filter-is-a-stupid-tag.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import collections\n",
    "import itertools\n",
    "import time\n",
    "\n",
    "import requests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://api.stackexchange.com/2.2/questions\"\n",
    "query = {\n",
    "    \"order\": \"desc\",\n",
    "    \"sort\": \"activity\",\n",
    "    \"tagged\": \"filter\",\n",
    "    \"site\": \"webapps\",\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'page': 1, 'pagesize': 100}\n"
     ]
    }
   ],
   "source": [
    "pageinfo = {\n",
    "    \"page\": 1,\n",
    "    \"pagesize\": 100,\n",
    "}\n",
    "questions = []\n",
    "while True:\n",
    "    print(pageinfo)\n",
    "    response = requests.get(url, params={**query, **pageinfo})\n",
    "    \n",
    "    data = response.json()\n",
    "    items = data.pop(\"items\")\n",
    "\n",
    "    questions.extend(items)\n",
    "    \n",
    "    if not data[\"has_more\"]:\n",
    "        break\n",
    "    if data[\"quota_remaining\"] < 100:\n",
    "        break\n",
    "    \n",
    "    pageinfo[\"page\"] += 1\n",
    "    time.sleep(0.5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[(2, 22), (5, 19), (3, 18), (4, 11)]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "n_tags_per_q = collections.Counter(len(q[\"tags\"]) for q in questions)\n",
    "assert 1 not in n_tags_per_q  # there are no questions *ONLY* tagged [filter]\n",
    "n_tags_per_q.most_common()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('google-sheets', 10),\n",
       " ('twitter', 3),\n",
       " ('google-search', 2),\n",
       " ('yahoo-mail', 2),\n",
       " ('netflix', 1),\n",
       " ('spam-prevention', 1),\n",
       " ('youtube', 1),\n",
       " ('outlook.com', 1),\n",
       " ('search', 1)]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "the_one_other_tag = collections.Counter(itertools.chain(*(q[\"tags\"] for q in questions if len(q[\"tags\"]) == 2)))\n",
    "the_one_other_tag.pop(\"filter\")\n",
    "the_one_other_tag.most_common()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('google-sheets', 42),\n",
       " ('formulas', 27),\n",
       " ('google-sheets-query', 14),\n",
       " ('google-sheets-arrayformula', 13),\n",
       " ('twitter', 5),\n",
       " ('importrange', 4),\n",
       " ('gmail', 4),\n",
       " ('search', 4),\n",
       " ('google-search', 4),\n",
       " ('regex', 3)]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tag_counts = collections.Counter(itertools.chain(*(q[\"tags\"] for q in questions)))\n",
    "assert tag_counts.pop(\"filter\") == len(questions)  # is on all..boring.\n",
    "tag_counts.most_common(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('google-sheets', 42),\n",
       " ('twitter', 5),\n",
       " ('gmail', 4),\n",
       " ('google-search', 3),\n",
       " ('spam-prevention', 2),\n",
       " ('yahoo-mail', 2),\n",
       " ('search', 2),\n",
       " ('google-apps', 1),\n",
       " ('google-sheets-query', 1),\n",
       " ('regex', 1),\n",
       " ('netflix', 1),\n",
       " ('youtube', 1),\n",
       " ('outlook.com', 1),\n",
       " ('amazon', 1),\n",
       " ('firefox-extensions', 1),\n",
       " ('google-reader', 1),\n",
       " ('rss', 1)]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "most_common_other_tags = collections.Counter()\n",
    "for question in questions:\n",
    "    mcot = max(question[\"tags\"], key=lambda x: tag_counts[x])\n",
    "    most_common_other_tags[mcot] += 1\n",
    "most_common_other_tags.most_common()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.1"
  },
  "spitball": {
   "api_url": "",
   "desc": "",
   "id": "",
   "vis": ""
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}