col]]\n",
    "df_filtered = df_filtered[[col for col in df_filtered.columns if 'templogger' not in col]]\n",
    "# df_filtered = df_filtered.dropna()\n",
    "df_filtered.head(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 363,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_filtered['date'] = pd.to_datetime(df_filtered['date'], format = \"%Y-%m-%d %H:%M:%S\")\n",
    "df_filtered = df_filtered[ (df_filtered.date.dt.date >date(2018, 5, 1)) & (df_filtered.date.dt.date< date(2020, 5, 1))] #(2018, 5, 1)\n",
    "# df_filtered.isna().sum()\n",
    "if df_filtered.isna().any().any():\n",
    "    print(\"There are NA values in the DataFrame columns.\",df_filtered.isna().sum().tolist())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 364,
   "metadata": {},
   "outputs": [],
   "source": [
    "# df_filtered = df_filtered.loc[:,['date','hp_hws_temp',\n",
    "#  'rtu_003_sa_temp',\n",
    "#  'rtu_003_oadmpr_pct',\n",
    "#  'rtu_003_ra_temp',\n",
    "#  'rtu_003_oa_temp',\n",
    "#  'rtu_003_ma_temp',\n",
    "#  'rtu_003_sf_vfd_spd_fbk_tn',\n",
    "#  'rtu_003_rf_vfd_spd_fbk_tn',\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",
    "df_filtered = df_filtered.loc[:,['date','hp_hws_temp',\n",
    " 'rtu_003_sa_temp',\n",
    " 'rtu_003_oadmpr_pct',\n",
    " 'rtu_003_ra_temp',\n",
    " 'rtu_003_oa_temp',\n",
    " 'rtu_003_ma_temp',\n",
    " 'rtu_003_sf_vfd_spd_fbk_tn',\n",
    " 'rtu_003_rf_vfd_spd_fbk_tn',\n",
    " 'rtu_004_sa_temp',\n",
    " 'rtu_004_oadmpr_pct',\n",
    " 'rtu_004_ra_temp',\n",
    " 'rtu_004_oa_temp',\n",
    " 'rtu_004_ma_temp',\n",
    " 'rtu_004_sf_vfd_spd_fbk_tn',\n",
    " 'rtu_004_rf_vfd_spd_fbk_tn',\n",
    " 'rtu_001_sa_temp',\n",
    " 'rtu_001_oadmpr_pct',\n",
    " 'rtu_001_ra_temp',\n",
    " 'rtu_001_oa_temp',\n",
    " 'rtu_001_ma_temp',\n",
    " 'rtu_001_sf_vfd_spd_fbk_tn',\n",
    " 'rtu_001_rf_vfd_spd_fbk_tn',\n",
    " 'rtu_002_sa_temp',\n",
    " 'rtu_002_oadmpr_pct',\n",
    " 'rtu_002_ra_temp',\n",
    " 'rtu_002_oa_temp',\n",
    " 'rtu_002_ma_temp',\n",
    " 'rtu_002_sf_vfd_spd_fbk_tn',\n",
    " 'rtu_002_rf_vfd_spd_fbk_tn',\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']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 365,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[]\n",
      "[]\n"
     ]
    }
   ],
   "source": [
    "df_filtered = df_filtered.dropna()\n",
    "# df_filtered.to_csv(\"sample_data.csv\",index=False)\n",
    "\n",
    "#----------------------------------------------------------------------------------\n",
    "# testdataset_df = df_filtered[(df_filtered.date.dt.date >date(2019, 7, 21))]\n",
    "\n",
    "# traindataset_df = df_filtered[(df_filtered.date.dt.date <date(2019, 7, 21))]\n",
    "\n",
    "testdataset_df = df_filtered[(df_filtered.date.dt.date >date(2020, 1, 1))]\n",
    "\n",
    "traindataset_df = df_filtered[(df_filtered.date.dt.date <date(2020, 1, 1))]\n",
    "\n",
    "\n",
    "# testdataset_df.to_csv(\"sample_data_02.csv\",index=False)\n",
    "# .ewm(com = 1000,adjust=True).mean()\n",
    "testdataset = testdataset_df.drop(columns=[\"date\"]).rolling(window=30,min_periods=1).mean()\n",
    "\n",
    "traindataset = traindataset_df.drop(columns=[\"date\"]).rolling(window=30,min_periods=1).mean().values\n",
    "# testdataset.to_csv(\"sample_data_smooth_01.csv\",index=False)\n",
    "columns_with_na_train = traindataset_df.columns[traindataset_df.isna().any()].tolist()\n",
    "columns_with_na_test = testdataset_df.columns[testdataset_df.isna().any()].tolist()\n",
    "print(columns_with_na_train)\n",
    "print(columns_with_na_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 366,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\jerin\\anaconda3\\envs\\smartbuilding\\Lib\\site-packages\\sklearn\\base.py:486: UserWarning: X has feature names, but StandardScaler was fitted without feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "\n",
    "traindataset = traindataset.astype('float32')\n",
    "testdataset = testdataset.astype('float32')\n",
    "\n",
    "scaler = StandardScaler()\n",
    "traindataset = scaler.fit_transform(traindataset)\n",
