Github user davies commented on a diff in the pull request:

    https://github.com/apache/spark/pull/11347#discussion_r54308608
  
    --- Diff: python/pyspark/sql/dataframe.py ---
    @@ -257,53 +264,85 @@ def limit(self, num):
         @ignore_unicode_prefix
         @since(1.3)
         def take(self, num):
    -        """Returns the first ``num`` rows as a :class:`list` of 
:class:`Row`.
    +        """Returns the first ``num`` records as a :class:`list`.
     
             >>> df.take(2)
             [Row(age=2, name=u'Alice'), Row(age=5, name=u'Bob')]
             """
    -        with SCCallSiteSync(self._sc) as css:
    -            port = 
self._sc._jvm.org.apache.spark.sql.execution.python.EvaluatePython.takeAndServe(
    -                self._jdf, num)
    -        return list(_load_from_socket(port, 
BatchedSerializer(PickleSerializer())))
    +        return self.limit(num).collect()
     
         @ignore_unicode_prefix
    -    @since(1.3)
    -    def map(self, f):
    -        """ Returns a new :class:`RDD` by applying a the ``f`` function to 
each :class:`Row`.
    +    @since(2.0)
    +    def applySchema(self, schema=None):
    +        """Returns a new :class:`DataFrame` by appling the given schema, 
or infer the schema
    +        by all of the records if no schema is given.
     
    -        This is a shorthand for ``df.rdd.map()``.
    +        It is only allowed to apply schema for DataFrame which is returned 
by typed operations,
    +        e.g. map, flatMap, etc. And the record type of the schema-applied 
DataFrame will be row.
     
    -        >>> df.map(lambda p: p.name).collect()
    +        >>> ds = df.map(lambda row: row.name)
    +        >>> ds.collect()
             [u'Alice', u'Bob']
    +        >>> ds.schema
    +        StructType(List(StructField(value,BinaryType,false)))
    +        >>> ds2 = ds.applySchema(StringType())
    +        >>> ds2.collect()
    +        [Row(value=u'Alice'), Row(value=u'Bob')]
    +        >>> ds2.schema
    +        StructType(List(StructField(value,StringType,true)))
    +        >>> ds3 = ds.applySchema()
    +        >>> ds3.collect()
    +        [Row(value=u'Alice'), Row(value=u'Bob')]
    +        >>> ds3.schema
    +        StructType(List(StructField(value,StringType,true)))
    +        """
    +        msg = "Cannot apply schema to a DataFrame which is not returned by 
typed operations"
    +        raise RuntimeError(msg)
    --- End diff --
    
    Just Excaption


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to