{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from pprint import pprint\n",
    "from collections import Counter\n",
    "import common\n",
    "import math"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "commit_list_df = pd.read_csv(\"results/classifier/commitlist.csv\")\n",
    "mean_authors=commit_list_df.query(\"category == 'Uncategorized' & topic != 'not user facing'\").author.to_list()\n",
    "counts = Counter(mean_authors)\n",
    "commit_list_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "commit_list_df.category.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# The number un categorized and no topic commits\n",
    "no_category = commit_list_df.query(\"category == 'Uncategorized' & topic != 'not user facing'\")\n",
    "print(len(no_category))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# check for cherry-picked commits\n",
    "example_sha = '55c76baf579cb6593f87d1a23e9a49afeb55f15a'\n",
    "commit_hashes = set(commit_list_df.commit_hash.to_list())\n",
    "\n",
    "example_sha[:11] in commit_hashes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get the difference between known categories and categories from commits\n",
    "\n",
    "diff_categories = set(commit_list_df.category.to_list()) - set(common.categories)\n",
    "print(len(diff_categories))\n",
    "pprint(diff_categories)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Counts of categories\n"
   ]
  }
 ],
 "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"
  },
  "vscode": {
   "interpreter": {
    "hash": "a867c59af434d7534e61ccb37014830daefd5fcd3816cab68d595dde5e446f52"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}