[SPARK-15134][EXAMPLE] Indent SparkSession builder patterns and update binary_classification_metrics_example.py
## What changes were proposed in this pull request? This issue addresses the comments in SPARK-15031 and also fix java-linter errors. - Use multiline format in SparkSession builder patterns. - Update `binary_classification_metrics_example.py` to use `SparkSession`. - Fix Java Linter errors (in SPARK-13745, SPARK-15031, and so far) ## How was this patch tested? After passing the Jenkins tests and run `dev/lint-java` manually. Author: Dongjoon Hyun <dongj...@apache.org> Closes #12911 from dongjoon-hyun/SPARK-15134. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/2c170dd3 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/2c170dd3 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/2c170dd3 Branch: refs/heads/master Commit: 2c170dd3d731bd848d62265431795e1c141d75d7 Parents: bb9991d Author: Dongjoon Hyun <dongj...@apache.org> Authored: Thu May 5 14:37:50 2016 -0700 Committer: Andrew Or <and...@databricks.com> Committed: Thu May 5 14:37:50 2016 -0700 ---------------------------------------------------------------------- .../network/shuffle/ExternalShuffleBlockHandler.java | 7 +++++-- .../ml/JavaAFTSurvivalRegressionExample.java | 5 ++++- .../org/apache/spark/examples/ml/JavaALSExample.java | 5 ++++- .../spark/examples/ml/JavaBinarizerExample.java | 8 ++++---- .../examples/ml/JavaBisectingKMeansExample.java | 5 ++++- .../spark/examples/ml/JavaBucketizerExample.java | 5 ++++- .../spark/examples/ml/JavaChiSqSelectorExample.java | 8 ++++---- .../examples/ml/JavaCountVectorizerExample.java | 5 ++++- .../org/apache/spark/examples/ml/JavaDCTExample.java | 8 ++++---- .../spark/examples/ml/JavaDeveloperApiExample.java | 5 ++++- .../examples/ml/JavaElementwiseProductExample.java | 7 +++---- .../ml/JavaGradientBoostedTreeClassifierExample.java | 10 ++++++---- .../spark/examples/ml/JavaIndexToStringExample.java | 5 ++++- .../apache/spark/examples/ml/JavaKMeansExample.java | 5 ++++- .../org/apache/spark/examples/ml/JavaLDAExample.java | 5 ++++- .../spark/examples/ml/JavaMaxAbsScalerExample.java | 14 ++++++++++---- .../spark/examples/ml/JavaMinMaxScalerExample.java | 10 ++++++++-- .../apache/spark/examples/ml/JavaNGramExample.java | 5 ++++- .../spark/examples/ml/JavaNaiveBayesExample.java | 5 ++++- .../spark/examples/ml/JavaNormalizerExample.java | 5 ++++- .../spark/examples/ml/JavaOneHotEncoderExample.java | 5 ++++- .../spark/examples/ml/JavaOneVsRestExample.java | 5 ++++- .../org/apache/spark/examples/ml/JavaPCAExample.java | 5 ++++- .../spark/examples/ml/JavaPipelineExample.java | 5 ++++- .../examples/ml/JavaPolynomialExpansionExample.java | 5 ++++- .../spark/examples/ml/JavaRFormulaExample.java | 5 ++++- .../spark/examples/ml/JavaSQLTransformerExample.java | 5 ++++- .../spark/examples/ml/JavaSimpleParamsExample.java | 5 ++++- .../spark/examples/ml/JavaStandardScalerExample.java | 5 ++++- .../examples/ml/JavaStopWordsRemoverExample.java | 5 ++++- .../spark/examples/ml/JavaStringIndexerExample.java | 5 ++++- .../apache/spark/examples/ml/JavaTfIdfExample.java | 5 ++++- .../spark/examples/ml/JavaTokenizerExample.java | 5 ++++- .../examples/ml/JavaVectorAssemblerExample.java | 5 ++++- .../spark/examples/ml/JavaVectorIndexerExample.java | 5 ++++- .../spark/examples/ml/JavaVectorSlicerExample.java | 5 ++++- .../spark/examples/ml/JavaWord2VecExample.java | 5 ++++- .../org/apache/spark/examples/sql/JavaSparkSQL.java | 8 ++++++-- .../examples/streaming/JavaSqlNetworkWordCount.java | 5 ++++- examples/src/main/python/ml/als_example.py | 5 ++++- examples/src/main/python/ml/binarizer_example.py | 5 ++++- .../src/main/python/ml/bisecting_k_means_example.py | 5 ++++- examples/src/main/python/ml/bucketizer_example.py | 5 ++++- .../src/main/python/ml/chisq_selector_example.py | 5 ++++- .../src/main/python/ml/count_vectorizer_example.py | 5 ++++- examples/src/main/python/ml/cross_validator.py | 5 ++++- examples/src/main/python/ml/dataframe_example.py | 5 ++++- examples/src/main/python/ml/dct_example.py | 5 ++++- .../ml/decision_tree_classification_example.py | 5 ++++- .../python/ml/decision_tree_regression_example.py | 5 ++++- .../main/python/ml/elementwise_product_example.py | 5 ++++- .../python/ml/estimator_transformer_param_example.py | 5 ++++- .../ml/gradient_boosted_tree_classifier_example.py | 5 ++++- .../ml/gradient_boosted_tree_regressor_example.py | 5 ++++- .../src/main/python/ml/index_to_string_example.py | 5 ++++- examples/src/main/python/ml/kmeans_example.py | 5 ++++- .../python/ml/linear_regression_with_elastic_net.py | 5 ++++- .../ml/logistic_regression_with_elastic_net.py | 5 ++++- .../src/main/python/ml/max_abs_scaler_example.py | 5 ++++- .../src/main/python/ml/min_max_scaler_example.py | 5 ++++- examples/src/main/python/ml/n_gram_example.py | 5 ++++- examples/src/main/python/ml/naive_bayes_example.py | 5 ++++- examples/src/main/python/ml/normalizer_example.py | 5 ++++- .../src/main/python/ml/onehot_encoder_example.py | 5 ++++- examples/src/main/python/ml/pca_example.py | 5 ++++- examples/src/main/python/ml/pipeline_example.py | 5 ++++- .../main/python/ml/polynomial_expansion_example.py | 5 ++++- .../python/ml/random_forest_classifier_example.py | 5 ++++- .../python/ml/random_forest_regressor_example.py | 5 ++++- examples/src/main/python/ml/rformula_example.py | 5 ++++- .../python/ml/simple_text_classification_pipeline.py | 5 ++++- examples/src/main/python/ml/sql_transformer.py | 5 ++++- .../src/main/python/ml/standard_scaler_example.py | 5 ++++- .../src/main/python/ml/stopwords_remover_example.py | 5 ++++- .../src/main/python/ml/string_indexer_example.py | 5 ++++- examples/src/main/python/ml/tf_idf_example.py | 5 ++++- examples/src/main/python/ml/tokenizer_example.py | 5 ++++- .../src/main/python/ml/train_validation_split.py | 5 ++++- .../src/main/python/ml/vector_assembler_example.py | 5 ++++- .../src/main/python/ml/vector_indexer_example.py | 5 ++++- examples/src/main/python/ml/vector_slicer_example.py | 5 ++++- examples/src/main/python/ml/word2vec_example.py | 5 ++++- .../mllib/binary_classification_metrics_example.py | 15 ++++++++++----- examples/src/main/python/sql.py | 5 ++++- .../main/python/streaming/sql_network_wordcount.py | 6 ++++-- .../examples/ml/AFTSurvivalRegressionExample.scala | 5 ++++- .../org/apache/spark/examples/ml/ALSExample.scala | 5 ++++- .../apache/spark/examples/ml/BinarizerExample.scala | 5 ++++- .../apache/spark/examples/ml/BucketizerExample.scala | 5 ++++- .../spark/examples/ml/ChiSqSelectorExample.scala | 5 ++++- .../spark/examples/ml/CountVectorizerExample.scala | 5 ++++- .../org/apache/spark/examples/ml/DCTExample.scala | 5 ++++- .../apache/spark/examples/ml/DataFrameExample.scala | 5 ++++- .../ml/DecisionTreeClassificationExample.scala | 5 ++++- .../spark/examples/ml/DecisionTreeExample.scala | 4 +++- .../examples/ml/DecisionTreeRegressionExample.scala | 5 ++++- .../spark/examples/ml/DeveloperApiExample.scala | 5 ++++- .../examples/ml/ElementwiseProductExample.scala | 5 ++++- .../ml/EstimatorTransformerParamExample.scala | 5 ++++- .../ml/GradientBoostedTreeClassifierExample.scala | 5 ++++- .../ml/GradientBoostedTreeRegressorExample.scala | 5 ++++- .../spark/examples/ml/IndexToStringExample.scala | 5 ++++- .../org/apache/spark/examples/ml/KMeansExample.scala | 5 ++++- .../org/apache/spark/examples/ml/LDAExample.scala | 5 ++++- .../ml/LinearRegressionWithElasticNetExample.scala | 5 ++++- .../ml/LogisticRegressionSummaryExample.scala | 5 ++++- .../spark/examples/ml/MaxAbsScalerExample.scala | 5 ++++- .../spark/examples/ml/MinMaxScalerExample.scala | 5 ++++- .../ml/MultilayerPerceptronClassifierExample.scala | 5 ++++- .../org/apache/spark/examples/ml/NGramExample.scala | 5 ++++- .../apache/spark/examples/ml/NaiveBayesExample.scala | 5 ++++- .../apache/spark/examples/ml/NormalizerExample.scala | 5 ++++- .../spark/examples/ml/OneHotEncoderExample.scala | 5 ++++- .../apache/spark/examples/ml/OneVsRestExample.scala | 5 ++++- .../org/apache/spark/examples/ml/PCAExample.scala | 5 ++++- .../apache/spark/examples/ml/PipelineExample.scala | 5 ++++- .../examples/ml/PolynomialExpansionExample.scala | 5 ++++- .../examples/ml/QuantileDiscretizerExample.scala | 5 ++++- .../apache/spark/examples/ml/RFormulaExample.scala | 5 ++++- .../examples/ml/RandomForestClassifierExample.scala | 5 ++++- .../examples/ml/RandomForestRegressorExample.scala | 5 ++++- .../spark/examples/ml/SQLTransformerExample.scala | 5 ++++- .../spark/examples/ml/SimpleParamsExample.scala | 5 ++++- .../ml/SimpleTextClassificationPipeline.scala | 5 ++++- .../spark/examples/ml/StandardScalerExample.scala | 5 ++++- .../spark/examples/ml/StopWordsRemoverExample.scala | 5 ++++- .../spark/examples/ml/StringIndexerExample.scala | 5 ++++- .../org/apache/spark/examples/ml/TfIdfExample.scala | 5 ++++- .../apache/spark/examples/ml/TokenizerExample.scala | 5 ++++- .../spark/examples/ml/VectorAssemblerExample.scala | 5 ++++- .../spark/examples/ml/VectorIndexerExample.scala | 5 ++++- .../spark/examples/ml/VectorSlicerExample.scala | 5 ++++- .../apache/spark/examples/ml/Word2VecExample.scala | 5 ++++- .../org/apache/spark/examples/mllib/LDAExample.scala | 4 +++- .../spark/examples/mllib/RankingMetricsExample.scala | 5 ++++- .../examples/mllib/RegressionMetricsExample.scala | 5 ++++- .../org/apache/spark/examples/sql/RDDRelation.scala | 5 ++++- .../examples/streaming/SqlNetworkWordCount.scala | 5 ++++- .../parquet/VectorizedPlainValuesReader.java | 5 +++-- .../execution/vectorized/OffHeapColumnVector.java | 15 ++++++++------- .../sql/execution/vectorized/OnHeapColumnVector.java | 7 ++++--- .../hive/service/cli/session/SessionManager.java | 2 -- 142 files changed, 585 insertions(+), 178 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java ---------------------------------------------------------------------- diff --git a/common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java b/common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java index fb1226c..22fd592 100644 --- a/common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java +++ b/common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java @@ -87,8 +87,11 @@ public class ExternalShuffleBlockHandler extends RpcHandler { blocks.add(blockManager.getBlockData(msg.appId, msg.execId, blockId)); } long streamId = streamManager.registerStream(client.getClientId(), blocks.iterator()); - logger.trace("Registered streamId {} with {} buffers for client {} from host {}", streamId, - msg.blockIds.length, client.getClientId(), NettyUtils.getRemoteAddress(client.getChannel())); + logger.trace("Registered streamId {} with {} buffers for client {} from host {}", + streamId, + msg.blockIds.length, + client.getClientId(), + NettyUtils.getRemoteAddress(client.getChannel())); callback.onSuccess(new StreamHandle(streamId, msg.blockIds.length).toByteBuffer()); } else if (msgObj instanceof RegisterExecutor) { http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java index ecb7084..2c2aa6d 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaAFTSurvivalRegressionExample.java @@ -33,7 +33,10 @@ import org.apache.spark.sql.types.*; public class JavaAFTSurvivalRegressionExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaAFTSurvivalRegressionExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaAFTSurvivalRegressionExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaALSExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaALSExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaALSExample.java index 9a9a104..4b13ba6 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaALSExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaALSExample.java @@ -81,7 +81,10 @@ public class JavaALSExample { // $example off$ public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaALSExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaALSExample") + .getOrCreate(); // $example on$ JavaRDD<Rating> ratingsRDD = spark http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java index 88e4298..5f964ac 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaBinarizerExample.java @@ -17,8 +17,6 @@ package org.apache.spark.examples.ml; -import org.apache.spark.SparkConf; -import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.sql.Dataset; import org.apache.spark.sql.SparkSession; @@ -26,7 +24,6 @@ import org.apache.spark.sql.SparkSession; import java.util.Arrays; import java.util.List; -import org.apache.spark.api.java.JavaRDD; import org.apache.spark.ml.feature.Binarizer; import org.apache.spark.sql.Row; import org.apache.spark.sql.RowFactory; @@ -38,7 +35,10 @@ import org.apache.spark.sql.types.StructType; public class JavaBinarizerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaBinarizerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaBinarizerExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java index 51aa350..810ad90 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaBisectingKMeansExample.java @@ -42,7 +42,10 @@ import org.apache.spark.sql.types.StructType; public class JavaBisectingKMeansExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaBisectingKMeansExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaBisectingKMeansExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java index 0c24f52..691df38 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaBucketizerExample.java @@ -35,7 +35,10 @@ import org.apache.spark.sql.types.StructType; public class JavaBucketizerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaBucketizerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaBucketizerExample") + .getOrCreate(); // $example on$ double[] splits = {Double.NEGATIVE_INFINITY, -0.5, 0.0, 0.5, Double.POSITIVE_INFINITY}; http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java index 684cf9a..f8f2fb1 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaChiSqSelectorExample.java @@ -17,9 +17,6 @@ package org.apache.spark.examples.ml; -import org.apache.spark.SparkConf; -import org.apache.spark.api.java.JavaRDD; -import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.sql.Dataset; import org.apache.spark.sql.SparkSession; @@ -40,7 +37,10 @@ import org.apache.spark.sql.types.StructType; public class JavaChiSqSelectorExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaChiSqSelectorExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaChiSqSelectorExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaCountVectorizerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaCountVectorizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaCountVectorizerExample.java index 0631f9d..0a6b136 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaCountVectorizerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaCountVectorizerExample.java @@ -32,7 +32,10 @@ import org.apache.spark.sql.types.*; public class JavaCountVectorizerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaCountVectorizerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaCountVectorizerExample") + .getOrCreate(); // $example on$ // Input data: Each row is a bag of words from a sentence or document. