From b3c22912284c2a010a4af3c43dc5e6fd53c68f8c Mon Sep 17 00:00:00 2001
From: Gaetan Semet <gaetan@xeberon.net>
Date: Mon, 12 Sep 2016 12:21:33 +0100
Subject: [PATCH] [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.
---
examples/src/main/python/ml/quantile_discretizer_example.py | 2 +-
examples/src/main/python/ml/vector_slicer_example.py | 4 ++--
examples/src/main/python/sql/hive.py | 2 +-
3 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/examples/src/main/python/ml/quantile_discretizer_example.py b/examples/src/main/python/ml/quantile_discretizer_example.py
index 788a0baffe..0fc1d1949a 100644
--- a/examples/src/main/python/ml/quantile_discretizer_example.py
+++ b/examples/src/main/python/ml/quantile_discretizer_example.py
@@ -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"])
# $example off$
diff --git a/examples/src/main/python/ml/vector_slicer_example.py b/examples/src/main/python/ml/vector_slicer_example.py
index d2f46b190f..68c8cfe27e 100644
--- a/examples/src/main/python/ml/vector_slicer_example.py
+++ b/examples/src/main/python/ml/vector_slicer_example.py
@@ -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])
diff --git a/examples/src/main/python/sql/hive.py b/examples/src/main/python/sql/hive.py
index 9b2a2c4e6a..98b48908b5 100644
--- a/examples/src/main/python/sql/hive.py
+++ b/examples/src/main/python/sql/hive.py
@@ -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.
--
GitLab