[SPARK-16403][Examples] Cleanup to remove unused imports, consistent style, minor fixes

examples/src/main/java/org/apache/spark/examples/ml/JavaPipelineExample.java

@@ -60,7 +60,7 @@ public static void main(String[] args) {
       .setOutputCol("features");
     LogisticRegression lr = new LogisticRegression()
       .setMaxIter(10)
-      .setRegParam(0.01);
+      .setRegParam(0.001);
     Pipeline pipeline = new Pipeline()
       .setStages(new PipelineStage[] {tokenizer, hashingTF, lr});
 
@@ -71,7 +71,7 @@ public static void main(String[] args) {
     Dataset<Row> test = spark.createDataFrame(Arrays.asList(
       new JavaDocument(4L, "spark i j k"),
       new JavaDocument(5L, "l m n"),
-      new JavaDocument(6L, "mapreduce spark"),
+      new JavaDocument(6L, "spark hadoop spark"),
       new JavaDocument(7L, "apache hadoop")
     ), JavaDocument.class);
 

examples/src/main/java/org/apache/spark/examples/ml/JavaStopWordsRemoverExample.java

@@ -47,7 +47,7 @@ public static void main(String[] args) {
       .setOutputCol("filtered");
 
     List<Row> data = Arrays.asList(
-      RowFactory.create(Arrays.asList("I", "saw", "the", "red", "baloon")),
+      RowFactory.create(Arrays.asList("I", "saw", "the", "red", "balloon")),
       RowFactory.create(Arrays.asList("Mary", "had", "a", "little", "lamb"))
     );
 

examples/src/main/java/org/apache/spark/examples/ml/JavaTokenizerExample.java

@@ -57,17 +57,24 @@ public static void main(String[] args) {
 
     Tokenizer tokenizer = new Tokenizer().setInputCol("sentence").setOutputCol("words");
 
-    Dataset<Row> wordsDataFrame = tokenizer.transform(sentenceDataFrame);
-    for (Row r : wordsDataFrame.select("words", "label").takeAsList(3)) {
+    RegexTokenizer regexTokenizer = new RegexTokenizer()
+        .setInputCol("sentence")
+        .setOutputCol("words")
+        .setPattern("\\W");  // alternatively .setPattern("\\w+").setGaps(false);
+
+    Dataset<Row> tokenized = tokenizer.transform(sentenceDataFrame);
+    for (Row r : tokenized.select("words", "label").takeAsList(3)) {
       java.util.List<String> words = r.getList(0);
       for (String word : words) System.out.print(word + " ");
       System.out.println();
     }
 
-    RegexTokenizer regexTokenizer = new RegexTokenizer()
-      .setInputCol("sentence")
-      .setOutputCol("words")
-      .setPattern("\\W");  // alternatively .setPattern("\\w+").setGaps(false);
+    Dataset<Row> regexTokenized = regexTokenizer.transform(sentenceDataFrame);
+    for (Row r : regexTokenized.select("words", "label").takeAsList(3)) {
+      java.util.List<String> words = r.getList(0);
+      for (String word : words) System.out.print(word + " ");
+      System.out.println();
+    }
     // $example off$
     spark.stop();
   }

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

@@ -32,7 +32,7 @@
 if __name__ == "__main__":
     spark = SparkSession \
         .builder \
-        .appName("PythonAFTSurvivalRegressionExample") \
+        .appName("AFTSurvivalRegressionExample") \
         .getOrCreate()
 
     # $example on$

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

@@ -31,7 +31,7 @@
 if __name__ == "__main__":
     spark = SparkSession\
         .builder\
-        .appName("PythonBisectingKMeansExample")\
+        .appName("BisectingKMeansExample")\
         .getOrCreate()
 
     # $example on$

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

@@ -24,7 +24,7 @@
 from pyspark.ml.feature import HashingTF, Tokenizer
 from pyspark.ml.tuning import CrossValidator, ParamGridBuilder
 # $example off$
-from pyspark.sql import Row, SparkSession
+from pyspark.sql import SparkSession
 
