dhlab_class_demo.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# dhlab class demo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dhlab as dh"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Corpus"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[0;31mInit signature:\u001b[0m\n",
      "\u001b[0mdh\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mCorpus\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mdoctype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mauthor\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mfreetext\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mfulltext\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mfrom_year\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mto_year\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mfrom_timestamp\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mto_timestamp\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mtitle\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mddk\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0msubject\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mlang\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mlimit\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0morder_by\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'random'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mSource:\u001b[0m        \n",
      "\u001b[0;32mclass\u001b[0m \u001b[0mCorpus\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mDhlabObj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m\"\"\"Class representing as DHLAB Corpus\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m    Primary object for working with dhlab data. Contains references to texts\u001b[0m\n",
      "\u001b[0;34m    in National Library's collections and metadata about them.\u001b[0m\n",
      "\u001b[0;34m    Use with `.coll`, `.conc` or `.freq` to analyse using dhlab tools.\u001b[0m\n",
      "\u001b[0;34m    \"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mdoctype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mauthor\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mfreetext\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mfulltext\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mfrom_year\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mto_year\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mfrom_timestamp\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mto_timestamp\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mtitle\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mddk\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0msubject\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mlang\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mlimit\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0morder_by\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"random\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mif\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mdoctype\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mor\u001b[0m \u001b[0mauthor\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mor\u001b[0m \u001b[0mfreetext\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mor\u001b[0m \u001b[0mfulltext\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mor\u001b[0m \u001b[0mfrom_year\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mor\u001b[0m \u001b[0mto_year\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mor\u001b[0m \u001b[0mfrom_timestamp\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mor\u001b[0m \u001b[0mto_timestamp\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mor\u001b[0m \u001b[0mtitle\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mor\u001b[0m \u001b[0mddk\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mor\u001b[0m \u001b[0mlang\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;34m\"\"\"Create Corpus\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        :param str doctype: ``\"digibok\"``, ``\"digavis\"``, \\\u001b[0m\n",
      "\u001b[0;34m            ``\"digitidsskrift\"`` or ``\"digistorting\"``\u001b[0m\n",
      "\u001b[0;34m        :param str author: Name of an author.\u001b[0m\n",
      "\u001b[0;34m        :param str freetext: any of the parameters, for example:\\\u001b[0m\n",
      "\u001b[0;34m            ``\"digibok AND Ibsen\"``.\u001b[0m\n",
      "\u001b[0;34m        :param str fulltext: words within the publication.\u001b[0m\n",
      "\u001b[0;34m        :param int from_year: Start year for time period of interest.\u001b[0m\n",
      "\u001b[0;34m        :param int to_year: End year for time period of interest.\u001b[0m\n",
      "\u001b[0;34m        :param int from_timestamp: Start date for time period of interest.\u001b[0m\n",
      "\u001b[0;34m            Format: ``YYYYMMDD``, books have ``YYYY0101``\u001b[0m\n",
      "\u001b[0;34m        :param int to_timestamp: End date for time period of interest.\u001b[0m\n",
      "\u001b[0;34m            Format: ``YYYYMMDD``, books have ``YYYY0101``\u001b[0m\n",
      "\u001b[0;34m        :param str title: Name or title of a document.\u001b[0m\n",
      "\u001b[0;34m        :param str ddk: `Dewey Decimal Classification \\\u001b[0m\n",
      "\u001b[0;34m            <https://no.wikipedia.org/wiki/Deweys_desimalklassifikasjon>`\\\u001b[0m\n",
      "\u001b[0;34m                _ identifier.\u001b[0m\n",
      "\u001b[0;34m        :param str subject: subject (keywords) of the publication.\u001b[0m\n",
      "\u001b[0;34m        :param str lang: Language of the publication, as a 3-letter ISO code.\u001b[0m\n",
      "\u001b[0;34m            Example: ``\"nob\"`` or ``\"nno\"``\u001b[0m\n",
      "\u001b[0;34m        :param int limit: number of items to sample.\u001b[0m\n",
