[SPARK-5704] [SQL] [PySpark] createDataFrame from RDD with columns

Deprecate inferSchema() and applySchema(), use createDataFrame() instead, which could take an optional `schema` to create an DataFrame from an RDD. The `schema` could be StructType or list of names of columns.

Author: Davies Liu <davies@databricks.com>

Closes #4498 from davies/create and squashes the following commits:

08469c1 [Davies Liu] remove Scala/Java API for now
c80a7a9 [Davies Liu] fix hive test
d1bd8f2 [Davies Liu] cleanup applySchema
9526e97 [Davies Liu] createDataFrame from RDD with columns

4 files changed, 4 insertions, 4 deletions

diff --git a/mllib/src/test/java/org/apache/spark/ml/JavaPipelineSuite.java b/mllib/src/test/java/org/apache/spark/ml/JavaPipelineSuite.java
index 50995ffef9..0a8c9e5954 100644
--- a/mllib/src/test/java/org/apache/spark/ml/JavaPipelineSuite.java
+++ b/mllib/src/test/java/org/apache/spark/ml/JavaPipelineSuite.java
@@ -45,7 +45,7 @@ public class JavaPipelineSuite {
     jsql = new SQLContext(jsc);
     JavaRDD<LabeledPoint> points =
       jsc.parallelize(generateLogisticInputAsList(1.0, 1.0, 100, 42), 2);
-    dataset = jsql.applySchema(points, LabeledPoint.class);
+    dataset = jsql.createDataFrame(points, LabeledPoint.class);
   }
 
   @After
diff --git a/mllib/src/test/java/org/apache/spark/ml/classification/JavaLogisticRegressionSuite.java b/mllib/src/test/java/org/apache/spark/ml/classification/JavaLogisticRegressionSuite.java
index d4b6644792..3f8e59de0f 100644
--- a/mllib/src/test/java/org/apache/spark/ml/classification/JavaLogisticRegressionSuite.java
+++ b/mllib/src/test/java/org/apache/spark/ml/classification/JavaLogisticRegressionSuite.java
@@ -50,7 +50,7 @@ public class JavaLogisticRegressionSuite implements Serializable {
     jsql = new SQLContext(jsc);
     List<LabeledPoint> points = generateLogisticInputAsList(1.0, 1.0, 100, 42);
     datasetRDD = jsc.parallelize(points, 2);
-    dataset = jsql.applySchema(datasetRDD, LabeledPoint.class);
+    dataset = jsql.createDataFrame(datasetRDD, LabeledPoint.class);
     dataset.registerTempTable("dataset");
   }
 
diff --git a/mllib/src/test/java/org/apache/spark/ml/regression/JavaLinearRegressionSuite.java b/mllib/src/test/java/org/apache/spark/ml/regression/JavaLinearRegressionSuite.java
index 40d5a92bb3..0cc36c8d56 100644
--- a/mllib/src/test/java/org/apache/spark/ml/regression/JavaLinearRegressionSuite.java
+++ b/mllib/src/test/java/org/apache/spark/ml/regression/JavaLinearRegressionSuite.java
@@ -46,7 +46,7 @@ public class JavaLinearRegressionSuite implements Serializable {
     jsql = new SQLContext(jsc);
     List<LabeledPoint> points = generateLogisticInputAsList(1.0, 1.0, 100, 42);
     datasetRDD = jsc.parallelize(points, 2);
-    dataset = jsql.applySchema(datasetRDD, LabeledPoint.class);
+    dataset = jsql.createDataFrame(datasetRDD, LabeledPoint.class);
     dataset.registerTempTable("dataset");
   }
 
diff --git a/mllib/src/test/java/org/apache/spark/ml/tuning/JavaCrossValidatorSuite.java b/mllib/src/test/java/org/apache/spark/ml/tuning/JavaCrossValidatorSuite.java
index 074b58c07d..0bb6b489f2 100644
--- a/mllib/src/test/java/org/apache/spark/ml/tuning/JavaCrossValidatorSuite.java
+++ b/mllib/src/test/java/org/apache/spark/ml/tuning/JavaCrossValidatorSuite.java
@@ -45,7 +45,7 @@ public class JavaCrossValidatorSuite implements Serializable {
     jsc = new JavaSparkContext("local", "JavaCrossValidatorSuite");
     jsql = new SQLContext(jsc);
     List<LabeledPoint> points = generateLogisticInputAsList(1.0, 1.0, 100, 42);
-    dataset = jsql.applySchema(jsc.parallelize(points, 2), LabeledPoint.class);
+    dataset = jsql.createDataFrame(jsc.parallelize(points, 2), LabeledPoint.class);
   }
 
   @After