Skip to content

fix python #9

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

Merged
merged 1 commit into from
Mar 10, 2016
Merged

fix python #9

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
140 changes: 70 additions & 70 deletions python/pyspark/sql/tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -528,76 +528,76 @@ def check_datatype(datatype):
_verify_type(PythonOnlyPoint(1.0, 2.0), PythonOnlyUDT())
self.assertRaises(ValueError, lambda: _verify_type([1.0, 2.0], PythonOnlyUDT()))

# def test_infer_schema_with_udt(self):
# from pyspark.sql.tests import ExamplePoint, ExamplePointUDT
# row = Row(label=1.0, point=ExamplePoint(1.0, 2.0))
# df = self.sqlCtx.createDataFrame([row])
# schema = df.schema
# field = [f for f in schema.fields if f.name == "point"][0]
# self.assertEqual(type(field.dataType), ExamplePointUDT)
# df.registerTempTable("labeled_point")
# point = self.sqlCtx.sql("SELECT point FROM labeled_point").head().point
# self.assertEqual(point, ExamplePoint(1.0, 2.0))

# row = Row(label=1.0, point=PythonOnlyPoint(1.0, 2.0))
# df = self.sqlCtx.createDataFrame([row])
# schema = df.schema
# field = [f for f in schema.fields if f.name == "point"][0]
# self.assertEqual(type(field.dataType), PythonOnlyUDT)
# df.registerTempTable("labeled_point")
# point = self.sqlCtx.sql("SELECT point FROM labeled_point").head().point
# self.assertEqual(point, PythonOnlyPoint(1.0, 2.0))

# def test_apply_schema_with_udt(self):
# from pyspark.sql.tests import ExamplePoint, ExamplePointUDT
# row = (1.0, ExamplePoint(1.0, 2.0))
# schema = StructType([StructField("label", DoubleType(), False),
# StructField("point", ExamplePointUDT(), False)])
# df = self.sqlCtx.createDataFrame([row], schema)
# point = df.head().point
# self.assertEqual(point, ExamplePoint(1.0, 2.0))

# row = (1.0, PythonOnlyPoint(1.0, 2.0))
# schema = StructType([StructField("label", DoubleType(), False),
# StructField("point", PythonOnlyUDT(), False)])
# df = self.sqlCtx.createDataFrame([row], schema)
# point = df.head().point
# self.assertEqual(point, PythonOnlyPoint(1.0, 2.0))

# def test_udf_with_udt(self):
# from pyspark.sql.tests import ExamplePoint, ExamplePointUDT
# row = Row(label=1.0, point=ExamplePoint(1.0, 2.0))
# df = self.sqlCtx.createDataFrame([row])
# self.assertEqual(1.0, df.rdd.map(lambda r: r.point.x).first())
# udf = UserDefinedFunction(lambda p: p.y, DoubleType())
# self.assertEqual(2.0, df.select(udf(df.point)).first()[0])
# udf2 = UserDefinedFunction(lambda p: ExamplePoint(p.x + 1, p.y + 1), ExamplePointUDT())
# self.assertEqual(ExamplePoint(2.0, 3.0), df.select(udf2(df.point)).first()[0])

# row = Row(label=1.0, point=PythonOnlyPoint(1.0, 2.0))
# df = self.sqlCtx.createDataFrame([row])
# self.assertEqual(1.0, df.rdd.map(lambda r: r.point.x).first())
# udf = UserDefinedFunction(lambda p: p.y, DoubleType())
# self.assertEqual(2.0, df.select(udf(df.point)).first()[0])
# udf2 = UserDefinedFunction(lambda p: PythonOnlyPoint(p.x + 1, p.y + 1), PythonOnlyUDT())
# self.assertEqual(PythonOnlyPoint(2.0, 3.0), df.select(udf2(df.point)).first()[0])

# def test_parquet_with_udt(self):
# from pyspark.sql.tests import ExamplePoint, ExamplePointUDT
# row = Row(label=1.0, point=ExamplePoint(1.0, 2.0))
# df0 = self.sqlCtx.createDataFrame([row])
# output_dir = os.path.join(self.tempdir.name, "labeled_point")
# df0.write.parquet(output_dir)
# df1 = self.sqlCtx.read.parquet(output_dir)
# point = df1.head().point
# self.assertEqual(point, ExamplePoint(1.0, 2.0))

