From adb9d73cd6543c9edfc6b03a6d20061ff09c69f9 Mon Sep 17 00:00:00 2001
From: Zheng RuiFeng <ruifengz@foxmail.com>
Date: Sat, 9 Apr 2016 11:25:39 -0700
Subject: [PATCH] [SPARK-14339][DOC] Add python examples for
DCT,MinMaxScaler,MaxAbsScaler
## What changes were proposed in this pull request?
add three python examples
## How was this patch tested?
manual tests
Author: Zheng RuiFeng <ruifengz@foxmail.com>
Closes #12063 from zhengruifeng/dct_pe.
---
docs/ml-features.md | 24 ++++++++++
examples/src/main/python/ml/dct_example.py | 45 +++++++++++++++++++
.../main/python/ml/max_abs_scaler_example.py | 43 ++++++++++++++++++
.../main/python/ml/min_max_scaler_example.py | 43 ++++++++++++++++++
4 files changed, 155 insertions(+)
create mode 100644 examples/src/main/python/ml/dct_example.py
create mode 100644 examples/src/main/python/ml/max_abs_scaler_example.py
create mode 100644 examples/src/main/python/ml/min_max_scaler_example.py
diff --git a/docs/ml-features.md b/docs/ml-features.md
index 4fe8eefc26..5cc27d3565 100644
--- a/docs/ml-features.md
+++ b/docs/ml-features.md
@@ -413,6 +413,14 @@ for more details on the API.
{% include_example java/org/apache/spark/examples/ml/JavaDCTExample.java %}
</div>
+
+<div data-lang="python" markdown="1">
+
+Refer to the [DCT Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.DCT)
+for more details on the API.
+
+{% include_example python/ml/dct_example.py %}
+</div>
</div>
## StringIndexer
@@ -771,6 +779,14 @@ for more details on the API.
{% include_example java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java %}
</div>
+
+<div data-lang="python" markdown="1">
+
+Refer to the [MinMaxScaler Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.MinMaxScaler)
+for more details on the API.
+
+{% include_example python/ml/min_max_scaler_example.py %}
+</div>
</div>
@@ -803,6 +819,14 @@ for more details on the API.
{% include_example java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java %}
</div>
+
+<div data-lang="python" markdown="1">
+
+Refer to the [MaxAbsScaler Python docs](api/python/pyspark.ml.html#pyspark.ml.feature.MaxAbsScaler)
+for more details on the API.
+
+{% include_example python/ml/max_abs_scaler_example.py %}
+</div>
</div>
## Bucketizer
diff --git a/examples/src/main/python/ml/dct_example.py b/examples/src/main/python/ml/dct_example.py
new file mode 100644
index 0000000000..264d47f404
--- /dev/null
+++ b/examples/src/main/python/ml/dct_example.py
@@ -0,0 +1,45 @@
+#
+# 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 DCT
+from pyspark.mllib.linalg import Vectors
+# $example off$
+
+if __name__ == "__main__":
+ sc = SparkContext(appName="DCTExample")
+ sqlContext = SQLContext(sc)
+
+ # $example on$
+ df = sqlContext.createDataFrame([
+ (Vectors.dense([0.0, 1.0, -2.0, 3.0]),),
+ (Vectors.dense([-1.0, 2.0, 4.0, -7.0]),),
+ (Vectors.dense([14.0, -2.0, -5.0, 1.0]),)], ["features"])
+
+ dct = DCT(inverse=False, inputCol="features", outputCol="featuresDCT")
+
+ dctDf = dct.transform(df)
+
+ for dcts in dctDf.select("featuresDCT").take(3):
+ print(dcts)
+ # $example off$
+
+ sc.stop()
diff --git a/examples/src/main/python/ml/max_abs_scaler_example.py b/examples/src/main/python/ml/max_abs_scaler_example.py
new file mode 100644
index 0000000000..d9b69eef1c
--- /dev/null
+++ b/examples/src/main/python/ml/max_abs_scaler_example.py
@@ -0,0 +1,43 @@
+#
+# 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 MaxAbsScaler
+# $example off$
+
+if __name__ == "__main__":
+ sc = SparkContext(appName="MaxAbsScalerExample")
+ sqlContext = SQLContext(sc)
+
+ # $example on$
+ dataFrame = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
+
+ scaler = MaxAbsScaler(inputCol="features", outputCol="scaledFeatures")
+
+ # Compute summary statistics and generate MaxAbsScalerModel
+ scalerModel = scaler.fit(dataFrame)
+
+ # rescale each feature to range [-1, 1].
+ scaledData = scalerModel.transform(dataFrame)
+ scaledData.show()
+ # $example off$
+
+ sc.stop()
diff --git a/examples/src/main/python/ml/min_max_scaler_example.py b/examples/src/main/python/ml/min_max_scaler_example.py
new file mode 100644
index 0000000000..2f8e4ade46
--- /dev/null
+++ b/examples/src/main/python/ml/min_max_scaler_example.py
@@ -0,0 +1,43 @@
+#
+# 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 MinMaxScaler
+# $example off$
+
+if __name__ == "__main__":
+ sc = SparkContext(appName="MinMaxScalerExample")
+ sqlContext = SQLContext(sc)
+
+ # $example on$
+ dataFrame = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
+
+ scaler = MinMaxScaler(inputCol="features", outputCol="scaledFeatures")
+
+ # Compute summary statistics and generate MinMaxScalerModel
+ scalerModel = scaler.fit(dataFrame)
+
+ # rescale each feature to range [min, max].
+ scaledData = scalerModel.transform(dataFrame)
+ scaledData.show()
+ # $example off$
+
+ sc.stop()
--
GitLab