From 135ade905089fe90d3cc9e84f8fedc7637e901d8 Mon Sep 17 00:00:00 2001
From: Xiangrui Meng <meng@databricks.com>
Date: Tue, 20 Oct 2015 18:38:06 -0700
Subject: [PATCH] [MINOR][ML] fix doc warnings
Without an empty line, sphinx will treat doctest as docstring. holdenk
~~~
/Users/meng/src/spark/python/pyspark/ml/feature.py:docstring of pyspark.ml.feature.CountVectorizer:3: ERROR: Undefined substitution referenced: "label|raw |vectors | +-----+---------------+-------------------------+ |0 |[a, b, c] |(3,[0,1,2],[1.0,1.0,1.0])".
/Users/meng/src/spark/python/pyspark/ml/feature.py:docstring of pyspark.ml.feature.CountVectorizer:3: ERROR: Undefined substitution referenced: "1 |[a, b, b, c, a]|(3,[0,1,2],[2.0,2.0,1.0])".
~~~
Author: Xiangrui Meng <meng@databricks.com>
Closes #9188 from mengxr/py-count-vec-doc-fix.
---
python/pyspark/ml/feature.py | 1 +
1 file changed, 1 insertion(+)
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py
index a4e60f916b..55bde6d0ea 100644
--- a/python/pyspark/ml/feature.py
+++ b/python/pyspark/ml/feature.py
@@ -178,6 +178,7 @@ class CountVectorizer(JavaEstimator, HasInputCol, HasOutputCol):
.. note:: Experimental
Extracts a vocabulary from document collections and generates a :py:attr:`CountVectorizerModel`.
+
>>> df = sqlContext.createDataFrame(
... [(0, ["a", "b", "c"]), (1, ["a", "b", "b", "c", "a"])],
... ["label", "raw"])
--
GitLab