Skip to content

[SPARK-12380] [PYSPARK] use SQLContext.getOrCreate in mllib #10338

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
davies wants to merge 2 commits into from
Closed

[SPARK-12380] [PYSPARK] use SQLContext.getOrCreate in mllib #10338

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9ae9bd4
use SQLContext.getOrCreate in mllib
Dec 16, 2015
518e37c
address comments
Dec 16, 2015
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions python/pyspark/mllib/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,7 @@ def _java2py(sc, r, encoding="bytes"):
return RDD(jrdd, sc)

if clsName == 'DataFrame':
return DataFrame(r, SQLContext(sc))
return DataFrame(r, SQLContext.getOrCreate(sc))

if clsName in _picklable_classes:
r = sc._jvm.SerDe.dumps(r)
Expand All @@ -125,7 +125,7 @@ def callJavaFunc(sc, func, *args):

def callMLlibFunc(name, *args):
""" Call API in PythonMLLibAPI """
sc = SparkContext._active_spark_context
sc = SparkContext.getOrCreate()
api = getattr(sc._jvm.PythonMLLibAPI(), name)
return callJavaFunc(sc, api, *args)

Expand All @@ -135,7 +135,7 @@ class JavaModelWrapper(object):
Wrapper for the model in JVM
"""
def __init__(self, java_model):
self._sc = SparkContext._active_spark_context
self._sc = SparkContext.getOrCreate()
self._java_model = java_model

def __del__(self):
Expand Down
10 changes: 5 additions & 5 deletions python/pyspark/mllib/evaluation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ class BinaryClassificationMetrics(JavaModelWrapper):

def __init__(self, scoreAndLabels):
sc = scoreAndLabels.ctx
sql_ctx = SQLContext(sc)
sql_ctx = SQLContext.getOrCreate(sc)
df = sql_ctx.createDataFrame(scoreAndLabels, schema=StructType([
StructField("score", DoubleType(), nullable=False),
StructField("label", DoubleType(), nullable=False)]))
Expand Down Expand Up @@ -103,7 +103,7 @@ class RegressionMetrics(JavaModelWrapper):

def __init__(self, predictionAndObservations):
sc = predictionAndObservations.ctx
sql_ctx = SQLContext(sc)
sql_ctx = SQLContext.getOrCreate(sc)
df = sql_ctx.createDataFrame(predictionAndObservations, schema=StructType([
StructField("prediction", DoubleType(), nullable=False),
StructField("observation", DoubleType(), nullable=False)]))
Expand Down Expand Up @@ -197,7 +197,7 @@ class MulticlassMetrics(JavaModelWrapper):

def __init__(self, predictionAndLabels):
sc = predictionAndLabels.ctx
sql_ctx = SQLContext(sc)
sql_ctx = SQLContext.getOrCreate(sc)
df = sql_ctx.createDataFrame(predictionAndLabels, schema=StructType([
StructField("prediction", DoubleType(), nullable=False),
StructField("label", DoubleType(), nullable=False)]))
Expand Down Expand Up @@ -338,7 +338,7 @@ class RankingMetrics(JavaModelWrapper):

def __init__(self, predictionAndLabels):
sc = predictionAndLabels.ctx
sql_ctx = SQLContext(sc)
sql_ctx = SQLContext.getOrCreate(sc)
df = sql_ctx.createDataFrame(predictionAndLabels,
schema=sql_ctx._inferSchema(predictionAndLabels))
java_model = callMLlibFunc("newRankingMetrics", df._jdf)
Expand Down Expand Up @@ -424,7 +424,7 @@ class MultilabelMetrics(JavaModelWrapper):

def __init__(self, predictionAndLabels):
sc = predictionAndLabels.ctx
sql_ctx = SQLContext(sc)
sql_ctx = SQLContext.getOrCreate(sc)
df = sql_ctx.createDataFrame(predictionAndLabels,
schema=sql_ctx._inferSchema(predictionAndLabels))
java_class = sc._jvm.org.apache.spark.mllib.evaluation.MultilabelMetrics
Expand Down
3 changes: 1 addition & 2 deletions python/pyspark/mllib/feature.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,8 +100,7 @@ def transform(self, vector):
:return: normalized vector. If the norm of the input is zero, it
will return the input vector.
"""
sc = SparkContext._active_spark_context
assert sc is not None, "SparkContext should be initialized first"
sc = SparkContext.getOrCreate()

@jkbradley jkbradley Dec 16, 2015

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actually, sc is not even used here, so it could be removed.

if isinstance(vector, RDD):
vector = vector.map(_convert_to_vector)
else:
Expand Down