fix python style

Author: yinxusen

examples/src/main/python/ml/gradient_boosted_tree_classifier_example.py

@@ -38,41 +38,41 @@
     # $example on$
     # Load and parse the data file, converting it to a DataFrame.
     data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt").toDF()
-    
+
     # Index labels, adding metadata to the label column.
     # Fit on whole dataset to include all labels in index.
     labelIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel").fit(data)
     # Automatically identify categorical features, and index them.
     # Set maxCategories so features with > 4 distinct values are treated as continuous.
     featureIndexer =\
         VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)
-    
+
     # Split the data into training and test sets (30% held out for testing)
     (trainingData, testData) = data.randomSplit([0.7, 0.3])
-    
+
     # Train a GBT model.
     gbt = GBTClassifier(labelCol="indexedLabel", featuresCol="indexedFeatures", maxIter=10)
-    
+
     # Chain indexers and GBT in a Pipeline
     pipeline = Pipeline(stages=[labelIndexer, featureIndexer, gbt])
-    
+
     # Train model.  This also runs the indexers.
     model = pipeline.fit(trainingData)
-    
+
     # Make predictions.
     predictions = model.transform(testData)
-    
+
     # Select example rows to display.
     predictions.select("prediction", "indexedLabel", "features").show(5)
-    
+
     # Select (prediction, true label) and compute test error
     evaluator = MulticlassClassificationEvaluator(
         labelCol="indexedLabel", predictionCol="prediction", metricName="precision")
     accuracy = evaluator.evaluate(predictions)
     print("Test Error = %g" % (1.0 - accuracy))
-    
+
     gbtModel = model.stages[2]
-    print(gbtModel) # summary only
+    print(gbtModel)  # summary only
     # $example off$
 
     sc.stop()

examples/src/main/python/ml/gradient_boosted_tree_regressor_example.py

@@ -38,38 +38,38 @@
     # $example on$
     # Load and parse the data file, converting it to a DataFrame.
     data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt").toDF()
-    
+
     # Automatically identify categorical features, and index them.
     # Set maxCategories so features with > 4 distinct values are treated as continuous.
     featureIndexer =\
         VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)
-    
+
     # Split the data into training and test sets (30% held out for testing)
     (trainingData, testData) = data.randomSplit([0.7, 0.3])
-    
+
     # Train a GBT model.
     gbt = GBTRegressor(featuresCol="indexedFeatures", maxIter=10)
-    
+
     # Chain indexer and GBT in a Pipeline
     pipeline = Pipeline(stages=[featureIndexer, gbt])
-    
+
     # Train model.  This also runs the indexer.
     model = pipeline.fit(trainingData)
-    
+
     # Make predictions.
     predictions = model.transform(testData)
-    
+
     # Select example rows to display.
     predictions.select("prediction", "label", "features").show(5)
-    
+
     # Select (prediction, true label) and compute test error
     evaluator = RegressionEvaluator(
         labelCol="label", predictionCol="prediction", metricName="rmse")
     rmse = evaluator.evaluate(predictions)
     print("Root Mean Squared Error (RMSE) on test data = %g" % rmse)
-    
+
     gbtModel = model.stages[1]
-    print(gbtModel) # summary only
+    print(gbtModel)  # summary only
     # $example off$
 
     sc.stop()

examples/src/main/python/ml/random_forest_classifier_example.py

@@ -38,41 +38,41 @@
     # $example on$
     # Load and parse the data file, converting it to a DataFrame.
     data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt").toDF()
-    
+
     # Index labels, adding metadata to the label column.
     # Fit on whole dataset to include all labels in index.
     labelIndexer = StringIndexer(inputCol="label", outputCol="indexedLabel").fit(data)
     # Automatically identify categorical features, and index them.
     # Set maxCategories so features with > 4 distinct values are treated as continuous.
     featureIndexer =\
         VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)
-    
+
     # Split the data into training and test sets (30% held out for testing)
     (trainingData, testData) = data.randomSplit([0.7, 0.3])
-    
+
     # Train a RandomForest model.
     rf = RandomForestClassifier(labelCol="indexedLabel", featuresCol="indexedFeatures")
-    
+
     # Chain indexers and forest in a Pipeline
     pipeline = Pipeline(stages=[labelIndexer, featureIndexer, rf])
-    
+
     # Train model.  This also runs the indexers.
     model = pipeline.fit(trainingData)
-    
+
     # Make predictions.
     predictions = model.transform(testData)
-    
+
     # Select example rows to display.
     predictions.select("prediction", "indexedLabel", "features").show(5)
-    
+
     # Select (prediction, true label) and compute test error
     evaluator = MulticlassClassificationEvaluator(
         labelCol="indexedLabel", predictionCol="prediction", metricName="precision")
     accuracy = evaluator.evaluate(predictions)
     print("Test Error = %g" % (1.0 - accuracy))
-    
+
     rfModel = model.stages[2]
-    print(rfModel) # summary only
+    print(rfModel)  # summary only
     # $example off$
 
     sc.stop()

examples/src/main/python/ml/random_forest_regressor_example.py

@@ -38,38 +38,38 @@
     # $example on$
     # Load and parse the data file, converting it to a DataFrame.
     data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt").toDF()
-    
+
     # Automatically identify categorical features, and index them.
     # Set maxCategories so features with > 4 distinct values are treated as continuous.
     featureIndexer =\
         VectorIndexer(inputCol="features", outputCol="indexedFeatures", maxCategories=4).fit(data)
-    
+
     # Split the data into training and test sets (30% held out for testing)
     (trainingData, testData) = data.randomSplit([0.7, 0.3])
-    
+
     # Train a RandomForest model.
     rf = RandomForestRegressor(featuresCol="indexedFeatures")
-    
+
     # Chain indexer and forest in a Pipeline
     pipeline = Pipeline(stages=[featureIndexer, rf])
-    
+
     # Train model.  This also runs the indexer.
     model = pipeline.fit(trainingData)
-    
+
     # Make predictions.
     predictions = model.transform(testData)
-    
+
     # Select example rows to display.
     predictions.select("prediction", "label", "features").show(5)
-    
+
     # Select (prediction, true label) and compute test error
     evaluator = RegressionEvaluator(
         labelCol="label", predictionCol="prediction", metricName="rmse")
     rmse = evaluator.evaluate(predictions)
     print("Root Mean Squared Error (RMSE) on test data = %g" % rmse)
-    
+
     rfModel = model.stages[1]
-    print(rfModel) # summary only
+    print(rfModel)  # summary only
     # $example off$
 
     sc.stop()