Skip to content

[SPARK-2854][SQL] Finalize _acceptable_types in pyspark.sql #1793

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
wants to merge 2 commits into from
Closed

[SPARK-2854][SQL] Finalize _acceptable_types in pyspark.sql #1793

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c2b23dd
Do data type conversions based on the specified Spark SQL data type.
yhuai Aug 5, 2014
32f0708
LongType only accepts long values.
yhuai Aug 5, 2014
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
29 changes: 20 additions & 9 deletions python/pyspark/sql.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -672,12 +672,12 @@ def _infer_schema_type(obj, dataType):
ByteType: (int, long),
ShortType: (int, long),
IntegerType: (int, long),
LongType: (int, long),
LongType: (long,),
FloatType: (float,),
DoubleType: (float,),
DecimalType: (decimal.Decimal,),
StringType: (str, unicode),
TimestampType: (datetime.datetime, datetime.time, datetime.date),
TimestampType: (datetime.datetime,),
ArrayType: (list, tuple, array),
MapType: (dict,),
StructType: (tuple, list),
Expand Down Expand Up @@ -1042,12 +1042,15 @@ def applySchema(self, rdd, schema):
[Row(field1=1, field2=u'row1'),..., Row(field1=3, field2=u'row3')]

>>> from datetime import datetime
>>> rdd = sc.parallelize([(127, -32768, 1.0,
>>> rdd = sc.parallelize([(127, -128L, -32768, 32767, 2147483647L, 1.0,
... datetime(2010, 1, 1, 1, 1, 1),
... {"a": 1}, (2,), [1, 2, 3], None)])
>>> schema = StructType([
... StructField("byte", ByteType(), False),
... StructField("short", ShortType(), False),
... StructField("byte1", ByteType(), False),
... StructField("byte2", ByteType(), False),
... StructField("short1", ShortType(), False),
... StructField("short2", ShortType(), False),
... StructField("int", IntegerType(), False),
... StructField("float", FloatType(), False),
... StructField("time", TimestampType(), False),
... StructField("map",
Expand All @@ -1056,11 +1059,19 @@ def applySchema(self, rdd, schema):
... StructType([StructField("b", ShortType(), False)]), False),
... StructField("list", ArrayType(ByteType(), False), False),
... StructField("null", DoubleType(), True)])
>>> srdd = sqlCtx.applySchema(rdd, schema).map(
... lambda x: (x.byte, x.short, x.float, x.time,
>>> srdd = sqlCtx.applySchema(rdd, schema)
>>> results = srdd.map(
... lambda x: (x.byte1, x.byte2, x.short1, x.short2, x.int, x.float, x.time,
... x.map["a"], x.struct.b, x.list, x.null))
>>> srdd.collect()[0]
(127, -32768, 1.0, ...(2010, 1, 1, 1, 1, 1), 1, 2, [1, 2, 3], None)
>>> results.collect()[0]
(127, -128, -32768, 32767, 2147483647, 1.0, ...(2010, 1, 1, 1, 1, 1), 1, 2, [1, 2, 3], None)
Copy link
Contributor

Choose a reason for hiding this comment

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

This line is too long, it could be "...2010...1, 2, [1, 2, 3], None)"


>>> srdd.registerTempTable("table2")
>>> sqlCtx.sql(
... "SELECT byte1 - 1 AS byte1, byte2 + 1 AS byte2, " +
... "short1 + 1 AS short1, short2 - 1 AS short2, int - 1 AS int, " +
... "float + 1.1 as float FROM table2").collect()
[Row(byte1=126, byte2=-127, short1=-32767, short2=32766, int=2147483646, float=2.1)]

>>> rdd = sc.parallelize([(127, -32768, 1.0,
... datetime(2010, 1, 1, 1, 1, 1),
Expand Down
3 changes: 3 additions & 0 deletions sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -491,7 +491,10 @@ class SQLContext(@transient val sparkContext: SparkContext)
new java.sql.Timestamp(c.getTime().getTime())

case (c: Int, ByteType) => c.toByte
case (c: Long, ByteType) => c.toByte
case (c: Int, ShortType) => c.toShort
case (c: Long, ShortType) => c.toShort
case (c: Long, IntegerType) => c.toInt
case (c: Double, FloatType) => c.toFloat
case (c, StringType) if !c.isInstanceOf[String] => c.toString

Expand Down