{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd \n",
    "from datetime import datetime \n",
    "from datetime import date\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from keras.models import Sequential\n",
    "from keras.layers import LSTM, Dense\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import MinMaxScaler,StandardScaler\n",
    "from keras.callbacks import ModelCheckpoint\n",
    "import tensorflow as tf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "merged = pd.read_csv(r'../data/long_merge.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "ename": "MemoryError",
     "evalue": "Unable to allocate 8.15 GiB for an array with shape (528, 2072154) and data type float64",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mMemoryError\u001b[0m                               Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[10], line 23\u001b[0m\n\u001b[0;32m     14\u001b[0m \u001b[38;5;66;03m# for rtu in rtus:\u001b[39;00m\n\u001b[0;32m     15\u001b[0m \u001b[38;5;66;03m#     for column in merged.columns:\u001b[39;00m\n\u001b[0;32m     16\u001b[0m \u001b[38;5;66;03m#         if f\"rtu_00{rtu}_fltrd_sa\" in column:\u001b[39;00m\n\u001b[0;32m     17\u001b[0m \u001b[38;5;66;03m#                 cols.append(column)\u001b[39;00m\n\u001b[0;32m     18\u001b[0m cols \u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdate\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m+\u001b[39m cols \u001b[38;5;241m+\u001b[39m [\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mair_temp_set_1\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m     19\u001b[0m  \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mair_temp_set_2\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m     20\u001b[0m  \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdew_point_temperature_set_1d\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m     21\u001b[0m  \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mrelative_humidity_set_1\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m     22\u001b[0m  \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msolar_radiation_set_1\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[1;32m---> 23\u001b[0m input_dataset \u001b[38;5;241m=\u001b[39m \u001b[43mmerged\u001b[49m\u001b[43m[\u001b[49m\u001b[43mcols\u001b[49m\u001b[43m]\u001b[49m\n\u001b[0;32m     24\u001b[0m input_dataset\u001b[38;5;241m.\u001b[39mcolumns\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\frame.py:4105\u001b[0m, in \u001b[0;36mDataFrame.__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m   4102\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(indexer, \u001b[38;5;28mslice\u001b[39m):\n\u001b[0;32m   4103\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_slice(indexer, axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m-> 4105\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_take_with_is_copy\u001b[49m\u001b[43m(\u001b[49m\u001b[43mindexer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m   4107\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_single_key:\n\u001b[0;32m   4108\u001b[0m     \u001b[38;5;66;03m# What does looking for a single key in a non-unique index return?\u001b[39;00m\n\u001b[0;32m   4109\u001b[0m     \u001b[38;5;66;03m# The behavior is inconsistent. It returns a Series, except when\u001b[39;00m\n\u001b[0;32m   4110\u001b[0m     \u001b[38;5;66;03m# - the key itself is repeated (test on data.shape, #9519), or\u001b[39;00m\n\u001b[0;32m   4111\u001b[0m     \u001b[38;5;66;03m# - we have a MultiIndex on columns (test on self.columns, #21309)\u001b[39;00m\n\u001b[0;32m   4112\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m data\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m1\u001b[39m] \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m1\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns, MultiIndex):\n\u001b[0;32m   4113\u001b[0m         \u001b[38;5;66;03m# GH#26490 using data[key] can cause RecursionError\u001b[39;00m\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\generic.py:4150\u001b[0m, in \u001b[0;36mNDFrame._take_with_is_copy\u001b[1;34m(self, indices, axis)\u001b[0m\n\u001b[0;32m   4139\u001b[0m \u001b[38;5;129m@final\u001b[39m\n\u001b[0;32m   4140\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_with_is_copy\u001b[39m(\u001b[38;5;28mself\u001b[39m, indices, axis: Axis \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Self:\n\u001b[0;32m   4141\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m   4142\u001b[0m \u001b[38;5;124;03m    Internal version of the `take` method that sets the `_is_copy`\u001b[39;00m\n\u001b[0;32m   4143\u001b[0m \u001b[38;5;124;03m    attribute to keep track of the parent dataframe (using in indexing\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   4148\u001b[0m \u001b[38;5;124;03m    See the docstring of `take` for full explanation of the parameters.\u001b[39;00m\n\u001b[0;32m   4149\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[1;32m-> 4150\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtake\u001b[49m\u001b[43m(\u001b[49m\u001b[43mindices\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mindices\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   4151\u001b[0m     \u001b[38;5;66;03m# Maybe set copy if we didn't actually change the index.\u001b[39;00m\n\u001b[0;32m   4152\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mndim \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m2\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m result\u001b[38;5;241m.\u001b[39m_get_axis(axis)\u001b[38;5;241m.\u001b[39mequals(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_axis(axis)):\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\generic.py:4130\u001b[0m, in \u001b[0;36mNDFrame.take\u001b[1;34m(self, indices, axis, **kwargs)\u001b[0m\n\u001b[0;32m   4125\u001b[0m     \u001b[38;5;66;03m# We can get here with a slice via DataFrame.__getitem__\u001b[39;00m\n\u001b[0;32m   4126\u001b[0m     indices \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39marange(\n\u001b[0;32m   4127\u001b[0m         indices\u001b[38;5;241m.\u001b[39mstart, indices\u001b[38;5;241m.\u001b[39mstop, indices\u001b[38;5;241m.\u001b[39mstep, dtype\u001b[38;5;241m=\u001b[39mnp\u001b[38;5;241m.\u001b[39mintp\n\u001b[0;32m   4128\u001b[0m     )\n\u001b[1;32m-> 4130\u001b[0m new_data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_mgr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtake\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   4131\u001b[0m \u001b[43m    \u001b[49m\u001b[43mindices\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   4132\u001b[0m \u001b[43m    \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_block_manager_axis\u001b[49m\u001b[43m(\u001b[49m\u001b[43maxis\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   4133\u001b[0m \u001b[43m    \u001b[49m\u001b[43mverify\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[0;32m   4134\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   4135\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_constructor_from_mgr(new_data, axes\u001b[38;5;241m=\u001b[39mnew_data\u001b[38;5;241m.\u001b[39maxes)\u001b[38;5;241m.\u001b[39m__finalize__(\n\u001b[0;32m   4136\u001b[0m     \u001b[38;5;28mself\u001b[39m, method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtake\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m   4137\u001b[0m )\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\internals\\managers.py:894\u001b[0m, in \u001b[0;36mBaseBlockManager.take\u001b[1;34m(self, indexer, axis, verify)\u001b[0m\n\u001b[0;32m    891\u001b[0m indexer \u001b[38;5;241m=\u001b[39m maybe_convert_indices(indexer, n, verify\u001b[38;5;241m=\u001b[39mverify)\n\u001b[0;32m    893\u001b[0m new_labels \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxes[axis]\u001b[38;5;241m.