python/ml/pca_example.py

0001 #
0002 # Licensed to the Apache Software Foundation (ASF) under one or more
0003 # contributor license agreements.  See the NOTICE file distributed with
0004 # this work for additional information regarding copyright ownership.
0005 # The ASF licenses this file to You under the Apache License, Version 2.0
0006 # (the "License"); you may not use this file except in compliance with
0007 # the License.  You may obtain a copy of the License at
0008 #
0009 #    http://www.apache.org/licenses/LICENSE-2.0
0010 #
0011 # Unless required by applicable law or agreed to in writing, software
0012 # distributed under the License is distributed on an "AS IS" BASIS,
0013 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014 # See the License for the specific language governing permissions and
0015 # limitations under the License.
0016 #
0017
0018 from __future__ import print_function
0019
0020 # $example on$
0021 from pyspark.ml.feature import PCA
0022 from pyspark.ml.linalg import Vectors
0023 # $example off$
0024 from pyspark.sql import SparkSession
0025
0026 if __name__ == "__main__":
0027     spark = SparkSession\
0028         .builder\
0029         .appName("PCAExample")\
0030         .getOrCreate()
0031
0032     # $example on$
0033     data = [(Vectors.sparse(5, [(1, 1.0), (3, 7.0)]),),
0034             (Vectors.dense([2.0, 0.0, 3.0, 4.0, 5.0]),),
0035             (Vectors.dense([4.0, 0.0, 0.0, 6.0, 7.0]),)]
0036     df = spark.createDataFrame(data, ["features"])
0037
0038     pca = PCA(k=3, inputCol="features", outputCol="pcaFeatures")
0039     model = pca.fit(df)
0040
0041     result = model.transform(df).select("pcaFeatures")
0042     result.show(truncate=False)
0043     # $example off$
0044
0045     spark.stop()