From 028ad4bd29106747089bb9a863e9a8dee738770e Mon Sep 17 00:00:00 2001
From: Reynold Xin <rxin@databricks.com>
Date: Mon, 11 May 2015 20:04:36 -0700
Subject: [PATCH] [SPARK-7509][SQL] DataFrame.drop in Python for dropping
columns.
Author: Reynold Xin <rxin@databricks.com>
Closes #6068 from rxin/drop-column and squashes the following commits:
9d7d5ec [Reynold Xin] [SPARK-7509][SQL] DataFrame.drop in Python for dropping columns.
---
python/pyspark/sql/dataframe.py | 14 +++++++++++++-
1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py
index 4eaa8d9c57..72180f6d05 100644
--- a/python/pyspark/sql/dataframe.py
+++ b/python/pyspark/sql/dataframe.py
@@ -1014,7 +1014,7 @@ class DataFrame(object):
@ignore_unicode_prefix
def withColumnRenamed(self, existing, new):
- """REturns a new :class:`DataFrame` by renaming an existing column.
+ """Returns a new :class:`DataFrame` by renaming an existing column.
:param existing: string, name of the existing column to rename.
:param col: string, new name of the column.
@@ -1027,6 +1027,18 @@ class DataFrame(object):
for c in self.columns]
return self.select(*cols)
+ @ignore_unicode_prefix
+ def drop(self, colName):
+ """Returns a new :class:`DataFrame` that drops the specified column.
+
+ :param colName: string, name of the column to drop.
+
+ >>> df.drop('age').collect()
+ [Row(name=u'Alice'), Row(name=u'Bob')]
+ """
+ jdf = self._jdf.drop(colName)
+ return DataFrame(jdf, self.sql_ctx)
+
def toPandas(self):
"""Returns the contents of this :class:`DataFrame` as Pandas ``pandas.DataFrame``.
--
GitLab