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java index ec57a24..eee92c7 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaDCTExample.java @@ -17,8 +17,6 @@ package org.apache.spark.examples.ml; -import org.apache.spark.SparkConf; -import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.sql.Dataset; import org.apache.spark.sql.SparkSession; @@ -26,7 +24,6 @@ import org.apache.spark.sql.SparkSession; import java.util.Arrays; import java.util.List; -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; @@ -39,7 +36,10 @@ import org.apache.spark.sql.types.StructType; public class JavaDCTExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaDCTExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaDCTExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaDeveloperApiExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaDeveloperApiExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaDeveloperApiExample.java index 90023ac..49bad0a 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaDeveloperApiExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaDeveloperApiExample.java @@ -49,7 +49,10 @@ import org.apache.spark.sql.SparkSession; public class JavaDeveloperApiExample { public static void main(String[] args) throws Exception { - SparkSession spark = SparkSession.builder().appName("JavaDeveloperApiExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaDeveloperApiExample") + .getOrCreate(); // Prepare training data. List<LabeledPoint> localTraining = Lists.newArrayList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java index a062a6f..9126242 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaElementwiseProductExample.java @@ -17,8 +17,6 @@ package org.apache.spark.examples.ml; -import org.apache.spark.SparkConf; -import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.sql.Dataset; import org.apache.spark.sql.SparkSession; @@ -27,7 +25,6 @@ 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; @@ -42,7 +39,9 @@ import org.apache.spark.sql.types.StructType; public class JavaElementwiseProductExample { public static void main(String[] args) { SparkSession spark = SparkSession - .builder().appName("JavaElementwiseProductExample").getOrCreate(); + .builder() + .appName("JavaElementwiseProductExample") + .getOrCreate(); // $example on$ // Create some vector data; also works for sparse vectors http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java index a7c89b9..baacd79 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaGradientBoostedTreeClassifierExample.java @@ -17,8 +17,6 @@ package org.apache.spark.examples.ml; -import org.apache.spark.SparkConf; -import org.apache.spark.api.java.JavaSparkContext; // $example on$ import org.apache.spark.ml.Pipeline; import org.apache.spark.ml.PipelineModel; @@ -35,11 +33,15 @@ import org.apache.spark.sql.SparkSession; public class JavaGradientBoostedTreeClassifierExample { public static void main(String[] args) { SparkSession spark = SparkSession - .builder().appName("JavaGradientBoostedTreeClassifierExample").getOrCreate(); + .builder() + .appName("JavaGradientBoostedTreeClassifierExample") + .getOrCreate(); // $example on$ // Load and parse the data file, converting it to a DataFrame. - Dataset<Row> data = spark.read().format("libsvm") + Dataset<Row> data = spark + .read() + .format("libsvm") .load("data/mllib/sample_libsvm_data.txt"); // Index labels, adding metadata to the label column. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java index ccd74f2..0064beb 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaIndexToStringExample.java @@ -37,7 +37,10 @@ import org.apache.spark.sql.types.StructType; public class JavaIndexToStringExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaIndexToStringExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaIndexToStringExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java index e6d82a0..65e29ad 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaKMeansExample.java @@ -70,7 +70,10 @@ public class JavaKMeansExample { int k = Integer.parseInt(args[1]); // Parses the arguments - SparkSession spark = SparkSession.builder().appName("JavaKMeansExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaKMeansExample") + .getOrCreate(); // $example on$ // Loads data http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java index b8baca5..1c52f37 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java @@ -65,7 +65,10 @@ public class JavaLDAExample { String inputFile = "data/mllib/sample_lda_data.txt"; // Parses the arguments - SparkSession spark = SparkSession.builder().appName("JavaLDAExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaLDAExample") + .getOrCreate(); // Loads data JavaRDD<Row> points = spark.read().text(inputFile).javaRDD().map(new ParseVector()); http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java index 80cdd36..9a27b0e 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaMaxAbsScalerExample.java @@ -28,13 +28,19 @@ import org.apache.spark.sql.SparkSession; public class JavaMaxAbsScalerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaMaxAbsScalerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaMaxAbsScalerExample") + .getOrCreate(); // $example on$ - Dataset<Row> dataFrame = spark.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt"); + Dataset<Row> dataFrame = spark + .read() + .format("libsvm") + .load("data/mllib/sample_libsvm_data.txt"); MaxAbsScaler scaler = new MaxAbsScaler() - .setInputCol("features") - .setOutputCol("scaledFeatures"); + .setInputCol("features") + .setOutputCol("scaledFeatures"); // Compute summary statistics and generate MaxAbsScalerModel MaxAbsScalerModel scalerModel = scaler.fit(dataFrame); http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java index 022940f..37fa1c5 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaMinMaxScalerExample.java @@ -28,10 +28,16 @@ import org.apache.spark.sql.Row; public class JavaMinMaxScalerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaMinMaxScalerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaMinMaxScalerExample") + .getOrCreate(); // $example on$ - Dataset<Row> dataFrame = spark.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt"); + Dataset<Row> dataFrame = spark + .read() + .format("libsvm") + .load("data/mllib/sample_libsvm_data.txt"); MinMaxScaler scaler = new MinMaxScaler() .setInputCol("features") .setOutputCol("scaledFeatures"); http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaNGramExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaNGramExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaNGramExample.java index 325b7b5..899815f 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaNGramExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaNGramExample.java @@ -35,7 +35,10 @@ import org.apache.spark.sql.types.StructType; public class JavaNGramExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaNGramExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaNGramExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java index 1f24a23..50a46a5 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java @@ -32,7 +32,10 @@ import org.apache.spark.sql.SparkSession; public class JavaNaiveBayesExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaNaiveBayesExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaNaiveBayesExample") + .getOrCreate(); // $example on$ // Load training data http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java index 4b3a718..abc38f8 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaNormalizerExample.java @@ -27,7 +27,10 @@ import org.apache.spark.sql.Row; public class JavaNormalizerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaNormalizerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaNormalizerExample") + .getOrCreate(); // $example on$ Dataset<Row> dataFrame = http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java index d6e4d21..5d29e54 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaOneHotEncoderExample.java @@ -37,7 +37,10 @@ import org.apache.spark.sql.types.StructType; public class JavaOneHotEncoderExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaOneHotEncoderExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaOneHotEncoderExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java index 9cc983b..e0cb752 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaOneVsRestExample.java @@ -58,7 +58,10 @@ public class JavaOneVsRestExample { public static void main(String[] args) { // parse the arguments Params params = parse(args); - SparkSession spark = SparkSession.builder().appName("JavaOneVsRestExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaOneVsRestExample") + .getOrCreate(); // $example on$ // configure the base classifier http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java index 6b1dcb6..ffa979e 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaPCAExample.java @@ -37,7 +37,10 @@ import org.apache.spark.sql.types.StructType; public class JavaPCAExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaPCAExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaPCAExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaPipelineExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaPipelineExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaPipelineExample.java index 556a457..9a43189 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaPipelineExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaPipelineExample.java @@ -36,7 +36,10 @@ import org.apache.spark.sql.SparkSession; */ public class JavaPipelineExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaPipelineExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaPipelineExample") + .getOrCreate(); // $example on$ // Prepare training documents, which are labeled. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java index e328454..7afcd0e 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaPolynomialExpansionExample.java @@ -36,7 +36,10 @@ import org.apache.spark.sql.types.StructType; public class JavaPolynomialExpansionExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaPolynomialExpansionExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaPolynomialExpansionExample") + .getOrCreate(); // $example on$ PolynomialExpansion polyExpansion = new PolynomialExpansion() http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaRFormulaExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaRFormulaExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaRFormulaExample.java index 8282ce0..428067e 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaRFormulaExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaRFormulaExample.java @@ -35,7 +35,10 @@ import static org.apache.spark.sql.types.DataTypes.*; public class JavaRFormulaExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaRFormulaExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaRFormulaExample") + .getOrCreate(); // $example on$ StructType schema = createStructType(new StructField[]{ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaSQLTransformerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaSQLTransformerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaSQLTransformerExample.java index 492718b..2a3d62d 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaSQLTransformerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaSQLTransformerExample.java @@ -31,7 +31,10 @@ import org.apache.spark.sql.types.*; public class JavaSQLTransformerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaSQLTransformerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaSQLTransformerExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java index f906843..0787079 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java @@ -40,7 +40,10 @@ import org.apache.spark.sql.SparkSession; public class JavaSimpleParamsExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaSimpleParamsExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaSimpleParamsExample") + .getOrCreate(); // Prepare training data. // We use LabeledPoint, which is a JavaBean. Spark SQL can convert RDDs of JavaBeans http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java index 10f82f2..08ea285 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaStandardScalerExample.java @@ -28,7 +28,10 @@ import org.apache.spark.sql.Row; public class JavaStandardScalerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaStandardScalerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaStandardScalerExample") + .getOrCreate(); // $example on$ Dataset<Row> dataFrame = http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java index 23ed071..def5994 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java @@ -36,7 +36,10 @@ import org.apache.spark.sql.types.StructType; public class JavaStopWordsRemoverExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaStopWordsRemoverExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaStopWordsRemoverExample") + .getOrCreate(); // $example on$ StopWordsRemover remover = new StopWordsRemover() http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java index d4c2cf9..7533c18 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaStringIndexerExample.java @@ -35,7 +35,10 @@ import static org.apache.spark.sql.types.DataTypes.*; public class JavaStringIndexerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaStringIndexerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaStringIndexerExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java index a816991..6e07539 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaTfIdfExample.java @@ -38,7 +38,10 @@ import org.apache.spark.sql.types.StructType; public class JavaTfIdfExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaTfIdfExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaTfIdfExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java index a65735a..1cc16bb 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java @@ -36,7 +36,10 @@ import org.apache.spark.sql.types.StructType; public class JavaTokenizerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaTokenizerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaTokenizerExample") + .getOrCreate(); // $example on$ List<Row> data = Arrays.asList( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java index 9569bc2..41f1d87 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorAssemblerExample.java @@ -35,7 +35,10 @@ import static org.apache.spark.sql.types.DataTypes.*; public class JavaVectorAssemblerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaVectorAssemblerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaVectorAssemblerExample") + .getOrCreate(); // $example on$ StructType schema = createStructType(new StructField[]{ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java index 217d5a0..dd9d757 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorIndexerExample.java @@ -30,7 +30,10 @@ import org.apache.spark.sql.Row; public class JavaVectorIndexerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaVectorIndexerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaVectorIndexerExample") + .getOrCreate(); // $example on$ Dataset<Row> data = spark.