[SPARK-6657] [PYSPARK] Fix doc warnings

python/pyspark/mllib/evaluation.py

@@ -334,11 +334,10 @@ def ndcgAt(self, k):
         """
         Compute the average NDCG value of all the queries, truncated at ranking position k.
         The discounted cumulative gain at position k is computed as:
-            sum,,i=1,,^k^ (2^{relevance of ''i''th item}^ - 1) / log(i + 1),
+        sum,,i=1,,^k^ (2^{relevance of ''i''th item}^ - 1) / log(i + 1),
         and the NDCG is obtained by dividing the DCG value on the ground truth set.
         In the current implementation, the relevance value is binary.
-
-        If a query has an empty ground truth set, zero will be used as ndcg together with
+        If a query has an empty ground truth set, zero will be used as NDCG together with
         a log warning.
         """
         return self.call("ndcgAt", int(k))

python/pyspark/mllib/fpm.py

@@ -61,12 +61,12 @@ class FPGrowth(object):
     def train(cls, data, minSupport=0.3, numPartitions=-1):
         """
         Computes an FP-Growth model that contains frequent itemsets.
-        :param data:            The input data set, each element
-                                contains a transaction.
-        :param minSupport:      The minimal support level
-                                (default: `0.3`).
-        :param numPartitions:   The number of partitions used by parallel
-                                FP-growth (default: same as input data).
+
+        :param data: The input data set, each element contains a
+            transaction.
+        :param minSupport: The minimal support level (default: `0.3`).
+        :param numPartitions: The number of partitions used by
+            parallel FP-growth (default: same as input data).
         """
         model = callMLlibFunc("trainFPGrowthModel", data, float(minSupport), int(numPartitions))
         return FPGrowthModel(model)

python/pyspark/sql/dataframe.py

@@ -943,6 +943,7 @@ def replace(self, to_replace, value, subset=None):
             Columns specified in subset that do not have matching data type are ignored.
             For example, if `value` is a string, and subset contains a non-string column,
             then the non-string column is simply ignored.
+
         >>> df4.replace(10, 20).show()
         +----+------+-----+
         | age|height| name|

python/pyspark/streaming/kafka.py

@@ -132,11 +132,12 @@ def createRDD(sc, kafkaParams, offsetRanges, leaders={},
         .. note:: Experimental
 
         Create a RDD from Kafka using offset ranges for each topic and partition.
+
         :param sc:  SparkContext object
         :param kafkaParams: Additional params for Kafka
         :param offsetRanges:  list of offsetRange to specify topic:partition:[start, end) to consume
         :param leaders: Kafka brokers for each TopicAndPartition in offsetRanges.  May be an empty
-                        map, in which case leaders will be looked up on the driver.
+            map, in which case leaders will be looked up on the driver.
         :param keyDecoder:  A function used to decode key (default is utf8_decoder)
         :param valueDecoder:  A function used to decode value (default is utf8_decoder)
         :return: A RDD object