diff options
Diffstat (limited to 'python')
-rw-r--r-- | python/pyspark/sql/dataframe.py | 21 |
1 files changed, 18 insertions, 3 deletions
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 7673153abe..03b01a1136 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -1189,15 +1189,30 @@ class DataFrame(object): @since(1.4) @ignore_unicode_prefix - def drop(self, colName): + def drop(self, col): """Returns a new :class:`DataFrame` that drops the specified column. - :param colName: string, name of the column to drop. + :param col: a string name of the column to drop, or a + :class:`Column` to drop. >>> df.drop('age').collect() [Row(name=u'Alice'), Row(name=u'Bob')] + + >>> df.drop(df.age).collect() + [Row(name=u'Alice'), Row(name=u'Bob')] + + >>> df.join(df2, df.name == df2.name, 'inner').drop(df.name).collect() + [Row(age=5, height=85, name=u'Bob')] + + >>> df.join(df2, df.name == df2.name, 'inner').drop(df2.name).collect() + [Row(age=5, name=u'Bob', height=85)] """ - jdf = self._jdf.drop(colName) + if isinstance(col, basestring): + jdf = self._jdf.drop(col) + elif isinstance(col, Column): + jdf = self._jdf.drop(col._jc) + else: + raise TypeError("col should be a string or a Column") return DataFrame(jdf, self.sql_ctx) @since(1.3) |