{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "os              : Windows-10-10.0.19045-SP0\n",
      "python          : 3.11.5\n",
      "tsai            : 0.3.8\n",
      "fastai          : 2.7.13\n",
      "fastcore        : 1.5.29\n",
      "sklearn         : 1.3.2\n",
      "torch           : 2.1.1+cpu\n",
      "device          : cpu\n",
      "cpu cores       : 6\n",
      "threads per cpu : 1\n",
      "RAM             : 15.8 GB\n",
      "GPU memory      : [2.0] GB\n"
     ]
    }
   ],
   "source": [
    "import sklearn\n",
    "from tsai.basics import *\n",
    "my_setup(sklearn)\n",
    "import config"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['current_ir', 'electrical_energy', 'frequency', 'power', 'powerfactor', 'pressure', 'temperature', 'voltage_vb', 'voltage_vr', 'voltage_vy']\n"
     ]
    },
    {
     "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>current_ir</th>\n",
       "      <th>electrical_energy</th>\n",
       "      <th>frequency</th>\n",
       "      <th>power</th>\n",
       "      <th>powerfactor</th>\n",
       "      <th>pressure</th>\n",
       "      <th>temperature</th>\n",
       "      <th>parameter_timestamp</th>\n",
       "      <th>voltage_vb</th>\n",
       "      <th>voltage_vr</th>\n",
       "      <th>voltage_vy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>0.8</td>\n",
       "      <td>0.90</td>\n",
       "      <td>-10.0</td>\n",
       "      <td>2023-04-04 14:14:00</td>\n",
       "      <td>210.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>212</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.4</td>\n",
       "      <td>120.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>110.0</td>\n",
       "      <td>0.9</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2023-04-04 14:16:00</td>\n",
       "      <td>216.0</td>\n",
       "      <td>214.0</td>\n",
       "      <td>218</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.3</td>\n",
       "      <td>160.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>150.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.93</td>\n",
       "      <td>10.0</td>\n",
       "      <td>2023-04-04 14:18:00</td>\n",
       "      <td>222.0</td>\n",
       "      <td>220.0</td>\n",
       "      <td>224</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.8</td>\n",
       "      <td>380.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>370.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>35.0</td>\n",
       "      <td>2023-04-04 10:10:00</td>\n",
       "      <td>214.0</td>\n",
       "      <td>210.0</td>\n",
       "      <td>218</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.6</td>\n",
       "      <td>280.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>270.0</td>\n",
       "      <td>0.9</td>\n",
       "      <td>1.10</td>\n",
       "      <td>25.0</td>\n",
       "      <td>2023-04-04 14:24:00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>216.0</td>\n",
       "      <td>219</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   current_ir  electrical_energy  frequency  power  powerfactor  pressure  \\\n",
       "0         0.0               60.0       50.0   50.0          0.8      0.90   \n",
       "1         0.4              120.0       50.0  110.0          0.9      0.00   \n",
       "2         1.3              160.0       50.0  150.0          1.0      0.93   \n",
       "3         1.8              380.0       50.0  370.0          1.0      1.00   \n",
       "4         0.6              280.0       50.0  270.0          0.9      1.10   \n",
       "\n",
       "   temperature  parameter_timestamp  voltage_vb  voltage_vr  voltage_vy  \n",
       "0        -10.0  2023-04-04 14:14:00       210.0         0.0         212  \n",
       "1          0.0  2023-04-04 14:16:00       216.0       214.0         218  \n",
       "2         10.0  2023-04-04 14:18:00       222.0       220.0         224  \n",
       "3         35.0  2023-04-04 10:10:00       214.0       210.0         218  \n",
       "4         25.0  2023-04-04 14:24:00         0.0       216.0         219  "
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "df=pd.read_csv('D:/project/energymeter.csv')\n",
    "df=df.drop(config.ENERGY_DROP_COLOUMNS,axis=1)\n",
    "print(config.ENERGY_COLOUMNS)\n",
    "df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "data directory already exists.\n",
      "Pipeline saved as data\\Enerpreproc_pipe.pkl\n",
      "Initial memory usage: 138.92 KB \n",
      "Final memory usage  : 72.68 KB   (-47.7%)\n",
      "[Pipeline] .......... (step 1 of 4) Processing shrinker, total=   0.0s\n",
      "[Pipeline] ... (step 2 of 4) Processing drop_duplicates, total=   0.0s\n",
      "[Pipeline] ........... (step 3 of 4) Processing add_mts, total=   0.0s\n",
      "[Pipeline] ...... (step 4 of 4) Processing fill_missing, total=   0.0s\n"
     ]
    },
    {
     "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>parameter_timestamp</th>\n",
       "      <th>current_ir</th>\n",
       "      <th>electrical_energy</th>\n",
       "      <th>frequency</th>\n",
       "      <th>power</th>\n",
       "      <th>powerfactor</th>\n",
       "      <th>pressure</th>\n",
       "      <th>temperature</th>\n",
       "      <th>voltage_vb</th>\n",
       "      <th>voltage_vr</th>\n",
       "      <th>voltage_vy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2023-02-01 10:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>0.8</td>\n",
       "      <td>0.90</td>\n",
       "      <td>-10.0</td>\n",
       "      <td>210.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>212.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2023-02-01 11:00:50</td>\n",
       "      <td>1.2</td>\n",
       "      <td>470.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>440.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.05</td>\n",
       "      <td>40.0</td>\n",
       "      <td>222.0</td>\n",
       "      <td>216.0</td>\n",
       "      <td>230.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2023-02-01 12:00:50</td>\n",
       "      <td>0.6</td>\n",
       "      <td>110.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>0.9</td>\n",
       "      <td>0.97</td>\n",
       "      <td>40.0</td>\n",
       "      <td>224.0</td>\n",
       "      <td>230.0</td>\n",
       "      <td>218.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2023-02-01 13:00:50</td>\n",
       "      <td>1.2</td>\n",
       "      <td>420.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>410.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>225.0</td>\n",
       "      <td>211.0</td>\n",
       "      <td>230.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2023-02-01 14:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3886</th>\n",
       "      <td>2023-07-13 08:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3887</th>\n",
       "      <td>2023-07-13 09:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3888</th>\n",
       "      <td>2023-07-13 10:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3889</th>\n",
       "      <td>2023-07-13 11:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3890</th>\n",
       "      <td>2023-07-13 12:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3891 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     parameter_timestamp  current_ir  electrical_energy  frequency  power  \\\n",
       "0    2023-02-01 10:00:50         0.0               60.0       50.0   50.0   \n",
       "1    2023-02-01 11:00:50         1.2              470.0       50.0  440.0   \n",
       "2    2023-02-01 12:00:50         0.6              110.0       50.0   80.0   \n",
       "3    2023-02-01 13:00:50         1.2              420.0       50.0  410.0   \n",
       "4    2023-02-01 14:00:50         0.0              140.0       50.0  130.0   \n",
       "...                  ...         ...                ...        ...    ...   \n",
       "3886 2023-07-13 08:00:50         0.0              140.0       50.0  130.0   \n",
       "3887 2023-07-13 09:00:50         0.0              140.0       50.0  130.0   \n",
       "3888 2023-07-13 10:00:50         0.0              140.0       50.0  130.0   \n",
       "3889 2023-07-13 11:00:50         0.0              140.0       50.0  130.0   \n",