    "testdataset = scaler.transform(testdataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 250,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['scaler_1.pkl']"
      ]
     },
     "execution_count": 250,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import joblib\n",
    "# joblib.dump(scaler, 'scaler_1.pkl')\n",
    "# loaded_scaler = joblib.load('scaler.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 201,
   "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 1/5\n",
      "\u001b[1m8067/8067\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 0.0568\n",
      "Epoch 1: val_loss improved from inf to 0.08613, saving model to lstm_2rtu_smooth_02.keras\n",
      "\u001b[1m8067/8067\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m198s\u001b[0m 24ms/step - loss: 0.0568 - val_loss: 0.0861\n",
      "Epoch 2/5\n",
      "\u001b[1m8066/8067\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 9.6620e-04\n",
      "Epoch 2: val_loss improved from 0.08613 to 0.07149, saving model to lstm_2rtu_smooth_02.keras\n",
      "\u001b[1m8067/8067\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m189s\u001b[0m 23ms/step - loss: 9.6615e-04 - val_loss: 0.0715\n",
      "Epoch 3/5\n",
      "\u001b[1m8067/8067\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 5.0913e-04\n",
      "Epoch 3: val_loss improved from 0.07149 to 0.06955, saving model to lstm_2rtu_smooth_02.keras\n",
      "\u001b[1m8067/8067\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m187s\u001b[0m 23ms/step - loss: 5.0913e-04 - val_loss: 0.0695\n",
      "Epoch 4/5\n",
      "\u001b[1m8066/8067\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 3.9422e-04\n",
      "Epoch 4: val_loss improved from 0.06955 to 0.06820, saving model to lstm_2rtu_smooth_02.keras\n",
      "\u001b[1m8067/8067\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m185s\u001b[0m 23ms/step - loss: 3.9421e-04 - val_loss: 0.0682\n",
      "Epoch 5/5\n",
      "\u001b[1m8066/8067\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 15ms/step - loss: 3.6433e-04\n",
      "Epoch 5: val_loss improved from 0.06820 to 0.06542, saving model to lstm_2rtu_smooth_02.keras\n",
      "\u001b[1m8067/8067\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m188s\u001b[0m 23ms/step - loss: 3.6432e-04 - val_loss: 0.0654\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.src.callbacks.history.History at 0x15088066a50>"
      ]
     },
     "execution_count": 201,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#2 rtu model\n",
    "\n",
    "# train,test = traindataset,testdataset\n",
    "\n",
    "# def create_dataset(dataset,time_step):\n",
    "#     x = [[] for _ in range(20)] \n",
    "#     Y = []\n",
    "#     for i in range(len(dataset) - time_step - 1):\n",
    "#         for j in range(20):\n",
    "#             x[j].append(dataset[i:(i + time_step), j])\n",
    "#         Y.append([dataset[i + time_step, 0],dataset[i + time_step, 1],dataset[i + time_step, 2],dataset[i + time_step, 3],\n",
    "#                   dataset[i + time_step, 4],dataset[i + time_step, 5],\n",
    "#                   dataset[i + time_step, 6],dataset[i + time_step, 7],\n",
    "#                   dataset[i + time_step, 8],dataset[i + time_step, 9],dataset[i + time_step, 10],\n",
    "#                   dataset[i + time_step, 11],dataset[i + time_step, 12],\n",
    "#                   dataset[i + time_step, 13],dataset[i + time_step, 14]])\n",
    "#     x= [np.array(feature_list) for feature_list in x]\n",
    "#     Y = np.reshape(Y,(len(Y),15))\n",
    "#     return np.stack(x,axis=2),Y\n",
    "\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",
    "\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=15))\n",
    "\n",
    "# model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "\n",
    "# checkpoint_path = \"lstm_2rtu_smooth_02.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": 340,
   "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 1/5\n",
      "\u001b[1m7132/7133\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.0395\n",
      "Epoch 1: val_loss improved from inf to 0.06411, saving model to lstm_4rtu_smooth_04.keras\n",
      "\u001b[1m7133/7133\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m247s\u001b[0m 34ms/step - loss: 0.0395 - val_loss: 0.0641\n",
