diff options
author | Davies Liu <davies@databricks.com> | 2015-02-18 14:17:04 -0800 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2015-02-18 14:17:04 -0800 |
commit | aa8f10e82a743d59ce87348af19c0177eb618a66 (patch) | |
tree | 87fc8bfc978015fcf3d7ff9ff2aa3717b0885f28 /python/pyspark/sql/types.py | |
parent | f0e3b71077a6c28aba29a7a75e901a9e0911b9f0 (diff) | |
download | spark-aa8f10e82a743d59ce87348af19c0177eb618a66.tar.gz spark-aa8f10e82a743d59ce87348af19c0177eb618a66.tar.bz2 spark-aa8f10e82a743d59ce87348af19c0177eb618a66.zip |
[SPARK-5722] [SQL] [PySpark] infer int as LongType
The `int` is 64-bit on 64-bit machine (very common now), we should infer it as LongType for it in Spark SQL.
Also, LongType in SQL will come back as `int`.
Author: Davies Liu <davies@databricks.com>
Closes #4666 from davies/long and squashes the following commits:
6bc6cc4 [Davies Liu] infer int as LongType
Diffstat (limited to 'python/pyspark/sql/types.py')
-rw-r--r-- | python/pyspark/sql/types.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/python/pyspark/sql/types.py b/python/pyspark/sql/types.py index 40bd7e54a9..9409c6f9f6 100644 --- a/python/pyspark/sql/types.py +++ b/python/pyspark/sql/types.py @@ -583,7 +583,7 @@ def _parse_datatype_json_value(json_value): _type_mappings = { type(None): NullType, bool: BooleanType, - int: IntegerType, + int: LongType, long: LongType, float: DoubleType, str: StringType, @@ -933,11 +933,11 @@ def _infer_schema_type(obj, dataType): >>> schema = _parse_schema_abstract("a b c d") >>> row = (1, 1.0, "str", datetime.date(2014, 10, 10)) >>> _infer_schema_type(row, schema) - StructType...IntegerType...DoubleType...StringType...DateType... + StructType...LongType...DoubleType...StringType...DateType... >>> row = [[1], {"key": (1, 2.0)}] >>> schema = _parse_schema_abstract("a[] b{c d}") >>> _infer_schema_type(row, schema) - StructType...a,ArrayType...b,MapType(StringType,...c,IntegerType... + StructType...a,ArrayType...b,MapType(StringType,...c,LongType... """ if dataType is None: return _infer_type(obj) @@ -992,7 +992,7 @@ def _verify_type(obj, dataType): >>> _verify_type(None, StructType([])) >>> _verify_type("", StringType()) - >>> _verify_type(0, IntegerType()) + >>> _verify_type(0, LongType()) >>> _verify_type(range(3), ArrayType(ShortType())) >>> _verify_type(set(), ArrayType(StringType())) # doctest: +IGNORE_EXCEPTION_DETAIL Traceback (most recent call last): |