diff options
author | Davies Liu <davies@databricks.com> | 2015-03-26 00:01:24 -0700 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2015-03-26 00:01:32 -0700 |
commit | 0ba759985288f5df6940c37f5f401bc31de53a1c (patch) | |
tree | dd309547ba0eeb0498dac156b83e2d1e2da18815 /python/pyspark/sql/dataframe.py | |
parent | 9edb34fc38147bd150340e006f05d346b4a40f8c (diff) | |
download | spark-0ba759985288f5df6940c37f5f401bc31de53a1c.tar.gz spark-0ba759985288f5df6940c37f5f401bc31de53a1c.tar.bz2 spark-0ba759985288f5df6940c37f5f401bc31de53a1c.zip |
[SPARK-6536] [PySpark] Column.inSet() in Python
```
>>> df[df.name.inSet("Bob", "Mike")].collect()
[Row(age=5, name=u'Bob')]
>>> df[df.age.inSet([1, 2, 3])].collect()
[Row(age=2, name=u'Alice')]
```
Author: Davies Liu <davies@databricks.com>
Closes #5190 from davies/in and squashes the following commits:
6b73a47 [Davies Liu] Column.inSet() in Python
(cherry picked from commit f535802977c5a3ce45894d89fdf59f8723f023c8)
Signed-off-by: Reynold Xin <rxin@databricks.com>
Diffstat (limited to 'python/pyspark/sql/dataframe.py')
-rw-r--r-- | python/pyspark/sql/dataframe.py | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 5cb89da7a8..bf7c47b726 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -985,6 +985,23 @@ class Column(object): __getslice__ = substr + 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. + + >>> df[df.name.inSet("Bob", "Mike")].collect() + [Row(age=5, name=u'Bob')] + >>> df[df.age.inSet([1, 2, 3])].collect() + [Row(age=2, name=u'Alice')] + """ + if len(cols) == 1 and isinstance(cols[0], (list, set)): + cols = cols[0] + cols = [c._jc if isinstance(c, Column) else _create_column_from_literal(c) for c in cols] + sc = SparkContext._active_spark_context + jcols = ListConverter().convert(cols, sc._gateway._gateway_client) + jc = getattr(self._jc, "in")(sc._jvm.PythonUtils.toSeq(jcols)) + return Column(jc) + # order asc = _unary_op("asc", "Returns a sort expression based on the" " ascending order of the given column name.") |