      "Epoch 2/5\n",
      "\u001b[1m7131/7133\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 0.0012\n",
      "Epoch 2: val_loss improved from 0.06411 to 0.04068, saving model to lstm_4rtu_smooth_04.keras\n",
      "\u001b[1m7133/7133\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m248s\u001b[0m 35ms/step - loss: 0.0012 - val_loss: 0.0407\n",
      "Epoch 3/5\n",
      "\u001b[1m7133/7133\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 7.2848e-04\n",
      "Epoch 3: val_loss improved from 0.04068 to 0.03509, saving model to lstm_4rtu_smooth_04.keras\n",
      "\u001b[1m7133/7133\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m245s\u001b[0m 34ms/step - loss: 7.2848e-04 - val_loss: 0.0351\n",
      "Epoch 4/5\n",
      "\u001b[1m7132/7133\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 5.7519e-04\n",
      "Epoch 4: val_loss did not improve from 0.03509\n",
      "\u001b[1m7133/7133\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m245s\u001b[0m 34ms/step - loss: 5.7520e-04 - val_loss: 0.0400\n",
      "Epoch 5/5\n",
      "\u001b[1m7132/7133\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 5.3138e-04\n",
      "Epoch 5: val_loss did not improve from 0.03509\n",
      "\u001b[1m7133/7133\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m244s\u001b[0m 34ms/step - loss: 5.3136e-04 - val_loss: 0.0357\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.src.callbacks.history.History at 0x229f1af02d0>"
      ]
     },
     "execution_count": 340,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train,test = traindataset,testdataset\n",
    "\n",
    "def create_dataset(dataset,time_step):\n",
    "    x = [[] for _ in range(34)] \n",
    "    Y = []\n",
    "    for i in range(len(dataset) - time_step - 1):\n",
    "        for j in range(34):\n",
    "            x[j].append(dataset[i:(i + time_step), j])\n",
    "        Y.append([dataset[i + time_step, 0],dataset[i + time_step, 1],dataset[i + time_step, 2],dataset[i + time_step, 3],\n",
    "                  dataset[i + time_step, 4],dataset[i + time_step, 5],\n",
    "                  dataset[i + time_step, 6],dataset[i + time_step, 7],\n",
    "                  dataset[i + time_step, 8],dataset[i + time_step, 9],dataset[i + time_step, 10],\n",
    "                  dataset[i + time_step, 11],dataset[i + time_step, 12],\n",
    "                  dataset[i + time_step, 13],dataset[i + time_step, 14],\n",
    "                  dataset[i + time_step, 15],dataset[i + time_step, 16],dataset[i + time_step, 17],\n",
    "                  dataset[i + time_step, 18],dataset[i + time_step, 19],\n",
    "                  dataset[i + time_step, 20],dataset[i + time_step, 21],\n",
    "                  dataset[i + time_step, 22],dataset[i + time_step, 23],dataset[i + time_step, 24],\n",
    "                  dataset[i + time_step, 24],dataset[i + time_step, 26],\n",
    "                  dataset[i + time_step, 27],dataset[i + time_step, 28]])\n",
    "    x= [np.array(feature_list) for feature_list in x]\n",
    "    Y = np.reshape(Y,(len(Y),29))\n",
    "    return np.stack(x,axis=2),Y\n",
    "\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",
    "\n",
    "model = Sequential()\n",
    "model.add(LSTM(units=80, return_sequences=True, input_shape=(X_train.shape[1], X_train.shape[2])))\n",
    "model.add(LSTM(units=60, return_sequences=True))\n",
    "model.add(LSTM(units=60))\n",
    "model.add(Dense(units=29))\n",
    "\n",
    "model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "\n",
    "checkpoint_path = \"lstm_4rtu_smooth_04.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": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/5\n",
      "\u001b[1m8061/8061\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 8.9528e-04\n",
      "Epoch 1: val_loss did not improve from 0.19006\n",
      "\u001b[1m8061/8061\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m239s\u001b[0m 30ms/step - loss: 8.9529e-04 - val_loss: 0.2020\n",
      "Epoch 2/5\n",
      "\u001b[1m8060/8061\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 8.0121e-04\n",
      "Epoch 2: val_loss improved from 0.19006 to 0.18934, saving model to lstm_4rtu_smooth_03.keras\n",
