aboutsummaryrefslogtreecommitdiff
path: root/examples/src/main/python/ml/pca_example.py
diff options
context:
space:
mode:
authorXusen Yin <yinxusen@gmail.com>2015-12-09 12:00:48 -0800
committerXiangrui Meng <meng@databricks.com>2015-12-09 12:00:48 -0800
commit051c6a066f7b5fcc7472412144c15b50a5319bd5 (patch)
tree810e743d0bd63ec07818e57d51469238e0998564 /examples/src/main/python/ml/pca_example.py
parent1eb7c22ce72a1b82ed194a51bbcf0da9c771605a (diff)
downloadspark-051c6a066f7b5fcc7472412144c15b50a5319bd5.tar.gz
spark-051c6a066f7b5fcc7472412144c15b50a5319bd5.tar.bz2
spark-051c6a066f7b5fcc7472412144c15b50a5319bd5.zip
[SPARK-11551][DOC] Replace example code in ml-features.md using include_example
PR on behalf of somideshmukh, thanks! Author: Xusen Yin <yinxusen@gmail.com> Author: somideshmukh <somilde@us.ibm.com> Closes #10219 from yinxusen/SPARK-11551.
Diffstat (limited to 'examples/src/main/python/ml/pca_example.py')
-rw-r--r--examples/src/main/python/ml/pca_example.py42
1 files changed, 42 insertions, 0 deletions
diff --git a/examples/src/main/python/ml/pca_example.py b/examples/src/main/python/ml/pca_example.py
new file mode 100644
index 0000000000..a17181f1b8
--- /dev/null
+++ b/examples/src/main/python/ml/pca_example.py
@@ -0,0 +1,42 @@
+#
+# 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.sql import SQLContext
+# $example on$
+from pyspark.ml.feature import PCA
+from pyspark.mllib.linalg import Vectors
+# $example off$
+
+if __name__ == "__main__":
+ sc = SparkContext(appName="PCAExample")
+ sqlContext = SQLContext(sc)
+
+ # $example on$
+ data = [(Vectors.sparse(5, [(1, 1.0), (3, 7.0)]),),
+ (Vectors.dense([2.0, 0.0, 3.0, 4.0, 5.0]),),
+ (Vectors.dense([4.0, 0.0, 0.0, 6.0, 7.0]),)]
+ df = sqlContext.createDataFrame(data, ["features"])
+ pca = PCA(k=3, inputCol="features", outputCol="pcaFeatures")
+ model = pca.fit(df)
+ result = model.transform(df).select("pcaFeatures")
+ result.show(truncate=False)
+ # $example off$
+
+ sc.stop()