python/mllib/pca_rowmatrix_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 pyspark import SparkContext
0019 # $example on$
0020 from pyspark.mllib.linalg import Vectors
0021 from pyspark.mllib.linalg.distributed import RowMatrix
0022 # $example off$
0023
0024 if __name__ == "__main__":
0025     sc = SparkContext(appName="PythonPCAOnRowMatrixExample")
0026
0027     # $example on$
0028     rows = sc.parallelize([
0029         Vectors.sparse(5, {1: 1.0, 3: 7.0}),
0030         Vectors.dense(2.0, 0.0, 3.0, 4.0, 5.0),
0031         Vectors.dense(4.0, 0.0, 0.0, 6.0, 7.0)
0032     ])
0033
0034     mat = RowMatrix(rows)
0035     # Compute the top 4 principal components.
0036     # Principal components are stored in a local dense matrix.
0037     pc = mat.computePrincipalComponents(4)
0038
0039     # Project the rows to the linear space spanned by the top 4 principal components.
0040     projected = mat.multiply(pc)
0041     # $example off$
0042     collected = projected.rows.collect()
0043     print("Projected Row Matrix of principal component:")
0044     for vector in collected:
0045         print(vector)
0046     sc.stop()