      "\u001b[1m8061/8061\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m234s\u001b[0m 29ms/step - loss: 8.0122e-04 - val_loss: 0.1893\n",
      "Epoch 3/5\n",
      "\u001b[1m8061/8061\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 9.8454e-04\n",
      "Epoch 3: val_loss did not improve from 0.18934\n",
      "\u001b[1m8061/8061\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m231s\u001b[0m 29ms/step - loss: 9.8453e-04 - val_loss: 0.2004\n",
      "Epoch 4/5\n",
      "\u001b[1m8060/8061\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 7.8113e-04\n",
      "Epoch 4: val_loss did not improve from 0.18934\n",
      "\u001b[1m8061/8061\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m232s\u001b[0m 29ms/step - loss: 7.8114e-04 - val_loss: 0.2031\n",
      "Epoch 5/5\n",
      "\u001b[1m8059/8061\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 8.8365e-04\n",
      "Epoch 5: val_loss did not improve from 0.18934\n",
      "\u001b[1m8061/8061\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m234s\u001b[0m 29ms/step - loss: 8.8360e-04 - val_loss: 0.1915\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.src.callbacks.history.History at 0x22477217090>"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "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": 284,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tensorflow.keras.models import load_model\n",
    "checkpoint_path = \"lstm_4rtu_smooth_02.keras\"\n",
    "model = load_model(checkpoint_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 341,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m11765/11765\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m84s\u001b[0m 7ms/step\n"
     ]
    }
   ],
   "source": [
    "test_predict1 = model.predict(X_test)\n",
    "# train_predict1 = model.predict(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 362,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib qt\n",
    "var = 13\n",
    "plt.plot(y_test[:,var], label='Original Testing Data', color='blue')\n",
    "plt.plot(test_predict2[:,var], label='Predicted Testing Data', color='red',alpha=0.8)\n",
    "# anomalies = np.where(abs(test_predict1[:,var] - y_test[:,var]) > 0.38)\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": 82,
   "metadata": {},
   "outputs": [],
   "source": [
    "params = [\n",
    " 'rtu_003_sa_temp',\n",
    " 'rtu_003_oadmpr_pct',\n",
    " 'rtu_003_ra_temp',\n",
    " 'rtu_003_oa_temp',\n",
    " 'rtu_003_ma_temp',\n",
    " 'rtu_003_sf_vfd_spd_fbk_tn',\n",
    " 'rtu_003_rf_vfd_spd_fbk_tn']\n",
    "\n",
    "idx_2_params = {}\n",
    "for i, param in enumerate(params):\n",
    "    idx_2_params[i] = param"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{0: 'rtu_003_sa_temp',\n",
       " 1: 'rtu_003_oadmpr_pct',\n",
       " 2: 'rtu_003_ra_temp',\n",
       " 3: 'rtu_003_oa_temp',\n",
       " 4: 'rtu_003_ma_temp',\n",
       " 5: 'rtu_003_sf_vfd_spd_fbk_tn',\n",
       " 6: 'rtu_003_rf_vfd_spd_fbk_tn'}"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "idx_2_params"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "KMEANS"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 195,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-3 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-3 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-3 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-3 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-3 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-3 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-3 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-3 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-3 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-3 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-3 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KMeans(n_clusters=1, random_state=10)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;KMeans<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.cluster.KMeans.html\">?<span>Documentation for KMeans</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>KMeans(n_clusters=1, random_state=10)</pre></div> </div></div></div></div>"
      ],
      "text/plain": [
       "KMeans(n_clusters=1, random_state=10)"