      "\u001b[0;34m        \"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdocument_corpus\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mdoctype\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mauthor\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mfreetext\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mfulltext\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mfrom_year\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mto_year\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mfrom_timestamp\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mto_timestamp\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mtitle\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mddk\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0msubject\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mlang\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mlimit\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0morder_by\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"urn\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m@\u001b[0m\u001b[0mclassmethod\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mfrom_identifiers\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcls\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0midentifiers\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\"Construct Corpus from list of identifiers\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mcorpus\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mCorpus\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mcorpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextend_from_identifiers\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0midentifiers\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0midentifiers\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mcorpus\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m@\u001b[0m\u001b[0mclassmethod\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mfrom_df\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcls\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcheck_for_urn\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\"Typecast Pandas DataFrame to Corpus class\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        DataFrame most contain URN column\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mcorpus\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mCorpus\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mif\u001b[0m \u001b[0mcheck_for_urn\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mcorpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcls\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_urn_id_in_dataframe_cols\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mcorpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mcorpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcorpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mcorpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mcorpus\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m@\u001b[0m\u001b[0mclassmethod\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mfrom_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcls\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpath\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\"Import corpus from csv\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mcls\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_df\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m@\u001b[0m\u001b[0mstaticmethod\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0m_urn_id_in_dataframe_cols\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataframe\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\"Checks if dataframe contains URN column\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mif\u001b[0m \u001b[0;34m\"urn\"\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdataframe\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mif\u001b[0m \u001b[0mdataframe\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0murn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontains\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"^URN:NBN:no-nb_.+\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0;32mreturn\u001b[0m \u001b[0mdataframe\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"No'urn'-column in dataframe.\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mextend_from_identifiers\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0midentifiers\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mnew_corpus\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_metadata\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0murnlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0midentifiers\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnew_corpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mevaluate_words\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwordbags\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mevaluate_documents\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mwordbags\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mwordbags\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0murn\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mint\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mcols\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'dhlabid'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'urn'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'dhlabid'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'urn'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mcols\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfillna\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnew_corpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\"Utility for appending Corpus or DataFrame to self\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_is_Corpus\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnew_corpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mnew_corpus\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnew_corpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnew_corpus\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdrop_duplicates\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreset_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdrop\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0msample\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mn\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m5\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"Create random subkorpus with `n` entries\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mn\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0msample\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msample\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_df\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msample\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mconc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwords\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwindow\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m20\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlimit\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m500\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"Get concodances of `words` in