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt"); http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java index 4f1ea82..24959c0 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaVectorSlicerExample.java @@ -37,7 +37,10 @@ import org.apache.spark.sql.types.*; public class JavaVectorSlicerExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaVectorSlicerExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaVectorSlicerExample") + .getOrCreate(); // $example on$ Attribute[] attrs = new Attribute[]{ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/ml/JavaWord2VecExample.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaWord2VecExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaWord2VecExample.java index d9b1a79..9be6e63 100644 --- a/examples/src/main/java/org/apache/spark/examples/ml/JavaWord2VecExample.java +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaWord2VecExample.java @@ -32,7 +32,10 @@ import org.apache.spark.sql.types.*; public class JavaWord2VecExample { public static void main(String[] args) { - SparkSession spark = SparkSession.builder().appName("JavaWord2VecExample").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaWord2VecExample") + .getOrCreate(); // $example on$ // Input data: Each row is a bag of words from a sentence or document. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java b/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java index ec2142e..755b4f5 100644 --- a/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java +++ b/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java @@ -51,7 +51,10 @@ public class JavaSparkSQL { } public static void main(String[] args) throws Exception { - SparkSession spark = SparkSession.builder().appName("JavaSparkSQL").getOrCreate(); + SparkSession spark = SparkSession + .builder() + .appName("JavaSparkSQL") + .getOrCreate(); System.out.println("=== Data source: RDD ==="); // Load a text file and convert each line to a Java Bean. @@ -147,7 +150,8 @@ public class JavaSparkSQL { // a RDD[String] storing one JSON object per string. List<String> jsonData = Arrays.asList( "{\"name\":\"Yin\",\"address\":{\"city\":\"Columbus\",\"state\":\"Ohio\"}}"); - JavaRDD<String> anotherPeopleRDD = spark.createDataFrame(jsonData, String.class).toJSON().javaRDD(); + JavaRDD<String> anotherPeopleRDD = spark + .createDataFrame(jsonData, String.class).toJSON().javaRDD(); Dataset<Row> peopleFromJsonRDD = spark.read().json(anotherPeopleRDD); // Take a look at the schema of this new DataFrame. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/java/org/apache/spark/examples/streaming/JavaSqlNetworkWordCount.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/streaming/JavaSqlNetworkWordCount.java b/examples/src/main/java/org/apache/spark/examples/streaming/JavaSqlNetworkWordCount.java index 44f1e80..57953ef 100644 --- a/examples/src/main/java/org/apache/spark/examples/streaming/JavaSqlNetworkWordCount.java +++ b/examples/src/main/java/org/apache/spark/examples/streaming/JavaSqlNetworkWordCount.java @@ -115,7 +115,10 @@ class JavaSparkSessionSingleton { private static transient SparkSession instance = null; public static SparkSession getInstance(SparkConf sparkConf) { if (instance == null) { - instance = SparkSession.builder().config(sparkConf).getOrCreate(); + instance = SparkSession + .builder() + .config(sparkConf) + .getOrCreate(); } return instance; } http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/als_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/als_example.py b/examples/src/main/python/ml/als_example.py index e36444f..ff0829b 100644 --- a/examples/src/main/python/ml/als_example.py +++ b/examples/src/main/python/ml/als_example.py @@ -30,7 +30,10 @@ from pyspark.sql import Row # $example off$ if __name__ == "__main__": - spark = SparkSession.builder.appName("ALSExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("ALSExample")\ + .getOrCreate() # $example on$ lines = spark.read.text("data/mllib/als/sample_movielens_ratings.txt").rdd http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/binarizer_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/binarizer_example.py b/examples/src/main/python/ml/binarizer_example.py index 072187e..4224a27 100644 --- a/examples/src/main/python/ml/binarizer_example.py +++ b/examples/src/main/python/ml/binarizer_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import Binarizer # $example off$ if __name__ == "__main__": - spark = SparkSession.builder.appName("BinarizerExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("BinarizerExample")\ + .getOrCreate() # $example on$ continuousDataFrame = spark.createDataFrame([ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/bisecting_k_means_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/bisecting_k_means_example.py b/examples/src/main/python/ml/bisecting_k_means_example.py index 836a89c..540a4bc 100644 --- a/examples/src/main/python/ml/bisecting_k_means_example.py +++ b/examples/src/main/python/ml/bisecting_k_means_example.py @@ -30,7 +30,10 @@ A simple example demonstrating a bisecting k-means clustering. """ if __name__ == "__main__": - spark = SparkSession.builder.appName("PythonBisectingKMeansExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("PythonBisectingKMeansExample")\ + .getOrCreate() # $example on$ data = spark.read.text("data/mllib/kmeans_data.txt").rdd http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/bucketizer_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/bucketizer_example.py b/examples/src/main/python/ml/bucketizer_example.py index 288ec62..8177e56 100644 --- a/examples/src/main/python/ml/bucketizer_example.py +++ b/examples/src/main/python/ml/bucketizer_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import Bucketizer # $example off$ if __name__ == "__main__": - spark = SparkSession.builder.appName("BucketizerExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("BucketizerExample")\ + .getOrCreate() # $example on$ splits = [-float("inf"), -0.5, 0.0, 0.5, float("inf")] http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/chisq_selector_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/chisq_selector_example.py b/examples/src/main/python/ml/chisq_selector_example.py index 8f58fc2..8bafb94 100644 --- a/examples/src/main/python/ml/chisq_selector_example.py +++ b/examples/src/main/python/ml/chisq_selector_example.py @@ -24,7 +24,10 @@ from pyspark.mllib.linalg import Vectors # $example off$ if __name__ == "__main__": - spark = SparkSession.builder.appName("ChiSqSelectorExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("ChiSqSelectorExample")\ + .getOrCreate() # $example on$ df = spark.createDataFrame([ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/count_vectorizer_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/count_vectorizer_example.py b/examples/src/main/python/ml/count_vectorizer_example.py index 9dbf995..38cfac8 100644 --- a/examples/src/main/python/ml/count_vectorizer_example.py +++ b/examples/src/main/python/ml/count_vectorizer_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import CountVectorizer # $example off$ if __name__ == "__main__": - spark = SparkSession.builder.appName("CountVectorizerExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("CountVectorizerExample")\ + .getOrCreate() # $example on$ # Input data: Each row is a bag of words with a ID. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/cross_validator.