\u001b[39mtake(indexer)\n\u001b[1;32m--> 894\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreindex_indexer\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    895\u001b[0m \u001b[43m    \u001b[49m\u001b[43mnew_axis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnew_labels\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    896\u001b[0m \u001b[43m    \u001b[49m\u001b[43mindexer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mindexer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    897\u001b[0m \u001b[43m    \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    898\u001b[0m \u001b[43m    \u001b[49m\u001b[43mallow_dups\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[0;32m    899\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcopy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[0;32m    900\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\internals\\managers.py:680\u001b[0m, in \u001b[0;36mBaseBlockManager.reindex_indexer\u001b[1;34m(self, new_axis, indexer, axis, fill_value, allow_dups, copy, only_slice, use_na_proxy)\u001b[0m\n\u001b[0;32m    677\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mIndexError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRequested axis not found in manager\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m    679\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m axis \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[1;32m--> 680\u001b[0m     new_blocks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_slice_take_blocks_ax0\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    681\u001b[0m \u001b[43m        \u001b[49m\u001b[43mindexer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    682\u001b[0m \u001b[43m        \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfill_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    683\u001b[0m \u001b[43m        \u001b[49m\u001b[43monly_slice\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43monly_slice\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    684\u001b[0m \u001b[43m        \u001b[49m\u001b[43muse_na_proxy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_na_proxy\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    685\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    686\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m    687\u001b[0m     new_blocks \u001b[38;5;241m=\u001b[39m [\n\u001b[0;32m    688\u001b[0m         blk\u001b[38;5;241m.\u001b[39mtake_nd(\n\u001b[0;32m    689\u001b[0m             indexer,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    695\u001b[0m         \u001b[38;5;28;01mfor\u001b[39;00m blk \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mblocks\n\u001b[0;32m    696\u001b[0m     ]\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\internals\\managers.py:843\u001b[0m, in \u001b[0;36mBaseBlockManager._slice_take_blocks_ax0\u001b[1;34m(self, slice_or_indexer, fill_value, only_slice, use_na_proxy, ref_inplace_op)\u001b[0m\n\u001b[0;32m    841\u001b[0m                     blocks\u001b[38;5;241m.\u001b[39mappend(nb)\n\u001b[0;32m    842\u001b[0m             \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 843\u001b[0m                 nb \u001b[38;5;241m=\u001b[39m \u001b[43mblk\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtake_nd\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtaker\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnew_mgr_locs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmgr_locs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    844\u001b[0m                 blocks\u001b[38;5;241m.\u001b[39mappend(nb)\n\u001b[0;32m    846\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m blocks\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\internals\\blocks.py:1307\u001b[0m, in \u001b[0;36mBlock.take_nd\u001b[1;34m(self, indexer, axis, new_mgr_locs, fill_value)\u001b[0m\n\u001b[0;32m   1304\u001b[0m     allow_fill \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[0;32m   1306\u001b[0m \u001b[38;5;66;03m# Note: algos.take_nd has upcast logic similar to coerce_to_target_dtype\u001b[39;00m\n\u001b[1;32m-> 1307\u001b[0m new_values \u001b[38;5;241m=\u001b[39m \u001b[43malgos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtake_nd\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1308\u001b[0m \u001b[43m    \u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindexer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mallow_fill\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mallow_fill\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfill_value\u001b[49m\n\u001b[0;32m   1309\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1311\u001b[0m \u001b[38;5;66;03m# Called from three places in managers, all of which satisfy\u001b[39;00m\n\u001b[0;32m   1312\u001b[0m \u001b[38;5;66;03m#  these assertions\u001b[39;00m\n\u001b[0;32m   1313\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m, ExtensionBlock):\n\u001b[0;32m   1314\u001b[0m     \u001b[38;5;66;03m# NB: in this case, the 'axis' kwarg will be ignored in the\u001b[39;00m\n\u001b[0;32m   1315\u001b[0m     \u001b[38;5;66;03m#  algos.take_nd call above.\u001b[39;00m\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\array_algos\\take.py:117\u001b[0m, in \u001b[0;36mtake_nd\u001b[1;34m(arr, indexer, axis, fill_value, allow_fill)\u001b[0m\n\u001b[0;32m    114\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m arr\u001b[38;5;241m.\u001b[39mtake(indexer, fill_value\u001b[38;5;241m=\u001b[39mfill_value, allow_fill\u001b[38;5;241m=\u001b[39mallow_fill)\n\u001b[0;32m    116\u001b[0m arr \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39masarray(arr)\n\u001b[1;32m--> 117\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_take_nd_ndarray\u001b[49m\u001b[43m(\u001b[49m\u001b[43marr\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindexer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mallow_fill\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\array_algos\\take.py:157\u001b[0m, in \u001b[0;36m_take_nd_ndarray\u001b[1;34m(arr, indexer, axis, fill_value, allow_fill)\u001b[0m\n\u001b[0;32m    155\u001b[0m     out \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mempty(out_shape, dtype\u001b[38;5;241m=\u001b[39mdtype, order\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mF\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m    156\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 157\u001b[0m     out \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mempty(out_shape, dtype\u001b[38;5;241m=\u001b[39mdtype)\n\u001b[0;32m    159\u001b[0m func \u001b[38;5;241m=\u001b[39m _get_take_nd_function(\n\u001b[0;32m    160\u001b[0m     arr\u001b[38;5;241m.\u001b[39mndim, arr\u001b[38;5;241m.\u001b[39mdtype, out\u001b[38;5;241m.\u001b[39mdtype, axis\u001b[38;5;241m=\u001b[39maxis, mask_info\u001b[38;5;241m=\u001b[39mmask_info\n\u001b[0;32m    161\u001b[0m )\n\u001b[0;32m    162\u001b[0m func(arr, indexer, out, fill_value)\n",
      "\u001b[1;31mMemoryError\u001b[0m: Unable to allocate 8.15 GiB for an array with shape (528, 2072154) and data type float64"
     ]
    }
   ],
   "source": [
    "zones = [69, 68,67, 66,65.64, 42,41,40,39,38,37,36]\n",
    "rtus = [1]\n",
    "cols = []\n",
    "\n",
    "for zone in zones:\n",
    "        for column in merged.columns:\n",
    "            if f\"zone_0{zone}\" in column and 'co2' not in column and \"hw_valve\" not in column and \"cooling_sp\" not in column and \"heating_sp\" not in column:\n",
    "                cols.append(column)\n",