corpus\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mdh\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mConcordance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mquery\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mwords\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwindow\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mwindow\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlimit\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlimit\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mcoll\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mwords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mbefore\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mafter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mreference\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0msamplesize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m20000\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0malpha\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mignore_caps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"Get collocations of `words` in corpus\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mdh\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mCollocations\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mcorpus\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mwords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mwords\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mbefore\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbefore\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mafter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mafter\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mreference\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mreference\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0msamplesize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msamplesize\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0malpha\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0malpha\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mignore_caps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mignore_caps\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mcount\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"Get word frequencies for corpus\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mdh\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mCounts\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwords\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mfreq\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"Get word frequencies for corpus\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mdh\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mCounts\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwords\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m@\u001b[0m\u001b[0mstaticmethod\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0m_is_Corpus\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mbool\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\"Check if `input` is Corpus or DataFrame\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mif\u001b[0m \u001b[0mtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mCorpus\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mraise\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Input is not Corpus or DataFrame\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mCorpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mFile:\u001b[0m           ~/anaconda3/envs/digital_tekstanalyse3.10/lib/python3.10/site-packages/dhlab/text/corpus.py\n",
      "\u001b[0;31mType:\u001b[0m           type\n",
      "\u001b[0;31mSubclasses:\u001b[0m     "
     ]
    }
   ],
   "source": [
    "dh.Corpus??"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "```python\n",
    "Init signature:\n",
    "dh.Corpus(\n",
    "    doctype=None,\n",
    "    author=None,\n",
    "    freetext=None,\n",
    "    fulltext=None,\n",
    "    from_year=None,\n",
    "    to_year=None,\n",
    "    from_timestamp=None,\n",
    "    to_timestamp=None,\n",
    "    title=None,\n",
    "    ddk=None,\n",
    "    subject=None,\n",
    "    lang=None,\n",
    "    limit=10,\n",
    "    order_by='random',\n",
    ")\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "korpus = dh.Corpus(doctype=\"digibok\", title=\"Dracula\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>dhlabid</th>\n",
       "      <th>urn</th>\n",
       "      <th>title</th>\n",
       "      <th>authors</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100439375</td>\n",
       "      <td>URN:NBN:no-nb_digibok_2021042058016</td>\n",
       "      <td>Dracula : av Lars Saabye Christensen : fritt e...</td>\n",
       "      <td></td>\n",
       "      <td>2000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>100346414</td>\n",
       "      <td>URN:NBN:no-nb_digibok_2017091805047</td>\n",
       "      <td>Dracula</td>\n",
       "      <td>MacDonald , Eric / Stoker , Bram</td>\n",
       "      <td>1983</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>100547952</td>\n",
       "      <td>URN:NBN:no-nb_digibok_2011071108102</td>\n",
       "      <td>Dracula</td>\n",
       "      <td>Stoker , Bram / Carling , Bjørn</td>\n",
       "      <td>2006</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>100138345</td>\n",
       "      <td>URN:NBN:no-nb_digibok_2013013008275</td>\n",
       "      <td>Dracula house</td>\n",
       "      <td>Flikke , Nina</td>\n",
       "      <td>1986</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>100138409</td>\n",
       "      <td>URN:NBN:no-nb_digibok_2013013108024</td>\n",
       "      <td>Dracula</td>\n",
       "      <td>Stoker , Bram / Bringsværd , Tor Åge / Bing , ...</td>\n",
       "      <td>1974</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     dhlabid                                  urn  \\\n",
       "0  100439375  URN:NBN:no-nb_digibok_2021042058016   \n",
       "1  100346414  URN:NBN:no-nb_digibok_2017091805047   \n",
       "2  100547952  URN:NBN:no-nb_digibok_2011071108102   \n",
       "3  100138345  URN:NBN:no-nb_digibok_2013013008275   \n",
       "4  100138409  URN:NBN:no-nb_digibok_2013013108024   \n",
       "\n",
       "                                               title  \\\n",
       "0  Dracula : av Lars Saabye Christensen : fritt e...   \n",
       "1                                            Dracula   \n",
       "2                                            Dracula   \n",
       "3                                      Dracula house   \n",