 """
 A simple example demonstrating model selection using CrossValidator.
@@ -39,6 +39,7 @@
         .builder\
         .appName("CrossValidatorExample")\
         .getOrCreate()
+
     # $example on$
     # Prepare training documents, which are labeled.
     training = spark.createDataFrame([

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

@@ -34,15 +34,16 @@
     if len(sys.argv) > 2:
         print("Usage: dataframe_example.py <libsvm file>", file=sys.stderr)
         exit(-1)
-    spark = SparkSession\
-        .builder\
-        .appName("DataFrameExample")\
-        .getOrCreate()
-    if len(sys.argv) == 2:
+    elif len(sys.argv) == 2:
         input = sys.argv[1]
     else:
         input = "data/mllib/sample_libsvm_data.txt"
 
+    spark = SparkSession \
+        .builder \
+        .appName("DataFrameExample") \
+        .getOrCreate()
+
     # Load input data
     print("Loading LIBSVM file with UDT from " + input + ".")
     df = spark.read.format("libsvm").load(input).cache()

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

@@ -31,7 +31,7 @@
 if __name__ == "__main__":
     spark = SparkSession\
         .builder\
-        .appName("decision_tree_classification_example")\
+        .appName("DecisionTreeClassificationExample")\
         .getOrCreate()
 
     # $example on$

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

@@ -18,6 +18,7 @@
 """
 Estimator Transformer Param Example.
 """
+from __future__ import print_function
 
 # $example on$
 from pyspark.ml.linalg import Vectors
@@ -42,7 +43,7 @@
     # Create a LogisticRegression instance. This instance is an Estimator.
     lr = LogisticRegression(maxIter=10, regParam=0.01)
     # Print out the parameters, documentation, and any default values.
-    print "LogisticRegression parameters:\n" + lr.explainParams() + "\n"
+    print("LogisticRegression parameters:\n" + lr.explainParams() + "\n")
 
     # Learn a LogisticRegression model. This uses the parameters stored in lr.
     model1 = lr.fit(training)
@@ -51,8 +52,8 @@
     # we can view the parameters it used during fit().
     # This prints the parameter (name: value) pairs, where names are unique IDs for this
     # LogisticRegression instance.
-    print "Model 1 was fit using parameters: "
-    print model1.extractParamMap()
+    print("Model 1 was fit using parameters: ")
+    print(model1.extractParamMap())
 
     # We may alternatively specify parameters using a Python dictionary as a paramMap
     paramMap = {lr.maxIter: 20}
@@ -67,8 +68,8 @@
     # Now learn a new model using the paramMapCombined parameters.
     # paramMapCombined overrides all parameters set earlier via lr.set* methods.
     model2 = lr.fit(training, paramMapCombined)
-    print "Model 2 was fit using parameters: "
-    print model2.extractParamMap()
+    print("Model 2 was fit using parameters: ")
+    print(model2.extractParamMap())
 
     # Prepare test data
     test = spark.createDataFrame([
@@ -81,9 +82,12 @@
     # Note that model2.transform() outputs a "myProbability" column instead of the usual
     # 'probability' column since we renamed the lr.probabilityCol parameter previously.
     prediction = model2.transform(test)
-    selected = prediction.select("features", "label", "myProbability", "prediction")
-    for row in selected.collect():
-        print row
+    result = prediction.select("features", "label", "myProbability", "prediction") \
+        .collect()
+
+    for row in result:
+        print("features=%s, label=%s -> prob=%s, prediction=%s"
+              % (row.features, row.label, row.myProbability, row.prediction))
     # $example off$
 
     spark.stop()

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

@@ -31,7 +31,7 @@
 if __name__ == "__main__":
     spark = SparkSession\
         .builder\
-        .appName("PythonGuassianMixtureExample")\
+        .appName("GaussianMixtureExample")\
         .getOrCreate()
 
     # $example on$