[SPARK-3909][PySpark][Doc] A corrupted format in Sphinx documents and building warnings

Author: cocoatomo

python/docs/conf.py

@@ -131,7 +131,7 @@
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+#html_static_path = ['_static']
 
 # Add any extra paths that contain custom files (such as robots.txt or
 # .htaccess) here, relative to this directory. These files are copied

python/pyspark/mllib/feature.py

@@ -44,6 +44,7 @@ def transform(self, word):
         """
         :param word: a word
         :return: vector representation of word
+
         Transforms a word to its vector representation
 
         Note: local use only
@@ -57,6 +58,7 @@ def findSynonyms(self, x, num):
         :param x: a word or a vector representation of word
         :param num: number of synonyms to find
         :return: array of (word, cosineSimilarity)
+
         Find synonyms of a word
 
         Note: local use only

python/pyspark/rdd.py

@@ -2009,7 +2009,7 @@ def countApproxDistinct(self, relativeSD=0.05):
         of The Art Cardinality Estimation Algorithm", available
         <a href="http://dx.doi.org/10.1145/2452376.2452456">here</a>.
 
-        :param relativeSD Relative accuracy. Smaller values create
+        :param relativeSD: Relative accuracy. Smaller values create
                            counters that require more space.
                            It must be greater than 0.000017.
 

python/pyspark/sql.py

@@ -19,14 +19,14 @@
 public classes of Spark SQL:
 
     - L{SQLContext}
-    Main entry point for SQL functionality.
+      Main entry point for SQL functionality.
     - L{SchemaRDD}
-    A Resilient Distributed Dataset (RDD) with Schema information for the data contained. In
-    addition to normal RDD operations, SchemaRDDs also support SQL.
+      A Resilient Distributed Dataset (RDD) with Schema information for the data contained. In
+      addition to normal RDD operations, SchemaRDDs also support SQL.
     - L{Row}
-    A Row of data returned by a Spark SQL query.
+      A Row of data returned by a Spark SQL query.
     - L{HiveContext}
-    Main entry point for accessing data stored in Apache Hive..
+      Main entry point for accessing data stored in Apache Hive..
 """
 
 import itertools