{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "loving-given",
   "metadata": {},
   "source": [
    "# hmjr is a package of tools to help researchers as well as users with simpler needs directly interact with the HMJr diary collection.\n",
    "\n",
    "- <https://github.com/TeddyRandby/hmjrPyTools/blob/main/README.md>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "korean-intensity",
   "metadata": {},
   "source": [
    "<img src=\"Images/header_count.png\"/> \n",
    "<img src=\"Images/volume_count.png\"/> \n",
    "<img src=\"Images/word_count.png\"/>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "wanted-charles",
   "metadata": {},
   "source": [
    "# Getting started"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "engaging-locking",
   "metadata": {},
   "source": [
    "To install our package and import what you need, run the following two lines."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "spanish-experience",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Install the package that let's us analyze the JSON DB\n",
    "!pip install hmjr===0.1.0\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "adapted-frontier",
   "metadata": {},
   "source": [
    "Query here is the first point of contact for interacting with the HMJR Diary database. In order to use it, we need to initialize the object. Don't worry about what that means behind the scenes, just make sure to follow Query up with a () whenver we use it, like this: Query().\n",
    "\n",
    "At this point, you may be seeing some suggestions popping up, especially if you're using a Notebook. The best starting point here is just run(), which just grabs entries in the simplest way possible, just the order they happen to be stored in the database.\n",
    "\n",
    "So for now, we'll go with that."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "lonely-gospel",
   "metadata": {},
   "outputs": [],
   "source": [
    "from hmjr import Query\n",
    "import matplotlib.pylab as plt\n",
    "import numpy as np\n",
    "import datetime\n",
    "\n",
    "Query().run(max=5).entries"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "official-specialist",
   "metadata": {},
   "source": [
    ".entries selects the data the query gave us out of the Queries object. And after running that, you should see the data output!\n",
    "\n",
    "Before we get to some new queries, lets go over some of the ways we can influence the queries we make. One way is with the default argument max. It refers to the maximum number of entries the query should ask for. This can be changed like this:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "korean-corporation",
   "metadata": {},
   "outputs": [],
   "source": [
    "Query().run(max=5).entries"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "recreational-boston",
   "metadata": {},
   "source": [
    "This time we should see a lot fewer entries when we run the query.\n",
    "\n",
    "Speaking of volumes - lets move on to a more complex query."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "greek-drink",
   "metadata": {},
   "outputs": [],
   "source": [
    "Query().withBookBetween(1,5).run().entries"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "complete-walter",
   "metadata": {},
   "source": [
    "This query should be self explanatory, but it does have a quirk in that the book range includes the lower bound, and excludes the upper bound. So this query will return entries with books 1, 2, 3, 4.\n",
    "\n",
    "Under the hood, withBookBetween(start,stop) uses a different function to query the database, and that function is simply withBook(). It works like this:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "knowing-needle",
   "metadata": {},
   "outputs": [],
   "source": [
    "Query().withBook([1,2,3,4]).run().entries"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "elegant-computer",
   "metadata": {},
   "source": [
    "This is the query our previous withBookBetween(1,5) generated for us. The brackets hold a list of book numbers, and they don't have to be in any order. [1,2,3,4] is the same as [2,4,1,3], and it could even be something like [708,1,66].\n",
    "\n",
    "By the way, all these queries share that default argument max. Its used the same way that we saw earlier.\n",
    "\n",
    "Heres our next query:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "compatible-arbitration",
   "metadata": {},
   "outputs": [],
   "source": [
    "Query().withKeywords([\"Refugee\", \"refugee\"]).run().entries"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "systematic-ceremony",
   "metadata": {},
   "source": [
    "We see another list, which works the same way as our previous list. This time we have quotes around words to differentiate them from code - don't forget the quotes. If you get a syntax error, that might be why.\n",
    "\n",
    "Heres the last kind of query we can do:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "everyday-recorder",
