{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Feature Extraction Notebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import interpreTS as it"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Features from Original Data:\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>length_value1</th>\n",
       "      <th>length_value2</th>\n",
       "      <th>mean_value1</th>\n",
       "      <th>mean_value2</th>\n",
       "      <th>variance_value1</th>\n",
       "      <th>variance_value2</th>\n",
       "      <th>stability_value1</th>\n",
       "      <th>stability_value2</th>\n",
       "      <th>entropy_value1</th>\n",
       "      <th>entropy_value2</th>\n",
       "      <th>spikeness_value1</th>\n",
       "      <th>spikeness_value2</th>\n",
       "      <th>seasonality_strength_value1</th>\n",
       "      <th>seasonality_strength_value2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>-0.090984</td>\n",
       "      <td>20.984855</td>\n",
       "      <td>0.980715</td>\n",
       "      <td>96.393343</td>\n",
       "      <td>0.945029</td>\n",
       "      <td>0.957836</td>\n",
       "      <td>0.953598</td>\n",
       "      <td>0.936353</td>\n",
       "      <td>-0.171176</td>\n",
       "      <td>0.002747</td>\n",
       "      <td>0.024829</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>-0.041073</td>\n",
       "      <td>19.321699</td>\n",
       "      <td>0.860151</td>\n",
       "      <td>122.939138</td>\n",
       "      <td>0.966346</td>\n",
       "      <td>0.967090</td>\n",
       "      <td>0.965428</td>\n",
       "      <td>0.943508</td>\n",
       "      <td>0.057399</td>\n",
       "      <td>-0.160669</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.029677</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>0.040655</td>\n",
       "      <td>19.561352</td>\n",
       "      <td>1.013766</td>\n",
       "      <td>94.271772</td>\n",
       "      <td>0.959903</td>\n",
       "      <td>0.959041</td>\n",
       "      <td>0.960737</td>\n",
       "      <td>0.971435</td>\n",
       "      <td>0.039584</td>\n",
       "      <td>-0.037157</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>0.089580</td>\n",
       "      <td>18.423254</td>\n",
       "      <td>0.919226</td>\n",
       "      <td>105.640273</td>\n",
       "      <td>0.961216</td>\n",
       "      <td>0.961425</td>\n",
       "      <td>0.960473</td>\n",
       "      <td>0.972152</td>\n",
       "      <td>0.162142</td>\n",
       "      <td>-0.209542</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.002774</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>0.043688</td>\n",
       "      <td>20.889307</td>\n",
       "      <td>1.016813</td>\n",
       "      <td>98.086690</td>\n",
       "      <td>0.953565</td>\n",
       "      <td>0.972875</td>\n",
       "      <td>0.976043</td>\n",
       "      <td>0.968271</td>\n",
       "      <td>-0.094232</td>\n",
       "      <td>-0.039167</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.014184</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>0.071281</td>\n",
       "      <td>22.267479</td>\n",
       "      <td>0.958148</td>\n",
       "      <td>83.890173</td>\n",
       "      <td>0.941137</td>\n",
       "      <td>0.965725</td>\n",
       "      <td>0.948012</td>\n",
       "      <td>0.917666</td>\n",
       "      <td>-0.313000</td>\n",
       "      <td>-0.285326</td>\n",
       "      <td>0.093162</td>\n",
       "      <td>0.076888</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>0.180755</td>\n",
       "      <td>18.164891</td>\n",
       "      <td>1.205403</td>\n",
       "      <td>115.013098</td>\n",
       "      <td>0.940937</td>\n",
       "      <td>0.963686</td>\n",
       "      <td>0.965665</td>\n",
       "      <td>0.954352</td>\n",
       "      <td>0.045914</td>\n",
       "      <td>-0.356734</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>0.027402</td>\n",
       "      <td>20.088945</td>\n",
       "      <td>1.018580</td>\n",
       "      <td>111.999915</td>\n",
       "      <td>0.948826</td>\n",
       "      <td>0.966604</td>\n",
       "      <td>0.969764</td>\n",
       "      <td>0.979842</td>\n",
       "      <td>-0.325421</td>\n",
       "      <td>-0.167496</td>\n",
       "      <td>0.199431</td>\n",
       "      <td>0.053288</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>-0.035698</td>\n",
       "      <td>21.318984</td>\n",
       "      <td>0.805854</td>\n",
       "      <td>97.065517</td>\n",
       "      <td>0.959439</td>\n",
       "      <td>0.965456</td>\n",
       "      <td>0.943548</td>\n",
       "      <td>0.956747</td>\n",
       "      <td>-0.008034</td>\n",
       "      <td>-0.280393</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.112888</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>100</td>\n",
       "      <td>100</td>\n",
       "      <td>0.174627</td>\n",
       "      <td>21.461813</td>\n",
       "      <td>0.883258</td>\n",