       "4                                            Dracula   \n",
       "\n",
       "                                             authors  year  \n",
       "0                                                     2000  \n",
       "1                   MacDonald , Eric / Stoker , Bram  1983  \n",
       "2                    Stoker , Bram / Carling , Bjørn  2006  \n",
       "3                                      Flikke , Nina  1986  \n",
       "4  Stoker , Bram / Bringsværd , Tor Åge / Bing , ...  1974  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "korpus.frame.iloc[:5, [0,1,2,3,9]]"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Conkordans"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[0;31mInit signature:\u001b[0m \u001b[0mdh\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mConcordance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mquery\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwindow\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m20\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlimit\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m500\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mSource:\u001b[0m        \n",
      "\u001b[0;32mclass\u001b[0m \u001b[0mConcordance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mDhlabObj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m\"\"\"Wrapper for concordance function\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcorpus\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mquery\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwindow\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m20\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlimit\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m500\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\"Get concordances for word(s) in corpus\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        :param corpus: Target corpus, defaults to None\u001b[0m\n",
      "\u001b[0;34m        :param query: word or list or words, defaults to None\u001b[0m\n",
      "\u001b[0;34m        :param window: how many tokens to consider around the target word, \\\u001b[0m\n",
      "\u001b[0;34m            defaults to 20\u001b[0m\n",
      "\u001b[0;34m        :param limit: limit returned hits, defaults to 500\u001b[0m\n",
      "\u001b[0;34m        \"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcordance\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconcordance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0murns\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0murnlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mquery\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwindow\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mwindow\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlimit\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlimit\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcordance\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"link\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcordance\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0murn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmake_link\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcordance\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcordance\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"link\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"urn\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"conc\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcordance\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m\"link\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"urn\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"concordance\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpus\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcorpus\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcordance\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcordance\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mshow\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mn\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstyle\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mif\u001b[0m \u001b[0mstyle\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcordance\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msample\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0;34m[\u001b[0m\u001b[0;34m\"link\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"concordance\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstyle\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcordance\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msample\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mFile:\u001b[0m           ~/anaconda3/envs/digital_tekstanalyse3.10/lib/python3.10/site-packages/dhlab/text/conc_coll.py\n",
      "\u001b[0;31mType:\u001b[0m           type\n",
      "\u001b[0;31mSubclasses:\u001b[0m     "
     ]
    }
   ],
   "source": [
    "dh.Concordance??"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "```python\n",
    "dh.Concordance(corpus=None, query=None, window=20, limit=500)\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style type=\"text/css\">\n",
       "</style>\n",
       "<table id=\"T_14e11\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"blank level0\" >&nbsp;</th>\n",
       "      <th id=\"T_14e11_level0_col0\" class=\"col_heading level0 col0\" >link</th>\n",
       "      <th id=\"T_14e11_level0_col1\" class=\"col_heading level0 col1\" >concordance</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_14e11_level0_row0\" class=\"row_heading level0 row0\" >233</th>\n",
       "      <td id=\"T_14e11_row0_col0\" class=\"data row0 col0\" ><a target='_blank' href = 'https://urn.nb.no/URN:NBN:no-nb_digibok_2014052008098'>URN:NBN:no-nb_digibok_2014052008098</a></td>\n",
       "      <td id=\"T_14e11_row0_col1\" class=\"data row0 col1\" ><b>DRACULA</b></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_14e11_level0_row1\" class=\"row_heading level0 row1\" >530</th>\n",
       "      <td id=\"T_14e11_row1_col0\" class=\"data row1 col0\" ><a target='_blank' href = 'https://urn.nb.no/URN:NBN:no-nb_digibok_2011071108102'>URN:NBN:no-nb_digibok_2011071108102</a></td>\n",
       "      <td id=\"T_14e11_row1_col1\" class=\"data row1 col1\" ><b>DRACULA</b></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_14e11_level0_row2\" class=\"row_heading level0 row2\" >300</th>\n",