    "\n",
    "for zone in zones:\n",
    "        for column in merged.columns:\n",
    "              if f\"zone_0{zone}\" in column and \"cooling_sp\" in column or \"heating_sp\" in column:\n",
    "                cols.append(column)\n",
    "# for rtu in rtus:\n",
    "#     for column in merged.columns:\n",
    "#         if f\"rtu_00{rtu}_fltrd_sa\" in column:\n",
    "#                 cols.append(column)\n",
    "cols =['date'] + cols + ['air_temp_set_1',\n",
    " 'air_temp_set_2',\n",
    " 'dew_point_temperature_set_1d',\n",
    " 'relative_humidity_set_1',\n",
    " 'solar_radiation_set_1']\n",
    "input_dataset = merged[cols]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\arbal\\AppData\\Local\\Temp\\ipykernel_32464\\216607548.py:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  input_dataset['date'] = pd.to_datetime(input_dataset['date'], format = \"%Y-%m-%d %H:%M:%S\")\n"
     ]
    },
    {
     "ename": "MemoryError",
     "evalue": "Unable to allocate 8.15 GiB for an array with shape (528, 2070713) and data type float64",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mMemoryError\u001b[0m                               Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[11], line 2\u001b[0m\n\u001b[0;32m      1\u001b[0m input_dataset[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdate\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mto_datetime(input_dataset[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdate\u001b[39m\u001b[38;5;124m'\u001b[39m], \u001b[38;5;28mformat\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mY-\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mm-\u001b[39m\u001b[38;5;132;01m%d\u001b[39;00m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mH:\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mM:\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124mS\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m----> 2\u001b[0m df_filtered \u001b[38;5;241m=\u001b[39m \u001b[43minput_dataset\u001b[49m\u001b[43m[\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43minput_dataset\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdate\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdt\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdate\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m>\u001b[39;49m\u001b[43mdate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m2018\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m&\u001b[39;49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43minput_dataset\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdate\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdt\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdate\u001b[49m\u001b[38;5;241;43m<\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mdate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m2021\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m\n\u001b[0;32m      4\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m df_filtered\u001b[38;5;241m.\u001b[39misna()\u001b[38;5;241m.\u001b[39many()\u001b[38;5;241m.\u001b[39many():\n\u001b[0;32m      5\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThere are NA values in the DataFrame columns.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\frame.py:4081\u001b[0m, in \u001b[0;36mDataFrame.__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m   4079\u001b[0m \u001b[38;5;66;03m# Do we have a (boolean) 1d indexer?\u001b[39;00m\n\u001b[0;32m   4080\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m com\u001b[38;5;241m.\u001b[39mis_bool_indexer(key):\n\u001b[1;32m-> 4081\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_getitem_bool_array\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   4083\u001b[0m \u001b[38;5;66;03m# We are left with two options: a single key, and a collection of keys,\u001b[39;00m\n\u001b[0;32m   4084\u001b[0m \u001b[38;5;66;03m# We interpret tuples as collections only for non-MultiIndex\u001b[39;00m\n\u001b[0;32m   4085\u001b[0m is_single_key \u001b[38;5;241m=\u001b[39m \u001b[38;5;28misinstance\u001b[39m(key, \u001b[38;5;28mtuple\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_list_like(key)\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\frame.py:4143\u001b[0m, in \u001b[0;36mDataFrame._getitem_bool_array\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m   4140\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcopy(deep\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[0;32m   4142\u001b[0m indexer \u001b[38;5;241m=\u001b[39m key\u001b[38;5;241m.\u001b[39mnonzero()[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m-> 4143\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_take_with_is_copy\u001b[49m\u001b[43m(\u001b[49m\u001b[43mindexer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\generic.py:4150\u001b[0m, in \u001b[0;36mNDFrame._take_with_is_copy\u001b[1;34m(self, indices, axis)\u001b[0m\n\u001b[0;32m   4139\u001b[0m \u001b[38;5;129m@final\u001b[39m\n\u001b[0;32m   4140\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_with_is_copy\u001b[39m(\u001b[38;5;28mself\u001b[39m, indices, axis: Axis \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Self:\n\u001b[0;32m   4141\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m   4142\u001b[0m \u001b[38;5;124;03m    Internal version of the `take` method that sets the `_is_copy`\u001b[39;00m\n\u001b[0;32m   4143\u001b[0m \u001b[38;5;124;03m    attribute to keep track of the parent dataframe (using in indexing\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   4148\u001b[0m \u001b[38;5;124;03m    See the docstring of `take` for full explanation of the parameters.\u001b[39;00m\n\u001b[0;32m   4149\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[1;32m-> 4150\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtake\u001b[49m\u001b[43m(\u001b[49m\u001b[43mindices\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mindices\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   4151\u001b[0m     \u001b[38;5;66;03m# Maybe set copy if we didn't actually change the index.\u001b[39;00m\n\u001b[0;32m   4152\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mndim \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m2\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m result\u001b[38;5;241m.\u001b[39m_get_axis(axis)\u001b[38;5;241m.\u001b[39mequals(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_axis(axis)):\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\generic.py:4130\u001b[0m, in \u001b[0;36mNDFrame.take\u001b[1;34m(self, indices, axis, **kwargs)\u001b[0m\n\u001b[0;32m   4125\u001b[0m     \u001b[38;5;66;03m# We can get here with a slice via DataFrame.__getitem__\u001b[39;00m\n\u001b[0;32m   4126\u001b[0m     indices \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39marange(\n\u001b[0;32m   4127\u001b[0m         indices\u001b[38;5;241m.\u001b[39mstart, indices\u001b[38;5;241m.\u001b[39mstop, indices\u001b[38;5;241m.\u001b[39mstep, dtype\u001b[38;5;241m=\u001b[39mnp\u001b[38;5;241m.\u001b[39mintp\n\u001b[0;32m   4128\u001b[0m     )\n\u001b[1;32m-> 4130\u001b[0m new_data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_mgr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtake\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   4131\u001b[0m \u001b[43m    \u001b[49m\u001b[43mindices\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   4132\u001b[0m \u001b[43m    \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_block_manager_axis\u001b[49m\u001b[43m(\u001b[49m\u001b[43maxis\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   4133\u001b[0m \u001b[43m    \u001b[49m\u001b[43mverify\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[0;32m   4134\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   4135\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_constructor_from_mgr(new_data, axes\u001b[38;5;241m=\u001b[39mnew_data\u001b[38;5;241m.