       "3890 2023-07-13 12:00:50         0.0              140.0       50.0  130.0   \n",
       "\n",
       "      powerfactor  pressure  temperature  voltage_vb  voltage_vr  voltage_vy  \n",
       "0             0.8      0.90        -10.0       210.0         0.0       212.0  \n",
       "1             1.0      1.05         40.0       222.0       216.0       230.0  \n",
       "2             0.9      0.97         40.0       224.0       230.0       218.0  \n",
       "3             1.0      0.00          0.0       225.0       211.0       230.0  \n",
       "4             1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "...           ...       ...          ...         ...         ...         ...  \n",
       "3886          1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "3887          1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "3888          1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "3889          1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "3890          1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "\n",
       "[3891 rows x 11 columns]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['parameter_timestamp']=pd.to_datetime(df['parameter_timestamp'],format='mixed')\n",
    "datetime_col=config.ENERGY_DATETIME\n",
    "freq=config.FREQUENCY\n",
    "coloumns=config.ENERGY_COLOUMNS\n",
    "method=config.METHOD\n",
    "value=config.VALUE\n",
    "\n",
    "\n",
    "preproc_pipe=sklearn.pipeline.Pipeline([\n",
    "    ('shrinker',TSShrinkDataFrame()),\n",
    "    ('drop_duplicates',TSDropDuplicates(datetime_col=datetime_col)),\n",
    "    ('add_mts',TSAddMissingTimestamps(datetime_col=datetime_col,freq=freq)),\n",
    "    ('fill_missing',TSFillMissing(columns=coloumns,method=method,value=value)),\n",
    "    ],\n",
    "    verbose=True)\n",
    "\n",
    "mkdir('data', exist_ok=True,parents=True)\n",
    "save_object(preproc_pipe,'data/Enerpreproc_pipe.pkl')\n",
    "preproc_pipe=load_object('data/Enerpreproc_pipe.pkl')\n",
    "\n",
    "df=preproc_pipe.fit_transform(df)\n",
    "\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "parameter_timestamp    datetime64[ns]\n",
       "current_ir                    float32\n",
       "electrical_energy             float32\n",
       "frequency                     float32\n",
       "power                         float32\n",
       "powerfactor                   float32\n",
       "pressure                      float32\n",
       "temperature                   float32\n",
       "voltage_vb                    float32\n",
       "voltage_vr                    float32\n",
       "voltage_vy                    float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1600x50 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "((#2233) [0,1,2,3,4,5,6,7,8,9...],\n",
       " (#319) [2400,2401,2402,2403,2404,2405,2406,2407,2408,2409...],\n",
       " (#638) [2886,2887,2888,2889,2890,2891,2892,2893,2894,2895...])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fcst_history= config.FCST_HISTORY\n",
    "fcst_horizon= config.FCST_HORIZON\n",
    "valid_size= config.VALID_SIZE\n",
    "test_size= config.TEST_SIZE\n",
    "\n",
    "splits=get_forecasting_splits(df,fcst_history=fcst_history,fcst_horizon=fcst_horizon,datetime_col=datetime_col,\n",
    "                              valid_size=valid_size,test_size=test_size)\n",
    "\n",
    "splits"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "data directory already exists.\n",
      "Pipeline saved as data\\Ener_exp_pipe.pkl\n",
      "[Pipeline] ............ (step 1 of 1) Processing scaler, total=   0.0s\n"
     ]
    },
    {
     "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>parameter_timestamp</th>\n",
       "      <th>current_ir</th>\n",
       "      <th>electrical_energy</th>\n",
       "      <th>frequency</th>\n",
       "      <th>power</th>\n",
       "      <th>powerfactor</th>\n",
       "      <th>pressure</th>\n",
       "      <th>temperature</th>\n",
       "      <th>voltage_vb</th>\n",
       "      <th>voltage_vr</th>\n",
       "      <th>voltage_vy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2023-02-01 10:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-8.594179</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-8.850472</td>\n",
       "      <td>-42.236080</td>\n",
       "      <td>-7.002370</td>\n",
       "      <td>-35.778999</td>\n",
       "      <td>22.492144</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>22.471300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2023-02-01 11:00:50</td>\n",
       "      <td>31.479530</td>\n",
       "      <td>35.328056</td>\n",
       "      <td>0.0</td>\n",
       "      <td>34.184769</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>-0.413303</td>\n",
       "      <td>11.321944</td>\n",
       "      <td>23.779827</td>\n",
       "      <td>26.865999</td>\n",
       "      <td>24.382834</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2023-02-01 12:00:50</td>\n",
       "      <td>15.722124</td>\n",
       "      <td>-3.237809</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-5.540069</td>\n",
       "      <td>-21.103851</td>\n",
       "      <td>-3.927469</td>\n",
       "      <td>11.321944</td>\n",
       "      <td>23.994442</td>\n",
       "      <td>28.609688</td>\n",
       "      <td>23.108478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2023-02-01 13:00:50</td>\n",
       "      <td>31.479530</td>\n",
       "      <td>29.971687</td>\n",
       "      <td>0.0</td>\n",
       "      <td>30.874365</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>-46.536777</td>\n",
       "      <td>-26.358810</td>\n",
       "      <td>24.101749</td>\n",
       "      <td>26.243252</td>\n",
       "      <td>24.382834</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2023-02-01 14:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3886</th>\n",
       "      <td>2023-07-13 08:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3887</th>\n",
       "      <td>2023-07-13 09:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3888</th>\n",
       "      <td>2023-07-13 10:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3889</th>\n",
       "      <td>2023-07-13 11:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3890</th>\n",
       "      <td>2023-07-13 12:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3891 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     parameter_timestamp  current_ir  electrical_energy  frequency      power  \\\n",
       "0    2023-02-01 10:00:50   -0.035283          -8.594179        0.0  -8.850472   \n",
       "1    2023-02-01 11:00:50   31.479530          35.328056        0.0  34.184769   \n",
       "2    2023-02-01 12:00:50   15.722124          -3.237809        0.0  -5.540069   \n",
       "3    2023-02-01 13:00:50   31.479530          29.971687        0.0  30.874365   \n",
       "4    2023-02-01 14:00:50   -0.035283          -0.023987        0.0  -0.022731   \n",
       "...                  ...         ...                ...        ...        ...   \n",
       "3886 2023-07-13 08:00:50   -0.035283          -0.023987        0.0  -0.022731   \n",
       "3887 2023-07-13 09:00:50   -0.035283          -0.023987        0.0  -0.022731   \n",
       "3888 2023-07-13 10:00:50   -0.035283          -0.023987        0.0  -0.022731   \n",
       "3889 2023-07-13 11:00:50   -0.035283          -0.023987        0.0  -0.022731   \n",
       "3890 2023-07-13 12:00:50   -0.035283          -0.023987        0.0  -0.022731   \n",
       "\n",
       "      powerfactor   pressure  temperature  voltage_vb  voltage_vr  voltage_vy  \n",
       "0      -42.236080  -7.002370   -35.778999   22.492144   -0.036645   22.471300  \n",
       "1        0.028391  -0.413303    11.321944   23.779827   26.865999   24.382834  \n",
       "2      -21.103851  -3.927469    11.321944   23.994442   28.609688   23.108478  \n",
       "3        0.028391 -46.536777   -26.358810   24.101749   26.243252   24.382834  \n",
       "4        0.028391   0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "...           ...        ...          ...         ...         ...         ...  \n",