       "      <td id=\"T_14e11_row2_col0\" class=\"data row2 col0\" ><a target='_blank' href = 'https://urn.nb.no/URN:NBN:no-nb_digibok_2014052008098'>URN:NBN:no-nb_digibok_2014052008098</a></td>\n",
       "      <td id=\"T_14e11_row2_col1\" class=\"data row2 col1\" ><b>DRACULA</b> I</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_14e11_level0_row3\" class=\"row_heading level0 row3\" >607</th>\n",
       "      <td id=\"T_14e11_row3_col0\" class=\"data row3 col0\" ><a target='_blank' href = 'https://urn.nb.no/URN:NBN:no-nb_digibok_2011071108102'>URN:NBN:no-nb_digibok_2011071108102</a></td>\n",
       "      <td id=\"T_14e11_row3_col1\" class=\"data row3 col1\" ><b>DRACULA</b></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_14e11_level0_row4\" class=\"row_heading level0 row4\" >379</th>\n",
       "      <td id=\"T_14e11_row4_col0\" class=\"data row4 col0\" ><a target='_blank' href = 'https://urn.nb.no/URN:NBN:no-nb_digibok_2014052008098'>URN:NBN:no-nb_digibok_2014052008098</a></td>\n",
       "      <td id=\"T_14e11_row4_col1\" class=\"data row4 col1\" ><b>DRACULA</b> !</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_14e11_level0_row5\" class=\"row_heading level0 row5\" >589</th>\n",
       "      <td id=\"T_14e11_row5_col0\" class=\"data row5 col0\" ><a target='_blank' href = 'https://urn.nb.no/URN:NBN:no-nb_digibok_2011071108102'>URN:NBN:no-nb_digibok_2011071108102</a></td>\n",
       "      <td id=\"T_14e11_row5_col1\" class=\"data row5 col1\" ><b>DRACULA</b></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_14e11_level0_row6\" class=\"row_heading level0 row6\" >491</th>\n",
       "      <td id=\"T_14e11_row6_col0\" class=\"data row6 col0\" ><a target='_blank' href = 'https://urn.nb.no/URN:NBN:no-nb_digibok_2011071108102'>URN:NBN:no-nb_digibok_2011071108102</a></td>\n",
       "      <td id=\"T_14e11_row6_col1\" class=\"data row6 col1\" ><b>DRACULA</b></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_14e11_level0_row7\" class=\"row_heading level0 row7\" >42</th>\n",
       "      <td id=\"T_14e11_row7_col0\" class=\"data row7 col0\" ><a target='_blank' href = 'https://urn.nb.no/URN:NBN:no-nb_digibok_2010020103031'>URN:NBN:no-nb_digibok_2010020103031</a></td>\n",
       "      <td id=\"T_14e11_row7_col1\" class=\"data row7 col1\" >K <b>Dracula</b> ... ;</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_14e11_level0_row8\" class=\"row_heading level0 row8\" >84</th>\n",
       "      <td id=\"T_14e11_row8_col0\" class=\"data row8 col0\" ><a target='_blank' href = 'https://urn.nb.no/URN:NBN:no-nb_digibok_2017091805047'>URN:NBN:no-nb_digibok_2017091805047</a></td>\n",
       "      <td id=\"T_14e11_row8_col1\" class=\"data row8 col1\" ><b>Dracula</b> ( opphisset ) :</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_14e11_level0_row9\" class=\"row_heading level0 row9\" >610</th>\n",
       "      <td id=\"T_14e11_row9_col0\" class=\"data row9 col0\" ><a target='_blank' href = 'https://urn.nb.no/URN:NBN:no-nb_digibok_2011071108102'>URN:NBN:no-nb_digibok_2011071108102</a></td>\n",
       "      <td id=\"T_14e11_row9_col1\" class=\"data row9 col1\" ><b>dracula</b> !</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x7fb017ce3f40>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "korpus.conc(\"Dracula\").show()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Frekvens"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[0;31mInit signature:\u001b[0m \u001b[0mdh\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mCounts\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mSource:\u001b[0m        \n",
      "\u001b[0;32mclass\u001b[0m \u001b[0mCounts\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mDhlabObj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m\"\"\"Provide counts for a corpus - shouldn't be too large\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcorpus\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\"Get frequency list for Corpus\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        :param corpus: target Corpus, defaults to None\u001b[0m\n",
      "\u001b[0;34m        :param words: list of words to be counted, defaults to None\u001b[0m\n",
      "\u001b[0;34m        \"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mif\u001b[0m \u001b[0mcorpus\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mwords\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcounts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtitle_dct\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32melif\u001b[0m \u001b[0mcorpus\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;31m# count - if words is none result will be as if counting all words\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;31m# in the corpus\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcounts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_document_frequencies\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0murns\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0murnlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcutoff\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mwords\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;31m# Include dhlab and title link in object\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtitle_dct\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0mk\u001b[0m \u001b[0;34m:\u001b[0m \u001b[0mv\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mk\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mv\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mzip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcorpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdhlabid\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcorpus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtitle\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m}\u001b[0m \u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcounts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\"Summarize Corpus frequencies\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        :return: frequency list for Corpus\u001b[0m\n",
