From a23ed25f3cd6e76784f831d0ab7de7d3e193b59f Mon Sep 17 00:00:00 2001
From: Matei Zaharia <matei@eecs.berkeley.edu>
Date: Sun, 20 Jan 2013 02:10:25 -0800
Subject: [PATCH] Add a class comment to Accumulator
---
python/pyspark/accumulators.py | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/python/pyspark/accumulators.py b/python/pyspark/accumulators.py
index 438af4cfc0..c00c3a37af 100644
--- a/python/pyspark/accumulators.py
+++ b/python/pyspark/accumulators.py
@@ -76,6 +76,18 @@ def _deserialize_accumulator(aid, zero_value, accum_param):
class Accumulator(object):
+ """
+ A shared variable that can be accumulated, i.e., has a commutative and associative "add"
+ operation. Worker tasks on a Spark cluster can add values to an Accumulator with the C{+=}
+ operator, but only the driver program is allowed to access its value, using C{value}.
+ Updates from the workers get propagated automatically to the driver program.
+
+ While C{SparkContext} supports accumulators for primitive data types like C{int} and
+ C{float}, users can also define accumulators for custom types by providing a custom
+ C{AccumulatorParam} object with a C{zero} and C{addInPlace} method. Refer to the doctest
+ of this module for an example.
+ """
+
def __init__(self, aid, value, accum_param):
"""Create a new Accumulator with a given initial value and AccumulatorParam object"""
from pyspark.accumulators import _accumulatorRegistry
--
GitLab