      ]
     },
     "execution_count": 195,
     "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",
    "np.random.seed(0)\n",
    "X1 = train_predict1[:,1:8] - y_train[:,1:8]\n",
    "X2 = train_predict1[:,8:15] - y_train[:,8:15]\n",
    "X3 = train_predict1[:,15:22] - y_train[:,15:22]\n",
    "X4 = train_predict1[:,22:29] - y_train[:,22:29]\n",
    "\n",
    "k = 1\n",
    "\n",
    "kmeans1 = KMeans(n_clusters=k, random_state=10) #2 for without smoothing\n",
    "kmeans1.fit(X1)\n",
    "kmeans2 = KMeans(n_clusters=k, random_state=10) #2 for without smoothing\n",
    "kmeans2.fit(X2)\n",
    "kmeans3 = KMeans(n_clusters=k, random_state=10) #2 for without smoothing\n",
    "kmeans3.fit(X3)\n",
    "kmeans4 = KMeans(n_clusters=k, random_state=10) #2 for without smoothing\n",
    "kmeans4.fit(X4)\n",
    "\n",
    "\n",
    "\n",
    "# pca = PCA(n_components=2)\n",
    "# X = pca.fit_transform(X2)\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "# # Getting the cluster centers and labels\n",
    "# centroids = pca.transform(kmeans.cluster_centers_)\n",
    "# labels = kmeans.labels_\n",
    "# print(kmeans.cluster_centers_)\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": 249,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['kmeans_model4.pkl']"
      ]
     },
     "execution_count": 249,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import joblib\n",
    "# joblib.dump(kmeans4, 'kmeans_model4.pkl')\n",
    "# joblib.dump(pca, 'pca_model.pkl')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 196,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['rtu_003_oadmpr_pct',\n",
       " 'rtu_003_oa_temp',\n",
       " 'rtu_003_ra_temp',\n",
       " 'rtu_003_rf_vfd_spd_fbk_tn',\n",
       " 'rtu_003_sf_vfd_spd_fbk_tn',\n",
       " 'rtu_003_ma_temp',\n",
       " 'rtu_003_sa_temp']"
      ]
     },
     "execution_count": 196,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[ params[i] for i in np.flip(np.argsort(abs(kmeans1.cluster_centers_[0])))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 323,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x228993bb690>]"
      ]
     },
     "execution_count": 323,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%matplotlib qt\n",
    "\n",
    "distance1 = np.linalg.norm((test_predict1[:,1:8]-y_test[:,1:8])-kmeans1.cluster_centers_[0], ord=2, axis = 1)\n",
    "distance2 = np.linalg.norm((test_predict1[:,8:15]-y_test[:,8:15])-kmeans2.cluster_centers_[0], ord=2, axis = 1)\n",
    "distance3 = np.linalg.norm((test_predict1[:,15:22]-y_test[:,15:22])-kmeans3.cluster_centers_[0], ord=2, axis = 1)\n",
    "distance4 = np.linalg.norm((test_predict1[:,22:29]-y_test[:,22:29])-kmeans4.cluster_centers_[0], ord=2, axis = 1)\n",
    "# distance_a = np.linalg.norm(test_predict1[:,8:]-a, ord=2, axis = 1)\n",
    "# plt.plot(y_test[:,23],alpha=0.6)\n",
    "plt.plot(y_test[:,3],alpha=0.6)\n",
    "# plt.plot(y_test[:,6],alpha=0.6)\n",
    "# plt.plot(y_test[:,7],alpha=0.6)\n",
    "plt.plot(test_predict1[:,3],alpha=0.6)\n",
    "plt.plot(abs(distance1)>2)\n",
    "# plt.plot(abs(distance2)>3.5)\n",
    "# plt.plot(abs(distance3)>5)\n",
    "# plt.plot(abs(distance4)>5)\n",
    "# plt.plot(distance_a>8,c='g')\n",
    "\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 277,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x2292a1bde50>]"
      ]
     },
     "execution_count": 277,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# fault = []\n",
    "# for i in range(60,len(distance4)):\n",
    "#     if np.mean((abs(distance4)>5)[i-60:i])>0.60 :\n",
    "#         fault.append(1)\n",
    "#     else:\n",
    "#         fault.append(0)\n",
    "plt.plot(fault,c='r')\n",
    "plt.plot(abs(distance4)>5,c='b')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x227020e5bd0>]"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test[:,23]\n",
    "arr = test[:, 23]\n",
    "condition = (arr < 5) & (np.arange(len(arr)) < 35000) & (np.arange(len(arr)) > 30000)\n",
    "arr[condition] = 2\n",
    "plt.plot(test[:,23])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 5.8607887e-02, -2.4713947e-01,  2.4978706e-01, -7.8289807e-01,\n",
       "        -2.0218764e-01, -2.8860569e-01,  2.7817219e-01,  2.4209845e-01],\n",
