[
https://issues.apache.org/jira/browse/SPARK-41900?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Sandeep Singh updated SPARK-41900:
----------------------------------
Description:
{code:java}
import numpy as np
from pyspark.sql.functions import lit
dtype_to_spark_dtypes = [
(np.int8, [("CAST(1 AS TINYINT)", "tinyint")]),
(np.int16, [("CAST(1 AS SMALLINT)", "smallint")]),
(np.int32, [("CAST(1 AS INT)", "int")]),
(np.int64, [("CAST(1 AS BIGINT)", "bigint")]),
(np.float32, [("CAST(1.0 AS FLOAT)", "float")]),
(np.float64, [("CAST(1.0 AS DOUBLE)", "double")]),
(np.bool_, [("true", "boolean")]),
]
for dtype, spark_dtypes in dtype_to_spark_dtypes:
self.assertEqual(self.spark.range(1).select(lit(dtype(1))).dtypes,
spark_dtypes){code}
{code:java}
Traceback (most recent call last):
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_functions.py",
line 1064, in test_lit_np_scalar
self.assertEqual(self.spark.range(1).select(lit(dtype(1))).dtypes,
spark_dtypes)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/utils.py", line
332, in wrapped
return getattr(functions, f.__name__)(*args, **kwargs)
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 198, in lit
return Column(LiteralExpression._from_value(col))
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/expressions.py",
line 266, in _from_value
return LiteralExpression(value=value,
dataType=LiteralExpression._infer_type(value))
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/expressions.py",
line 262, in _infer_type
raise ValueError(f"Unsupported Data Type {type(value).__name__}")
ValueError: Unsupported Data Type int8
{code}
was:
{code:java}
row = self.spark.createDataFrame([("Alice", None, None, None)],
schema).fillna(True).first()
self.assertEqual(row.age, None){code}
{code:java}
Traceback (most recent call last):
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py",
line 231, in test_fillna
self.assertEqual(row.age, None)
AssertionError: nan != None{code}
{code:java}
row = (
self.spark.createDataFrame([("Alice", 10, None)], schema)
.replace(10, 20, subset=["name", "height"])
.first()
)
self.assertEqual(row.name, "Alice")
self.assertEqual(row.age, 10)
self.assertEqual(row.height, None) {code}
{code:java}
Traceback (most recent call last): File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_dataframe.py",
line 372, in test_replace self.assertEqual(row.height, None)
AssertionError: nan != None
{code}
> Support data type int8
> ----------------------
>
> Key: SPARK-41900
> URL: https://issues.apache.org/jira/browse/SPARK-41900
> Project: Spark
> Issue Type: Sub-task
> Components: Connect
> Affects Versions: 3.4.0
> Reporter: Sandeep Singh
> Priority: Major
>
> {code:java}
> import numpy as np
> from pyspark.sql.functions import lit
> dtype_to_spark_dtypes = [
> (np.int8, [("CAST(1 AS TINYINT)", "tinyint")]),
> (np.int16, [("CAST(1 AS SMALLINT)", "smallint")]),
> (np.int32, [("CAST(1 AS INT)", "int")]),
> (np.int64, [("CAST(1 AS BIGINT)", "bigint")]),
> (np.float32, [("CAST(1.0 AS FLOAT)", "float")]),
> (np.float64, [("CAST(1.0 AS DOUBLE)", "double")]),
> (np.bool_, [("true", "boolean")]),
> ]
> for dtype, spark_dtypes in dtype_to_spark_dtypes:
> self.assertEqual(self.spark.range(1).select(lit(dtype(1))).dtypes,
> spark_dtypes){code}
> {code:java}
> Traceback (most recent call last):
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_functions.py",
> line 1064, in test_lit_np_scalar
> self.assertEqual(self.spark.range(1).select(lit(dtype(1))).dtypes,
> spark_dtypes)
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/utils.py", line
> 332, in wrapped
> return getattr(functions, f.__name__)(*args, **kwargs)
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
> line 198, in lit
> return Column(LiteralExpression._from_value(col))
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/expressions.py",
> line 266, in _from_value
> return LiteralExpression(value=value,
> dataType=LiteralExpression._infer_type(value))
> File
> "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/expressions.py",
> line 262, in _infer_type
> raise ValueError(f"Unsupported Data Type {type(value).__name__}")
> ValueError: Unsupported Data Type int8
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
