{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Notebook Test Example of Features"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Test calculation of features implemented in versio 0.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "sys.path.append(r'D:\\pbl\\InterpreTS')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_crossing_points import calculate_crossing_points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'crossing_count': 7, 'crossing_points': [0, 1, 2, 3, 4, 5, 6]}\n",
      "{'crossing_count': 0, 'crossing_points': []}\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 3, 2, 4, 1, 5, 2, 6])\n",
    "result = calculate_crossing_points(data)\n",
    "print(result)\n",
    "\n",
    "data = pd.Series([2, 2, 2, 2])\n",
    "res2 = calculate_crossing_points(data)\n",
    "print(res2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_amplitude_change_rate import calculate_amplitude_change_rate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.8333333333333335\n",
      "nan\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 3, 2, 4, 1, 5, 2, 6, 3])\n",
    "res = calculate_amplitude_change_rate(data)\n",
    "print(res)\n",
    "\n",
    "data = pd.Series([1, 1, 1, 1])\n",
    "res2 =calculate_amplitude_change_rate(data)\n",
    "print(res2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_linearity import calculate_linearity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n",
      "0.0\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4, 5])\n",
    "res = calculate_linearity(data)\n",
    "print(res)\n",
    "\n",
    "data = pd.Series([1, 2, 1, 2, 1, 2, 1, 2, 1, 2])\n",
    "res2 = calculate_linearity(data)\n",
    "print(res2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.seasonality_strength import calculate_seasonality_strength"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n",
      "0.8333333333333333\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 2, 1, 2, 3, 2, 1, 2, 3, 2], index=pd.date_range(\"2023-01-01\", periods=12, freq=\"M\"))\n",
    "res1 = calculate_seasonality_strength(data, period=3)\n",
    "print(res)\n",
    "\n",
    "data = pd.Series([1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2])\n",
    "res2 = calculate_seasonality_strength(data, period=2)\n",
    "print(res2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.distance_to_the_last_change_point import calculate_distance_to_last_trend_change"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 2, 1, 2, 3, 2, 1])\n",
    "res =  calculate_distance_to_last_trend_change(data, window_size=2)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_above_9th_decile import calculate_above_9th_decile"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pd.Series([8, 9, 10, 11, 12])\n",
    "training_data = pd.Series([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])\n",
    "calculate_above_9th_decile(data, training_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_absolute_energy import calculate_absolute_energy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "30\n",
      "13\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4])\n",
    "res1 = calculate_absolute_energy(data)\n",
    "print(res1)\n",
    "\n",
    "res2 = calculate_absolute_energy(data, start=1, end=3)\n",
    "print(res2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_below_1st_decile import calculate_below_1st_decile"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.2\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4, 5])\n",
    "training_data = pd.Series([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])\n",
    "res1 = calculate_below_1st_decile(data, training_data)\n",
    "print(res1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_binarize_mean import calculate_binarize_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.6\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4, 5])\n",
    "res = calculate_binarize_mean(data)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_entropy import calculate_entropy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n",
      "0.0\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 1, 2, 3, 1, 2, 3])\n",
    "res1 = calculate_entropy(data, bins=3)\n",
    "print(res1)\n",
    "\n",
    "data = pd.Series([1, 1, 1, 1])\n",
    "res2 = calculate_entropy(data, bins=2)\n",
    "print(res2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_flat_spots import calculate_flat_spots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 1, 1, 2, 3, 3, 4, 4, 4, 4, 4, 5, 1, 1])\n",
    "res = calculate_flat_spots(data)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_heterogeneity import calculate_heterogeneity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5270462766947299\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4, 5])\n",
    "res = calculate_heterogeneity(data)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_length import calculate_length"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4, 5])\n",
    "res = calculate_length(data)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_mean import calculate_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3.0\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4, 5])\n",
    "res = calculate_mean(data)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_missing_points import calculate_missing_points"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.4\n",
      "3.0\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, np.nan, 4, None])\n",
    "res1 = calculate_missing_points(data)\n",
    "print(res1)\n",
    "\n",
    "res2 = calculate_missing_points(data, percentage=False)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_outliers_iqr import calculate_outliers_iqr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.25\n",
      "0.25\n"
     ]
    }
   ],
   "source": [
    "training_data = np.array([10, 12, 14, 15, 16, 18, 19])\n",
    "data = np.array([9, 15, 20, 25])\n",
    "res1 = calculate_outliers_iqr(data, training_data)\n",
    "print(res1)\n",
    "\n",
    "training_data = np.array([10, 10, 10, 10, 10])\n",
    "data = np.array([10, 11, 12, 9])\n",
    "res2 = calculate_outliers_iqr(data, training_data)\n",
    "print(res2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_outliers_std import calculate_outliers_std"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.2\n"
     ]
    }
   ],
   "source": [
    "training_data = pd.Series([1, 2, 3, 4, 5, 6, 7, 8, 9])\n",
    "data = pd.Series([0, 10, 2, 3, 15])\n",
    "res = calculate_outliers_std(data, training_data)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_peak import calculate_peak"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "7\n",
      "5\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 5, 4, 7])\n",
    "res1 =  calculate_peak(data)\n",
    "print(res1)\n",
    "\n",
    "res2 =calculate_peak(data, start=1, end=3)\n",
    "print(res2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_significant_changes import calculate_significant_changes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.0\n"
     ]
    }
   ],
   "source": [
    "data = np.array([1, 100, 1, 200, 50, 3, 1])\n",
    "res1 = calculate_significant_changes(data)\n",
    "print(res1) #isn't correct, all examples was 0.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_spikeness import calculate_spikeness"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.0\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4, 5])\n",
    "res =  calculate_spikeness(data)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_stability import calculate_stability"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8410385081084804\n",
      "0.6144144729613819\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([10, 12, 11, 13, 12, 14, 11, 13, 12, 14, 13])\n",
    "res1 = calculate_stability(data)\n",
    "print(res1)\n",
    "\n",
    "data = pd.Series([5, 20, 3, 18, 1, 25, 2, 22, 0, 19])\n",
    "res2 = calculate_stability(data)\n",
    "print(res2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_std_1st_der import calculate_std_1st_der"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.0\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4, 5])\n",
    "res = calculate_std_1st_der(data)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_trough import calculate_trough"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1\n",
      "2\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 5, 4, 3])\n",
    "res1 = calculate_trough(data)\n",
    "print(res1)\n",
    "\n",
    "res2 = calculate_trough(data, start=1, end=3)\n",
    "print(res2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.feature_variance import calculate_variance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10.0\n",
      "8.0\n",
      "0.0\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([10, 12, 14, 16, 18])\n",
    "res1 = calculate_variance(data)\n",
    "print(res1)\n",
    "\n",
    "data = np.array([2, 4, 6, 8, 10])\n",
    "res2 = calculate_variance(data, ddof=0)\n",
    "print(res2)\n",
    "\n",
    "data = pd.Series([5])\n",
    "res3 = calculate_variance(data)\n",
    "print(res3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.histogram_dominant import calculate_dominant"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.6\n",
      "30.0\n",
      "0.8333333333333333\n"
     ]
    }
   ],
   "source": [
    "data = np.array([1, 2, 2, 3, 3, 3, 4, 4, 5])\n",
    "res1 = calculate_dominant(data, bins=5)\n",
    "print(res1)\n",
    "\n",
    "data = np.array([10, 20, 20, 30, 30, 30, 40, 40, 50])\n",
    "res2 = calculate_dominant(data, bins=5, return_bin_center=True)\n",
    "print(res2)\n",
    "\n",
    "data = np.array([1, 1, 1, 1, 1])\n",
    "res3 = calculate_dominant(data, bins=3)\n",
    "print(res3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.mean_change import calculate_mean_change"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0    NaN\n",
      "1    NaN\n",
      "2    NaN\n",
      "3    1.0\n",
      "4    1.0\n",
      "5    1.0\n",
      "6    1.0\n",
      "7    1.0\n",
      "8    1.0\n",
      "9    1.0\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])\n",
    "res = calculate_mean_change(data, window_size=3)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.trend_strength import calculate_trend_strength"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4, 5])\n",
    "res = calculate_trend_strength(data)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.variability_in_sub_periods import calculate_variability_in_sub_periods"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0    2.0\n",
      "1    2.0\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])\n",
    "res = calculate_variability_in_sub_periods(data, window_size=5)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "from interpreTS.core.features.variance_change import calculate_change_in_variance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0          NaN\n",
      "1          NaN\n",
      "2          NaN\n",
      "3    -4.000000\n",
      "4    -4.000000\n",
      "5     4.666667\n",
      "6     5.333333\n",
      "7    -8.000000\n",
      "8    26.666667\n",
      "9    -8.666667\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "data = pd.Series([1, 2, 7, 4, 5, 9, 12, 8, 1, 10])\n",
    "res = calculate_change_in_variance(data, window_size=3)\n",
    "print(res)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "PBL",
   "language": "python",
   "name": "env"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.20"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}