-
Notifications
You must be signed in to change notification settings - Fork 28.3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[SPARK-11551][DOC] Replace example code in ml-features.md using include_example #10219
Closed
Closed
Changes from all commits
Commits
Show all changes
16 commits
Select commit
Hold shift + click to select a range
d14f55d
[SPARK-11551][DOC][Example]Replace example code in ml-features.md usi…
somideshmukh 12b1cf3
[SPARK-11551][DOC][Example]Replace example code in ml-features.md usi…
somideshmukh 87e673e
fix java code issues
yinxusen 0e19113
fix scala issues
yinxusen f6a975e
add java vectorindexer, standardscaler, normalizer
yinxusen dd1d2c1
add jsc stop
yinxusen 3d1efc3
fix scala issues
yinxusen c23bab4
add python examples
yinxusen c143d4b
Merge pull request #1 from yinxusen/SomilBranch1.33
somideshmukh b688b4d
[SPARK-11551][DOC][Example]Replace example code in ml-features.md usi…
somideshmukh 8a0d883
fix minor issues
yinxusen bed2192
merge with master
yinxusen e31fb4a
fix python style
yinxusen 8748a88
merge with master
yinxusen 199c45b
remove extra lines
yinxusen 771d015
add show to all examples
yinxusen File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
Large diffs are not rendered by default.
Oops, something went wrong.
68 changes: 68 additions & 0 deletions
68
examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,68 @@ | ||
/* | ||
* 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. | ||
*/ | ||
|
||
package org.apache.spark.examples.ml; | ||
|
||
import org.apache.spark.SparkConf; | ||
import org.apache.spark.api.java.JavaSparkContext; | ||
import org.apache.spark.sql.SQLContext; | ||
|
||
// $example on$ | ||
import java.util.Arrays; | ||
|
||
import org.apache.spark.api.java.JavaRDD; | ||
import org.apache.spark.ml.feature.Binarizer; | ||
import org.apache.spark.sql.DataFrame; | ||
import org.apache.spark.sql.Row; | ||
import org.apache.spark.sql.RowFactory; | ||
import org.apache.spark.sql.types.DataTypes; | ||
import org.apache.spark.sql.types.Metadata; | ||
import org.apache.spark.sql.types.StructField; | ||
import org.apache.spark.sql.types.StructType; | ||
// $example off$ | ||
|
||
public class JavaBinarizerExample { | ||
public static void main(String[] args) { | ||
SparkConf conf = new SparkConf().setAppName("JavaBinarizerExample"); | ||
JavaSparkContext jsc = new JavaSparkContext(conf); | ||
SQLContext jsql = new SQLContext(jsc); | ||
|
||
// $example on$ | ||
JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList( | ||
RowFactory.create(0, 0.1), | ||
RowFactory.create(1, 0.8), | ||
RowFactory.create(2, 0.2) | ||
)); | ||
StructType schema = new StructType(new StructField[]{ | ||
new StructField("label", DataTypes.DoubleType, false, Metadata.empty()), | ||
new StructField("feature", DataTypes.DoubleType, false, Metadata.empty()) | ||
}); | ||
DataFrame continuousDataFrame = jsql.createDataFrame(jrdd, schema); | ||
Binarizer binarizer = new Binarizer() | ||
.setInputCol("feature") | ||
.setOutputCol("binarized_feature") | ||
.setThreshold(0.5); | ||
DataFrame binarizedDataFrame = binarizer.transform(continuousDataFrame); | ||
DataFrame binarizedFeatures = binarizedDataFrame.select("binarized_feature"); | ||
for (Row r : binarizedFeatures.collect()) { | ||
Double binarized_value = r.getDouble(0); | ||
System.out.println(binarized_value); | ||
} | ||
// $example off$ | ||
jsc.stop(); | ||
} | ||
} |
71 changes: 71 additions & 0 deletions
71
examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,71 @@ | ||
/* | ||
* 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. | ||
*/ | ||
|
||
package org.apache.spark.examples.ml; | ||
|
||
import org.apache.spark.SparkConf; | ||
import org.apache.spark.api.java.JavaSparkContext; | ||
