Created
September 19, 2017 05:29
-
-
Save NoRaincheck/b67fc1d8d8b5edf3914dd9ac225dd73e to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # | |
| # 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. | |
| # | |
| """ | |
| Counts words in UTF8 encoded, '\n' delimited text received from the network every second. | |
| Usage: 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/network_wordcount.py localhost 9999` | |
| """ | |
| from __future__ import print_function | |
| import sys | |
| from pyspark import SparkContext | |
| from pyspark.streaming import StreamingContext | |
| def transform(x): | |
| x1 = x.split(" ") | |
| test = ["a" + b for b in x1] | |
| return test | |
| if __name__ == "__main__": | |
| if len(sys.argv) != 3: | |
| print("Usage: network_wordcount.py <hostname> <port>", file=sys.stderr) | |
| exit(-1) | |
| sc = SparkContext(appName="PythonStreamingNetworkWordCount") | |
| ssc = StreamingContext(sc, 5) | |
| lines = ssc.socketTextStream(sys.argv[1], int(sys.argv[2])) | |
| counts = lines.flatMap(lambda line: transform(line)) | |
| counts.pprint() | |
| #counts = lines.flatMap(lambda line: line.split(" "))\ | |
| # .map(lambda word: (word, 1))\ | |
| # .reduceByKey(lambda a, b: a+b) | |
| #counts.pprint() | |
| ssc.start() | |
| ssc.awaitTermination() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment