diff options
Diffstat (limited to 'python')
| -rw-r--r-- | python/pyspark/mllib/util.py | 8 | ||||
| -rw-r--r-- | python/pyspark/rdd.py | 4 | ||||
| -rw-r--r-- | python/pyspark/sql/dataframe.py | 2 | ||||
| -rw-r--r-- | python/pyspark/sql/streaming.py | 6 |
4 files changed, 10 insertions, 10 deletions
diff --git a/python/pyspark/mllib/util.py b/python/pyspark/mllib/util.py index 48867a08db..ed6fd4bca4 100644 --- a/python/pyspark/mllib/util.py +++ b/python/pyspark/mllib/util.py @@ -140,8 +140,8 @@ class MLUtils(object): >>> from pyspark.mllib.regression import LabeledPoint >>> from glob import glob >>> from pyspark.mllib.util import MLUtils - >>> examples = [LabeledPoint(1.1, Vectors.sparse(3, [(0, 1.23), (2, 4.56)])), \ - LabeledPoint(0.0, Vectors.dense([1.01, 2.02, 3.03]))] + >>> examples = [LabeledPoint(1.1, Vectors.sparse(3, [(0, 1.23), (2, 4.56)])), + ... LabeledPoint(0.0, Vectors.dense([1.01, 2.02, 3.03]))] >>> tempFile = NamedTemporaryFile(delete=True) >>> tempFile.close() >>> MLUtils.saveAsLibSVMFile(sc.parallelize(examples), tempFile.name) @@ -166,8 +166,8 @@ class MLUtils(object): >>> from tempfile import NamedTemporaryFile >>> from pyspark.mllib.util import MLUtils >>> from pyspark.mllib.regression import LabeledPoint - >>> examples = [LabeledPoint(1.1, Vectors.sparse(3, [(0, -1.23), (2, 4.56e-7)])), \ - LabeledPoint(0.0, Vectors.dense([1.01, 2.02, 3.03]))] + >>> examples = [LabeledPoint(1.1, Vectors.sparse(3, [(0, -1.23), (2, 4.56e-7)])), + ... LabeledPoint(0.0, Vectors.dense([1.01, 2.02, 3.03]))] >>> tempFile = NamedTemporaryFile(delete=True) >>> tempFile.close() >>> sc.parallelize(examples, 1).saveAsTextFile(tempFile.name) diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 0508235c1c..5fb10f86f4 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -754,8 +754,8 @@ class RDD(object): Applies a function to each partition of this RDD. >>> def f(iterator): - ... for x in iterator: - ... print(x) + ... for x in iterator: + ... print(x) >>> sc.parallelize([1, 2, 3, 4, 5]).foreachPartition(f) """ def func(it): diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 0f7d8fba3b..0ac481a8a8 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -61,7 +61,7 @@ class DataFrame(object): people = sqlContext.read.parquet("...") department = sqlContext.read.parquet("...") - people.filter(people.age > 30).join(department, people.deptId == department.id)\ + people.filter(people.age > 30).join(department, people.deptId == department.id) \\ .groupBy(department.name, "gender").agg({"salary": "avg", "age": "max"}) .. versionadded:: 1.3 diff --git a/python/pyspark/sql/streaming.py b/python/pyspark/sql/streaming.py index cbd827950b..4e438fd5be 100644 --- a/python/pyspark/sql/streaming.py +++ b/python/pyspark/sql/streaming.py @@ -315,9 +315,9 @@ class DataStreamReader(OptionUtils): :param schema: optional :class:`pyspark.sql.types.StructType` for the input schema. :param options: all other string options - >>> json_sdf = spark.readStream.format("json")\ - .schema(sdf_schema)\ - .load(tempfile.mkdtemp()) + >>> json_sdf = spark.readStream.format("json") \\ + ... .schema(sdf_schema) \\ + ... .load(tempfile.mkdtemp()) >>> json_sdf.isStreaming True >>> json_sdf.schema == sdf_schema |