import org.apache.spark.sql.SQLContext; | ||
|
||
// $example on$ | ||
import java.util.Arrays; | ||
|
||
import org.apache.spark.api.java.JavaRDD; | ||
import org.apache.spark.ml.feature.Bucketizer; | ||
import org.apache.spark.sql.DataFrame; | ||
import org.apache.spark.sql.Row; | ||
import org.apache.spark.sql.RowFactory; | ||
import org.apache.spark.sql.types.DataTypes; | ||
import org.apache.spark.sql.types.Metadata; | ||
import org.apache.spark.sql.types.StructField; | ||
import org.apache.spark.sql.types.StructType; | ||
// $example off$ | ||
|
||
public class JavaBucketizerExample { | ||
public static void main(String[] args) { | ||
SparkConf conf = new SparkConf().setAppName("JavaBucketizerExample"); | ||
JavaSparkContext jsc = new JavaSparkContext(conf); | ||
SQLContext jsql = new SQLContext(jsc); | ||
|
||
// $example on$ | ||
double[] splits = {Double.NEGATIVE_INFINITY, -0.5, 0.0, 0.5, Double.POSITIVE_INFINITY}; | ||
|
||
JavaRDD<Row> data = jsc.parallelize(Arrays.asList( | ||
RowFactory.create(-0.5), | ||
RowFactory.create(-0.3), | ||
RowFactory.create(0.0), | ||
RowFactory.create(0.2) | ||
)); | ||
StructType schema = new StructType(new StructField[]{ | ||
new StructField("features", DataTypes.DoubleType, false, Metadata.empty()) | ||
}); | ||
DataFrame dataFrame = jsql.createDataFrame(data, schema); | ||
|
||
Bucketizer bucketizer = new Bucketizer() | ||
.setInputCol("features") | ||
.setOutputCol("bucketedFeatures") | ||
.setSplits(splits); | ||
|
||
// Transform original data into its bucket index. | ||
DataFrame bucketedData = bucketizer.transform(dataFrame); | ||
bucketedData.show(); | ||
// $example off$ | ||
jsc.stop(); | ||
} | ||
} | ||
|
||
|
65 changes: 65 additions & 0 deletions
65
examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,65 @@ | ||
/* | ||
* 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. | ||
*/ | ||
|
||
package org.apache.spark.examples.ml; | ||
|
||
import org.apache.spark.SparkConf; | ||
import org.apache.spark.api.java.JavaSparkContext; | ||
import org.apache.spark.sql.SQLContext; | ||
|
||
// $example on$ | ||
import java.util.Arrays; | ||
|
||
import org.apache.spark.api.java.JavaRDD; | ||
import org.apache.spark.ml.feature.DCT; | ||
import org.apache.spark.mllib.linalg.VectorUDT; | ||
import org.apache.spark.mllib.linalg.Vectors; | ||
import org.apache.spark.sql.DataFrame; | ||
import org.apache.spark.sql.Row; | ||
import org.apache.spark.sql.RowFactory; | ||
import org.apache.spark.sql.types.Metadata; | ||
import org.apache.spark.sql.types.StructField; | ||
import org.apache.spark.sql.types.StructType; | ||
// $example off$ | ||
|
||
public class JavaDCTExample { | ||
public static void main(String[] args) { | ||
SparkConf conf = new SparkConf().setAppName("JavaDCTExample"); | ||
JavaSparkContext jsc = new JavaSparkContext(conf); | ||
SQLContext jsql = new SQLContext(jsc); | ||
|
||
// $example on$ | ||
JavaRDD<Row> data = jsc.parallelize(Arrays.asList( | ||
RowFactory.create(Vectors.dense(0.0, 1.0, -2.0, 3.0)), | ||
RowFactory.create(Vectors.dense(-1.0, 2.0, 4.0, -7.0)), | ||
RowFactory.create(Vectors.dense(14.0, -2.0, -5.0, 1.0)) | ||
)); | ||
StructType schema = new StructType(new StructField[]{ | ||
new StructField("features", new VectorUDT(), false, Metadata.empty()), | ||
}); | ||
DataFrame df = jsql.createDataFrame(data, schema); | ||
DCT dct = new DCT() | ||
.setInputCol("features") | ||
.setOutputCol("featuresDCT") | ||
.setInverse(false); | ||
DataFrame dctDf = dct.transform(df); | ||
dctDf.select("featuresDCT").show(3); | ||
// $example off$ | ||
jsc.stop(); | ||
} | ||
} | ||
|
75 changes: 75 additions & 0 deletions
75
examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,75 @@ | ||
/* | ||