# row = Row(label=1.0, point=PythonOnlyPoint(1.0, 2.0))
# df0 = self.sqlCtx.createDataFrame([row])
# df0.write.parquet(output_dir, mode='overwrite')
# df1 = self.sqlCtx.read.parquet(output_dir)
# point = df1.head().point
# self.assertEqual(point, PythonOnlyPoint(1.0, 2.0))
def test_infer_schema_with_udt(self):
from pyspark.sql.tests import ExamplePoint, ExamplePointUDT
row = Row(label=1.0, point=ExamplePoint(1.0, 2.0))
df = self.sqlCtx.createDataFrame([row])
schema = df.schema
field = [f for f in schema.fields if f.name == "point"][0]
self.assertEqual(type(field.dataType), ExamplePointUDT)
df.registerTempTable("labeled_point")
point = self.sqlCtx.sql("SELECT point FROM labeled_point").head().point
self.assertEqual(point, ExamplePoint(1.0, 2.0))

row = Row(label=1.0, point=PythonOnlyPoint(1.0, 2.0))
df = self.sqlCtx.createDataFrame([row])
schema = df.schema
field = [f for f in schema.fields if f.name == "point"][0]
self.assertEqual(type(field.dataType), PythonOnlyUDT)
df.registerTempTable("labeled_point")
point = self.sqlCtx.sql("SELECT point FROM labeled_point").head().point
self.assertEqual(point, PythonOnlyPoint(1.0, 2.0))

def test_apply_schema_with_udt(self):
from pyspark.sql.tests import ExamplePoint, ExamplePointUDT
row = (1.0, ExamplePoint(1.0, 2.0))
schema = StructType([StructField("label", DoubleType(), False),
StructField("point", ExamplePointUDT(), False)])
df = self.sqlCtx.createDataFrame([row], schema)
point = df.head().point
self.assertEqual(point, ExamplePoint(1.0, 2.0))

row = (1.0, PythonOnlyPoint(1.0, 2.0))
schema = StructType([StructField("label", DoubleType(), False),
StructField("point", PythonOnlyUDT(), False)])
df = self.sqlCtx.createDataFrame([row], schema)
point = df.head().point
self.assertEqual(point, PythonOnlyPoint(1.0, 2.0))

def test_udf_with_udt(self):
from pyspark.sql.tests import ExamplePoint, ExamplePointUDT
row = Row(label=1.0, point=ExamplePoint(1.0, 2.0))
df = self.sqlCtx.createDataFrame([row])
self.assertEqual(1.0, df.rdd.map(lambda r: r.point.x).first())
udf = UserDefinedFunction(lambda p: p.y, DoubleType())
self.assertEqual(2.0, df.select(udf(df.point)).first()[0])
udf2 = UserDefinedFunction(lambda p: ExamplePoint(p.x + 1, p.y + 1), ExamplePointUDT())
self.assertEqual(ExamplePoint(2.0, 3.0), df.select(udf2(df.point)).first()[0])

row = Row(label=1.0, point=PythonOnlyPoint(1.0, 2.0))
df = self.sqlCtx.createDataFrame([row])
self.assertEqual(1.0, df.rdd.map(lambda r: r.point.x).first())
udf = UserDefinedFunction(lambda p: p.y, DoubleType())
self.assertEqual(2.0, df.select(udf(df.point)).first()[0])
udf2 = UserDefinedFunction(lambda p: PythonOnlyPoint(p.x + 1, p.y + 1), PythonOnlyUDT())
self.assertEqual(PythonOnlyPoint(2.0, 3.0), df.select(udf2(df.point)).first()[0])

def test_parquet_with_udt(self):
from pyspark.sql.tests import ExamplePoint, ExamplePointUDT
row = Row(label=1.0, point=ExamplePoint(1.0, 2.0))
df0 = self.sqlCtx.createDataFrame([row])
output_dir = os.path.join(self.tempdir.name, "labeled_point")
df0.write.parquet(output_dir)
df1 = self.sqlCtx.read.parquet(output_dir)
point = df1.head().point
self.assertEqual(point, ExamplePoint(1.0, 2.0))

row = Row(label=1.0, point=PythonOnlyPoint(1.0, 2.0))
df0 = self.sqlCtx.createDataFrame([row])
df0.write.parquet(output_dir, mode='overwrite')
df1 = self.sqlCtx.read.parquet(output_dir)
point = df1.head().point
self.assertEqual(point, PythonOnlyPoint(1.0, 2.0))

def test_unionAll_with_udt(self):
from pyspark.sql.tests import ExamplePoint, ExamplePointUDT
Expand Down
10 changes: 8 additions & 2 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/encoders/RowEncoder.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,8 @@ object RowEncoder {
case NullType | BooleanType | ByteType | ShortType | IntegerType | LongType |
FloatType | DoubleType | BinaryType | CalendarIntervalType => inputObject

case p: PythonUserDefinedType => extractorsFor(inputObject, p.sqlType)

case udt: UserDefinedType[_] =>
val obj = NewInstance(
udt.userClass.getAnnotation(classOf[SQLUserDefinedType]).udt(),
Expand Down Expand Up @@ -151,10 +153,14 @@ object RowEncoder {

private def constructorFor(schema: StructType): Expression = {
val fields = schema.zipWithIndex.map { case (f, i) =>
val field = BoundReference(i, f.dataType, f.nullable)
val dt = f.dataType match {
case p: PythonUserDefinedType => p.sqlType
case other => other
}
val field = BoundReference(i, dt, f.nullable)
If(
IsNull(field),
Literal.create(null, externalDataTypeFor(f.dataType)),
Literal.create(null, externalDataTypeFor(dt)),
constructorFor(field)
)
}
Expand Down