Merge branch 'master' of https://github.com/Azure/Azure-MachineLearning-DataScience

Author: gopitk

Data-Science-Virtual-Machine/Samples/Notebooks/DocumentDBSample.ipynb

@@ -0,0 +1,240 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Demonstrate Basic Querying of DocumentDB\n",
+    "\n",
+    "### Prerequisite:\n",
+    "1. Install DocumentDB Python SDK  (pip install pydocumentdb)\n",
+    "1. Create DocumentDB account and Document DB database from Azure portal\n",
+    "1. Download \"DocumentDB Migration tool\" from [here](http://www.microsoft.com/downloads/details.aspx?FamilyID=cda7703a-2774-4c07-adcc-ad02ddc1a44d)\n",
+    "1. Import JSON data (volcano data) stored on a local file into documentDB with following command parameters to the migration tool. You can also use the GUI tool and enter the source and target location parameters from below. \n",
+    "\n",
+    "<code>/s:JsonFile /s.Files:[JSON File Location] /t:DocumentDBBulk /t.ConnectionString:AccountEndpoint=https://[DocDBAccountName].documents.azure.com:443/;AccountKey=[[KEY];Database=volcano /t.Collection:volcano1</code>\n",
+    "\n",
+    "Copy of volcano data also be found on a blob: https://cahandson.blob.core.windows.net/samples/volcano.json\n",
+    "\n",
+    "Execute rest of the code. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import pydocumentdb.documents as documents\n",
+    "import pydocumentdb.document_client as document_client\n",
+    "import pydocumentdb.errors as errors"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "#Doc DB access parameters. \n",
+    "# You can find the DocDB Account name and \"Key\" on Azure Portal. \n",
+    "# ReadyOnly key is adequate if you are not writing new records\n",
+    "masterKey = 'ENTER DOC DB Master KEY'\n",
+    "host = 'https://[ENTER DOCDB ACCOUNT NAME].documents.azure.com:443'\n",
+    "db = u'volcano'\n",
+    "collection = 'volcano1'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "# client object is the main object to operate with Doc DB\n",
+    "client = document_client.DocumentClient(host,{'masterKey': masterKey})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "# Get the pointer to the database you want\n",
+    "database = next((data for data in client.ReadDatabases() if data['id'] == db))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "# Get the link to the collection within the database\n",
+    "coll = next((coll for coll in client.ReadCollections(database['_self']) if coll['id'] == collection))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "# Use the Doc DB SQL like query language.\n",
+    "# Cheat sheet for DocDB SQL: https://azure.microsoft.com/en-us/documentation/articles/documentdb-sql-query-cheat-sheet/\n",
+    "\n",
+    "# Query tries to get list of volcanoes within 300 kms from a given coordinates (Redmond, WA in this case)\n",
+    "# Uses Geospatial Built-in functions ST_DISTANCE( point1, point2 )\n",
+    "\n",
+    "query = u'SELECT * \\\n",
+    "FROM volcanoes v \\\n",
+    "WHERE ST_DISTANCE(v.Location, { \\\n",
+    "\t\"type\": \"Point\", \\\n",
+    "\t\"coordinates\": [-122.19, 47.36] \\\n",
+    "\t}) < 300 * 1000 \\\n",
+    "AND v.Type = \"Stratovolcano\" \\\n",
+    "AND v[\"Last Known Eruption\"] = \"Last known eruption from 1800-1899, inclusive\"'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "u'SELECT * FROM volcanoes v WHERE ST_DISTANCE(v.Location, { \\t\"type\": \"Point\", \\t\"coordinates\": [-122.19, 47.36] \\t}) < 300 * 1000 AND v.Type = \"Stratovolcano\" AND v[\"Last Known Eruption\"] = \"Last known eruption from 1800-1899, inclusive\"'"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "query"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "# Run the query\n",
+    "docs = list(client.QueryDocuments(coll['_self'], {'query': query, 'parameters':[]}))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{u'Country': u'United States',\n",
+       "  u'Elevation': 4392,\n",
+       "  u'Last Known Eruption': u'Last known eruption from 1800-1899, inclusive',\n",
+       "  u'Location': {u'coordinates': [-121.758, 46.87], u'type': u'Point'},\n",
+       "  u'Region': u'US-Washington',\n",
+       "  u'Status': u'Dendrochronology',\n",
+       "  u'Type': u'Stratovolcano',\n",
+       "  u'Volcano Name': u'Rainier',\n",
+       "  u'_attachments': u'attachments/',\n",
+       "  u'_etag': u'\"0000c501-0000-0000-0000-5696f9700000\"',\n",
+       "  u'_rid': u'+-hhAPg2OAC5AQAAAAAAAA==',\n",
+       "  u'_self': u'dbs/+-hhAA==/colls/+-hhAPg2OAA=/docs/+-hhAPg2OAC5AQAAAAAAAA==/',\n",
+       "  u'_ts': 1452734832,\n",
+       "  u'id': u'682fe1d3-1e2a-c135-d47f-f3351afd03e3'},\n",
+       " {u'Country': u'United States',\n",
+       "  u'Elevation': 3426,\n",
+       "  u'Last Known Eruption': u'Last known eruption from 1800-1899, inclusive',\n",
+       "  u'Location': {u'coordinates': [-121.694, 45.374], u'type': u'Point'},\n",
+       "  u'Region': u'US-Oregon',\n",
+       "  u'Status': u'Historical',\n",
+       "  u'Type': u'Stratovolcano',\n",
+       "  u'Volcano Name': u'Hood',\n",
+       "  u'_attachments': u'attachments/',\n",
+       "  u'_etag': u'\"0000d202-0000-0000-0000-5696f9730000\"',\n",
+       "  u'_rid': u'+-hhAPg2OADGAgAAAAAAAA==',\n",
+       "  u'_self': u'dbs/+-hhAA==/colls/+-hhAPg2OAA=/docs/+-hhAPg2OADGAgAAAAAAAA==/',\n",
+       "  u'_ts': 1452734835,\n",
+       "  u'id': u'acf67a43-d1db-0d15-4b73-ffd267d6ac9f'},\n",
+       " {u'Country': u'United States',\n",
+       "  u'Elevation': 3285,\n",
+       "  u'Last Known Eruption': u'Last known eruption from 1800-1899, inclusive',\n",
+       "  u'Location': {u'coordinates': [-121.82, 48.786], u'type': u'Point'},\n",
+       "  u'Region': u'US-Washington',\n",
+       "  u'Status': u'Historical',\n",
+       "  u'Type': u'Stratovolcano',\n",
+       "  u'Volcano Name': u'Baker',\n",
+       "  u'_attachments': u'attachments/',\n",
+       "  u'_etag': u'\"00004105-0000-0000-0000-5696f9770000\"',\n",
+       "  u'_rid': u'+-hhAPg2OAA1BQAAAAAAAA==',\n",
+       "  u'_self': u'dbs/+-hhAA==/colls/+-hhAPg2OAA=/docs/+-hhAPg2OAA1BQAAAAAAAA==/',\n",
+       "  u'_ts': 1452734839,\n",
+       "  u'id': u'1d1913ad-fff9-c2aa-2ff9-9f67deda3578'}]"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 2",
+   "language": "python",
+   "name": "python2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}