   "metadata": {},
   "outputs": [],
   "source": [
    "Query().withDates({\"day\": 1, \"month\": 1, \"year\":44}).run().entries\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "educational-recipe",
   "metadata": {},
   "source": [
    "Earlier we saw a python list with the square brackets, this notation is called a dictionary, and it holds any number of key:value pairs. Here, our query expects a dictionary with day, month and year keys.\n",
    "\n",
    "Now that we've got all the queries working individually, we can combine them before we use run().\n",
    "\n",
    "Try something like:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dimensional-contribution",
   "metadata": {},
   "outputs": [],
   "source": [
    "Query().withKeywords([\"Camp\", \"camp\"]).withBookBetween(738, 349).run().entries\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "vertical-struggle",
   "metadata": {},
   "source": [
    "We've dropped the .entries off the end of our query, and are storing the result of run() in the variable entries. This result has more to it than just a list of entries. We can call a couple methods on this object. Heres what it looks like:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "flush-archives",
   "metadata": {},
   "outputs": [],
   "source": [
    "entries.associate([\"HMJr\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "horizontal-address",
   "metadata": {},
   "source": [
    "What the associate() method does is take a list of words, and rank the appearences of every other word in proximity to this word. \"Proximity\" is defined as appearing with at least one of the given words in the content of an Index.\n",
    "\n",
    "There are two more methods for analyzing the data: the deltaTime() method and the deltaBooks() method.\n",
    "\n",
    "They work just like the associate() method, taking a list of words. They both return a dictionary which counts the appearences of the words over the books or over the dates in the entries.\n",
    "\n",
    "There are some additional helper methods, such as:\n",
    "\n",
    "- headerCounts() counts the occurences of each unique header in the entries\n",
    "- headerWords() returns a dictionary counting the unique words in the headers\n",
    "- contentWords() returns a dictionary counting the unique words in the content\n",
    "- words returns the combination of headerWords() and contentWords()\n",
    "- headers() returns an array of the header strings in the entries, not sorted\n",
    "- content() returns an array of the content strings in the entries, not sorted\n",
    "- dates() returns an array of the date dictionaries in the entries, not sorted\n",
    "- indexes() returns an array of the index dictionaries in the entries, not sorted\n",
    "- dateRange() returns the tuple (minimumDate, maximumDate) mentioned in the entries\n",
    "- bookRange() returns the tuple (minimumBook, maximumBook) mentioned in the entries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ruled-amber",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get the entries with a maximum of 2K entries, and save them in the entries variable.\n",
    "#entries = Query().withBookBetween(696,697).run(max=2000)\n",
    "entries = Query().withBook([696]).run()\n",
    "numEntries = len(entries.content())\n",
    "print(\"Number of entries: \" + str(numEntries))\n",
    "print(\"Avg entries per volume: \" + str(numEntries / 1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "initial-adrian",
   "metadata": {},
   "outputs": [],
   "source": [
    "entries.headers()[27]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "higher-tumor",
   "metadata": {},
   "source": [
    "Your results should have entries with \"Camp\" or \"camp\" in their text, in a volume between 738 and 749.\n",
    "\n",
    "Now we can make complex queries on the data, lets look at how we can analyze it.\n",
    "\n",
    "After we use the run() method, we get a different object back."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "treated-socket",
   "metadata": {},
   "outputs": [],
   "source": [
    "from hmjr import Query\n",
    "import matplotlib.pylab as plt\n",
    "import numpy as np\n",
    "import datetime\n",
    "#import stanza\n",
    "#stanza.download('en')\n",
    "#nlp = stanza.Pipeline(\"en\", processors='tokenize,ner', ner_model_path='en_hmjr_nertagger.pt')\n",
    "import json\n",
    "# Import the Query, and some other tools to help analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "incomplete-compression",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Make a query for entries with book between 689 and 749 (excluding 749)\n",
    "# Take a maximum of 20K entries\n",
    "# Count the occurrences of unique headers amoung these headers\n",
    "data = Query().withBookBetween(688,699).run(max=20000)\n",
    "#for entry in data.entries:\n",
    "#  content = entry[\"header\"] + \" \" + entry[\"content\"]\n",