      "\u001b[0;34m        \"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;31m#c = Counts()\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;31m#c.counts = self.counts.sum(axis=1)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_df\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcounts\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_frame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"freqs\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mdisplay_names\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"Display data with record names as column titles.\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrename\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtitle_dct\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m@\u001b[0m\u001b[0mclassmethod\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mfrom_df\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcls\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mobj\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mCounts\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mobj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcounts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mobj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mobj\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mFile:\u001b[0m           ~/anaconda3/envs/digital_tekstanalyse3.10/lib/python3.10/site-packages/dhlab/text/conc_coll.py\n",
      "\u001b[0;31mType:\u001b[0m           type\n",
      "\u001b[0;31mSubclasses:\u001b[0m     "
     ]
    }
   ],
   "source": [
    "dh.Counts??"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "```python\n",
    "dh.Counts(corpus=None, words=None)\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Dracula</th>\n",
       "      <th>Dracula : fritt etter Bram Stokers roman</th>\n",
       "      <th>Bram Stoker's Dracula</th>\n",
       "      <th>Dracula</th>\n",
       "      <th>Dracula house</th>\n",
       "      <th>Dracula</th>\n",
       "      <th>Dracula</th>\n",
       "      <th>Dracula</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>.</th>\n",
       "      <td>646.0</td>\n",
       "      <td>3268.0</td>\n",
       "      <td>578.0</td>\n",
       "      <td>8495.0</td>\n",
       "      <td>287.0</td>\n",
       "      <td>8447.0</td>\n",
       "      <td>8162.0</td>\n",
       "      <td>832.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>,</th>\n",
       "      <td>500.0</td>\n",
       "      <td>1384.0</td>\n",
       "      <td>368.0</td>\n",
       "      <td>9133.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>9659.0</td>\n",
       "      <td>9611.0</td>\n",
       "      <td>678.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>og</th>\n",
       "      <td>288.0</td>\n",
       "      <td>524.0</td>\n",
       "      <td>147.0</td>\n",
       "      <td>6206.0</td>\n",
       "      <td>151.0</td>\n",
       "      <td>6350.0</td>\n",
       "      <td>6312.0</td>\n",
       "      <td>261.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>i</th>\n",
       "      <td>265.0</td>\n",
       "      <td>449.0</td>\n",
       "      <td>250.0</td>\n",
       "      <td>2137.0</td>\n",
       "      <td>129.0</td>\n",
       "      <td>3092.0</td>\n",
       "      <td>2509.0</td>\n",
       "      <td>187.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>^</th>\n",
       "      <td>154.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>189.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>forts.</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Nu</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Pause</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ton</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>17.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>onathan</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>25.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>22202 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         Dracula  Dracula : fritt etter Bram Stokers roman  \\\n",
       ".          646.0                                    3268.0   \n",
       ",          500.0                                    1384.0   \n",
       "og         288.0                                     524.0   \n",
       "i          265.0                                     449.0   \n",
       "^          154.0                                       0.0   \n",
       "...          ...                                       ...   \n",
       "forts.       0.0                                       0.0   \n",
       "Nu           0.0                                       0.0   \n",
       "Pause        0.0                                       0.0   \n",
       "Ton          0.0                                       0.0   \n",
       "onathan      0.0                                       0.0   \n",
       "\n",
       "         Bram Stoker's Dracula  Dracula  Dracula house  Dracula  Dracula  \\\n",
       ".                        578.0   8495.0          287.0   8447.0   8162.0   \n",
       ",                        368.0   9133.0          140.0   9659.0   9611.0   \n",
       "og                       147.0   6206.0          151.0   6350.0   6312.0   \n",
       "i                        250.0   2137.0          129.0   3092.0   2509.0   \n",
       "^                        189.0      0.0            1.0      2.0      0.0   \n",
       "...                        ...      ...            ...      ...      ...   \n",
       "forts.                     0.0      0.0            0.0      0.0      0.0   \n",
       "Nu                         0.0      0.0            0.0      0.0      0.0   \n",
       "Pause                      0.0      0.0            0.0      0.0      0.0   \n",
       "Ton                        0.0      0.0            0.0      0.0      0.0   \n",
       "onathan                    0.0      0.0            0.0      0.0      0.0   \n",
       "\n",
       "         Dracula  \n",
       ".          832.0  \n",
       ",          678.0  \n",
       "og         261.0  \n",
       "i          187.0  \n",
       "^            1.0  \n",
       "...          ...  \n",
       "forts.      10.0  \n",
       "Nu          13.0  \n",
       "Pause       13.0  \n",
       "Ton         17.0  \n",
       "onathan     25.0  \n",
       "\n",
       "[22202 rows x 8 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "korpus.count().display_names()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "from dhlab import totals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "tot = totals()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       ".               7655423257\n",
       ",               5052171514\n",
       "i               2531262027\n",
       "og              2520268056\n",
       "-               1314451583\n",
       "                   ...    \n",
       "tidspunkter         110667\n",
       "dirigenter          110660\n",
       "ondartet            110652\n",
       "kulturtilbud        110652\n",
       "trassig             110651\n",
