diff options
Diffstat (limited to 'examples/src')
3 files changed, 154 insertions, 0 deletions
diff --git a/examples/src/main/python/streaming/hdfs_wordcount.py b/examples/src/main/python/streaming/hdfs_wordcount.py new file mode 100644 index 0000000000..40faff0ccc --- /dev/null +++ b/examples/src/main/python/streaming/hdfs_wordcount.py @@ -0,0 +1,49 @@ +# +# 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 new text files created in the given directory + Usage: hdfs_wordcount.py <directory> + <directory> is the directory that Spark Streaming will use to find and read new text files. + + To run this on your local machine on directory `localdir`, run this example + $ bin/spark-submit examples/src/main/python/streaming/network_wordcount.py localdir + + Then create a text file in `localdir` and the words in the file will get counted. +""" + +import sys + +from pyspark import SparkContext +from pyspark.streaming import StreamingContext + +if __name__ == "__main__": + if len(sys.argv) != 2: + print >> sys.stderr, "Usage: hdfs_wordcount.py <directory>" + exit(-1) + + sc = SparkContext(appName="PythonStreamingHDFSWordCount") + ssc = StreamingContext(sc, 1) + + lines = ssc.textFileStream(sys.argv[1]) + counts = lines.flatMap(lambda line: line.split(" "))\ + .map(lambda x: (x, 1))\ + .reduceByKey(lambda a, b: a+b) + counts.pprint() + + ssc.start() + ssc.awaitTermination() diff --git a/examples/src/main/python/streaming/network_wordcount.py b/examples/src/main/python/streaming/network_wordcount.py new file mode 100644 index 0000000000..cfa9c1ff5b --- /dev/null +++ b/examples/src/main/python/streaming/network_wordcount.py @@ -0,0 +1,48 @@ +# +# 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` +""" + +import sys + +from pyspark import SparkContext +from pyspark.streaming import StreamingContext + +if __name__ == "__main__": + if len(sys.argv) != 3: + print >> sys.stderr, "Usage: network_wordcount.py <hostname> <port>" + exit(-1) + sc = SparkContext(appName="PythonStreamingNetworkWordCount") + ssc = StreamingContext(sc, 1) + + lines = ssc.socketTextStream(sys.argv[1], int(sys.argv[2])) + counts = lines.flatMap(lambda line: line.split(" "))\ + .map(lambda word: (word, 1))\ + .reduceByKey(lambda a, b: a+b) + counts.pprint() + + ssc.start() + ssc.awaitTermination() diff --git a/examples/src/main/python/streaming/stateful_network_wordcount.py b/examples/src/main/python/streaming/stateful_network_wordcount.py new file mode 100644 index 0000000000..18a9a5a452 --- /dev/null +++ b/examples/src/main/python/streaming/stateful_network_wordcount.py @@ -0,0 +1,57 @@ +# +# 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: stateful_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/stateful_network_wordcount.py \ + localhost 9999` +""" + +import sys + +from pyspark import SparkContext +from pyspark.streaming import StreamingContext + +if __name__ == "__main__": + if len(sys.argv) != 3: + print >> sys.stderr, "Usage: stateful_network_wordcount.py <hostname> <port>" + exit(-1) + sc = SparkContext(appName="PythonStreamingStatefulNetworkWordCount") + ssc = StreamingContext(sc, 1) + ssc.checkpoint("checkpoint") + + def updateFunc(new_values, last_sum): + return sum(new_values) + (last_sum or 0) + + lines = ssc.socketTextStream(sys.argv[1], int(sys.argv[2])) + running_counts = lines.flatMap(lambda line: line.split(" "))\ + .map(lambda word: (word, 1))\ + .updateStateByKey(updateFunc) + + running_counts.pprint() + + ssc.start() + ssc.awaitTermination() |