{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "model training         128\n",
       "model evaluation        91\n",
       "model deployment        75\n",
       "data cleaning           59\n",
       "model requirements      47\n",
       "feature engineering     36\n",
       "data collection         25\n",
       "Name: classification, dtype: int64"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "data = pd.read_csv('sampling_nb - sampling_nb.csv')\n",
    "\n",
    "data.drop(['second', 'url'], inplace=True, axis=1)\n",
    "\n",
    "data = data[~data['classification'].isin(['?', '', 'no pipeline', 'page not found', 'chinese', 'data labeling'])]\n",
    "\n",
    "data['classification'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "classification       L2 class\n",
       "data cleaning        DP-DF        8\n",
       "                     DP-LD        1\n",
       "                     DP-O        17\n",
       "                     DP-P         3\n",
       "                     DP-R        13\n",
       "                     DP-TE        9\n",
       "                     DP-TM        2\n",
       "                     DP-UT        6\n",
       "data collection      DC-DC       13\n",
       "                     DC-DF        4\n",
       "                     DC-F         3\n",
       "                     DC-NS        1\n",
       "                     DC-O         1\n",
       "                     DC-S         3\n",
       "feature engineering  FE-BC        8\n",
       "                     FE-CP        8\n",
       "                     FE-H        10\n",
       "                     FE-O         4\n",
       "                     FE-T         6\n",
       "model deployment     MD-CI       44\n",
       "                     MD-LR        6\n",
       "                     MD-O        10\n",
       "                     MD-SM       14\n",
       "                     ME-O         1\n",
       "model evaluation     ME-AR       30\n",
       "                     ME-C        29\n",
       "                     ME-O        20\n",
       "                     ME-RQ        8\n",
       "                     ME-TP        4\n",
       "model requirements   MR-AM       18\n",
       "                     MR-FR       25\n",
       "                     MR-NM        2\n",
       "                     MR-O         2\n",
       "model training       MT-BL       28\n",
       "                     MT-GPU      19\n",
       "                     MT-O        49\n",
       "                     MT-RU       10\n",
       "                     MT-TT       16\n",
       "                     loss         6\n",
       "dtype: int64"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.groupby(['classification', 'L2 class']).size()"
   ]
  }
 ],
 "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": "3.9.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}