\u001b[39maxes)\u001b[38;5;241m.\u001b[39m__finalize__(\n\u001b[0;32m   4136\u001b[0m     \u001b[38;5;28mself\u001b[39m, method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtake\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m   4137\u001b[0m )\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\internals\\managers.py:894\u001b[0m, in \u001b[0;36mBaseBlockManager.take\u001b[1;34m(self, indexer, axis, verify)\u001b[0m\n\u001b[0;32m    891\u001b[0m indexer \u001b[38;5;241m=\u001b[39m maybe_convert_indices(indexer, n, verify\u001b[38;5;241m=\u001b[39mverify)\n\u001b[0;32m    893\u001b[0m new_labels \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxes[axis]\u001b[38;5;241m.\u001b[39mtake(indexer)\n\u001b[1;32m--> 894\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreindex_indexer\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    895\u001b[0m \u001b[43m    \u001b[49m\u001b[43mnew_axis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnew_labels\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    896\u001b[0m \u001b[43m    \u001b[49m\u001b[43mindexer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mindexer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    897\u001b[0m \u001b[43m    \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    898\u001b[0m \u001b[43m    \u001b[49m\u001b[43mallow_dups\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[0;32m    899\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcopy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[0;32m    900\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\internals\\managers.py:687\u001b[0m, in \u001b[0;36mBaseBlockManager.reindex_indexer\u001b[1;34m(self, new_axis, indexer, axis, fill_value, allow_dups, copy, only_slice, use_na_proxy)\u001b[0m\n\u001b[0;32m    680\u001b[0m     new_blocks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_slice_take_blocks_ax0(\n\u001b[0;32m    681\u001b[0m         indexer,\n\u001b[0;32m    682\u001b[0m         fill_value\u001b[38;5;241m=\u001b[39mfill_value,\n\u001b[0;32m    683\u001b[0m         only_slice\u001b[38;5;241m=\u001b[39monly_slice,\n\u001b[0;32m    684\u001b[0m         use_na_proxy\u001b[38;5;241m=\u001b[39muse_na_proxy,\n\u001b[0;32m    685\u001b[0m     )\n\u001b[0;32m    686\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 687\u001b[0m     new_blocks \u001b[38;5;241m=\u001b[39m \u001b[43m[\u001b[49m\n\u001b[0;32m    688\u001b[0m \u001b[43m        \u001b[49m\u001b[43mblk\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtake_nd\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    689\u001b[0m \u001b[43m            \u001b[49m\u001b[43mindexer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    690\u001b[0m \u001b[43m            \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m    691\u001b[0m \u001b[43m            \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[0;32m    692\u001b[0m \u001b[43m                \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mblk\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfill_value\u001b[49m\n\u001b[0;32m    693\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    694\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    695\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mblk\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mblocks\u001b[49m\n\u001b[0;32m    696\u001b[0m \u001b[43m    \u001b[49m\u001b[43m]\u001b[49m\n\u001b[0;32m    698\u001b[0m new_axes \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxes)\n\u001b[0;32m    699\u001b[0m new_axes[axis] \u001b[38;5;241m=\u001b[39m new_axis\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\internals\\managers.py:688\u001b[0m, in \u001b[0;36m<listcomp>\u001b[1;34m(.0)\u001b[0m\n\u001b[0;32m    680\u001b[0m     new_blocks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_slice_take_blocks_ax0(\n\u001b[0;32m    681\u001b[0m         indexer,\n\u001b[0;32m    682\u001b[0m         fill_value\u001b[38;5;241m=\u001b[39mfill_value,\n\u001b[0;32m    683\u001b[0m         only_slice\u001b[38;5;241m=\u001b[39monly_slice,\n\u001b[0;32m    684\u001b[0m         use_na_proxy\u001b[38;5;241m=\u001b[39muse_na_proxy,\n\u001b[0;32m    685\u001b[0m     )\n\u001b[0;32m    686\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m    687\u001b[0m     new_blocks \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m--> 688\u001b[0m         \u001b[43mblk\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtake_nd\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    689\u001b[0m \u001b[43m            \u001b[49m\u001b[43mindexer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    690\u001b[0m \u001b[43m            \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m    691\u001b[0m \u001b[43m            \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[0;32m    692\u001b[0m \u001b[43m                \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mblk\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfill_value\u001b[49m\n\u001b[0;32m    693\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    694\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    695\u001b[0m         \u001b[38;5;28;01mfor\u001b[39;00m blk \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mblocks\n\u001b[0;32m    696\u001b[0m     ]\n\u001b[0;32m    698\u001b[0m new_axes \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxes)\n\u001b[0;32m    699\u001b[0m new_axes[axis] \u001b[38;5;241m=\u001b[39m new_axis\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\internals\\blocks.py:1307\u001b[0m, in \u001b[0;36mBlock.take_nd\u001b[1;34m(self, indexer, axis, new_mgr_locs, fill_value)\u001b[0m\n\u001b[0;32m   1304\u001b[0m     allow_fill \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[0;32m   1306\u001b[0m \u001b[38;5;66;03m# Note: algos.take_nd has upcast logic similar to coerce_to_target_dtype\u001b[39;00m\n\u001b[1;32m-> 1307\u001b[0m new_values \u001b[38;5;241m=\u001b[39m \u001b[43malgos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtake_nd\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1308\u001b[0m \u001b[43m    \u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindexer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mallow_fill\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mallow_fill\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfill_value\u001b[49m\n\u001b[0;32m   1309\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1311\u001b[0m \u001b[38;5;66;03m# Called from three places in managers, all of which satisfy\u001b[39;00m\n\u001b[0;32m   1312\u001b[0m \u001b[38;5;66;03m#  these assertions\u001b[39;00m\n\u001b[0;32m   1313\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m, ExtensionBlock):\n\u001b[0;32m   1314\u001b[0m     \u001b[38;5;66;03m# NB: in this case, the 'axis' kwarg will be ignored in the\u001b[39;00m\n\u001b[0;32m   1315\u001b[0m     \u001b[38;5;66;03m#  algos.take_nd call above.\u001b[39;00m\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\array_algos\\take.py:117\u001b[0m, in \u001b[0;36mtake_nd\u001b[1;34m(arr, indexer, axis, fill_value, allow_fill)\u001b[0m\n\u001b[0;32m    114\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m arr\u001b[38;5;241m.