       "Name: freq, Length: 50000, dtype: int64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tot.freq"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Dracula</th>\n",
       "      <td>0.000325</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>grev</th>\n",
       "      <td>0.000093</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Jonathan</th>\n",
       "      <td>0.000044</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Grev</th>\n",
       "      <td>0.000042</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>tyrkerne</th>\n",
       "      <td>0.000037</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>uverdige</th>\n",
       "      <td>0.000026</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Depotbiblioteket</th>\n",
       "      <td>0.000025</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>vedlagte</th>\n",
       "      <td>0.000024</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>hungersnød</th>\n",
       "      <td>0.000024</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Helsing</th>\n",
       "      <td>0.000020</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                         0\n",
       "Dracula           0.000325\n",
       "grev              0.000093\n",
       "Jonathan          0.000044\n",
       "Grev              0.000042\n",
       "tyrkerne          0.000037\n",
       "uverdige          0.000026\n",
       "Depotbiblioteket  0.000025\n",
       "vedlagte          0.000024\n",
       "hungersnød        0.000024\n",
       "Helsing           0.000020"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(korpus.coll(\"Dracula\").frame.counts / tot.freq).sort_values(ascending=False).to_frame().head(10)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Ngram"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[0;31mInit signature:\u001b[0m\n",
      "\u001b[0mdh\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mNgram\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mwords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mfrom_year\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mto_year\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mdoctype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'bok'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mmode\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'relative'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0mlang\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'nob'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mSource:\u001b[0m        \n",
      "\u001b[0;32mclass\u001b[0m \u001b[0mNgram\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mDhlabObj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;34m\"\"\"Top level class for ngrams\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                 \u001b[0mwords\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                 \u001b[0mfrom_year\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                 \u001b[0mto_year\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                 \u001b[0mdoctype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'bok'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                 \u001b[0mmode\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'relative'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                 \u001b[0mlang\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"nob\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                 \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                 \u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\"Ngram builder class.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        Build Ngrams from the National Librarys collections.\u001b[0m\n",
      "\u001b[0;34m        Use with book corpus or newspaper corpus.\u001b[0m\n",
      "\u001b[0;34m        Lang parameter is only supported for book (`bok`) corpus.\u001b[0m\n",
      "\u001b[0;34m        Defaults to `None` if doctype is `avis`.\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m        :param words: words to examine, defaults to None\u001b[0m\n",
      "\u001b[0;34m        :type words: str or list of str, optional\u001b[0m\n",
      "\u001b[0;34m        :param from_year: lower period cutoff, defaults to None\u001b[0m\n",
      "\u001b[0;34m        :type from_year: int, optional\u001b[0m\n",
      "\u001b[0;34m        :param to_year: upper period cutoff, defaults to None\u001b[0m\n",
      "\u001b[0;34m        :type to_year: int, optional\u001b[0m\n",
      "\u001b[0;34m        :param doctype: `bok` or `avis` , defaults to 'bok'\u001b[0m\n",
      "\u001b[0;34m        :type doctype: str, optional\u001b[0m\n",
      "\u001b[0;34m        :param mode: Frequency measure, defaults to 'relative'\u001b[0m\n",
      "\u001b[0;34m        :type mode: str, optional\u001b[0m\n",
      "\u001b[0;34m        :param lang: `nob`, `nno`. Only use with docytype='bok', defaults to 'nob'\u001b[0m\n",
      "\u001b[0;34m        :type lang: str, optional\u001b[0m\n",
      "\u001b[0;34m        :param \\**kwargs: Keyword arguments for  Ngram._ipython_display_() Ngram.plot()\u001b[0m\n",
      "\u001b[0;34m        \"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdate\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdatetime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnow\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mif\u001b[0m \u001b[0mto_year\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mto_year\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdate\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0myear\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mif\u001b[0m \u001b[0mfrom_year\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mfrom_year\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m1950\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_year\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfrom_year\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_year\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mto_year\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwords\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mwords\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlang\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlang\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mif\u001b[0m \u001b[0mdoctype\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32mif\u001b[0m \u001b[0;34m'bok'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdoctype\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mdoctype\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'bok'\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32melif\u001b[0m \u001b[0;34m'avis'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdoctype\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mdoctype\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'avis'\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                \u001b[0mdoctype\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'bok'\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mdoctype\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'bok'\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;31m# Set default lang for 'bok'-corpus\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mif\u001b[0m \u001b[0mdoctype\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m\"avis\"\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m            \u001b[0mlang\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mngrm\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnb_ngram\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mterms\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m', '\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mwords\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                        \u001b[0mcorpus\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdoctype\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                        \u001b[0myears\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfrom_year\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mto_year\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                        \u001b[0msmooth\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlang\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlang\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                        \u001b[0mmode\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mngrm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mngrm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mngram\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mngrm\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkwargs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mngram\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mplot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msmooth\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m4\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\":param smooth: smoothing the curve\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mgrf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mngram\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrolling\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mwindow\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msmooth\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwin_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'triang'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmean\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mgrf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0mcompare\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0manother_ngram\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;34m\"\"\"Divide one ngram by another - measures difference\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mstart_year\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmax\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdatetime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_year\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m                         \u001b[0mdatetime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0manother_ngram\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_year\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0myear\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mend_year\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdatetime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_year\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdatetime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0manother_ngram\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_year\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0myear\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mtransposed_ngram\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mngram\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstart_year\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mend_year\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtranspose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0msum_other_ngram\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0manother_ngram\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mngram\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstart_year\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mend_year\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtranspose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mcompare\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mtransposed_ngram\u001b[0m \u001b[0;34m/\u001b[0m \u001b[0msum_other_ngram\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtranspose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0;32mreturn\u001b[0m \u001b[0mcompare\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m    \u001b[0;32mdef\u001b[0m \u001b[0m_ipython_display_\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\n",
      "\u001b[0;34m\u001b[0m        \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mFile:\u001b[0m           ~/anaconda3/envs/digital_tekstanalyse3.10/lib/python3.10/site-packages/dhlab/ngram/ngram.py\n",
      "\u001b[0;31mType:\u001b[0m           type\n",
      "\u001b[0;31mSubclasses:\u001b[0m     NgramBook, NgramNews"
     ]
    }
   ],
   "source": [
    "??dh.Ngram"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "```python\n",
    "dh.Ngram(\n",
    "    words=None,\n",
    "    from_year=None,\n",
    "    to_year=None,\n",
    "    doctype='bok',\n",
    "    mode='relative',\n",
    "    lang='nob',\n",
    "    **kwargs,\n",
    ")\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1500x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dh.Ngram([\"Dracula\", \"Frankenstein\"], from_year=1880, to_year=2020)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "digital_tekstanalyse3.10",
   "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": "3.10.9"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "d8690eb2c1dc046ff8a1dfe7bf525939807e2535627dd86e41f3fd80422f59f7"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}