|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "metadata": { |
| 6 | + "collapsed": true |
| 7 | + }, |
| 8 | + "source": [ |
| 9 | + "### Check outputs from Data Engineering Capstone Project for Udacity" |
| 10 | + ] |
| 11 | + }, |
| 12 | + { |
| 13 | + "cell_type": "markdown", |
| 14 | + "metadata": {}, |
| 15 | + "source": [ |
| 16 | + "#### Read config" |
| 17 | + ] |
| 18 | + }, |
| 19 | + { |
| 20 | + "cell_type": "code", |
| 21 | + "execution_count": null, |
| 22 | + "metadata": {}, |
| 23 | + "outputs": [], |
| 24 | + "source": [ |
| 25 | + "# import necessary configurations\n", |
| 26 | + "import configparser\n", |
| 27 | + "\n", |
| 28 | + "config = configparser.ConfigParser()\n", |
| 29 | + "config.read_file(open('dwh.cfg'))\n", |
| 30 | + "\n", |
| 31 | + "# amazon aws\n", |
| 32 | + "KEY = config.get('AWS', 'key')\n", |
| 33 | + "SECRET = config.get('AWS', 'secret')\n", |
| 34 | + "\n", |
| 35 | + "# Redshift\n", |
| 36 | + "DWH_DB = config.get('DWH', 'DWH_DB')\n", |
| 37 | + "DWH_DB_USER = config.get('DWH', 'DWH_DB_USER')\n", |
| 38 | + "DWH_DB_PASSWORD = config.get('DWH', 'DWH_DB_PASSWORD')\n", |
| 39 | + "DWH_PORT = config.get('DWH', 'DWH_PORT')\n", |
| 40 | + "DWH_CLUSTER_TYPE = config.get('DWH', 'DWH_CLUSTER_TYPE')\n", |
| 41 | + "DWH_NUM_NODES = config.get('DWH', 'DWH_NUM_NODES')\n", |
| 42 | + "DWH_NODE_TYPE = config.get('DWH', 'DWH_NODE_TYPE')\n", |
| 43 | + "DWH_IAM_ROLE_NAME = config.get('DWH', 'DWH_IAM_ROLE_NAME')\n", |
| 44 | + "DWH_CLUSTER_IDENTIFIER = config.get('DWH', 'DWH_CLUSTER_IDENTIFIER')\n", |
| 45 | + "DWH_SCHEMA = config.get('DWH', 'DWH_SCHEMA')\n", |
| 46 | + "DWH_LOG_STAGING_TABLE = config.get('DWH', 'DWH_LOG_STAGING_TABLE')\n", |
| 47 | + "DWH_SONG_STAGING_TABLE = config.get('DWH', 'DWH_SONG_STAGING_TABLE')\n", |
| 48 | + "DWH_REGION = config.get('DWH', 'DWH_REGION')\n", |
| 49 | + "\n", |
| 50 | + "# s3\n", |
| 51 | + "LOG_JSON_FORMAT = config.get('S3', 'LOG_JSON_FORMAT')\n", |
| 52 | + "S3_BUCKET_LOG_JSON_PATH = config.get('S3', 'S3_BUCKET_LOG_JSON_PATH')\n", |
| 53 | + "S3_BUCKET_SONG_JSON_PATH = config.get('S3', 'S3_BUCKET_SONG_JSON_PATH')" |
| 54 | + ] |
| 55 | + }, |
| 56 | + { |
| 57 | + "cell_type": "markdown", |
| 58 | + "metadata": {}, |
| 59 | + "source": [ |
| 60 | + "#### Create SQL Connection String" |
| 61 | + ] |
| 62 | + }, |
| 63 | + { |
| 64 | + "cell_type": "code", |
| 65 | + "execution_count": null, |
| 66 | + "metadata": {}, |
| 67 | + "outputs": [], |
| 68 | + "source": [ |
| 69 | + "%load_ext sql" |
| 70 | + ] |
| 71 | + }, |
| 72 | + { |
| 73 | + "cell_type": "code", |
| 74 | + "execution_count": null, |
| 75 | + "metadata": {}, |
| 76 | + "outputs": [], |
| 77 | + "source": [ |
| 78 | + "# save your DWH_ENDPOINT here:\n", |
| 79 | + "DWH_ROLE_ARN = '<fill_it_up_here>'\n", |
| 80 | + "DWH_ENDPOINT = '<fill_it_up_here>'" |
| 81 | + ] |
| 82 | + }, |
| 83 | + { |
| 84 | + "cell_type": "code", |
| 85 | + "execution_count": null, |
| 86 | + "metadata": {}, |
| 87 | + "outputs": [], |
| 88 | + "source": [ |
| 89 | + "# creating connection to your DB in Amazon Redshift\n", |
| 90 | + "conn_string=\"postgresql://{}:{}@{}:{}/{}\".format(DWH_DB_USER, DWH_DB_PASSWORD, DWH_ENDPOINT, DWH_PORT, DWH_DB)\n", |
| 91 | + "print(conn_string)\n", |
| 92 | + "%sql $conn_string" |
| 93 | + ] |
| 94 | + }, |
| 95 | + { |
| 96 | + "cell_type": "markdown", |
| 97 | + "metadata": {}, |
| 98 | + "source": [ |
| 99 | + "#### Get result from query" |
| 100 | + ] |
| 101 | + }, |
| 102 | + { |
| 103 | + "cell_type": "code", |
| 104 | + "execution_count": null, |
| 105 | + "metadata": {}, |
| 106 | + "outputs": [], |
| 107 | + "source": [ |
| 108 | + "import pandas as pd\n", |
| 109 | + "import numpy as np\n", |
| 110 | + "from sqlalchemy import create_engine\n", |
| 111 | + " \n", |
| 112 | + "test_query = \"\"\"\n", |
| 113 | + "\n", |
| 114 | + "\"\"\"\n", |
| 115 | + " \n", |
| 116 | + "redshift_engine = create_engine('redshift+psycopg2://username:password@your.redshift.host.123456abcdef.us-east-1.redshift.amazonaws.com:port/database')\n", |
| 117 | + "test = pd.read_sql_query(test_query, redshift_engine)" |
| 118 | + ] |
| 119 | + }, |
| 120 | + { |
| 121 | + "cell_type": "code", |
| 122 | + "execution_count": null, |
| 123 | + "metadata": {}, |
| 124 | + "outputs": [], |
| 125 | + "source": [] |
| 126 | + } |
| 127 | + ], |
| 128 | + "metadata": { |
| 129 | + "kernelspec": { |
| 130 | + "display_name": "Python 3", |
| 131 | + "language": "python", |
| 132 | + "name": "python3" |
| 133 | + }, |
| 134 | + "language_info": { |
| 135 | + "codemirror_mode": { |
| 136 | + "name": "ipython", |
| 137 | + "version": 3 |
| 138 | + }, |
| 139 | + "file_extension": ".py", |
| 140 | + "mimetype": "text/x-python", |
| 141 | + "name": "python", |
| 142 | + "nbconvert_exporter": "python", |
| 143 | + "pygments_lexer": "ipython3", |
| 144 | + "version": "3.6.5" |
| 145 | + } |
| 146 | + }, |
| 147 | + "nbformat": 4, |
| 148 | + "nbformat_minor": 1 |
| 149 | +} |
0 commit comments