       "3886     0.028391   0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "3887     0.028391   0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "3888     0.028391   0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "3889     0.028391   0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "3890     0.028391   0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "\n",
       "[3891 rows x 11 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "coloumns=config.ENERGY_COLOUMNS\n",
    "train_split=splits[0]\n",
    "\n",
    "\n",
    "exp_pipe=sklearn.pipeline.Pipeline([\n",
    "    ('scaler',TSStandardScaler(columns=coloumns)),\n",
    "    ],\n",
    "    verbose=True)\n",
    "\n",
    "\n",
    "save_object(exp_pipe,'data/Ener_exp_pipe.pkl')\n",
    "exp_pipe=load_object('data/Ener_exp_pipe.pkl')\n",
    "\n",
    "df_scaled=exp_pipe.fit_transform(df,scaler__idxs=train_split)\n",
    "\n",
    "df_scaled"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_vars=config.ENERGY_COLOUMNS\n",
    "y_vars=config.ENERGY_COLOUMNS"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((3524, 10, 200), (3524, 10, 168))"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X,y=prepare_forecasting_data(df,fcst_history=fcst_history,fcst_horizon=fcst_horizon,x_vars=x_vars,y_vars=y_vars)\n",
    "X.shape , y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn=TSForecaster(X,y,splits=splits,\n",
    "                   batch_size=16,path=\"models\",\n",
    "                   pipelines=[preproc_pipe,exp_pipe],\n",
    "                   arch=\"InceptionTimePlus\",\n",
    "                   #arch_config=arch_config,\n",
    "                   metrics=[mae,mape],\n",
    "                   cbs=ShowGraph())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "not enough values to plot a chart\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "InceptionTimePlus (Input shape: 16 x 10 x 200)\n",
       "============================================================================\n",
       "Layer (type)         Output Shape         Param #    Trainable \n",
       "============================================================================\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    320        True      \n",
       "Conv1d                                    39936      True      \n",
       "Conv1d                                    19456      True      \n",
       "Conv1d                                    9216       True      \n",
       "MaxPool1d                                                      \n",
       "____________________________________________________________________________\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    320        True      \n",
       "____________________________________________________________________________\n",
       "                     16 x 128 x 200      \n",
       "Concat                                                         \n",
       "BatchNorm1d                               256        True      \n",
       "ReLU                                                           \n",
       "____________________________________________________________________________\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    4096       True      \n",
       "Conv1d                                    39936      True      \n",
       "Conv1d                                    19456      True      \n",
       "Conv1d                                    9216       True      \n",
       "MaxPool1d                                                      \n",
       "____________________________________________________________________________\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    4096       True      \n",
       "____________________________________________________________________________\n",
       "                     16 x 128 x 200      \n",
       "Concat                                                         \n",
       "BatchNorm1d                               256        True      \n",
       "ReLU                                                           \n",
       "____________________________________________________________________________\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    4096       True      \n",
       "Conv1d                                    39936      True      \n",
       "Conv1d                                    19456      True      \n",
       "Conv1d                                    9216       True      \n",
       "MaxPool1d                                                      \n",
       "____________________________________________________________________________\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    4096       True      \n",
       "____________________________________________________________________________\n",
       "                     16 x 128 x 200      \n",
       "Concat                                                         \n",
       "BatchNorm1d                               256        True      \n",
       "____________________________________________________________________________\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    4096       True      \n",
       "Conv1d                                    39936      True      \n",
       "Conv1d                                    19456      True      \n",
       "Conv1d                                    9216       True      \n",
       "MaxPool1d                                                      \n",
       "____________________________________________________________________________\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    4096       True      \n",
       "____________________________________________________________________________\n",
       "                     16 x 128 x 200      \n",
       "Concat                                                         \n",
       "BatchNorm1d                               256        True      \n",
       "ReLU                                                           \n",
       "____________________________________________________________________________\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    4096       True      \n",
       "Conv1d                                    39936      True      \n",
       "Conv1d                                    19456      True      \n",
       "Conv1d                                    9216       True      \n",
       "MaxPool1d                                                      \n",
       "____________________________________________________________________________\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    4096       True      \n",
       "____________________________________________________________________________\n",
       "                     16 x 128 x 200      \n",
       "Concat                                                         \n",
       "BatchNorm1d                               256        True      \n",
       "ReLU                                                           \n",
       "____________________________________________________________________________\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    4096       True      \n",
       "Conv1d                                    39936      True      \n",
       "Conv1d                                    19456      True      \n",
       "Conv1d                                    9216       True      \n",
       "MaxPool1d                                                      \n",
       "____________________________________________________________________________\n",
       "                     16 x 32 x 200       \n",
       "Conv1d                                    4096       True      \n",
       "____________________________________________________________________________\n",
       "                     16 x 128 x 200      \n",
       "Concat                                                         \n",
       "BatchNorm1d                               256        True      \n",
       "Conv1d                                    1280       True      \n",
       "BatchNorm1d                               256        True      \n",
       "BatchNorm1d                               256        True      \n",
       "ReLU                                                           \n",
       "ReLU                                                           \n",
       "Add                                                            \n",