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/cross_validator.py b/examples/src/main/python/ml/cross_validator.py index a61d0f6..a41df6c 100644 --- a/examples/src/main/python/ml/cross_validator.py +++ b/examples/src/main/python/ml/cross_validator.py @@ -35,7 +35,10 @@ Run with: """ if __name__ == "__main__": - spark = SparkSession.builder.appName("CrossValidatorExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("CrossValidatorExample")\ + .getOrCreate() # $example on$ # Prepare training documents, which are labeled. training = spark.createDataFrame([ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/dataframe_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/dataframe_example.py b/examples/src/main/python/ml/dataframe_example.py index b3e6710..a7d8b90 100644 --- a/examples/src/main/python/ml/dataframe_example.py +++ b/examples/src/main/python/ml/dataframe_example.py @@ -33,7 +33,10 @@ if __name__ == "__main__": if len(sys.argv) > 2: print("Usage: dataframe_example.py <libsvm file>", file=sys.stderr) exit(-1) - spark = SparkSession.builder.appName("DataFrameExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("DataFrameExample")\ + .getOrCreate() if len(sys.argv) == 2: input = sys.argv[1] else: http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/dct_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/dct_example.py b/examples/src/main/python/ml/dct_example.py index 1bf8fc6..e36fcde 100644 --- a/examples/src/main/python/ml/dct_example.py +++ b/examples/src/main/python/ml/dct_example.py @@ -24,7 +24,10 @@ from pyspark.mllib.linalg import Vectors from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("DCTExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("DCTExample")\ + .getOrCreate() # $example on$ df = spark.createDataFrame([ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/decision_tree_classification_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/decision_tree_classification_example.py b/examples/src/main/python/ml/decision_tree_classification_example.py index d2318e2..9b40b70 100644 --- a/examples/src/main/python/ml/decision_tree_classification_example.py +++ b/examples/src/main/python/ml/decision_tree_classification_example.py @@ -29,7 +29,10 @@ from pyspark.ml.evaluation import MulticlassClassificationEvaluator from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("decision_tree_classification_example").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("decision_tree_classification_example")\ + .getOrCreate() # $example on$ # Load the data stored in LIBSVM format as a DataFrame. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/decision_tree_regression_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/decision_tree_regression_example.py b/examples/src/main/python/ml/decision_tree_regression_example.py index 9e8cb38..b734d49 100644 --- a/examples/src/main/python/ml/decision_tree_regression_example.py +++ b/examples/src/main/python/ml/decision_tree_regression_example.py @@ -29,7 +29,10 @@ from pyspark.ml.evaluation import RegressionEvaluator from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("decision_tree_classification_example").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("decision_tree_classification_example")\ + .getOrCreate() # $example on$ # Load the data stored in LIBSVM format as a DataFrame. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/elementwise_product_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/elementwise_product_example.py b/examples/src/main/python/ml/elementwise_product_example.py index 6fa641b..41727ed 100644 --- a/examples/src/main/python/ml/elementwise_product_example.py +++ b/examples/src/main/python/ml/elementwise_product_example.py @@ -24,7 +24,10 @@ from pyspark.mllib.linalg import Vectors from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("ElementwiseProductExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("ElementwiseProductExample")\ + .getOrCreate() # $example on$ data = [(Vectors.dense([1.0, 2.0, 3.0]),), (Vectors.dense([4.0, 5.0, 6.0]),)] http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/estimator_transformer_param_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/estimator_transformer_param_example.py b/examples/src/main/python/ml/estimator_transformer_param_example.py index 4993b5a..0fcae0e 100644 --- a/examples/src/main/python/ml/estimator_transformer_param_example.py +++ b/examples/src/main/python/ml/estimator_transformer_param_example.py @@ -26,7 +26,10 @@ from pyspark.ml.classification import LogisticRegression from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("EstimatorTransformerParamExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("EstimatorTransformerParamExample")\ + .getOrCreate() # $example on$ # Prepare training data from a list of (label, features) tuples. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py b/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py index b09ad41..50026d7 100644 --- a/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py +++ b/examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py @@ -29,7 +29,10 @@ from pyspark.ml.evaluation import MulticlassClassificationEvaluator from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("gradient_boosted_tree_classifier_example").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("gradient_boosted_tree_classifier_example")\ + .getOrCreate() # $example on$ # Load and parse the data file, converting it to a DataFrame. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py b/examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py index caa7cfc..5dd2272 100644 --- a/examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py +++ b/examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py @@ -29,7 +29,10 @@ from pyspark.ml.evaluation import RegressionEvaluator from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("gradient_boosted_tree_regressor_example").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("gradient_boosted_tree_regressor_example")\ + .getOrCreate() # $example on$ # Load and parse the data file, converting it to a DataFrame. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/index_to_string_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/index_to_string_example.py b/examples/src/main/python/ml/index_to_string_example.py index dd04b2c..523caac 100644 --- a/examples/src/main/python/ml/index_to_string_example.py +++ b/examples/src/main/python/ml/index_to_string_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import IndexToString, StringIndexer from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("IndexToStringExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("IndexToStringExample")\ + .getOrCreate() # $example on$ df = spark.createDataFrame( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/kmeans_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/kmeans_example.py b/examples/src/main/python/ml/kmeans_example.py index 7d9d80e..7382396 100644 --- a/examples/src/main/python/ml/kmeans_example.py +++ b/examples/src/main/python/ml/kmeans_example.py @@ -49,7 +49,10 @@ if __name__ == "__main__": path = sys.argv[1] k = sys.argv[2] - spark = SparkSession.builder.appName("PythonKMeansExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("PythonKMeansExample")\ + .getOrCreate() lines = spark.read.text(path).rdd data = lines.map(parseVector) http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/linear_regression_with_elastic_net.