aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rwxr-xr-xdev/create-release/create-release.sh2
-rw-r--r--python/docs/conf.py6
-rw-r--r--python/docs/pyspark.sql.rst2
-rw-r--r--python/pyspark/rdd.py4
4 files changed, 9 insertions, 5 deletions
diff --git a/dev/create-release/create-release.sh b/dev/create-release/create-release.sh
index 607ce1c803..da15ce3e0e 100755
--- a/dev/create-release/create-release.sh
+++ b/dev/create-release/create-release.sh
@@ -237,7 +237,7 @@ if [[ ! "$@" =~ --skip-package ]]; then
sbt/sbt clean
cd docs
# Compile docs with Java 7 to use nicer format
- JAVA_HOME=$JAVA_7_HOME PRODUCTION=1 jekyll build
+ JAVA_HOME="$JAVA_7_HOME" PRODUCTION=1 RELEASE_VERSION="$RELEASE_VERSION" jekyll build
echo "Copying release documentation"
rc_docs_folder=${rc_folder}-docs
ssh $ASF_USERNAME@people.apache.org \
diff --git a/python/docs/conf.py b/python/docs/conf.py
index cbbf7ffb08..163987dd8e 100644
--- a/python/docs/conf.py
+++ b/python/docs/conf.py
@@ -48,16 +48,16 @@ master_doc = 'index'
# General information about the project.
project = u'PySpark'
-copyright = u'2014, Author'
+copyright = u''
# The version info for the project you're documenting, acts as replacement for
# |version| and |release|, also used in various other places throughout the
# built documents.
#
# The short X.Y version.
-version = '1.3-SNAPSHOT'
+version = 'master'
# The full version, including alpha/beta/rc tags.
-release = '1.3-SNAPSHOT'
+release = os.environ.get('RELEASE_VERSION', version)
# The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages.
diff --git a/python/docs/pyspark.sql.rst b/python/docs/pyspark.sql.rst
index 2e3f69b9a5..6259379ed0 100644
--- a/python/docs/pyspark.sql.rst
+++ b/python/docs/pyspark.sql.rst
@@ -17,7 +17,7 @@ pyspark.sql.types module
pyspark.sql.functions module
-------------------------
+----------------------------
.. automodule:: pyspark.sql.functions
:members:
:undoc-members:
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
index d3148de6f4..cb12fed98c 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -2111,6 +2111,7 @@ class RDD(object):
def countApprox(self, timeout, confidence=0.95):
"""
.. note:: Experimental
+
Approximate version of count() that returns a potentially incomplete
result within a timeout, even if not all tasks have finished.
@@ -2124,6 +2125,7 @@ class RDD(object):
def sumApprox(self, timeout, confidence=0.95):
"""
.. note:: Experimental
+
Approximate operation to return the sum within a timeout
or meet the confidence.
@@ -2140,6 +2142,7 @@ class RDD(object):
def meanApprox(self, timeout, confidence=0.95):
"""
.. note:: Experimental
+
Approximate operation to return the mean within a timeout
or meet the confidence.
@@ -2156,6 +2159,7 @@ class RDD(object):
def countApproxDistinct(self, relativeSD=0.05):
"""
.. note:: Experimental
+
Return approximate number of distinct elements in the RDD.
The algorithm used is based on streamlib's implementation of