       "____________________________________________________________________________\n",
       "                     16 x 25600          \n",
       "Reshape                                                        \n",
       "____________________________________________________________________________\n",
       "                     16 x 1680           \n",
       "Linear                                    43009680   True      \n",
       "____________________________________________________________________________\n",
       "                     16 x 10 x 168       \n",
       "Reshape                                                        \n",
       "____________________________________________________________________________\n",
       "\n",
       "Total params: 43,466,256\n",
       "Total trainable params: 43,466,256\n",
       "Total non-trainable params: 0\n",
       "\n",
       "Optimizer used: <function Adam at 0x000002060E192980>\n",
       "Loss function: FlattenedLoss of MSELoss()\n",
       "\n",
       "Callbacks:\n",
       "  - TrainEvalCallback\n",
       "  - CastToTensor\n",
       "  - Recorder\n",
       "  - ProgressCallback\n",
       "  - ShowGraph"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "learn.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "lr_max=learn.lr_find().valley"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: left;\">\n",
       "      <th>epoch</th>\n",
       "      <th>train_loss</th>\n",
       "      <th>valid_loss</th>\n",
       "      <th>mae</th>\n",
       "      <th>mape</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>0.006847</td>\n",
       "      <td>0.060231</td>\n",
       "      <td>0.195827</td>\n",
       "      <td>13604973.000000</td>\n",
       "      <td>01:56</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>0.007108</td>\n",
       "      <td>0.066659</td>\n",
       "      <td>0.204732</td>\n",
       "      <td>14276765.000000</td>\n",
       "      <td>01:52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>0.005240</td>\n",
       "      <td>0.061844</td>\n",
       "      <td>0.197786</td>\n",
       "      <td>13601250.000000</td>\n",
       "      <td>01:50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>0.001593</td>\n",
       "      <td>0.000245</td>\n",
       "      <td>0.012493</td>\n",
       "      <td>857236.062500</td>\n",
       "      <td>02:09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>0.003414</td>\n",
       "      <td>0.064100</td>\n",
       "      <td>0.201982</td>\n",
       "      <td>13824191.000000</td>\n",
       "      <td>01:48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5</td>\n",
       "      <td>0.001106</td>\n",
       "      <td>0.055820</td>\n",
       "      <td>0.189100</td>\n",
       "      <td>13087523.000000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6</td>\n",
       "      <td>0.001668</td>\n",
       "      <td>0.049496</td>\n",
       "      <td>0.177095</td>\n",
       "      <td>12192220.000000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7</td>\n",
       "      <td>0.001525</td>\n",
       "      <td>0.048186</td>\n",
       "      <td>0.174667</td>\n",
       "      <td>11928623.000000</td>\n",
       "      <td>01:45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8</td>\n",
       "      <td>0.001744</td>\n",
       "      <td>0.033855</td>\n",
       "      <td>0.146060</td>\n",
       "      <td>10060512.000000</td>\n",
       "      <td>01:40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>9</td>\n",
       "      <td>0.000902</td>\n",
       "      <td>0.034314</td>\n",
       "      <td>0.148649</td>\n",
       "      <td>10244203.000000</td>\n",
       "      <td>01:40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>10</td>\n",
       "      <td>0.000967</td>\n",
       "      <td>0.019427</td>\n",
       "      <td>0.111335</td>\n",
       "      <td>7628062.500000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>11</td>\n",
       "      <td>0.001472</td>\n",
       "      <td>0.081984</td>\n",
       "      <td>0.229339</td>\n",
       "      <td>15699212.000000</td>\n",
       "      <td>01:44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>12</td>\n",
       "      <td>0.003422</td>\n",
       "      <td>0.077661</td>\n",
       "      <td>0.223115</td>\n",
       "      <td>15250628.000000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>13</td>\n",
       "      <td>0.003182</td>\n",
       "      <td>0.068728</td>\n",
       "      <td>0.210763</td>\n",
       "      <td>14573507.000000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>14</td>\n",
       "      <td>0.000792</td>\n",
       "      <td>0.016976</td>\n",
       "      <td>0.103343</td>\n",
       "      <td>7125199.000000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>15</td>\n",
       "      <td>0.001112</td>\n",
       "      <td>0.062781</td>\n",
       "      <td>0.198572</td>\n",
       "      <td>13762592.000000</td>\n",
       "      <td>01:51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>16</td>\n",
       "      <td>0.001156</td>\n",
       "      <td>0.028168</td>\n",
       "      <td>0.133993</td>\n",
       "      <td>9317550.000000</td>\n",
       "      <td>01:58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>17</td>\n",
       "      <td>0.001140</td>\n",
       "      <td>0.047352</td>\n",
       "      <td>0.173333</td>\n",
       "      <td>12027601.000000</td>\n",
       "      <td>02:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>18</td>\n",
       "      <td>0.002329</td>\n",
       "      <td>0.035210</td>\n",
       "      <td>0.152324</td>\n",
       "      <td>11017726.000000</td>\n",
       "      <td>01:55</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>19</td>\n",
       "      <td>0.001176</td>\n",
       "      <td>0.057110</td>\n",
       "      <td>0.189917</td>\n",
       "      <td>13379663.000000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>20</td>\n",
       "      <td>0.000395</td>\n",
       "      <td>0.000221</td>\n",
       "      <td>0.011815</td>\n",
       "      <td>823702.125000</td>\n",
       "      <td>01:44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>21</td>\n",
       "      <td>0.001420</td>\n",
       "      <td>0.029581</td>\n",
       "      <td>0.139205</td>\n",
       "      <td>10088836.000000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>22</td>\n",
       "      <td>0.000654</td>\n",
       "      <td>0.028311</td>\n",
       "      <td>0.134113</td>\n",
       "      <td>9314097.000000</td>\n",
       "      <td>01:44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>23</td>\n",
       "      <td>0.000739</td>\n",
       "      <td>0.041696</td>\n",
       "      <td>0.162548</td>\n",
       "      <td>11389292.000000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>24</td>\n",
       "      <td>0.000735</td>\n",
       "      <td>0.046852</td>\n",
       "      <td>0.172180</td>\n",
       "      <td>12134271.000000</td>\n",
       "      <td>01:50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>25</td>\n",
       "      <td>0.000747</td>\n",
       "      <td>0.026198</td>\n",
       "      <td>0.130903</td>\n",
       "      <td>9466224.000000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>26</td>\n",
       "      <td>0.000426</td>\n",
       "      <td>0.038305</td>\n",
       "      <td>0.156854</td>\n",
       "      <td>11143937.000000</td>\n",
       "      <td>01:37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>27</td>\n",
       "      <td>0.000508</td>\n",
       "      <td>0.037100</td>\n",
       "      <td>0.153625</td>\n",
       "      <td>10868943.000000</td>\n",
       "      <td>01:39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>28</td>\n",
       "      <td>0.000495</td>\n",
       "      <td>0.037724</td>\n",
       "      <td>0.155111</td>\n",
       "      <td>11004322.000000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>29</td>\n",
       "      <td>0.000287</td>\n",
       "      <td>0.012688</td>\n",
       "      <td>0.089390</td>\n",
       "      <td>6244159.000000</td>\n",
       "      <td>01:39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>30</td>\n",
       "      <td>0.000268</td>\n",
       "      <td>0.039532</td>\n",
       "      <td>0.158910</td>\n",
