diff options
Diffstat (limited to 'python/pyspark/context.py')
| -rw-r--r-- | python/pyspark/context.py | 14 |
1 files changed, 12 insertions, 2 deletions
diff --git a/python/pyspark/context.py b/python/pyspark/context.py index aeb7ad4f2f..44d90f1437 100644 --- a/python/pyspark/context.py +++ b/python/pyspark/context.py @@ -324,10 +324,12 @@ class SparkContext(object): with SparkContext._lock: SparkContext._active_spark_context = None - def range(self, start, end, step=1, numSlices=None): + def range(self, start, end=None, step=1, numSlices=None): """ Create a new RDD of int containing elements from `start` to `end` - (exclusive), increased by `step` every element. + (exclusive), increased by `step` every element. Can be called the same + way as python's built-in range() function. If called with a single argument, + the argument is interpreted as `end`, and `start` is set to 0. :param start: the start value :param end: the end value (exclusive) @@ -335,9 +337,17 @@ class SparkContext(object): :param numSlices: the number of partitions of the new RDD :return: An RDD of int + >>> sc.range(5).collect() + [0, 1, 2, 3, 4] + >>> sc.range(2, 4).collect() + [2, 3] >>> sc.range(1, 7, 2).collect() [1, 3, 5] """ + if end is None: + end = start + start = 0 + return self.parallelize(xrange(start, end, step), numSlices) def parallelize(self, c, numSlices=None): |