       "       [-2.6845999e-02,  1.2596852e-01,  9.6294099e-01,  2.0099232e-01,\n",
       "         3.3391420e-02,  7.7613303e-04, -7.1204931e-02, -9.7836025e-02]],\n",
       "      dtype=float32)"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pca.components_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "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), 40 ):\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": 38,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'processed_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[38], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m X \u001b[38;5;241m=\u001b[39m \u001b[43mprocessed_data\u001b[49m\n\u001b[0;32m      4\u001b[0m k \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m      6\u001b[0m kmeans \u001b[38;5;241m=\u001b[39m KMeans(n_clusters\u001b[38;5;241m=\u001b[39mk,random_state\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m4\u001b[39m)\n",
      "\u001b[1;31mNameError\u001b[0m: name 'processed_data' is not defined"
     ]
    }
   ],
   "source": [
    "X = processed_data\n",
    "\n",
    "\n",
    "k = 2\n",
    "\n",
    "kmeans = KMeans(n_clusters=k,random_state=4)\n",
    "\n",
    "kmeans.fit(X)\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X = pca.fit_transform(X)\n",
    "\n",
    "centroids = pca.transform(kmeans.cluster_centers_)\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": 88,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-1.76482953e-02, -4.84286715e-03],\n",
       "       [ 2.35918490e+01,  6.47383719e+00]])"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kmeans.cluster_centers_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "operands could not be broadcast together with shapes (481579,2) (15,) ",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[123], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m distance \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mlinalg\u001b[38;5;241m.\u001b[39mnorm(\u001b[43mpca\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtransform\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtest_predict1\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[43mkmeans\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcluster_centers_\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m]\u001b[49m, \u001b[38;5;28mord\u001b[39m\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m2\u001b[39m, axis \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m)\n\u001b[0;32m      2\u001b[0m plt\u001b[38;5;241m.\u001b[39mplot(y_test[:,\u001b[38;5;241m6\u001b[39m])\n\u001b[0;32m      3\u001b[0m plt\u001b[38;5;241m.\u001b[39mplot(distance\u001b[38;5;241m>\u001b[39m\u001b[38;5;241m50\u001b[39m,c\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
      "\u001b[1;31mValueError\u001b[0m: operands could not be broadcast together with shapes (481579,2) (15,) "
     ]
    }
   ],
   "source": [
    "distance = np.linalg.norm(pca.transform(test_predict1)-kmeans.cluster_centers_[1], ord=2, axis = 1)\n",
    "plt.plot(y_test[:,6])\n",
    "plt.plot(distance>50,c='r')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from sklearn.mixture import GaussianMixture\n",
    "# import numpy as np\n",
    "# import matplotlib.pyplot as plt\n",
    "\n",
    "# X = processed_data\n",
    "\n",
    "\n",
    "# gmm = GaussianMixture(n_components=2,random_state=10)\n",
    "# gmm.fit(X)\n",
    "# labels = gmm.predict(X)\n",
    "\n",
    "\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": 297,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x1d3fea8bb10>]"
      ]
     },
     "execution_count": 297,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merged['date'] = pd.to_datetime(merged['date'], format = \"%Y-%m-%d %H:%M:%S\")\n",
    "plt.plot(merged['date'],merged['wifi_fourth_south'])\n",
    "# plt.plot(merged['date'],merged['hp_hws_temp'])\n",
    "# plt.plot(df_filtered['date'],df_filtered['hp_hws_temp'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 234,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 234,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "smartbuilding",
   "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
}