       "      <td>11243394.000000</td>\n",
       "      <td>01:40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>31</td>\n",
       "      <td>0.000261</td>\n",
       "      <td>0.027212</td>\n",
       "      <td>0.132988</td>\n",
       "      <td>9550949.000000</td>\n",
       "      <td>01:44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>32</td>\n",
       "      <td>0.000244</td>\n",
       "      <td>0.032230</td>\n",
       "      <td>0.143236</td>\n",
       "      <td>10066619.000000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>33</td>\n",
       "      <td>0.000243</td>\n",
       "      <td>0.028472</td>\n",
       "      <td>0.135775</td>\n",
       "      <td>9699461.000000</td>\n",
       "      <td>01:36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>34</td>\n",
       "      <td>0.000114</td>\n",
       "      <td>0.000762</td>\n",
       "      <td>0.022059</td>\n",
       "      <td>1534292.625000</td>\n",
       "      <td>01:39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>35</td>\n",
       "      <td>0.000229</td>\n",
       "      <td>0.029882</td>\n",
       "      <td>0.137425</td>\n",
       "      <td>9661759.000000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>36</td>\n",
       "      <td>0.000263</td>\n",
       "      <td>0.026170</td>\n",
       "      <td>0.130617</td>\n",
       "      <td>9436193.000000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>37</td>\n",
       "      <td>0.000131</td>\n",
       "      <td>0.023815</td>\n",
       "      <td>0.123353</td>\n",
       "      <td>8657830.000000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>38</td>\n",
       "      <td>0.000143</td>\n",
       "      <td>0.028465</td>\n",
       "      <td>0.134205</td>\n",
       "      <td>9478090.000000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>39</td>\n",
       "      <td>0.000180</td>\n",
       "      <td>0.025178</td>\n",
       "      <td>0.127793</td>\n",
       "      <td>9181777.000000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>40</td>\n",
       "      <td>0.000112</td>\n",
       "      <td>0.026104</td>\n",
       "      <td>0.129327</td>\n",
       "      <td>9158926.000000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>41</td>\n",
       "      <td>0.000159</td>\n",
       "      <td>0.024500</td>\n",
       "      <td>0.126292</td>\n",
       "      <td>9029098.000000</td>\n",
       "      <td>01:44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>42</td>\n",
       "      <td>0.000056</td>\n",
       "      <td>0.004775</td>\n",
       "      <td>0.055303</td>\n",
       "      <td>3864649.000000</td>\n",
       "      <td>01:44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>43</td>\n",
       "      <td>0.000066</td>\n",
       "      <td>0.024366</td>\n",
       "      <td>0.125917</td>\n",
       "      <td>9001758.000000</td>\n",
       "      <td>01:44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>44</td>\n",
       "      <td>0.000075</td>\n",
       "      <td>0.021532</td>\n",
       "      <td>0.117098</td>\n",
       "      <td>8187097.500000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>45</td>\n",
       "      <td>0.000179</td>\n",
       "      <td>0.014631</td>\n",
       "      <td>0.099449</td>\n",
       "      <td>7266168.500000</td>\n",
       "      <td>01:49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>46</td>\n",
       "      <td>0.000065</td>\n",
       "      <td>0.017360</td>\n",
       "      <td>0.104038</td>\n",
       "      <td>7266744.500000</td>\n",
       "      <td>01:58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>47</td>\n",
       "      <td>0.000048</td>\n",
       "      <td>0.021696</td>\n",
       "      <td>0.119561</td>\n",
       "      <td>8653430.000000</td>\n",
       "      <td>01:46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>48</td>\n",
       "      <td>0.000083</td>\n",
       "      <td>0.024138</td>\n",
       "      <td>0.124338</td>\n",
       "      <td>8819554.000000</td>\n",
       "      <td>02:02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>49</td>\n",
       "      <td>0.000030</td>\n",
       "      <td>0.000174</td>\n",
       "      <td>0.010540</td>\n",
       "      <td>725580.062500</td>\n",
       "      <td>01:52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>50</td>\n",
       "      <td>0.000036</td>\n",
       "      <td>0.021855</td>\n",
       "      <td>0.117481</td>\n",
       "      <td>8245410.000000</td>\n",
       "      <td>01:51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>51</td>\n",
       "      <td>0.000095</td>\n",
       "      <td>0.015925</td>\n",
       "      <td>0.103743</td>\n",
       "      <td>7587914.000000</td>\n",
       "      <td>01:47</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>52</td>\n",
       "      <td>0.000073</td>\n",
       "      <td>0.021388</td>\n",
       "      <td>0.117822</td>\n",
       "      <td>8500537.000000</td>\n",
       "      <td>01:46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>53</td>\n",
       "      <td>0.000049</td>\n",
       "      <td>0.022555</td>\n",
       "      <td>0.119906</td>\n",
       "      <td>8438498.000000</td>\n",
       "      <td>01:48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>54</td>\n",
       "      <td>0.000033</td>\n",
       "      <td>0.021307</td>\n",
       "      <td>0.116581</td>\n",
       "      <td>8245712.500000</td>\n",
       "      <td>01:50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>55</td>\n",
       "      <td>0.000025</td>\n",
       "      <td>0.018064</td>\n",
       "      <td>0.106662</td>\n",
       "      <td>7448303.000000</td>\n",
       "      <td>01:49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>56</td>\n",
       "      <td>0.000053</td>\n",
       "      <td>0.022700</td>\n",
       "      <td>0.120450</td>\n",
       "      <td>8609665.000000</td>\n",
       "      <td>01:49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>57</td>\n",
       "      <td>0.000040</td>\n",
       "      <td>0.017915</td>\n",
       "      <td>0.109083</td>\n",
       "      <td>7949559.000000</td>\n",
       "      <td>01:52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>58</td>\n",
       "      <td>0.000025</td>\n",
       "      <td>0.021165</td>\n",
       "      <td>0.116701</td>\n",
       "      <td>8380551.000000</td>\n",
       "      <td>01:52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>59</td>\n",
       "      <td>0.000029</td>\n",
       "      <td>0.018229</td>\n",
       "      <td>0.110137</td>\n",
       "      <td>8024512.000000</td>\n",
       "      <td>01:48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>60</td>\n",
       "      <td>0.000019</td>\n",
       "      <td>0.022742</td>\n",
       "      <td>0.120258</td>\n",
       "      <td>8522735.000000</td>\n",
       "      <td>01:46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>61</td>\n",
       "      <td>0.000022</td>\n",
       "      <td>0.022318</td>\n",
       "      <td>0.120326</td>\n",
       "      <td>8629685.000000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>62</td>\n",
       "      <td>0.000011</td>\n",
       "      <td>0.005392</td>\n",
       "      <td>0.058508</td>\n",
       "      <td>4051013.000000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>63</td>\n",
       "      <td>0.000026</td>\n",
       "      <td>0.017859</td>\n",
       "      <td>0.108757</td>\n",
       "      <td>7899343.000000</td>\n",
       "      <td>01:40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>64</td>\n",
       "      <td>0.000007</td>\n",
       "      <td>0.000059</td>\n",
       "      <td>0.006161</td>\n",
       "      <td>421538.093750</td>\n",
       "      <td>01:40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>65</td>\n",
       "      <td>0.000004</td>\n",
       "      <td>0.015945</td>\n",
       "      <td>0.099880</td>\n",
       "      <td>7010992.500000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>66</td>\n",
       "      <td>0.000017</td>\n",
       "      <td>0.021124</td>\n",
       "      <td>0.116767</td>\n",
       "      <td>8412442.000000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>67</td>\n",
       "      <td>0.000005</td>\n",
