From 1aa191e58e905f470f73663fc1c35f36e05e929a Mon Sep 17 00:00:00 2001 From: Bryan Cutler Date: Mon, 27 Jun 2016 12:58:39 -0700 Subject: [SPARK-16231][PYSPARK][ML][EXAMPLES] dataframe_example.py fails to convert ML style vectors ## What changes were proposed in this pull request? Need to convert ML Vectors to the old MLlib style before doing Statistics.colStats operations on the DataFrame ## How was this patch tested? Ran example, local tests Author: Bryan Cutler Closes #13928 from BryanCutler/pyspark-ml-example-vector-conv-SPARK-16231. --- examples/src/main/python/ml/dataframe_example.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'examples/src/main') diff --git a/examples/src/main/python/ml/dataframe_example.py b/examples/src/main/python/ml/dataframe_example.py index a7d8b9056d..c1818d72fe 100644 --- a/examples/src/main/python/ml/dataframe_example.py +++ b/examples/src/main/python/ml/dataframe_example.py @@ -28,6 +28,7 @@ import shutil from pyspark.sql import SparkSession from pyspark.mllib.stat import Statistics +from pyspark.mllib.util import MLUtils if __name__ == "__main__": if len(sys.argv) > 2: @@ -55,7 +56,8 @@ if __name__ == "__main__": labelSummary.show() # Convert features column to an RDD of vectors. - features = df.select("features").rdd.map(lambda r: r.features) + features = MLUtils.convertVectorColumnsFromML(df, "features") \ + .select("features").rdd.map(lambda r: r.features) summary = Statistics.colStats(features) print("Selected features column with average values:\n" + str(summary.mean())) -- cgit v1.2.3