{
 "cells": [
  {
   "cell_type": "code",
   "id": "initial_id",
   "metadata": {
    "collapsed": true,
    "ExecuteTime": {
     "end_time": "2024-05-15T07:49:59.747703Z",
     "start_time": "2024-05-15T07:49:59.134058Z"
    }
   },
   "source": [
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv('/home/gui/hf_dev/datatrove/blogpost/data/decont_ngrams-per_dump.csv')"
   ],
   "execution_count": 1,
   "outputs": []
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-15T07:51:52.324884Z",
     "start_time": "2024-05-15T07:51:52.283371Z"
    }
   },
   "cell_type": "code",
   "source": "df = df.groupby([\"ngram\", \"task\"], as_index=False)[\"count\"].sum().sort_values(\"count\", ascending=False)",
   "id": "c691b2709c417bf4",
   "execution_count": 8,
   "outputs": []
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-05-15T07:52:17.954219Z",
     "start_time": "2024-05-15T07:52:17.938060Z"
    }
   },
   "cell_type": "code",
   "source": "df.to_csv('/home/gui/hf_dev/datatrove/blogpost/data/decont_ngrams-global.csv', index=False)",
   "id": "9c0dfcd486f8e260",
   "execution_count": 9,
   "outputs": []
  },
  {
   "metadata": {},
   "cell_type": "code",
   "execution_count": null,
   "source": "",
   "id": "d5fef0e4bc91a43e",
   "outputs": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}