    "#  content = content.replace('\\n', '.')\n",
    "#  doc = nlp(content)\n",
    "#  for sent in doc.sentences:\n",
    "#    for ent in sent.ents:\n",
    "#      print(ent)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "hungry-recall",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get the same entries, but there is no max given. This uses the default, which is 50.\n",
    "\n",
    "#query = \"\"\"\n",
    "#    query ($max: Float!, $keywords: [String!]!, $dates: [DateInput!]!, $books: [String!]!) {\n",
    "#        entries(max: $max, keywords: $keywords, dates: $dates, books:$books) {\n",
    "#            _id\n",
    "#            header\n",
    "#            content\n",
    "#            people\n",
    "#            locations\n",
    "#            organizations\n",
    "#            book\n",
    "#        }\n",
    "#    }\n",
    "#\"\"\"\n",
    "#mutation = \"\"\"\n",
    "#mutation ($id: String!, $entry: EntryInput!) {\n",
    "#                updateEntry(id: $id, entry: $entry) {\n",
    "#                    book\n",
    "#                }\n",
    "#            }\n",
    "#\"\"\"\n",
    "\n",
    "#entries = Query().query(query, {\"max\": 30000, \"keywords\": [], \"dates\": [], \"books\": [\"689\"]})\n",
    "#for entry in entries.entries:\n",
    "#  content = entry[\"header\"] + \" \" + entry[\"content\"]\n",
    "#  content = content.replace('\\n', '.')\n",
    "#  doc = nlp(content)\n",
    "#  people = [ent.text for sent in doc.sentences for ent in sent.ents if ent.type == \"PERSON\"]\n",
    "#  locations = [ent.text for sent in doc.sentences for ent in sent.ents if ent.type == \"LOC\" or ent.type == \"GPE\"]\n",
    "#  organizations = [ent.text for sent in doc.sentences for ent in sent.ents if ent.type == \"ORG\"]\n",
    "#  vars = { \"id\": entry[\"_id\"], \"entry\":{ \"people\": people, \"locations\": locations, \"organizations\": organizations }}\n",
    "#  Query().query(mutation, vars, \"updateEntry\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "timely-history",
   "metadata": {},
   "outputs": [],
   "source": [
    "Query().withDates({\"day\": 26, \"month\": 1, \"year\":44}).run().entries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "guilty-pickup",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of entries: 1925\n",
      "Avg entries per volume: 32.083333333333336\n"
     ]
    }
   ],
   "source": [
    "# Get the entries with a maximum of 2K entries, and save them in the entries variable.\n",
    "entries = Query().withBookBetween(689,749).run(max=2000)\n",
    "numEntries = len(entries.content())\n",
    "print(\"Number of entries: \" + str(numEntries))\n",
    "print(\"Avg entries per volume: \" + str(numEntries / 60))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "applicable-choir",
   "metadata": {},
   "outputs": [],
   "source": [
    "entries = Query().withKeywords([\"Camp\", \"camp\"]).withBookBetween(738, 749).run()\n",
    "entries.associate([\"HMJr\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "lucky-lightning",
   "metadata": {},
   "outputs": [],
   "source": [
    "entries.headers()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "foreign-reserve",
   "metadata": {},
   "outputs": [],
   "source": [
    "entries.content()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "significant-entity",
   "metadata": {},
   "outputs": [],
   "source": [
    "entries.headerCounts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "upset-rolling",
   "metadata": {},
   "outputs": [],
   "source": [
    "entries.dates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "retired-native",
   "metadata": {},
   "outputs": [],
   "source": [
    "entries.indexes()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "legendary-humor",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "No handles with labels found to put in legend.\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Get the count of unique headers\n",
    "data = entries.headerCounts()\n",
    "# Sort the headers by their occurrence\n",
    "lists = sorted(data.items(), key=lambda x: x[1], reverse=True)[:20]\n",
    "# Transform the sorted headers into two lists, X and Y values\n",
    "X, Y = map(list, zip(*lists))\n",
    "# Plot them!\n",
    "plt.bar(X, Y)\n",
    "plt.xticks(rotation='vertical')\n",
    "plt.legend()\n",
    "plt.ylabel(\"Occurrences\")\n",
    "plt.title(\"Most popular entries\")\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "constitutional-techno",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "whole-korea",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "data = entries.dates()\n",
    "invalid = [[d for d in data if d[\"month\"] < 1 or d[\"month\"] > 12]]\n",
    "# Clean the data to only take dates with valid months\n",
    "data = [d for d in data if d[\"month\"] > 0 and d[\"month\"] < 13]\n",
    "# Transform the dates from the query into datetime objects\n",