\u001b[39mtake(indexer, fill_value\u001b[38;5;241m=\u001b[39mfill_value, allow_fill\u001b[38;5;241m=\u001b[39mallow_fill)\n\u001b[0;32m    116\u001b[0m arr \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39masarray(arr)\n\u001b[1;32m--> 117\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_take_nd_ndarray\u001b[49m\u001b[43m(\u001b[49m\u001b[43marr\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindexer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mallow_fill\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32md:\\Programs\\minconda3\\envs\\smartbuildings\\Lib\\site-packages\\pandas\\core\\array_algos\\take.py:157\u001b[0m, in \u001b[0;36m_take_nd_ndarray\u001b[1;34m(arr, indexer, axis, fill_value, allow_fill)\u001b[0m\n\u001b[0;32m    155\u001b[0m     out \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mempty(out_shape, dtype\u001b[38;5;241m=\u001b[39mdtype, order\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mF\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m    156\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 157\u001b[0m     out \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mempty(out_shape, dtype\u001b[38;5;241m=\u001b[39mdtype)\n\u001b[0;32m    159\u001b[0m func \u001b[38;5;241m=\u001b[39m _get_take_nd_function(\n\u001b[0;32m    160\u001b[0m     arr\u001b[38;5;241m.\u001b[39mndim, arr\u001b[38;5;241m.\u001b[39mdtype, out\u001b[38;5;241m.\u001b[39mdtype, axis\u001b[38;5;241m=\u001b[39maxis, mask_info\u001b[38;5;241m=\u001b[39mmask_info\n\u001b[0;32m    161\u001b[0m )\n\u001b[0;32m    162\u001b[0m func(arr, indexer, out, fill_value)\n",
      "\u001b[1;31mMemoryError\u001b[0m: Unable to allocate 8.15 GiB for an array with shape (528, 2070713) and data type float64"
     ]
    }
   ],
   "source": [
    "input_dataset['date'] = pd.to_datetime(input_dataset['date'], format = \"%Y-%m-%d %H:%M:%S\")\n",
    "df_filtered = input_dataset[ (input_dataset.date.dt.date >date(2019, 1, 1)) & (input_dataset.date.dt.date< date(2021, 1, 1))]\n",
    "\n",
    "if df_filtered.isna().any().any():\n",
    "    print(\"There are NA values in the DataFrame columns.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>zone_069_temp</th>\n",
       "      <th>zone_069_fan_spd</th>\n",
       "      <th>zone_068_temp</th>\n",
       "      <th>zone_068_fan_spd</th>\n",
       "      <th>zone_067_temp</th>\n",
       "      <th>zone_067_fan_spd</th>\n",
       "      <th>zone_066_temp</th>\n",
       "      <th>zone_066_fan_spd</th>\n",
       "      <th>zone_042_temp</th>\n",
       "      <th>...</th>\n",
       "      <th>zone_066_heating_sp</th>\n",
       "      <th>zone_067_heating_sp</th>\n",
       "      <th>zone_069_heating_sp</th>\n",
       "      <th>zone_070_heating_sp</th>\n",
       "      <th>zone_071_heating_sp</th>\n",
       "      <th>air_temp_set_1</th>\n",
       "      <th>air_temp_set_2</th>\n",
       "      <th>dew_point_temperature_set_1d</th>\n",
       "      <th>relative_humidity_set_1</th>\n",
       "      <th>solar_radiation_set_1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1440</th>\n",
       "      <td>2018-01-02 00:00:00</td>\n",
       "      <td>71.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>73.2</td>\n",
       "      <td>70.0</td>\n",
       "      <td>71.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>70.4</td>\n",
       "      <td>35.0</td>\n",
       "      <td>71.6</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>15.280</td>\n",
       "      <td>15.100</td>\n",
       "      <td>6.33</td>\n",
       "      <td>55.40</td>\n",
       "      <td>161.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1441</th>\n",
       "      <td>2018-01-02 00:01:00</td>\n",
       "      <td>71.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>73.2</td>\n",
       "      <td>70.0</td>\n",
       "      <td>71.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>70.4</td>\n",
       "      <td>35.0</td>\n",
       "      <td>71.6</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>15.280</td>\n",
       "      <td>15.100</td>\n",
       "      <td>6.33</td>\n",
       "      <td>55.40</td>\n",
       "      <td>161.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1442</th>\n",
       "      <td>2018-01-02 00:02:00</td>\n",
       "      <td>71.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>73.2</td>\n",
       "      <td>70.0</td>\n",
       "      <td>71.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>70.4</td>\n",
       "      <td>35.0</td>\n",
       "      <td>71.6</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>15.280</td>\n",
       "      <td>15.100</td>\n",
       "      <td>6.33</td>\n",
       "      <td>55.40</td>\n",
       "      <td>161.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1443</th>\n",
       "      <td>2018-01-02 00:03:00</td>\n",
       "      <td>71.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>73.2</td>\n",
       "      <td>70.0</td>\n",
       "      <td>71.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>70.4</td>\n",
       "      <td>35.0</td>\n",
       "      <td>71.6</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>15.280</td>\n",
       "      <td>15.100</td>\n",
       "      <td>6.33</td>\n",
       "      <td>55.40</td>\n",
       "      <td>161.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1444</th>\n",
       "      <td>2018-01-02 00:04:00</td>\n",
       "      <td>71.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>73.2</td>\n",
       "      <td>70.0</td>\n",
       "      <td>71.2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>70.4</td>\n",
       "      <td>35.0</td>\n",
       "      <td>71.6</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>15.280</td>\n",
       "      <td>15.100</td>\n",
       "      <td>6.33</td>\n",
       "      <td>55.40</td>\n",
       "      <td>161.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2072148</th>\n",
       "      <td>2020-12-31 23:57:00</td>\n",
       "      <td>68.8</td>\n",
       "      <td>20.0</td>\n",
       "      <td>71.7</td>\n",
       "      <td>20.0</td>\n",
       "      <td>70.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>68.6</td>\n",
       "      <td>35.0</td>\n",
       "      <td>71.4</td>\n",
       "      <td>...</td>\n",
       "      <td>68.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>65.0</td>\n",
       "      <td>67.0</td>\n",
       "      <td>13.994</td>\n",
       "      <td>13.528</td>\n",
       "      <td>4.11</td>\n",
       "      <td>51.61</td>\n",
       "      <td>188.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2072149</th>\n",
       "      <td>2020-12-31 23:58:00</td>\n",
       "      <td>68.8</td>\n",
       "      <td>20.0</td>\n",
       "      <td>71.7</td>\n",
       "      <td>20.0</td>\n",
       "      <td>70.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>68.6</td>\n",
       "      <td>35.0</td>\n",
       "      <td>71.4</td>\n",
       "      <td>...</td>\n",
       "      <td>68.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>65.0</td>\n",
       "      <td>67.0</td>\n",
       "      <td>13.994</td>\n",
       "      <td>13.528</td>\n",
       "      <td>4.11</td>\n",
       "      <td>51.61</td>\n",
       "      <td>188.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2072150</th>\n",
       "      <td>2020-12-31 23:58:00</td>\n",
       "      <td>68.8</td>\n",
       "      <td>20.0</td>\n",
       "      <td>71.7</td>\n",
       "      <td>20.0</td>\n",
       "      <td>70.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>68.6</td>\n",
       "      <td>35.0</td>\n",
       "      <td>71.4</td>\n",
       "      <td>...</td>\n",
       "      <td>68.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>65.0</td>\n",
       "      <td>67.0</td>\n",
       "      <td>13.994</td>\n",
       "      <td>13.528</td>\n",
       "      <td>4.11</td>\n",
       "      <td>51.61</td>\n",
