diff options
Diffstat (limited to 'python/pyspark')
| -rw-r--r-- | python/pyspark/mllib/stat/KernelDensity.py | 2 | ||||
| -rw-r--r-- | python/pyspark/mllib/util.py | 2 | ||||
| -rw-r--r-- | python/pyspark/rdd.py | 4 | ||||
| -rw-r--r-- | python/pyspark/streaming/kafka.py | 4 |
4 files changed, 6 insertions, 6 deletions
diff --git a/python/pyspark/mllib/stat/KernelDensity.py b/python/pyspark/mllib/stat/KernelDensity.py index 3b1c5519bd..7250eab670 100644 --- a/python/pyspark/mllib/stat/KernelDensity.py +++ b/python/pyspark/mllib/stat/KernelDensity.py @@ -28,7 +28,7 @@ from pyspark.rdd import RDD class KernelDensity(object): """ - Estimate probability density at required points given a RDD of samples + Estimate probability density at required points given an RDD of samples from the population. >>> kd = KernelDensity() diff --git a/python/pyspark/mllib/util.py b/python/pyspark/mllib/util.py index ed6fd4bca4..97755807ef 100644 --- a/python/pyspark/mllib/util.py +++ b/python/pyspark/mllib/util.py @@ -499,7 +499,7 @@ class LinearDataGenerator(object): def generateLinearRDD(sc, nexamples, nfeatures, eps, nParts=2, intercept=0.0): """ - Generate a RDD of LabeledPoints. + Generate an RDD of LabeledPoints. """ return callMLlibFunc( "generateLinearRDDWrapper", sc, int(nexamples), int(nfeatures), diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index a163ceafe9..641787ee20 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -1218,7 +1218,7 @@ class RDD(object): def top(self, num, key=None): """ - Get the top N elements from a RDD. + Get the top N elements from an RDD. Note that this method should only be used if the resulting array is expected to be small, as all the data is loaded into the driver's memory. @@ -1242,7 +1242,7 @@ class RDD(object): def takeOrdered(self, num, key=None): """ - Get the N elements from a RDD ordered in ascending order or as + Get the N elements from an RDD ordered in ascending order or as specified by the optional key function. Note that this method should only be used if the resulting array is expected diff --git a/python/pyspark/streaming/kafka.py b/python/pyspark/streaming/kafka.py index bf27d8047a..134424add3 100644 --- a/python/pyspark/streaming/kafka.py +++ b/python/pyspark/streaming/kafka.py @@ -144,7 +144,7 @@ class KafkaUtils(object): """ .. note:: Experimental - Create a RDD from Kafka using offset ranges for each topic and partition. + Create an RDD from Kafka using offset ranges for each topic and partition. :param sc: SparkContext object :param kafkaParams: Additional params for Kafka @@ -155,7 +155,7 @@ class KafkaUtils(object): :param valueDecoder: A function used to decode value (default is utf8_decoder) :param messageHandler: A function used to convert KafkaMessageAndMetadata. You can assess meta using messageHandler (default is None). - :return: A RDD object + :return: An RDD object """ if leaders is None: leaders = dict() |