       "      <td>0.000441</td>\n",
       "      <td>0.016719</td>\n",
       "      <td>1151929.250000</td>\n",
       "      <td>01:40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>68</td>\n",
       "      <td>0.000004</td>\n",
       "      <td>0.007369</td>\n",
       "      <td>0.068481</td>\n",
       "      <td>4755484.500000</td>\n",
       "      <td>01:39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>69</td>\n",
       "      <td>0.000010</td>\n",
       "      <td>0.018700</td>\n",
       "      <td>0.110762</td>\n",
       "      <td>8020486.500000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>70</td>\n",
       "      <td>0.000002</td>\n",
       "      <td>0.000006</td>\n",
       "      <td>0.001915</td>\n",
       "      <td>130664.890625</td>\n",
       "      <td>01:39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>71</td>\n",
       "      <td>0.000003</td>\n",
       "      <td>0.020625</td>\n",
       "      <td>0.115280</td>\n",
       "      <td>8289870.000000</td>\n",
       "      <td>01:40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>72</td>\n",
       "      <td>0.000003</td>\n",
       "      <td>0.021448</td>\n",
       "      <td>0.117105</td>\n",
       "      <td>8366023.000000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>73</td>\n",
       "      <td>0.000001</td>\n",
       "      <td>0.019169</td>\n",
       "      <td>0.109729</td>\n",
       "      <td>7709050.000000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>74</td>\n",
       "      <td>0.000002</td>\n",
       "      <td>0.017123</td>\n",
       "      <td>0.107129</td>\n",
       "      <td>7822817.500000</td>\n",
       "      <td>01:40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>75</td>\n",
       "      <td>0.000002</td>\n",
       "      <td>0.017381</td>\n",
       "      <td>0.107147</td>\n",
       "      <td>7787382.000000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>76</td>\n",
       "      <td>0.000001</td>\n",
       "      <td>0.020698</td>\n",
       "      <td>0.114409</td>\n",
       "      <td>8063217.500000</td>\n",
       "      <td>01:39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>77</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.017329</td>\n",
       "      <td>0.104317</td>\n",
       "      <td>7316558.000000</td>\n",
       "      <td>01:39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>78</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.002353</td>\n",
       "      <td>0.038679</td>\n",
       "      <td>2686916.000000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>79</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000210</td>\n",
       "      <td>0.011513</td>\n",
       "      <td>794970.750000</td>\n",
       "      <td>01:40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>80</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.018609</td>\n",
       "      <td>0.111045</td>\n",
       "      <td>8070433.500000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>81</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.021419</td>\n",
       "      <td>0.116750</td>\n",
       "      <td>8237241.500000</td>\n",
       "      <td>01:54</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>82</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.011875</td>\n",
       "      <td>0.086761</td>\n",
       "      <td>6042704.500000</td>\n",
       "      <td>01:58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>83</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.021744</td>\n",
       "      <td>0.117554</td>\n",
       "      <td>8362730.500000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>84</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.021490</td>\n",
       "      <td>0.117154</td>\n",
       "      <td>8296401.500000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>85</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.001018</td>\n",
       "      <td>0.025489</td>\n",
       "      <td>1765286.500000</td>\n",
       "      <td>01:40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>86</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.021109</td>\n",
       "      <td>0.116795</td>\n",
       "      <td>8381815.000000</td>\n",
       "      <td>01:45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>87</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000606</td>\n",
       "      <td>0.019626</td>\n",
       "      <td>1354899.750000</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>88</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.019501</td>\n",
       "      <td>0.113012</td>\n",
       "      <td>8174731.000000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>89</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.021064</td>\n",
       "      <td>0.115509</td>\n",
       "      <td>8133863.000000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>90</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.020799</td>\n",
       "      <td>0.115526</td>\n",
       "      <td>8280630.500000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>91</td>\n",
       "      <td>0.000010</td>\n",
       "      <td>0.000028</td>\n",
       "      <td>0.004218</td>\n",
       "      <td>290495.562500</td>\n",
       "      <td>01:41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>92</td>\n",
       "      <td>0.000001</td>\n",
       "      <td>0.021506</td>\n",
       "      <td>0.116903</td>\n",
       "      <td>8281606.500000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>93</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.004389</td>\n",
       "      <td>0.052855</td>\n",
       "      <td>3646920.750000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>94</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.016303</td>\n",
       "      <td>0.104775</td>\n",
       "      <td>7657274.000000</td>\n",
       "      <td>01:42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>95</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.019884</td>\n",
       "      <td>0.113477</td>\n",
       "      <td>8182254.500000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>96</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.017377</td>\n",
       "      <td>0.107296</td>\n",
       "      <td>7801061.500000</td>\n",
       "      <td>01:44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>97</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.021491</td>\n",
       "      <td>0.117124</td>\n",
       "      <td>8348766.000000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>98</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.021380</td>\n",
       "      <td>0.116812</td>\n",
       "      <td>8268752.500000</td>\n",
       "      <td>01:44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>99</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.011358</td>\n",
       "      <td>0.084572</td>\n",
       "      <td>5883725.500000</td>\n",
       "      <td>01:43</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1300x900 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "n_epochs=100\n",
    "\n",
    "learn.fit_one_cycle(n_epoch=n_epochs,lr_max=lr_max)\n",
    "learn.export('EnerInceptionTime.pt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatetimeIndex(['2023-07-05 05:00:50', '2023-07-05 06:00:50',\n",
       "               '2023-07-05 07:00:50', '2023-07-05 08:00:50',\n",
       "               '2023-07-05 09:00:50', '2023-07-05 10:00:50',\n",
       "               '2023-07-05 11:00:50', '2023-07-05 12:00:50',\n",
       "               '2023-07-05 13:00:50', '2023-07-05 14:00:50',\n",
       "               ...\n",
       "               '2023-07-13 03:00:50', '2023-07-13 04:00:50',\n",
       "               '2023-07-13 05:00:50', '2023-07-13 06:00:50',\n",
       "               '2023-07-13 07:00:50', '2023-07-13 08:00:50',\n",
       "               '2023-07-13 09:00:50', '2023-07-13 10:00:50',\n",
       "               '2023-07-13 11:00:50', '2023-07-13 12:00:50'],\n",
       "              dtype='datetime64[ns]', length=200, freq='H')"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fcst_date=\"2023-07-13 12:00:50\"\n",
    "dates=pd.date_range(start=None,end=fcst_date,periods=config.FCST_HISTORY,freq=config.FREQUENCY)\n",
