{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pymongo import MongoClient\n",
    "from datetime import datetime"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "class DBConnector():\n",
    "    def __init__(self,db_name,usr,ip,psw):\n",
    "        self.db_name = db_name\n",
    "        self.usr = usr\n",
    "        self.psw = psw\n",
    "        self.uri = 'mongodb://{0}:{1}@{2}/{3}'.format(usr,psw,ip,db_name)\n",
    "        print(self.uri)\n",
    "    def mongoClient(self, collection):\n",
    "        self.mongo_client = MongoClient(self.uri)\n",
    "        db = self.mongo_client[self.db_name]\n",
    "        db_client = db[collection]\n",
    "        return db_client\n",
    "\n",
    "    def close_connection(self):\n",
    "        self.mongo_client.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "db_connector = DBConnector(\"twitter_public\",\"btw17_public_user\",\"10.6.13.55\",\"btw17_public\")\n",
    "c = \"politicians_sample\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "collection = db_connector.mongoClient(c)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Query the sample data base. \n",
    "Example of a query to fetch tweets between 19:00 hours to 22:00 hours is shown below."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "query = collection.find({\"createdAt\" : {\"$gte\" : datetime(2017, 9, 23, 19, 0, 0), \"$lt\": datetime(2017, 9, 23, 22, 0 , 0)}})\n",
    "\n",
    "from pprint import pprint\n",
    "print(\"Print the first 5 elements\")\n",
    "pprint([el for el in query[0:5]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "collection.count_documents({\"createdAt\" : {\"$gte\" : datetime(2017, 9, 23, 19, 0, 0), \"$lt\": datetime(2017, 9, 23, 22, 0 , 0)}})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Import tweets into dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "query = collection.find({\"createdAt\" : {\"$gte\" : datetime(2017, 9, 23, 19, 0, 0), \"$lt\": datetime(2017, 9, 23, 22, 0 , 0)}})\n",
    "tweets =  pd.DataFrame(list(query))\n",
    "tweets"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Visualize number of tweets per hour"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "# aggregate per hour\n",
    "counts = tweets['createdAt'].dt.to_period('H').value_counts()\n",
    "\n",
    "# plot\n",
    "ax = counts.plot(kind='bar', title='Number of Tweets Per Hour')\n",
    "ax.tick_params(axis='x', labelsize=8)\n",
    "ax.tick_params(axis='y', labelsize=10)\n",
    "ax.set_xlabel('Time', fontsize=15)\n",
    "ax.set_ylabel('Number of tweets' , fontsize=15)\n",
    "ax.set_title('Number of Tweets Per Hour', fontsize=15, fontweight='bold')\n",
    "pass"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "hide_input": false,
  "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": "3.9.2"
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}