    "dates = [datetime.date(int(\"19\" + str(d[\"year\"])), d[\"month\"], d[\"day\"]) for d in data]\n",
    "\n",
    "#Plot the occurrences of each individual date\n",
    "fig, ax = plt.subplots()\n",
    "plt.xlim(datetime.date(1944,1,1),datetime.date(1944,6,30))\n",
    "unique, counts = np.unique(dates, return_counts=True)\n",
    "\n",
    "plt.plot(unique,counts)\n",
    "plt.title(\"Amount of entries\")\n",
    "plt.ylabel(\"Entries\")\n",
    "plt.xlabel(\"Date\")\n",
    "# rotate and align the tick labels so they look better\n",
    "fig.autofmt_xdate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "varied-daughter",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "No results found. Try running a query first.\n"
     ]
    },
    {
     "ename": "AttributeError",
     "evalue": "'NoneType' object has no attribute 'any'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-7-e0764c888d85>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0mstopWords\u001b[0m  \u001b[0;34m=\u001b[0m \u001b[0;34m\"of and to for Book Page page in by on from with See a) 1) b) also - be, New York York: as at Oswego Oswego,\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mkeyword\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"Oswego\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mentries\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0massociate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mkeyword\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstopWords\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      5\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[0;31m# Sort these by occurrence, and take the top 10\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/conda/lib/python3.8/site-packages/hmjr/Entries.py\u001b[0m in \u001b[0;36massociate\u001b[0;34m(self, words, badWords)\u001b[0m\n\u001b[1;32m    100\u001b[0m         \u001b[0;34m\"\"\"Count the appearances of each unique word in indexes that contain the given words. \"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    101\u001b[0m         \u001b[0mindexes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindexes\u001b[0m\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;32m--> 102\u001b[0;31m         \u001b[0;32mif\u001b[0m \u001b[0mindexes\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0many\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    103\u001b[0m             \u001b[0mcontainedStrs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0ms\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"content\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0ms\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mindexes\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mword\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mwords\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0ms\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"content\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mword\u001b[0m \u001b[0;32min\u001b[0m \u001b[0ms\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"content\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    104\u001b[0m             \u001b[0mwords\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mword\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0ms\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mcontainedStrs\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mword\u001b[0m \u001b[0;32min\u001b[0m \u001b[0ms\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\" \"\u001b[0m\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;31mAttributeError\u001b[0m: 'NoneType' object has no attribute 'any'"
     ]
    }
   ],
   "source": [
    "# Get all the words that cooccurr with \"HMJr\" or \"HMJT\", and arent in stopWords\n",
    "stopWords  = \"of and to for Book Page page in by on from with See a) 1) b) also - be, New York York: as at Oswego Oswego,\"\n",
    "keyword = \"Oswego\"\n",
    "data = entries.associate([keyword], stopWords)\n",
    "\n",
    "# Sort these by occurrence, and take the top 10\n",
    "lists = sorted(data.items(), key=lambda x: x[1], reverse=True)[:5]\n",
    "\n",
    "# For each of these words, track their occurrence in the entries over volumes\n",
    "for w in lists:\n",
    "  # Get the word\n",
    "  label = w[0]\n",
    "  # Track it over volumes\n",
    "  wOverTime = entries.deltaBooks(label)\n",
    "  # Sort this by volume\n",
    "  ordered = sorted(wOverTime.items(), key=lambda vol:vol[0])\n",
    "  # Make x and y lists out of the sorted values\n",
    "  x, y = zip(*ordered)\n",
    "  # Plot this line\n",
    "  plt.plot([int(i) for i in x], y, label=label, linewidth=1, alpha=0.5)\n",
    "\n",
    "\n",
    "plt.title(\"5 most associated words with \" + keyword + \", over volumes\")\n",
    "plt.ylabel(\"Occurrences\")\n",
    "plt.xlabel(\"Volume\")\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "driving-league",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}