This repository has been archived by the owner on Mar 24, 2021. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 23
/
Copy pathCloudantApp.py
44 lines (38 loc) · 2 KB
/
CloudantApp.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
#*******************************************************************************
# Copyright (c) 2015 IBM Corp.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#******************************************************************************/
import pprint
from pyspark.sql import SparkSession
spark = SparkSession\
.builder\
.appName("Cloudant Spark SQL Example in Python using temp tables")\
.config("cloudant.host","ACCOUNT.cloudant.com")\
.config("cloudant.username", "USERNAME")\
.config("cloudant.password","PASSWORD")\
.getOrCreate()
# ***1. Loading temp table from Cloudant db
spark.sql(" CREATE TEMPORARY TABLE airportTable USING com.cloudant.spark OPTIONS ( database 'n_airportcodemapping')")
airportData = spark.sql("SELECT _id, airportName FROM airportTable WHERE _id >= 'CAA' AND _id <= 'GAA' ORDER BY _id")
airportData.printSchema()
print 'Total # of rows in airportData: ' + str(airportData.count())
for code in airportData.collect():
print code._id
# ***2. Loading temp table from Cloudant search index
print 'About to test com.cloudant.spark for flight with index'
spark.sql(" CREATE TEMPORARY TABLE flightTable1 USING com.cloudant.spark OPTIONS ( database 'n_flight', index '_design/view/_search/n_flights')")
flightData = spark.sql("SELECT flightSegmentId, scheduledDepartureTime FROM flightTable1 WHERE flightSegmentId >'AA9' AND flightSegmentId<'AA95'")
flightData.printSchema()
for code in flightData.collect():
print 'Flight {0} on {1}'.format(code.flightSegmentId, code.scheduledDepartureTime)