diff options
author | jyotiska <jyotiska123@gmail.com> | 2014-02-22 15:10:31 -0800 |
---|---|---|
committer | Aaron Davidson <aaron@databricks.com> | 2014-02-22 15:10:31 -0800 |
commit | 722199fab072b4c19a82031c52e5d44f300bd2ea (patch) | |
tree | 27bb40d039424bce62ae1d58f31bb9eabf0c0082 /python/pyspark | |
parent | 3ff077d489af99ad36c9d2389e2afab6465648d4 (diff) | |
download | spark-722199fab072b4c19a82031c52e5d44f300bd2ea.tar.gz spark-722199fab072b4c19a82031c52e5d44f300bd2ea.tar.bz2 spark-722199fab072b4c19a82031c52e5d44f300bd2ea.zip |
doctest updated for mapValues, flatMapValues in rdd.py
Updated doctests for mapValues and flatMapValues in rdd.py
Author: jyotiska <jyotiska123@gmail.com>
Closes #621 from jyotiska/python_spark and squashes the following commits:
716f7cd [jyotiska] doctest updated for mapValues, flatMapValues in rdd.py
Diffstat (limited to 'python/pyspark')
-rw-r--r-- | python/pyspark/rdd.py | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 90f93a1926..1330e61468 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -946,6 +946,11 @@ class RDD(object): Pass each value in the key-value pair RDD through a flatMap function without changing the keys; this also retains the original RDD's partitioning. + + >>> x = sc.parallelize([("a", ["x", "y", "z"]), ("b", ["p", "r"])]) + >>> def f(x): return x + >>> x.flatMapValues(f).collect() + [('a', 'x'), ('a', 'y'), ('a', 'z'), ('b', 'p'), ('b', 'r')] """ flat_map_fn = lambda (k, v): ((k, x) for x in f(v)) return self.flatMap(flat_map_fn, preservesPartitioning=True) @@ -955,6 +960,11 @@ class RDD(object): Pass each value in the key-value pair RDD through a map function without changing the keys; this also retains the original RDD's partitioning. + + >>> x = sc.parallelize([("a", ["apple", "banana", "lemon"]), ("b", ["grapes"])]) + >>> def f(x): return len(x) + >>> x.mapValues(f).collect() + [('a', 3), ('b', 1)] """ map_values_fn = lambda (k, v): (k, f(v)) return self.map(map_values_fn, preservesPartitioning=True) |