       "      <td>188.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2072151</th>\n",
       "      <td>2020-12-31 23:59:00</td>\n",
       "      <td>68.8</td>\n",
       "      <td>20.0</td>\n",
       "      <td>71.7</td>\n",
       "      <td>20.0</td>\n",
       "      <td>70.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>68.6</td>\n",
       "      <td>35.0</td>\n",
       "      <td>71.4</td>\n",
       "      <td>...</td>\n",
       "      <td>68.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>65.0</td>\n",
       "      <td>67.0</td>\n",
       "      <td>13.994</td>\n",
       "      <td>13.528</td>\n",
       "      <td>4.11</td>\n",
       "      <td>51.61</td>\n",
       "      <td>188.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2072152</th>\n",
       "      <td>2020-12-31 23:59:00</td>\n",
       "      <td>68.8</td>\n",
       "      <td>20.0</td>\n",
       "      <td>71.7</td>\n",
       "      <td>20.0</td>\n",
       "      <td>70.4</td>\n",
       "      <td>20.0</td>\n",
       "      <td>68.6</td>\n",
       "      <td>35.0</td>\n",
       "      <td>71.4</td>\n",
       "      <td>...</td>\n",
       "      <td>68.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>65.0</td>\n",
       "      <td>67.0</td>\n",
       "      <td>13.994</td>\n",
       "      <td>13.528</td>\n",
       "      <td>4.11</td>\n",
       "      <td>51.61</td>\n",
       "      <td>188.8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2070713 rows × 529 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                       date  zone_069_temp  zone_069_fan_spd  zone_068_temp  \\\n",
       "1440    2018-01-02 00:00:00           71.4              20.0           73.2   \n",
       "1441    2018-01-02 00:01:00           71.4              20.0           73.2   \n",
       "1442    2018-01-02 00:02:00           71.4              20.0           73.2   \n",
       "1443    2018-01-02 00:03:00           71.4              20.0           73.2   \n",
       "1444    2018-01-02 00:04:00           71.4              20.0           73.2   \n",
       "...                     ...            ...               ...            ...   \n",
       "2072148 2020-12-31 23:57:00           68.8              20.0           71.7   \n",
       "2072149 2020-12-31 23:58:00           68.8              20.0           71.7   \n",
       "2072150 2020-12-31 23:58:00           68.8              20.0           71.7   \n",
       "2072151 2020-12-31 23:59:00           68.8              20.0           71.7   \n",
       "2072152 2020-12-31 23:59:00           68.8              20.0           71.7   \n",
       "\n",
       "         zone_068_fan_spd  zone_067_temp  zone_067_fan_spd  zone_066_temp  \\\n",
       "1440                 70.0           71.2              20.0           70.4   \n",
       "1441                 70.0           71.2              20.0           70.4   \n",
       "1442                 70.0           71.2              20.0           70.4   \n",
       "1443                 70.0           71.2              20.0           70.4   \n",
       "1444                 70.0           71.2              20.0           70.4   \n",
       "...                   ...            ...               ...            ...   \n",
       "2072148              20.0           70.4              20.0           68.6   \n",
       "2072149              20.0           70.4              20.0           68.6   \n",
       "2072150              20.0           70.4              20.0           68.6   \n",
       "2072151              20.0           70.4              20.0           68.6   \n",
       "2072152              20.0           70.4              20.0           68.6   \n",
       "\n",
       "         zone_066_fan_spd  zone_042_temp  ...  zone_066_heating_sp  \\\n",
       "1440                 35.0           71.6  ...                  NaN   \n",
       "1441                 35.0           71.6  ...                  NaN   \n",
       "1442                 35.0           71.6  ...                  NaN   \n",
       "1443                 35.0           71.6  ...                  NaN   \n",
       "1444                 35.0           71.6  ...                  NaN   \n",
       "...                   ...            ...  ...                  ...   \n",
       "2072148              35.0           71.4  ...                 68.0   \n",
       "2072149              35.0           71.4  ...                 68.0   \n",
       "2072150              35.0           71.4  ...                 68.0   \n",
       "2072151              35.0           71.4  ...                 68.0   \n",
       "2072152              35.0           71.4  ...                 68.0   \n",
       "\n",
       "         zone_067_heating_sp  zone_069_heating_sp  zone_070_heating_sp  \\\n",
       "1440                     NaN                  NaN                  NaN   \n",
       "1441                     NaN                  NaN                  NaN   \n",
       "1442                     NaN                  NaN                  NaN   \n",
       "1443                     NaN                  NaN                  NaN   \n",
       "1444                     NaN                  NaN                  NaN   \n",
       "...                      ...                  ...                  ...   \n",
       "2072148                 68.0                 68.0                 65.0   \n",
       "2072149                 68.0                 68.0                 65.0   \n",
       "2072150                 68.0                 68.0                 65.0   \n",
       "2072151                 68.0                 68.0                 65.0   \n",
       "2072152                 68.0                 68.0                 65.0   \n",
       "\n",
       "         zone_071_heating_sp  air_temp_set_1  air_temp_set_2  \\\n",
       "1440                     NaN          15.280          15.100   \n",
       "1441                     NaN          15.280          15.100   \n",
       "1442                     NaN          15.280          15.100   \n",
       "1443                     NaN          15.280          15.100   \n",
       "1444                     NaN          15.280          15.100   \n",
       "...                      ...             ...             ...   \n",
       "2072148                 67.0          13.994          13.528   \n",
       "2072149                 67.0          13.994          13.528   \n",
       "2072150                 67.0          13.994          13.528   \n",
       "2072151                 67.0          13.994          13.528   \n",
       "2072152                 67.0          13.994          13.528   \n",
       "\n",
       "         dew_point_temperature_set_1d  relative_humidity_set_1  \\\n",
       "1440                             6.33                    55.40   \n",
       "1441                             6.33                    55.40   \n",
       "1442                             6.33                    55.40   \n",
       "1443                             6.33                    55.40   \n",
       "1444                             6.33                    55.40   \n",
       "...                               ...                      ...   \n",
       "2072148                          4.11                    51.61   \n",
       "2072149                          4.11                    51.61   \n",
       "2072150                          4.11                    51.61   \n",
       "2072151                          4.11                    51.61   \n",
       "2072152                          4.11                    51.61   \n",
       "\n",
       "         solar_radiation_set_1  \n",
       "1440                     161.9  \n",
       "1441                     161.9  \n",
