[SPARK-16992][PYSPARK] use map comprehension in doc
Code is equivalent, but map comprehency is most of the time faster than a map. Author: Gaetan Semet <gaetan@xeberon.net> Closes #14863 from Stibbons/map_comprehension.
This commit is contained in:
parent
4efcdb7fea
commit
b3c2291228
|
@ -29,7 +29,7 @@ if __name__ == "__main__":
|
|||
.getOrCreate()
|
||||
|
||||
# $example on$
|
||||
data = [(0, 18.0,), (1, 19.0,), (2, 8.0,), (3, 5.0,), (4, 2.2,)]
|
||||
data = [(0, 18.0), (1, 19.0), (2, 8.0), (3, 5.0), (4, 2.2)]
|
||||
df = spark.createDataFrame(data, ["id", "hour"])
|
||||
# $example off$
|
||||
|
||||
|
|
|
@ -32,8 +32,8 @@ if __name__ == "__main__":
|
|||
|
||||
# $example on$
|
||||
df = spark.createDataFrame([
|
||||
Row(userFeatures=Vectors.sparse(3, {0: -2.0, 1: 2.3}),),
|
||||
Row(userFeatures=Vectors.dense([-2.0, 2.3, 0.0]),)])
|
||||
Row(userFeatures=Vectors.sparse(3, {0: -2.0, 1: 2.3})),
|
||||
Row(userFeatures=Vectors.dense([-2.0, 2.3, 0.0]))])
|
||||
|
||||
slicer = VectorSlicer(inputCol="userFeatures", outputCol="features", indices=[1])
|
||||
|
||||
|
|
|
@ -79,7 +79,7 @@ if __name__ == "__main__":
|
|||
|
||||
# You can also use DataFrames to create temporary views within a SparkSession.
|
||||
Record = Row("key", "value")
|
||||
recordsDF = spark.createDataFrame(map(lambda i: Record(i, "val_" + str(i)), range(1, 101)))
|
||||
recordsDF = spark.createDataFrame([Record(i, "val_" + str(i)) for i in range(1, 101)])
|
||||
recordsDF.createOrReplaceTempView("records")
|
||||
|
||||
# Queries can then join DataFrame data with data stored in Hive.
|
||||
|
|
Loading…
Reference in a new issue