{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Extract Features Using Dask for Large Time Series Data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook demonstrates how to use the `interpreTS` library with the Dask framework to process and extract features efficiently from large time series datasets."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 1: Import Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from interpreTS.core.feature_extractor import FeatureExtractor, Features"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 2: Generate Large Time Series Data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here, we create a large dataset with 100 unique time series (`id`) and 1,000 data points for each, resulting in a total of 100,000 rows. Each `id` represents a distinct time series."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.DataFrame({\n",
    "    'id': np.repeat(range(100), 1000),  # 100 time series\n",
    "    'time': np.tile(range(1000), 100),  # 1,000 time steps per series\n",
    "    'value': np.random.randn(100000)    # Random values\n",
    "})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 3: Initialize the FeatureExtractor"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We specify the following parameters for feature extraction:\n",
    "\n",
    "- `features`: Extracting only the mean (Features.MEAN) from the value column.\n",
    "- `feature_column`: The column from which to calculate the feature.\n",
    "- `id_column`: Grouping the data by the unique id column.\n",
    "- `window_size`: Rolling windows of 3 samples.\n",
    "- `stride`: Sliding by 5 samples per step."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "feature_extractor = FeatureExtractor(\n",
    "    features=[Features.MEAN],   # Extract mean feature\n",
    "    feature_column=\"value\",     # Target column\n",
    "    id_column=\"id\",             # Unique identifier for time series\n",
    "    window_size=3,              # Rolling window size\n",
    "    stride=5                    # Sliding step size\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 4: Extract Features Using Dask"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To handle the large dataset efficiently, we use the `mode='dask'` parameter in the `extract_features` method. This processes the data in parallel using Dask."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[########################################] | 100% Completed | 3.59 sms\n"
     ]
    }
   ],
   "source": [
    "features_df = feature_extractor.extract_features(data, mode='dask')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 5: Display the Extracted Features"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Finally, we print the first few rows of the extracted features."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>mean_value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.147607</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-1.034064</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.846525</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.319443</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-0.763688</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   mean_value\n",
       "0    0.147607\n",
       "1   -1.034064\n",
       "2    0.846525\n",
       "3   -0.319443\n",
       "4   -0.763688"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "display(features_df.head())"
   ]
  }
 ],
 "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
}