{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Wikipedia Page Titles\n",
    "- populate `page_titles` table from single dump file `enwiki-20190420-pages-articles-multistream.xml.bz2`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# basic defaults, including study dates, common SQL exclusions and parquet files for anonymized data\n",
    "%run -i 'data-defaults.py'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+-------+--------------------+\n",
      "|page_id|          page_title|\n",
      "+-------+--------------------+\n",
      "|     12|           Anarchism|\n",
      "|     25|              Autism|\n",
      "|     39|              Albedo|\n",
      "|    290|                   A|\n",
      "|    303|             Alabama|\n",
      "|    305|            Achilles|\n",
      "|    307|     Abraham Lincoln|\n",
      "|    308|           Aristotle|\n",
      "|    309|An American in Paris|\n",
      "|    316|Academy Award for...|\n",
      "|    324|      Academy Awards|\n",
      "|    330|             Actrius|\n",
      "|    332|     Animalia (book)|\n",
      "|    334|International Ato...|\n",
      "|    336|            Altruism|\n",
      "|    339|            Ayn Rand|\n",
      "|    340|        Alain Connes|\n",
      "|    344|          Allan Dwan|\n",
      "|    358|             Algeria|\n",
      "|    359|List of Atlas Shr...|\n",
      "+-------+--------------------+\n",
      "only showing top 20 rows\n",
      "\n"
     ]
    }
   ],
   "source": [
    "WIKIPEDIA_XML_DUMP = 'enwiki-20190420-pages-articles-multistream.xml.bz2'\n",
    "\n",
    "def page_title(entity):\n",
    "    page_title = entity.title\n",
    "    return Row(page_id=entity.id, page_title=entity.title)\n",
    "\n",
    "wikipedia = sqlContext.read.format('com.databricks.spark.xml').options(rowTag='page').load(WIKIPEDIA_XML_DUMP)\n",
    "articles = wikipedia\\\n",
    "    .filter(\"ns = '0'\")\\\n",
    "    .filter(\"redirect._title is null\") \\\n",
    "    .filter(\"revision.text._VALUE is not null\") \\\n",
    "    .filter(\"length(revision.text._VALUE) > 0\")\n",
    "page_titles = sqlContext.createDataFrame(articles.rdd.map(lambda entity: page_title(entity)))\n",
    "page_titles.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DataFrame[]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# save page titles data to a table for later use\n",
    "page_titles.registerTempTable(\"temp_page_titles\")\n",
    "sqlContext.sql(\"DROP TABLE IF EXISTS ryanmax.population_page_titles_20190420\")\n",
    "sqlContext.sql(\"CREATE TABLE ryanmax.population_page_titles_20190420 AS SELECT * FROM temp_page_titles\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+--------+-----------+\n",
      "|page_ids|page_titles|\n",
      "+--------+-----------+\n",
      "| 5847824|    5847824|\n",
      "+--------+-----------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# sanity check: 1:1 ratio of page_id to page_title\n",
    "q = \"\"\"\n",
    "select count(distinct page_id) as page_ids, count(distinct page_title) as page_titles \n",
    "    from ryanmax.population_page_titles_20190420\n",
    "\"\"\"\n",
    "sqlContext.sql(q).show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "PySpark large: spark-xml jar and local venv path ",
   "language": "python",
   "name": "spark-ryanmax"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}