       "1442                     161.9  \n",
       "1443                     161.9  \n",
       "1444                     161.9  \n",
       "...                        ...  \n",
       "2072148                  188.8  \n",
       "2072149                  188.8  \n",
       "2072150                  188.8  \n",
       "2072151                  188.8  \n",
       "2072152                  188.8  \n",
       "\n",
       "[2070713 rows x 529 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_filtered"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['zone_070_heating_sp',\n",
       " 'zone_070_heating_sp',\n",
       " 'zone_070_heating_sp',\n",
       " 'zone_070_heating_sp',\n",
       " 'zone_070_heating_sp',\n",
       " 'zone_070_heating_sp',\n",
       " 'zone_070_heating_sp',\n",
       " 'zone_070_heating_sp',\n",
       " 'zone_070_heating_sp',\n",
       " 'zone_070_heating_sp',\n",
       " 'zone_070_heating_sp',\n",
       " 'zone_070_heating_sp']"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "testdataset_df = df_filtered[(df_filtered.date.dt.date >date(2019, 5, 1)) & (df_filtered.date.dt.date <date(2019,7, 1))]\n",
    "\n",
    "# traindataset_df = df_filtered[ (df_filtered.date.dt.date >date(2019, 11, 8))]\n",
    "\n",
    "traindataset_df = df_filtered[(df_filtered.date.dt.date >date(2019, 3, 1)) & (df_filtered.date.dt.date <date(2019, 5, 1))]\n",
    "testdataset = testdataset_df.drop(columns=[\"date\"]).rolling(window = 5, step = 1, min_periods= 1).mean().values\n",
    "traindataset = traindataset_df.drop(columns=[\"date\"]).rolling(window = 5, step = 1, min_periods= 1).mean().values\n",
    "\n",
    "columns_with_na = traindataset_df.columns[traindataset_df.isna().any()].tolist()\n",
    "columns_with_na"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['date', 'zone_069_temp', 'zone_069_fan_spd', 'zone_068_temp',\n",
       "       'zone_068_fan_spd', 'zone_067_temp', 'zone_067_fan_spd',\n",
       "       'zone_066_temp', 'zone_066_fan_spd', 'zone_042_temp',\n",
       "       ...\n",
       "       'zone_066_heating_sp', 'zone_067_heating_sp', 'zone_069_heating_sp',\n",
       "       'zone_070_heating_sp', 'zone_071_heating_sp', 'air_temp_set_1',\n",
       "       'air_temp_set_2', 'dew_point_temperature_set_1d',\n",
       "       'relative_humidity_set_1', 'solar_radiation_set_1'],\n",
       "      dtype='object', length=529)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "traindataset_df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0 0\n"
     ]
    }
   ],
   "source": [
    "print(traindataset_df.isna().sum().sum(), testdataset_df.isna().sum().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(86400, 86400)"
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(traindataset), len(testdataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {},
   "outputs": [],
   "source": [
    "traindataset = traindataset.astype('float32')\n",
    "testdataset = testdataset.astype('float32')\n",
    "\n",
    "scaler = StandardScaler()\n",
    "traindataset = scaler.fit_transform(traindataset)\n",
    "testdataset = scaler.transform(testdataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(86400, 45)"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "traindataset.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "metadata": {},
   "outputs": [],
   "source": [
    "train,test = traindataset,testdataset\n",
    "\n",
    "def create_dataset(dataset,time_step):\n",
    "    x = []\n",
    "    Y = []\n",
    "    for i in range(len(dataset) - time_step - 1):\n",
    "        x.append(dataset[i:(i+time_step),:])\n",
    "        Y.append(dataset[i+time_step,0:-5])\n",
    "    x= np.array(x)\n",
    "    Y = np.array(Y)\n",
    "    return x,Y\n",
    "time_step = 30\n",
    "X_train, y_train = create_dataset(train, time_step)\n",
    "X_test, y_test = create_dataset(test, time_step)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((86369, 30, 45), (86369, 40))"
      ]
     },
     "execution_count": 128,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape, y_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/5\n",
      "674/675 [============================>.] - ETA: 0s - loss: 0.1090\n",
      "Epoch 1: val_loss improved from inf to 0.26433, saving model to lstm_vav_01.tf\n",
      "INFO:tensorflow:Assets written to: lstm_vav_01.tf\\assets\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Assets written to: lstm_vav_01.tf\\assets\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "675/675 [==============================] - 61s 84ms/step - loss: 0.1089 - val_loss: 0.2643\n",
      "Epoch 2/5\n",
      "675/675 [==============================] - ETA: 0s - loss: 0.0155\n",
      "Epoch 2: val_loss improved from 0.26433 to 0.21391, saving model to lstm_vav_01.tf\n",
      "INFO:tensorflow:Assets written to: lstm_vav_01.tf\\assets\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Assets written to: lstm_vav_01.tf\\assets\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "675/675 [==============================] - 45s 67ms/step - loss: 0.0155 - val_loss: 0.2139\n",
      "Epoch 3/5\n",
      "675/675 [==============================] - ETA: 0s - loss: 0.0081\n",
      "Epoch 3: val_loss improved from 0.21391 to 0.17155, saving model to lstm_vav_01.tf\n",
      "INFO:tensorflow:Assets written to: lstm_vav_01.tf\\assets\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Assets written to: lstm_vav_01.tf\\assets\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "675/675 [==============================] - 58s 86ms/step - loss: 0.0081 - val_loss: 0.1716\n",
      "Epoch 4/5\n",
      "675/675 [==============================] - ETA: 0s - loss: 0.0049\n",
      "Epoch 4: val_loss improved from 0.17155 to 0.14438, saving model to lstm_vav_01.tf\n",
      "INFO:tensorflow:Assets written to: lstm_vav_01.tf\\assets\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Assets written to: lstm_vav_01.tf\\assets\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "675/675 [==============================] - 54s 80ms/step - loss: 0.0049 - val_loss: 0.1444\n",
      "Epoch 5/5\n",
      "675/675 [==============================] - ETA: 0s - loss: 0.0030\n",
      "Epoch 5: val_loss improved from 0.14438 to 0.12414, saving model to lstm_vav_01.tf\n",
      "INFO:tensorflow:Assets written to: lstm_vav_01.tf\\assets\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Assets written to: lstm_vav_01.tf\\assets\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "675/675 [==============================] - 60s 89ms/step - loss: 0.0030 - val_loss: 0.1241\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.src.callbacks.History at 0x1d5bf064950>"
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "model = Sequential()\n",
    "model.add(LSTM(units=50, return_sequences=True, input_shape=(X_train.shape[1], X_train.shape[2])))\n",
    "model.add(LSTM(units=50, return_sequences=True))\n",
    "model.add(LSTM(units=30))\n",
    "model.add(Dense(units=y_train.shape[1]))\n",
    "\n",
    "model.compile(optimizer='adam', loss='mean_squared_error')\n",
    "\n",
    "checkpoint_path = \"lstm_vav_01.tf\"\n",
    "checkpoint_callback = ModelCheckpoint(filepath=checkpoint_path, monitor='val_loss', verbose=1, save_best_only=True, mode='min')\n",
    "model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=5, batch_size=128, verbose=1, callbacks=[checkpoint_callback])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<tensorflow.python.checkpoint.checkpoint.CheckpointLoadStatus at 0x1d55c631f10>"
      ]
     },
     "execution_count": 134,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.load_weights(checkpoint_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2700/2700 [==============================] - 25s 9ms/step\n"
