Github user yinxusen commented on a diff in the pull request:
https://github.com/apache/spark/pull/11116#discussion_r54224562
--- Diff: examples/src/main/python/mllib/streaming_k_means_example.py ---
@@ -0,0 +1,53 @@
+#
+# 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.
+#
+
+from __future__ import print_function
+
+from pyspark import SparkContext
+from pyspark.streaming import StreamingContext
+# $example on$
+from pyspark.mllib.linalg import Vectors
+from pyspark.mllib.regression import LabeledPoint
+from pyspark.mllib.clustering import StreamingKMeans
+# $example off$
+
+if __name__ == "__main__":
+ sc = SparkContext(appName="StreamingKMeansExample") # SparkContext
+ ssc = StreamingContext(sc, 1)
+
+ # $example on$
+ # we make an input stream of vectors for training,
+ # as well as a stream of labeled data points for testing
+ def parse(lp):
+ label = float(lp[lp.find('(') + 1: lp.find(')')])
+ vec = Vectors.dense(lp[lp.find('[') + 1: lp.find(']')].split(','))
+ return LabeledPoint(label, vec)
+
+ trainingData =
ssc.textFileStream("data/mllib/streaming_kmeans_data.txt").map(Vectors.parse)
+ testingData =
ssc.textFileStream("data/mllib/streaming_kmeans_data_test.txt").map(parse)
+
+ # We create a model with random clusters and specify the number of
clusters to find
+ model = StreamingKMeans(k=2, decayFactor=1.0).setRandomCenters(3, 1.0,
0)
+
+ # Now register the streams for training and testing and start the job,
+ # printing the predicted cluster assignments on new data points as
they arrive.
+ model.trainOn(trainingData)
+ print(model.predictOnValues(testingData.map(lambda lp: (lp.label,
lp.features))))
--- End diff --
The `textFileStream` only reads new files in a directory. See
https://github.com/apache/spark/blob/master/streaming/src/main/scala/org/apache/spark/streaming/dstream/FileInputDStream.scala#L79.
Maybe we can change the example with queueStream, refer to
[here](https://github.com/yinxusen/spark/blob/SPARK-12042/examples/src/main/python/mllib/streaming_test_example.py).
Also, we need to change the `ssc.awaitTermination()` in the end to
`ssc.stop(stopSparkContext=True, stopGraceFully=True)` ([link
here](https://github.com/yinxusen/spark/blob/SPARK-12042/examples/src/main/python/mllib/streaming_test_example.py#L53))
because the former requires stop manually.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