* 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. | ||
*/ | ||
|
||
package org.apache.spark.examples.ml; | ||
|
||
import org.apache.spark.SparkConf; | ||
import org.apache.spark.api.java.JavaSparkContext; | ||
import org.apache.spark.sql.SQLContext; | ||
|
||
// $example on$ | ||
import java.util.ArrayList; | ||
import java.util.Arrays; | ||
import java.util.List; | ||
|
||
import org.apache.spark.api.java.JavaRDD; | ||
import org.apache.spark.ml.feature.ElementwiseProduct; | ||
import org.apache.spark.mllib.linalg.Vector; | ||
import org.apache.spark.mllib.linalg.VectorUDT; | ||
import org.apache.spark.mllib.linalg.Vectors; | ||
import org.apache.spark.sql.DataFrame; | ||
import org.apache.spark.sql.Row; | ||
import org.apache.spark.sql.RowFactory; | ||
import org.apache.spark.sql.types.DataTypes; | ||
import org.apache.spark.sql.types.StructField; | ||
import org.apache.spark.sql.types.StructType; | ||
// $example off$ | ||
|
||
public class JavaElementwiseProductExample { | ||
public static void main(String[] args) { | ||
SparkConf conf = new SparkConf().setAppName("JavaElementwiseProductExample"); | ||
JavaSparkContext jsc = new JavaSparkContext(conf); | ||
SQLContext sqlContext = new SQLContext(jsc); | ||
|
||
// $example on$ | ||
// Create some vector data; also works for sparse vectors | ||
JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList( | ||
RowFactory.create("a", Vectors.dense(1.0, 2.0, 3.0)), | ||
RowFactory.create("b", Vectors.dense(4.0, 5.0, 6.0)) | ||
)); | ||
|
||
List<StructField> fields = new ArrayList<StructField>(2); | ||
fields.add(DataTypes.createStructField("id", DataTypes.StringType, false)); | ||
fields.add(DataTypes.createStructField("vector", new VectorUDT(), false)); | ||
|
||
StructType schema = DataTypes.createStructType(fields); | ||
|
||
DataFrame dataFrame = sqlContext.createDataFrame(jrdd, schema); | ||
|
||
Vector transformingVector = Vectors.dense(0.0, 1.0, 2.0); | ||
|
||
ElementwiseProduct transformer = new ElementwiseProduct() | ||
.setScalingVec(transformingVector) | ||
.setInputCol("vector") | ||
.setOutputCol("transformedVector"); | ||
|
||
// Batch transform the vectors to create new column: | ||
transformer.transform(dataFrame).show(); | ||
// $example off$ | ||
jsc.stop(); | ||
} | ||
} |
51 changes: 51 additions & 0 deletions
51
examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,51 @@ | ||
/* | ||
* 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. | ||
*/ | ||
|
||
package org.apache.spark.examples.ml; | ||
|
||
import org.apache.spark.SparkConf; | ||
import org.apache.spark.api.java.JavaSparkContext; | ||
import org.apache.spark.sql.SQLContext; | ||
|
||
// $example on$ | ||
import org.apache.spark.ml.feature.MinMaxScaler; | ||
import org.apache.spark.ml.feature.MinMaxScalerModel; | ||
import org.apache.spark.sql.DataFrame; | ||
// $example off$ | ||
|
||
public class JavaMinMaxScalerExample { | ||
public static void main(String[] args) { | ||
SparkConf conf = new SparkConf().setAppName("JaveMinMaxScalerExample"); | ||
JavaSparkContext jsc = new JavaSparkContext(conf); | ||
SQLContext jsql = new SQLContext(jsc); | ||
|
||
// $example on$ | ||
DataFrame dataFrame = jsql.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt"); | ||
MinMaxScaler scaler = new MinMaxScaler() | ||
.setInputCol("features") | ||
.setOutputCol("scaledFeatures"); | ||
|
||
// Compute summary statistics and generate MinMaxScalerModel | ||
MinMaxScalerModel scalerModel = scaler.fit(dataFrame); | ||
|
||
// rescale each feature to range [min, max]. | ||
DataFrame scaledData = scalerModel.transform(dataFrame); | ||
scaledData.show(); | ||
// $example off$ | ||
jsc.stop(); | ||
} | ||
} |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
indent