ingest_data.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Hands-on Example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "import json\n",
    "from elasticsearch import Elasticsearch\n",
    "# uncomment the next line to install elasticsearch\n",
    "# pip install elasticsearch "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Connect to the cluster\n",
    "es = Elasticsearch([{'host': 'localhost', 'port': 9200}])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# check the status of the cluster \n",
    "# if you just started the cluster, wait a bit before running this command. \n",
    "# Otherwise, you will get a \"no response\" error. If that happens, retry in a bit. \n",
    "print(es.cluster.health())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "es.indices.create(index='pokemon_characters', body={\"number_of_replicas\": 2, \"number_of_shards\":3})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# fetch data from programmingquotesapi and ingest the data into Elasticsearch \n",
    "r = requests.get('http://localhost:9200')\n",
    "i = 1\n",
    "while i <= 898:\n",
    "    r = requests.get('https://pokeapi.co/api/v2/pokemon/'+ str(i))\n",
    "    es.index(index='pokemon_characters', doc_type='pokemon', id=i, body=json.loads(r.content))\n",
    "    i=i+1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# return 3 documents \n",
    "res = es.search(index=\"pokemon_characters\", query = {\n",
    "    'match_all' : {}}, size = '3')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "documents = res['hits']['hits']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for num, doc in enumerate(documents):\n",
    "    for key, value in doc.items():\n",
    "        print (key, \":\", value)\n",
    "   \n",
    "    print (\"\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# return the character with id = 5\n",
    "es.get(index='pokemon_characters', doc_type='pokemon', id=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "es.search(index=\"pokemon_characters\", body={\"query\": {\"match\" : { \"name\" : 'cat'}}})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}