[SPARK-18133][EXAMPLES][ML] Python ML Pipeline Example has syntax e…

## What changes were proposed in this pull request?

In Python 3, there is only one integer type (i.e., int), which mostly behaves like the long type in Python 2. Since Python 3 won't accept "L", so removed "L" in all examples.

## How was this patch tested?

Unit tests.

…rrors]

Author: Jagadeesan <as2@us.ibm.com>

Closes #15660 from jagadeesanas2/SPARK-18133.

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

@@ -84,10 +84,10 @@ if __name__ == "__main__":
 
     # Prepare test documents, which are unlabeled.
     test = spark.createDataFrame([
-        (4L, "spark i j k"),
-        (5L, "l m n"),
-        (6L, "mapreduce spark"),
-        (7L, "apache hadoop")
+        (4, "spark i j k"),
+        (5, "l m n"),
+        (6, "mapreduce spark"),
+        (7, "apache hadoop")
     ], ["id", "text"])
 
     # Make predictions on test documents. cvModel uses the best model found (lrModel).

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

@@ -38,7 +38,7 @@ if __name__ == "__main__":
     # loads data
     dataset = spark.read.format("libsvm").load("data/mllib/sample_kmeans_data.txt")
 
-    gmm = GaussianMixture().setK(2).setSeed(538009335L)
+    gmm = GaussianMixture().setK(2).setSeed(538009335)
     model = gmm.fit(dataset)
 
     print("Gaussians shown as a DataFrame: ")

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

@@ -35,10 +35,10 @@ if __name__ == "__main__":
     # $example on$
     # Prepare training documents from a list of (id, text, label) tuples.
     training = spark.createDataFrame([
-        (0L, "a b c d e spark", 1.0),
-        (1L, "b d", 0.0),
-        (2L, "spark f g h", 1.0),
-        (3L, "hadoop mapreduce", 0.0)
+        (0, "a b c d e spark", 1.0),
+        (1, "b d", 0.0),
+        (2, "spark f g h", 1.0),
+        (3, "hadoop mapreduce", 0.0)
     ], ["id", "text", "label"])
 
     # Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and lr.
@@ -52,10 +52,10 @@ if __name__ == "__main__":
 
     # Prepare test documents, which are unlabeled (id, text) tuples.
     test = spark.createDataFrame([
-        (4L, "spark i j k"),
-        (5L, "l m n"),
-        (6L, "spark hadoop spark"),
-        (7L, "apache hadoop")
+        (4, "spark i j k"),
+        (5, "l m n"),
+        (6, "spark hadoop spark"),
+        (7, "apache hadoop")
     ], ["id", "text"])
 
     # Make predictions on test documents and print columns of interest.

examples/src/main/python/mllib/binary_classification_metrics_example.py

@@ -39,7 +39,7 @@ if __name__ == "__main__":
         .rdd.map(lambda row: LabeledPoint(row[0], row[1]))
 
     # Split data into training (60%) and test (40%)
-    training, test = data.randomSplit([0.6, 0.4], seed=11L)
+    training, test = data.randomSplit([0.6, 0.4], seed=11)
     training.cache()
 
     # Run training algorithm to build the model

examples/src/main/python/mllib/multi_class_metrics_example.py

@@ -32,7 +32,7 @@ if __name__ == "__main__":
     data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_multiclass_classification_data.txt")
 
     # Split data into training (60%) and test (40%)
-    training, test = data.randomSplit([0.6, 0.4], seed=11L)
+    training, test = data.randomSplit([0.6, 0.4], seed=11)
     training.cache()
 
     # Run training algorithm to build the model