     ]
    }
   ],
   "source": [
    "test_predict1 = model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x1d5582d61d0>]"
      ]
     },
     "execution_count": 136,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "plt.plot(y_test[:,3])\n",
    "plt.plot(y_train[:,3])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib qt\n",
    "var = 1\n",
    "plt.plot(y_test[:,var], label='Original Testing Data', color='blue')\n",
    "plt.plot(test_predict1[:,var], label='Predicted Testing Data', color='red',alpha=0.8)\n",
    "anomalies = np.where(abs(test_predict1[:,var] - y_test[:,var]) > 0.38)\n",
    "plt.scatter(anomalies,test_predict1[anomalies,var], color='black',marker =\"o\",s=100 )\n",
    "\n",
    "\n",
    "plt.title('Testing Data - Predicted vs Actual')\n",
    "plt.xlabel('Time')\n",
    "plt.ylabel('Value')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.mixture import GaussianMixture\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "# Generating random data for demonstration\n",
    "np.random.seed(0)\n",
    "X =  test_predict1 - y_test\n",
    "\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X = pca.fit_transform(X)\n",
    "\n",
    "\n",
    "# Creating the GMM instance with desired number of clusters\n",
    "gmm = GaussianMixture(n_components=2)\n",
    "\n",
    "# Fitting the model to the data\n",
    "gmm.fit(X)\n",
    "\n",
    "# Getting the cluster labels\n",
    "labels = gmm.predict(X)\n",
    "\n",
    "# Plotting the data points with colors representing different clusters\n",
    "plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis', alpha=0.5)\n",
    "plt.title('GMM Clustering')\n",
    "plt.xlabel('Feature 1')\n",
    "plt.ylabel('Feature 2')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "operands could not be broadcast together with shapes (199403,51) (8,) ",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[19], line 6\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[38;5;66;03m# Generating random data for demonstration\u001b[39;00m\n\u001b[0;32m      5\u001b[0m np\u001b[38;5;241m.\u001b[39mrandom\u001b[38;5;241m.\u001b[39mseed(\u001b[38;5;241m0\u001b[39m)\n\u001b[1;32m----> 6\u001b[0m X \u001b[38;5;241m=\u001b[39m \u001b[43m(\u001b[49m\u001b[43mtest_predict1\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[43m \u001b[49m\u001b[43my_test\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mscaler\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mvar_\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m:\u001b[49m\u001b[38;5;241;43m8\u001b[39;49m\u001b[43m]\u001b[49m \u001b[38;5;241m+\u001b[39m scaler\u001b[38;5;241m.\u001b[39mmean_[\u001b[38;5;241m0\u001b[39m:\u001b[38;5;241m8\u001b[39m]\n\u001b[0;32m      8\u001b[0m k \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m6\u001b[39m\n\u001b[0;32m     10\u001b[0m kmeans \u001b[38;5;241m=\u001b[39m KMeans(n_clusters\u001b[38;5;241m=\u001b[39mk)\n",
      "\u001b[1;31mValueError\u001b[0m: operands could not be broadcast together with shapes (199403,51) (8,) "
     ]
    }
   ],
   "source": [
    "from sklearn.cluster import KMeans\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "# Generating random data for demonstration\n",
    "np.random.seed(0)\n",
    "X = (test_predict1 - y_test)\n",
    "\n",
    "k = 6\n",
    "\n",
    "kmeans = KMeans(n_clusters=k)\n",
    "\n",
    "kmeans.fit(X)\n",
    "\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X = pca.fit_transform(X)\n",
    "\n",
    "\n",
    "\n",
    "# Getting the cluster centers and labels\n",
    "centroids = kmeans.cluster_centers_\n",
    "centroids = pca.transform(centroids)\n",
    "labels = kmeans.labels_\n",
    "\n",
    "# Plotting the data points and cluster centers\n",
    "plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis', alpha=0.5)\n",
    "plt.scatter(centroids[:, 0], centroids[:, 1], marker='x', c='red', s=200, linewidths=2)\n",
    "plt.title('KMeans Clustering')\n",
    "plt.xlabel('Feature 1')\n",
    "plt.ylabel('Feature 2')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "k = 60\n",
    "X= test_predict1 - y_test\n",
    "processed_data = []\n",
    "feat_df = pd.DataFrame(columns=[\"mean\",\"std\",])\n",
    "for i in range(0,len(X), 60):\n",
    "    mean = X[i:i+k].mean(axis = 0)\n",
    "    std = X[i:i+k].std(axis = 0)\n",
    "    max = X[i:i+k].max(axis = 0)\n",
    "    min = X[i:i+k].min(axis = 0)\n",
    "    iqr = np.percentile(X[i:i+k], 75, axis=0) - np.percentile(X[i:i+k], 25,axis=0)\n",
    "    data = np.concatenate([mean, std, max, min, iqr])\n",
    "    processed_data.append([data])\n",
    "processed_data = np.concatenate(processed_data,axis=0) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = processed_data\n",
    "\n",
    "kmeans = KMeans(n_clusters=3, algorithm='elkan', max_iter=1000, n_init = 5)\n",
    "\n",
    "kmeans.fit(X)\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X = pca.fit_transform(X)\n",
    "\n",
    "\n",
    "# Getting the cluster centers and labels\n",
    "centroids = kmeans.cluster_centers_\n",
    "centroids = pca.transform(centroids)\n",
    "labels = kmeans.labels_\n",
    "\n",
    "# Plotting the data points and cluster centers\n",
    "plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis', alpha=0.5)\n",
    "plt.scatter(centroids[:, 0], centroids[:, 1], marker='x', c='red', s=200, linewidths=2)\n",
    "plt.title('KMeans Clustering')\n",
    "plt.xlabel('Feature 1')\n",
    "plt.ylabel('Feature 2')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.mixture import GaussianMixture\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.decomposition import PCA\n",
    "\n",
    "# Generating random data for demonstration\n",
    "np.random.seed(0)\n",
    "X = processed_data\n",
    "\n",
    "# Creating the GMM instance with desired number of clusters\n",
    "gmm = GaussianMixture(n_components=3, init_params='k-means++')\n",
    "\n",
    "# Fitting the model to the data\n",
    "gmm.fit(X)\n",
    "labels = gmm.predict(X)\n",
    "\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X = pca.fit_transform(X)\n",
    "\n",
    "\n",
    "# Getting the cluster labels\n",
    "\n",
    "# Plotting the data points with colors representing different clusters\n",
    "plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis', alpha=0.5)\n",
    "plt.title('GMM Clustering')\n",
    "plt.xlabel('Feature 1')\n",
    "plt.ylabel('Feature 2')\n",
    "plt.show()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.cluster import KMeans\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "# Generating random data for demonstration\n",
    "np.random.seed(0)\n",
    "X = (test_predict1 * scaler.var_[0:8] + scaler.mean_[0:8]) - (y_test * scaler.var_[0:8] + scaler.mean_[0:8])\n",
    "k = 6\n",
    "\n",
    "kmeans = KMeans(n_clusters=k)\n",
    "\n",
    "kmeans.fit(X)\n",
    "\n",
    "\n",
    "pca = PCA(n_components=2)\n",
    "X = pca.fit_transform(X)\n",
    "\n",
    "\n",
    "\n",
    "# Getting the cluster centers and labels\n",
    "centroids = kmeans.cluster_centers_\n",
    "centroids = pca.transform(centroids)\n",
    "labels = kmeans.labels_\n",
    "\n",
    "# Plotting the data points and cluster centers\n",
    "plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis', alpha=0.5)\n",
    "plt.scatter(centroids[:, 0], centroids[:, 1], marker='x', c='red', s=200, linewidths=2)\n",
    "plt.title('KMeans Clustering')\n",
    "plt.xlabel('Feature 1')\n",
    "plt.ylabel('Feature 2')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "tensorflow",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}