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
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
|
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You 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.
#
"""
Use DataFrames and SQL to count words in UTF8 encoded, '\n' delimited text received from the
network every second.
Usage: sql_network_wordcount.py <hostname> <port>
<hostname> and <port> describe the TCP server that Spark Streaming would connect to receive data.
To run this on your local machine, you need to first run a Netcat server
`$ nc -lk 9999`
and then run the example
`$ bin/spark-submit examples/src/main/python/streaming/sql_network_wordcount.py localhost 9999`
"""
from __future__ import print_function
import sys
from pyspark import SparkContext
from pyspark.streaming import StreamingContext
from pyspark.sql import Row, SparkSession
def getSparkSessionInstance(sparkConf):
if ('sparkSessionSingletonInstance' not in globals()):
globals()['sparkSessionSingletonInstance'] = SparkSession\
.builder\
.config(conf=sparkConf)\
.getOrCreate()
return globals()['sparkSessionSingletonInstance']
if __name__ == "__main__":
if len(sys.argv) != 3:
print("Usage: sql_network_wordcount.py <hostname> <port> ", file=sys.stderr)
exit(-1)
host, port = sys.argv[1:]
sc = SparkContext(appName="PythonSqlNetworkWordCount")
ssc = StreamingContext(sc, 1)
# Create a socket stream on target ip:port and count the
# words in input stream of \n delimited text (eg. generated by 'nc')
lines = ssc.socketTextStream(host, int(port))
words = lines.flatMap(lambda line: line.split(" "))
# Convert RDDs of the words DStream to DataFrame and run SQL query
def process(time, rdd):
print("========= %s =========" % str(time))
try:
# Get the singleton instance of SparkSession
spark = getSparkSessionInstance(rdd.context.getConf())
# Convert RDD[String] to RDD[Row] to DataFrame
rowRdd = rdd.map(lambda w: Row(word=w))
wordsDataFrame = spark.createDataFrame(rowRdd)
# Register as table
wordsDataFrame.registerTempTable("words")
# Do word count on table using SQL and print it
wordCountsDataFrame = \
spark.sql("select word, count(*) as total from words group by word")
wordCountsDataFrame.show()
except:
pass
words.foreachRDD(process)
ssc.start()
ssc.awaitTermination()
|
