diff options
Diffstat (limited to 'examples/src/main/python/streaming')
-rw-r--r-- | examples/src/main/python/streaming/kafka_wordcount.py | 54 |
1 files changed, 54 insertions, 0 deletions
diff --git a/examples/src/main/python/streaming/kafka_wordcount.py b/examples/src/main/python/streaming/kafka_wordcount.py new file mode 100644 index 0000000000..ed398a82b8 --- /dev/null +++ b/examples/src/main/python/streaming/kafka_wordcount.py @@ -0,0 +1,54 @@ +# +# 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 <zk> <topic> + + To run this on your local machine, you need to setup Kafka and create a producer first, see + http://kafka.apache.org/documentation.html#quickstart + + and then run the example + `$ bin/spark-submit --driver-class-path external/kafka-assembly/target/scala-*/\ + spark-streaming-kafka-assembly-*.jar examples/src/main/python/streaming/kafka_wordcount.py \ + localhost:2181 test` +""" + +import sys + +from pyspark import SparkContext +from pyspark.streaming import StreamingContext +from pyspark.streaming.kafka import KafkaUtils + +if __name__ == "__main__": + if len(sys.argv) != 3: + print >> sys.stderr, "Usage: kafka_wordcount.py <zk> <topic>" + exit(-1) + + sc = SparkContext(appName="PythonStreamingKafkaWordCount") + ssc = StreamingContext(sc, 1) + + zkQuorum, topic = sys.argv[1:] + kvs = KafkaUtils.createStream(ssc, zkQuorum, "spark-streaming-consumer", {topic: 1}) + lines = kvs.map(lambda x: x[1]) + counts = lines.flatMap(lambda line: line.split(" ")) \ + .map(lambda word: (word, 1)) \ + .reduceByKey(lambda a, b: a+b) + counts.pprint() + + ssc.start() + ssc.awaitTermination() |