diff options
author | Xiangrui Meng <meng@databricks.com> | 2014-11-03 22:29:48 -0800 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2014-11-03 22:29:48 -0800 |
commit | 1a9c6cddadebdc53d083ac3e0da276ce979b5d1f (patch) | |
tree | b485818ba52a9287ae7124e57ef55f1d974f3a1f /examples/src/main/python | |
parent | 04450d11548cfb25d4fb77d4a33e3a7cd4254183 (diff) | |
download | spark-1a9c6cddadebdc53d083ac3e0da276ce979b5d1f.tar.gz spark-1a9c6cddadebdc53d083ac3e0da276ce979b5d1f.tar.bz2 spark-1a9c6cddadebdc53d083ac3e0da276ce979b5d1f.zip |
[SPARK-3573][MLLIB] Make MLlib's Vector compatible with SQL's SchemaRDD
Register MLlib's Vector as a SQL user-defined type (UDT) in both Scala and Python. With this PR, we can easily map a RDD[LabeledPoint] to a SchemaRDD, and then select columns or save to a Parquet file. Examples in Scala/Python are attached. The Scala code was copied from jkbradley.
~~This PR contains the changes from #3068 . I will rebase after #3068 is merged.~~
marmbrus jkbradley
Author: Xiangrui Meng <meng@databricks.com>
Closes #3070 from mengxr/SPARK-3573 and squashes the following commits:
3a0b6e5 [Xiangrui Meng] organize imports
236f0a0 [Xiangrui Meng] register vector as UDT and provide dataset examples
Diffstat (limited to 'examples/src/main/python')
-rw-r--r-- | examples/src/main/python/mllib/dataset_example.py | 62 |
1 files changed, 62 insertions, 0 deletions
diff --git a/examples/src/main/python/mllib/dataset_example.py b/examples/src/main/python/mllib/dataset_example.py new file mode 100644 index 0000000000..540dae785f --- /dev/null +++ b/examples/src/main/python/mllib/dataset_example.py @@ -0,0 +1,62 @@ +# +# 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. +# + +""" +An example of how to use SchemaRDD as a dataset for ML. Run with:: + bin/spark-submit examples/src/main/python/mllib/dataset_example.py +""" + +import os +import sys +import tempfile +import shutil + +from pyspark import SparkContext +from pyspark.sql import SQLContext +from pyspark.mllib.util import MLUtils +from pyspark.mllib.stat import Statistics + + +def summarize(dataset): + print "schema: %s" % dataset.schema().json() + labels = dataset.map(lambda r: r.label) + print "label average: %f" % labels.mean() + features = dataset.map(lambda r: r.features) + summary = Statistics.colStats(features) + print "features average: %r" % summary.mean() + +if __name__ == "__main__": + if len(sys.argv) > 2: + print >> sys.stderr, "Usage: dataset_example.py <libsvm file>" + exit(-1) + sc = SparkContext(appName="DatasetExample") + sqlCtx = SQLContext(sc) + if len(sys.argv) == 2: + input = sys.argv[1] + else: + input = "data/mllib/sample_libsvm_data.txt" + points = MLUtils.loadLibSVMFile(sc, input) + dataset0 = sqlCtx.inferSchema(points).setName("dataset0").cache() + summarize(dataset0) + tempdir = tempfile.NamedTemporaryFile(delete=False).name + os.unlink(tempdir) + print "Save dataset as a Parquet file to %s." % tempdir + dataset0.saveAsParquetFile(tempdir) + print "Load it back and summarize it again." + dataset1 = sqlCtx.parquetFile(tempdir).setName("dataset1").cache() + summarize(dataset1) + shutil.rmtree(tempdir) |