add more version for DataFrame API

Author: Davies Liu

python/pyspark/sql/column.py

@@ -162,6 +162,7 @@ def __init__(self, jc):
     bitwiseAND = _bin_op("bitwiseAND")
     bitwiseXOR = _bin_op("bitwiseXOR")
 
+    @since(1.3)
     def getItem(self, key):
         """An expression that gets an item at position `ordinal` out of a list,
          or gets an item by key out of a dict.
@@ -182,6 +183,7 @@ def getItem(self, key):
         """
         return self[key]
 
+    @since(1.3)
     def getField(self, name):
         """An expression that gets a field by name in a StructField.
 
@@ -214,6 +216,7 @@ def __getattr__(self, item):
     endswith = _bin_op("endsWith")
 
     @ignore_unicode_prefix
+    @since(1.3)
     def substr(self, startPos, length):
         """
         Return a :class:`Column` which is a substring of the column
@@ -237,6 +240,7 @@ def substr(self, startPos, length):
     __getslice__ = substr
 
     @ignore_unicode_prefix
+    @since(1.3)
     def inSet(self, *cols):
         """ A boolean expression that is evaluated to true if the value of this
         expression is contained by the evaluated values of the arguments.
@@ -262,6 +266,7 @@ def inSet(self, *cols):
     isNull = _unary_op("isNull", "True if the current expression is null.")
     isNotNull = _unary_op("isNotNull", "True if the current expression is not null.")
 
+    @since(1.3)
     def alias(self, *alias):
         """Returns this column aliased with a new name or names (in the case of expressions that
         return more than one column, such as explode).
@@ -277,6 +282,7 @@ def alias(self, *alias):
             return Column(getattr(self._jc, "as")(_to_seq(sc, list(alias))))
 
     @ignore_unicode_prefix
+    @since(1.3)
     def cast(self, dataType):
         """ Convert the column into type `dataType`
 
@@ -297,6 +303,7 @@ def cast(self, dataType):
         return Column(jc)
 
     @ignore_unicode_prefix
+    @since(1.3)
     def between(self, lowerBound, upperBound):
         """ A boolean expression that is evaluated to true if the value of this
         expression is between the given columns.

python/pyspark/sql/context.py

@@ -122,7 +122,7 @@ def getConf(self, key, defaultValue):
         return self._ssql_ctx.getConf(key, defaultValue)
 
     @property
-    @since(1.3)
+    @since("1.3.1")
     def udf(self):
         """Returns a :class:`UDFRegistration` for UDF registration."""
         return UDFRegistration(self)
@@ -149,6 +149,7 @@ def range(self, start, end, step=1, numPartitions=None):
         return DataFrame(jdf, self)
 
     @ignore_unicode_prefix
+    @since(1.2)
     def registerFunction(self, name, f, returnType=StringType()):
         """Registers a lambda function as a UDF so it can be used in SQL statements.
 
@@ -358,6 +359,7 @@ def registerDataFrameAsTable(self, df, tableName):
         else:
             raise ValueError("Can only register DataFrame as table")
 
+    @since(1.0)
     def parquetFile(self, *paths):
         """Loads a Parquet file, returning the result as a :class:`DataFrame`.
 
@@ -376,6 +378,7 @@ def parquetFile(self, *paths):
         jdf = self._ssql_ctx.parquetFile(jpaths)
         return DataFrame(jdf, self)
 
+    @since(1.0)
     def jsonFile(self, path, schema=None, samplingRatio=1.0):
         """Loads a text file storing one JSON object per line as a :class:`DataFrame`.
 
@@ -416,6 +419,7 @@ def jsonFile(self, path, schema=None, samplingRatio=1.0):
         return DataFrame(df, self)
 
     @ignore_unicode_prefix
+    @since(1.0)
     def jsonRDD(self, rdd, schema=None, samplingRatio=1.0):
         """Loads an RDD storing one JSON object per string as a :class:`DataFrame`.
 
@@ -500,6 +504,7 @@ def createExternalTable(self, tableName, path=None, source=None,
         return DataFrame(df, self)
 
     @ignore_unicode_prefix
+    @since(1.0)
     def sql(self, sqlQuery):
         """Returns a :class:`DataFrame` representing the result of the given query.
 
@@ -510,6 +515,7 @@ def sql(self, sqlQuery):
         """
         return DataFrame(self._ssql_ctx.sql(sqlQuery), self)
 
+    @since(1.0)
     def table(self, tableName):
         """Returns the specified table as a :class:`DataFrame`.
 
@@ -557,10 +563,12 @@ def tableNames(self, dbName=None):
         else:
             return [name for name in self._ssql_ctx.tableNames(dbName)]
 
+    @since(1.0)
     def cacheTable(self, tableName):
         """Caches the specified table in-memory."""
         self._ssql_ctx.cacheTable(tableName)
 
+    @since(1.0)
     def uncacheTable(self, tableName):
         """Removes the specified table from the in-memory cache."""
         self._ssql_ctx.uncacheTable(tableName)