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/linear_regression_with_elastic_net.py b/examples/src/main/python/ml/linear_regression_with_elastic_net.py index 99b7f7f..620ab5b 100644 --- a/examples/src/main/python/ml/linear_regression_with_elastic_net.py +++ b/examples/src/main/python/ml/linear_regression_with_elastic_net.py @@ -23,7 +23,10 @@ from pyspark.ml.regression import LinearRegression from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("LinearRegressionWithElasticNet").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("LinearRegressionWithElasticNet")\ + .getOrCreate() # $example on$ # Load training data http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/logistic_regression_with_elastic_net.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/logistic_regression_with_elastic_net.py b/examples/src/main/python/ml/logistic_regression_with_elastic_net.py index 0d7112e..33d0689 100644 --- a/examples/src/main/python/ml/logistic_regression_with_elastic_net.py +++ b/examples/src/main/python/ml/logistic_regression_with_elastic_net.py @@ -23,7 +23,10 @@ from pyspark.ml.classification import LogisticRegression from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("LogisticRegressionWithElasticNet").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("LogisticRegressionWithElasticNet")\ + .getOrCreate() # $example on$ # Load training data http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/max_abs_scaler_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/max_abs_scaler_example.py b/examples/src/main/python/ml/max_abs_scaler_example.py index 1cb95a9..ab91198 100644 --- a/examples/src/main/python/ml/max_abs_scaler_example.py +++ b/examples/src/main/python/ml/max_abs_scaler_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import MaxAbsScaler from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("MaxAbsScalerExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("MaxAbsScalerExample")\ + .getOrCreate() # $example on$ dataFrame = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/min_max_scaler_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/min_max_scaler_example.py b/examples/src/main/python/ml/min_max_scaler_example.py index 8d91a59..e3e7bc2 100644 --- a/examples/src/main/python/ml/min_max_scaler_example.py +++ b/examples/src/main/python/ml/min_max_scaler_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import MinMaxScaler from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("MinMaxScalerExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("MinMaxScalerExample")\ + .getOrCreate() # $example on$ dataFrame = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/n_gram_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/n_gram_example.py b/examples/src/main/python/ml/n_gram_example.py index b7fecf0..9ac07f2 100644 --- a/examples/src/main/python/ml/n_gram_example.py +++ b/examples/src/main/python/ml/n_gram_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import NGram from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("NGramExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("NGramExample")\ + .getOrCreate() # $example on$ wordDataFrame = spark.createDataFrame([ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/naive_bayes_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/naive_bayes_example.py b/examples/src/main/python/ml/naive_bayes_example.py index e370355..89255a2 100644 --- a/examples/src/main/python/ml/naive_bayes_example.py +++ b/examples/src/main/python/ml/naive_bayes_example.py @@ -24,7 +24,10 @@ from pyspark.ml.evaluation import MulticlassClassificationEvaluator from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("naive_bayes_example").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("naive_bayes_example")\ + .getOrCreate() # $example on$ # Load training data http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/normalizer_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/normalizer_example.py b/examples/src/main/python/ml/normalizer_example.py index ae25537..19012f5 100644 --- a/examples/src/main/python/ml/normalizer_example.py +++ b/examples/src/main/python/ml/normalizer_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import Normalizer from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("NormalizerExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("NormalizerExample")\ + .getOrCreate() # $example on$ dataFrame = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/onehot_encoder_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/onehot_encoder_example.py b/examples/src/main/python/ml/onehot_encoder_example.py index 9acc363..b9fceef 100644 --- a/examples/src/main/python/ml/onehot_encoder_example.py +++ b/examples/src/main/python/ml/onehot_encoder_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import OneHotEncoder, StringIndexer from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("OneHotEncoderExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("OneHotEncoderExample")\ + .getOrCreate() # $example on$ df = spark.createDataFrame([ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/pca_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/pca_example.py b/examples/src/main/python/ml/pca_example.py index adab151..f1b3cde 100644 --- a/examples/src/main/python/ml/pca_example.py +++ b/examples/src/main/python/ml/pca_example.py @@ -24,7 +24,10 @@ from pyspark.mllib.linalg import Vectors from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("PCAExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("PCAExample")\ + .getOrCreate() # $example on$ data = [(Vectors.sparse(5, [(1, 1.0), (3, 7.0)]),), http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/pipeline_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/pipeline_example.py b/examples/src/main/python/ml/pipeline_example.py index ed9765d..bd10cfd 100644 --- a/examples/src/main/python/ml/pipeline_example.py +++ b/examples/src/main/python/ml/pipeline_example.py @@ -27,7 +27,10 @@ from pyspark.ml.feature import HashingTF, Tokenizer from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("PipelineExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("PipelineExample")\ + .getOrCreate() # $example on$ # Prepare training documents from a list of (id, text, label) tuples. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/polynomial_expansion_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/polynomial_expansion_example.py b/examples/src/main/python/ml/polynomial_expansion_example.py index 328b559..08882bc 100644 --- a/examples/src/main/python/ml/polynomial_expansion_example.py +++ b/examples/src/main/python/ml/polynomial_expansion_example.py @@ -24,7 +24,10 @@ from pyspark.mllib.linalg import Vectors from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("PolynomialExpansionExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("PolynomialExpansionExample")\ + .getOrCreate() # $example on$ df = spark\ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/random_forest_classifier_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/random_forest_classifier_example.py b/examples/src/main/python/ml/random_forest_classifier_example.py index b0a93e0..c618eaf 100644 --- a/examples/src/main/python/ml/random_forest_classifier_example.py +++ b/examples/src/main/python/ml/random_forest_classifier_example.py @@ -29,7 +29,10 @@ from pyspark.ml.evaluation import MulticlassClassificationEvaluator from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("random_forest_classifier_example").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("random_forest_classifier_example")\ + .getOrCreate() # $example on$ # Load and parse the data file, converting it to a DataFrame. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/random_forest_regressor_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/random_forest_regressor_example.py b/examples/src/main/python/ml/random_forest_regressor_example.py index 4bb84f0..3a79373 100644 --- a/examples/src/main/python/ml/random_forest_regressor_example.py +++ b/examples/src/main/python/ml/random_forest_regressor_example.py @@ -29,7 +29,10 @@ from pyspark.ml.evaluation import RegressionEvaluator from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("random_forest_regressor_example").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("random_forest_regressor_example")\ + .getOrCreate() # $example on$ # Load and parse the data file, converting it to a DataFrame. http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/rformula_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/rformula_example.py b/examples/src/main/python/ml/rformula_example.py index 45cc116..d5df3ce 100644 --- a/examples/src/main/python/ml/rformula_example.py +++ b/examples/src/main/python/ml/rformula_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import RFormula from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("RFormulaExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("RFormulaExample")\ + .getOrCreate() # $example on$ dataset = spark.createDataFrame( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/simple_text_classification_pipeline.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/simple_text_classification_pipeline.py b/examples/src/main/python/ml/simple_text_classification_pipeline.py index 3600c12..886f43c 100644 --- a/examples/src/main/python/ml/simple_text_classification_pipeline.py +++ b/examples/src/main/python/ml/simple_text_classification_pipeline.py @@ -33,7 +33,10 @@ pipeline in Python. Run with: if __name__ == "__main__": - spark = SparkSession.builder.appName("SimpleTextClassificationPipeline").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("SimpleTextClassificationPipeline")\ + .getOrCreate() # Prepare training documents, which are labeled. training = spark.createDataFrame([ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/sql_transformer.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/sql_transformer.py b/examples/src/main/python/ml/sql_transformer.py index 26045db..0bf8f35 100644 --- a/examples/src/main/python/ml/sql_transformer.py +++ b/examples/src/main/python/ml/sql_transformer.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import SQLTransformer from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("SQLTransformerExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("SQLTransformerExample")\ + .getOrCreate() # $example on$ df = spark.createDataFrame([ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/standard_scaler_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/standard_scaler_example.py b/examples/src/main/python/ml/standard_scaler_example.py index c50804f..c002748 100644 --- a/examples/src/main/python/ml/standard_scaler_example.py +++ b/examples/src/main/python/ml/standard_scaler_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import StandardScaler from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("StandardScalerExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("StandardScalerExample")\ + .getOrCreate() # $example on$ dataFrame = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt") http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/stopwords_remover_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/stopwords_remover_example.py b/examples/src/main/python/ml/stopwords_remover_example.py index 5736267..395fdef 100644 --- a/examples/src/main/python/ml/stopwords_remover_example.py +++ b/examples/src/main/python/ml/stopwords_remover_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import StopWordsRemover from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("StopWordsRemoverExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("StopWordsRemoverExample")\ + .getOrCreate() # $example on$ sentenceData = spark.createDataFrame([ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/string_indexer_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/string_indexer_example.py b/examples/src/main/python/ml/string_indexer_example.py index aacd4f9..a328e04 100644 --- a/examples/src/main/python/ml/string_indexer_example.py +++ b/examples/src/main/python/ml/string_indexer_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import StringIndexer from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("StringIndexerExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("StringIndexerExample")\ + .getOrCreate() # $example on$ df = spark.createDataFrame( http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/tf_idf_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/tf_idf_example.py b/examples/src/main/python/ml/tf_idf_example.py index 25df816..fb4ad99 100644 --- a/examples/src/main/python/ml/tf_idf_example.py +++ b/examples/src/main/python/ml/tf_idf_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import HashingTF, IDF, Tokenizer from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("TfIdfExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("TfIdfExample")\ + .getOrCreate() # $example on$ sentenceData = spark.createDataFrame([ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/tokenizer_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/tokenizer_example.py b/examples/src/main/python/ml/tokenizer_example.py index 5be4b4c..e61ec92 100644 --- a/examples/src/main/python/ml/tokenizer_example.py +++ b/examples/src/main/python/ml/tokenizer_example.py @@ -23,7 +23,10 @@ from pyspark.ml.feature import Tokenizer, RegexTokenizer from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("TokenizerExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("TokenizerExample")\ + .getOrCreate() # $example on$ sentenceDataFrame = spark.createDataFrame([ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/train_validation_split.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/train_validation_split.py b/examples/src/main/python/ml/train_validation_split.py index 2e43a0f..5f5c52a 100644 --- a/examples/src/main/python/ml/train_validation_split.py +++ b/examples/src/main/python/ml/train_validation_split.py @@ -31,7 +31,10 @@ Run with: """ if __name__ == "__main__": - spark = SparkSession.builder.appName("TrainValidationSplit").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("TrainValidationSplit")\ + .getOrCreate() # $example on$ # Prepare training and test data. data = spark.read.format("libsvm")\ http://git-wip-us.apache.org/repos/asf/spark/blob/2c170dd3/examples/src/main/python/ml/vector_assembler_example.py ---------------------------------------------------------------------- diff --git a/examples/src/main/python/ml/vector_assembler_example.py b/examples/src/main/python/ml/vector_assembler_example.py index 019a9ea..b955ff0 100644 --- a/examples/src/main/python/ml/vector_assembler_example.py +++ b/examples/src/main/python/ml/vector_assembler_example.py @@ -24,7 +24,10 @@ from pyspark.ml.feature import VectorAssembler from pyspark.sql import SparkSession if __name__ == "__main__": - spark = SparkSession.builder.appName("VectorAssemblerExample").getOrCreate() + spark = SparkSession\ + .builder\ + .appName("VectorAssemblerExample")\ + .getOrCreate() # $example on$ dataset = spark.createDataFrame( --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