    "dates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "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>parameter_timestamp</th>\n",
       "      <th>current_ir</th>\n",
       "      <th>electrical_energy</th>\n",
       "      <th>frequency</th>\n",
       "      <th>power</th>\n",
       "      <th>powerfactor</th>\n",
       "      <th>pressure</th>\n",
       "      <th>temperature</th>\n",
       "      <th>voltage_vb</th>\n",
       "      <th>voltage_vr</th>\n",
       "      <th>voltage_vy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2023-07-05 05:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2023-07-05 06:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2023-07-05 07:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2023-07-05 08:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2023-07-05 09:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>195</th>\n",
       "      <td>2023-07-13 08:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>196</th>\n",
       "      <td>2023-07-13 09:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>197</th>\n",
       "      <td>2023-07-13 10:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>198</th>\n",
       "      <td>2023-07-13 11:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>199</th>\n",
       "      <td>2023-07-13 12:00:50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.06</td>\n",
       "      <td>28.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>200 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    parameter_timestamp  current_ir  electrical_energy  frequency  power  \\\n",
       "0   2023-07-05 05:00:50         0.0              140.0       50.0  130.0   \n",
       "1   2023-07-05 06:00:50         0.0              140.0       50.0  130.0   \n",
       "2   2023-07-05 07:00:50         0.0              140.0       50.0  130.0   \n",
       "3   2023-07-05 08:00:50         0.0              140.0       50.0  130.0   \n",
       "4   2023-07-05 09:00:50         0.0              140.0       50.0  130.0   \n",
       "..                  ...         ...                ...        ...    ...   \n",
       "195 2023-07-13 08:00:50         0.0              140.0       50.0  130.0   \n",
       "196 2023-07-13 09:00:50         0.0              140.0       50.0  130.0   \n",
       "197 2023-07-13 10:00:50         0.0              140.0       50.0  130.0   \n",
       "198 2023-07-13 11:00:50         0.0              140.0       50.0  130.0   \n",
       "199 2023-07-13 12:00:50         0.0              140.0       50.0  130.0   \n",
       "\n",
       "     powerfactor  pressure  temperature  voltage_vb  voltage_vr  voltage_vy  \n",
       "0            1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "1            1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "2            1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "3            1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "4            1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "..           ...       ...          ...         ...         ...         ...  \n",
       "195          1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "196          1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "197          1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "198          1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "199          1.0      1.06         28.0         0.0         0.0         0.0  \n",
       "\n",
       "[200 rows x 11 columns]"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df=df[df[config.ENERGY_DATETIME].isin(dates)].reset_index(drop=True)\n",
    "new_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Initial memory usage: 10.29 KB  \n",
      "Final memory usage  : 9.11 KB    (-11.4%)\n"
     ]
    },
    {
     "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>parameter_timestamp</th>\n",
       "      <th>current_ir</th>\n",
       "      <th>electrical_energy</th>\n",
       "      <th>frequency</th>\n",
       "      <th>power</th>\n",
       "      <th>powerfactor</th>\n",
       "      <th>pressure</th>\n",
       "      <th>temperature</th>\n",
       "      <th>voltage_vb</th>\n",
       "      <th>voltage_vr</th>\n",
       "      <th>voltage_vy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2023-07-05 05:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2023-07-05 06:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2023-07-05 07:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2023-07-05 08:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2023-07-05 09:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>195</th>\n",
       "      <td>2023-07-13 08:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>196</th>\n",
       "      <td>2023-07-13 09:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>197</th>\n",
       "      <td>2023-07-13 10:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>198</th>\n",
       "      <td>2023-07-13 11:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>199</th>\n",
       "      <td>2023-07-13 12:00:50</td>\n",
       "      <td>-0.035283</td>\n",
       "      <td>-0.023987</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.022731</td>\n",
       "      <td>0.028391</td>\n",
       "      <td>0.025968</td>\n",
       "      <td>0.017718</td>\n",
       "      <td>-0.042337</td>\n",
       "      <td>-0.036645</td>\n",
       "      <td>-0.042326</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>200 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    parameter_timestamp  current_ir  electrical_energy  frequency     power  \\\n",
       "0   2023-07-05 05:00:50   -0.035283          -0.023987        0.0 -0.022731   \n",
       "1   2023-07-05 06:00:50   -0.035283          -0.023987        0.0 -0.022731   \n",
       "2   2023-07-05 07:00:50   -0.035283          -0.023987        0.0 -0.022731   \n",
       "3   2023-07-05 08:00:50   -0.035283          -0.023987        0.0 -0.022731   \n",
       "4   2023-07-05 09:00:50   -0.035283          -0.023987        0.0 -0.022731   \n",
       "..                  ...         ...                ...        ...       ...   \n",
       "195 2023-07-13 08:00:50   -0.035283          -0.023987        0.0 -0.022731   \n",
       "196 2023-07-13 09:00:50   -0.035283          -0.023987        0.0 -0.022731   \n",
       "197 2023-07-13 10:00:50   -0.035283          -0.023987        0.0 -0.022731   \n",
       "198 2023-07-13 11:00:50   -0.035283          -0.023987        0.0 -0.022731   \n",
       "199 2023-07-13 12:00:50   -0.035283          -0.023987        0.0 -0.022731   \n",
       "\n",
       "     powerfactor  pressure  temperature  voltage_vb  voltage_vr  voltage_vy  \n",
       "0       0.028391  0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "1       0.028391  0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "2       0.028391  0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "3       0.028391  0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "4       0.028391  0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "..           ...       ...          ...         ...         ...         ...  \n",
       "195     0.028391  0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "196     0.028391  0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "197     0.028391  0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "198     0.028391  0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "199     0.028391  0.025968     0.017718   -0.042337   -0.036645   -0.042326  \n",
       "\n",
       "[200 rows x 11 columns]"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from tsai.inference import load_learner\n",
    "\n",
    "predict=load_learner('models/EnerInceptionTime.pt')\n",
    "new_df=predict.transform(new_df)\n",
    "\n",
    "new_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1, 10, 200)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_feat=new_df.columns[1:]\n",
    "new_x,__=prepare_forecasting_data(new_df,fcst_history=fcst_history,fcst_horizon=0,x_vars=x_vars,y_vars=y_vars)\n",
    "new_x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "<style>\n",
       "    /* Turns off some styling */\n",
       "    progress {\n",
       "        /* gets rid of default border in Firefox and Opera. */\n",
