diff options
| author | Jacky Li <jacky.likun@huawei.com> | 2015-02-26 10:40:58 -0800 |
|---|---|---|
| committer | Reynold Xin <rxin@databricks.com> | 2015-02-26 10:43:20 -0800 |
| commit | 7c779d8d52a445362fc57e740ce51bdc2e93ad7f (patch) | |
| tree | 12892f8cbd40d8b99b1344afeaa0727c0b1cccb2 /python/pyspark | |
| parent | b5c5e93d71741f3daa7bf9b3de838c36bd234511 (diff) | |
| download | spark-7c779d8d52a445362fc57e740ce51bdc2e93ad7f.tar.gz spark-7c779d8d52a445362fc57e740ce51bdc2e93ad7f.tar.bz2 spark-7c779d8d52a445362fc57e740ce51bdc2e93ad7f.zip | |
[SPARK-6007][SQL] Add numRows param in DataFrame.show()
It is useful to let the user decide the number of rows to show in DataFrame.show
Author: Jacky Li <jacky.likun@huawei.com>
Closes #4767 from jackylk/show and squashes the following commits:
a0e0f4b [Jacky Li] fix testcase
7cdbe91 [Jacky Li] modify according to comment
bb54537 [Jacky Li] for Java compatibility
d7acc18 [Jacky Li] modify according to comments
981be52 [Jacky Li] add numRows param in DataFrame.show()
(cherry picked from commit 2358657547016d647cdd2e2d363426fcd8d3e9ff)
Signed-off-by: Reynold Xin <rxin@databricks.com>
Diffstat (limited to 'python/pyspark')
| -rw-r--r-- | python/pyspark/sql/dataframe.py | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 6d42410020..aec99017fb 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -272,9 +272,9 @@ class DataFrame(object): """ return self._jdf.isLocal() - def show(self): + def show(self, n=20): """ - Print the first 20 rows. + Print the first n rows. >>> df DataFrame[age: int, name: string] @@ -283,7 +283,7 @@ class DataFrame(object): 2 Alice 5 Bob """ - print self._jdf.showString().encode('utf8', 'ignore') + print self._jdf.showString(n).encode('utf8', 'ignore') def __repr__(self): return "DataFrame[%s]" % (", ".join("%s: %s" % c for c in self.dtypes)) |