       "      <td>88.348130</td>\n",
       "      <td>0.962152</td>\n",
       "      <td>0.959698</td>\n",
       "      <td>0.966687</td>\n",
       "      <td>0.958974</td>\n",
       "      <td>0.212796</td>\n",
       "      <td>-0.443187</td>\n",
       "      <td>0.038056</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>100 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    length_value1  length_value2  mean_value1  mean_value2  variance_value1  \\\n",
       "0             100            100    -0.090984    20.984855         0.980715   \n",
       "1             100            100    -0.041073    19.321699         0.860151   \n",
       "2             100            100     0.040655    19.561352         1.013766   \n",
       "3             100            100     0.089580    18.423254         0.919226   \n",
       "4             100            100     0.043688    20.889307         1.016813   \n",
       "..            ...            ...          ...          ...              ...   \n",
       "95            100            100     0.071281    22.267479         0.958148   \n",
       "96            100            100     0.180755    18.164891         1.205403   \n",
       "97            100            100     0.027402    20.088945         1.018580   \n",
       "98            100            100    -0.035698    21.318984         0.805854   \n",
       "99            100            100     0.174627    21.461813         0.883258   \n",
       "\n",
       "    variance_value2  stability_value1  stability_value2  entropy_value1  \\\n",
       "0         96.393343          0.945029          0.957836        0.953598   \n",
       "1        122.939138          0.966346          0.967090        0.965428   \n",
       "2         94.271772          0.959903          0.959041        0.960737   \n",
       "3        105.640273          0.961216          0.961425        0.960473   \n",
       "4         98.086690          0.953565          0.972875        0.976043   \n",
       "..              ...               ...               ...             ...   \n",
       "95        83.890173          0.941137          0.965725        0.948012   \n",
       "96       115.013098          0.940937          0.963686        0.965665   \n",
       "97       111.999915          0.948826          0.966604        0.969764   \n",
       "98        97.065517          0.959439          0.965456        0.943548   \n",
       "99        88.348130          0.962152          0.959698        0.966687   \n",
       "\n",
       "    entropy_value2  spikeness_value1  spikeness_value2  \\\n",
       "0         0.936353         -0.171176          0.002747   \n",
       "1         0.943508          0.057399         -0.160669   \n",
       "2         0.971435          0.039584         -0.037157   \n",
       "3         0.972152          0.162142         -0.209542   \n",
       "4         0.968271         -0.094232         -0.039167   \n",
       "..             ...               ...               ...   \n",
       "95        0.917666         -0.313000         -0.285326   \n",
       "96        0.954352          0.045914         -0.356734   \n",
       "97        0.979842         -0.325421         -0.167496   \n",
       "98        0.956747         -0.008034         -0.280393   \n",
       "99        0.958974          0.212796         -0.443187   \n",
       "\n",
       "    seasonality_strength_value1  seasonality_strength_value2  \n",
       "0                      0.024829                     0.000000  \n",
       "1                      0.000000                     0.029677  \n",
       "2                      0.000000                     0.000000  \n",
       "3                      0.000000                     0.002774  \n",
       "4                      0.000000                     0.014184  \n",
       "..                          ...                          ...  \n",
       "95                     0.093162                     0.076888  \n",
       "96                     0.000000                     0.000000  \n",
       "97                     0.199431                     0.053288  \n",
       "98                     0.000000                     0.112888  \n",
       "99                     0.038056                     0.000000  \n",
       "\n",
       "[100 rows x 14 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Creating a time series data\n",
    "data = pd.DataFrame({\n",
    "    'id': np.repeat(range(100), 100),\n",
    "    'time': np.tile(range(100), 100),\n",
    "    'value1': np.random.normal(0, 1, 10000),\n",
    "    'value2': np.random.normal(20, 10, 10000)\n",
    "})\n",
    "# Creating a feature extractor object\n",
    "extractor = it.FeatureExtractor(id_column='id', sort_column='time')\n",
    "\n",
    "# Extracting features from data\n",
    "features = extractor.extract_features(data)\n",
    "print(\"\\nFeatures from Original Data:\")\n",
    "display(features)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}