       "        border: none;\n",
       "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "        background-size: auto;\n",
       "    }\n",
       "    progress:not([value]), progress:not([value])::-webkit-progress-bar {\n",
       "        background: repeating-linear-gradient(45deg, #7e7e7e, #7e7e7e 10px, #5c5c5c 10px, #5c5c5c 20px);\n",
       "    }\n",
       "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "        background: #F44336;\n",
       "    }\n",
       "</style>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>parameter_timestamp</th>\n",
       "      <th>current_ir</th>\n",
       "      <th>electrical_energy</th>\n",
       "      <th>frequency</th>\n",
       "      <th>power</th>\n",
       "      <th>powerfactor</th>\n",
       "      <th>pressure</th>\n",
       "      <th>temperature</th>\n",
       "      <th>voltage_vb</th>\n",
       "      <th>voltage_vr</th>\n",
       "      <th>voltage_vy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2023-07-13 13:00:50</td>\n",
       "      <td>0.001096</td>\n",
       "      <td>141.234711</td>\n",
       "      <td>50.0</td>\n",
       "      <td>127.811417</td>\n",
       "      <td>1.001055</td>\n",
       "      <td>1.057300</td>\n",
       "      <td>27.986296</td>\n",
       "      <td>-1.917876</td>\n",
       "      <td>0.576301</td>\n",
       "      <td>-0.040845</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2023-07-13 14:00:50</td>\n",
       "      <td>0.004344</td>\n",
       "      <td>139.727371</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.631073</td>\n",
       "      <td>1.000224</td>\n",
       "      <td>1.060515</td>\n",
       "      <td>28.029724</td>\n",
       "      <td>-1.008769</td>\n",
       "      <td>0.131339</td>\n",
       "      <td>-0.803190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2023-07-13 15:00:50</td>\n",
       "      <td>-0.004954</td>\n",
       "      <td>138.812119</td>\n",
       "      <td>50.0</td>\n",
       "      <td>129.651535</td>\n",
       "      <td>0.999673</td>\n",
       "      <td>1.060144</td>\n",
       "      <td>27.930075</td>\n",
       "      <td>-1.564345</td>\n",
       "      <td>-0.319494</td>\n",
       "      <td>-0.133825</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2023-07-13 16:00:50</td>\n",
       "      <td>0.001051</td>\n",
       "      <td>140.470779</td>\n",
       "      <td>50.0</td>\n",
       "      <td>127.855476</td>\n",
       "      <td>1.000330</td>\n",
       "      <td>1.059224</td>\n",
       "      <td>27.881578</td>\n",
       "      <td>0.151097</td>\n",
       "      <td>0.639718</td>\n",
       "      <td>-0.659135</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2023-07-13 17:00:50</td>\n",
       "      <td>-0.000661</td>\n",
       "      <td>138.916412</td>\n",
       "      <td>50.0</td>\n",
       "      <td>131.405380</td>\n",
       "      <td>1.000780</td>\n",
       "      <td>1.062929</td>\n",
       "      <td>28.005365</td>\n",
       "      <td>-1.031228</td>\n",
       "      <td>-1.475980</td>\n",
       "      <td>-0.234166</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>163</th>\n",
       "      <td>2023-07-20 08:00:50</td>\n",
       "      <td>0.001771</td>\n",
       "      <td>138.384018</td>\n",
       "      <td>50.0</td>\n",
       "      <td>129.857925</td>\n",
       "      <td>0.999521</td>\n",
       "      <td>1.062028</td>\n",
       "      <td>27.924028</td>\n",
       "      <td>0.229666</td>\n",
       "      <td>-1.267485</td>\n",
       "      <td>-1.298952</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>164</th>\n",
       "      <td>2023-07-20 09:00:50</td>\n",
       "      <td>0.000068</td>\n",
       "      <td>140.150238</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.151627</td>\n",
       "      <td>0.999780</td>\n",
       "      <td>1.061307</td>\n",
       "      <td>27.996088</td>\n",
       "      <td>-1.717520</td>\n",
       "      <td>-1.180167</td>\n",
       "      <td>0.026794</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>165</th>\n",
       "      <td>2023-07-20 10:00:50</td>\n",
       "      <td>0.000186</td>\n",
       "      <td>139.940826</td>\n",
       "      <td>50.0</td>\n",
       "      <td>128.701904</td>\n",
       "      <td>0.999633</td>\n",
       "      <td>1.060397</td>\n",
       "      <td>28.017605</td>\n",
       "      <td>-1.705875</td>\n",
       "      <td>-0.438039</td>\n",
       "      <td>0.817327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>166</th>\n",
       "      <td>2023-07-20 11:00:50</td>\n",
       "      <td>-0.007508</td>\n",
       "      <td>140.450912</td>\n",
       "      <td>50.0</td>\n",
       "      <td>128.328964</td>\n",
       "      <td>1.000353</td>\n",
       "      <td>1.061629</td>\n",
       "      <td>27.954876</td>\n",
       "      <td>-1.840141</td>\n",
       "      <td>-0.302064</td>\n",
       "      <td>-1.691164</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>167</th>\n",
       "      <td>2023-07-20 12:00:50</td>\n",
       "      <td>0.002726</td>\n",
       "      <td>139.368546</td>\n",
       "      <td>50.0</td>\n",
       "      <td>130.120071</td>\n",
       "      <td>1.000274</td>\n",
       "      <td>1.060468</td>\n",
       "      <td>27.879194</td>\n",
       "      <td>-0.467109</td>\n",
       "      <td>-1.259444</td>\n",
       "      <td>-1.089212</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>168 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    parameter_timestamp  current_ir  electrical_energy  frequency       power  \\\n",
       "0   2023-07-13 13:00:50    0.001096         141.234711       50.0  127.811417   \n",
       "1   2023-07-13 14:00:50    0.004344         139.727371       50.0  130.631073   \n",
       "2   2023-07-13 15:00:50   -0.004954         138.812119       50.0  129.651535   \n",
       "3   2023-07-13 16:00:50    0.001051         140.470779       50.0  127.855476   \n",
       "4   2023-07-13 17:00:50   -0.000661         138.916412       50.0  131.405380   \n",
       "..                  ...         ...                ...        ...         ...   \n",
       "163 2023-07-20 08:00:50    0.001771         138.384018       50.0  129.857925   \n",
       "164 2023-07-20 09:00:50    0.000068         140.150238       50.0  130.151627   \n",
       "165 2023-07-20 10:00:50    0.000186         139.940826       50.0  128.701904   \n",
       "166 2023-07-20 11:00:50   -0.007508         140.450912       50.0  128.328964   \n",
       "167 2023-07-20 12:00:50    0.002726         139.368546       50.0  130.120071   \n",
       "\n",
       "     powerfactor  pressure  temperature  voltage_vb  voltage_vr  voltage_vy  \n",
       "0       1.001055  1.057300    27.986296   -1.917876    0.576301   -0.040845  \n",
       "1       1.000224  1.060515    28.029724   -1.008769    0.131339   -0.803190  \n",
       "2       0.999673  1.060144    27.930075   -1.564345   -0.319494   -0.133825  \n",
       "3       1.000330  1.059224    27.881578    0.151097    0.639718   -0.659135  \n",
       "4       1.000780  1.062929    28.005365   -1.031228   -1.475980   -0.234166  \n",
       "..           ...       ...          ...         ...         ...         ...  \n",
       "163     0.999521  1.062028    27.924028    0.229666   -1.267485   -1.298952  \n",
       "164     0.999780  1.061307    27.996088   -1.717520   -1.180167    0.026794  \n",
       "165     0.999633  1.060397    28.017605   -1.705875   -0.438039    0.817327  \n",
       "166     1.000353  1.061629    27.954876   -1.840141   -0.302064   -1.691164  \n",
       "167     1.000274  1.060468    27.879194   -0.467109   -1.259444   -1.089212  \n",
       "\n",
       "[168 rows x 11 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_scaled_preds, *_ = learn.get_X_preds(new_x)\n",
    "\n",
    "new_scaled_preds=to_np(new_scaled_preds).swapaxes(1,2).reshape(-1,len(y_vars))\n",
    "dates=pd.date_range(start=fcst_date, periods=fcst_horizon+1,freq='1H')[1:]\n",
    "preds_df=pd.DataFrame(dates,columns=[datetime_col])\n",
    "preds_df.loc[:, y_vars]=new_scaled_preds\n",
    "preds_df=learn.inverse_transform(preds_df)\n",
    "\n",
    "preds_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "tsai",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}