[
https://issues.apache.org/jira/browse/SPARK-52266?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Xinrong Meng updated SPARK-52266:
---------------------------------
Description:
{code:java}
>>> pdf = pd.DataFrame({"a": ["x"], "b": [0]})
>>> pdf
a b
0 x 0
>>> psdf = ps.from_pandas(pdf)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/xinrong.meng/spark/python/pyspark/pandas/namespace.py", line
187, in from_pandas
return DataFrame(pobj)
File "/Users/xinrong.meng/spark/python/pyspark/pandas/frame.py", line 573, in
__init__
internal = InternalFrame.from_pandas(pdf)
File "/Users/xinrong.meng/spark/python/pyspark/pandas/internal.py", line
1480, in from_pandas
) = InternalFrame.prepare_pandas_frame(pdf,
prefer_timestamp_ntz=prefer_timestamp_ntz)
File "/Users/xinrong.meng/spark/python/pyspark/pandas/internal.py", line
1581, in prepare_pandas_frame
spark_type = infer_pd_series_spark_type(reset_index[col], dtype,
prefer_timestamp_ntz)
File "/Users/xinrong.meng/spark/python/pyspark/pandas/typedef/typehints.py",
line 368, in infer_pd_series_spark_type
return from_arrow_type(pa.Array.from_pandas(pser).type,
prefer_timestamp_ntz)
File "pyarrow/array.pxi", line 1115, in pyarrow.lib.Array.from_pandas
File "pyarrow/array.pxi", line 339, in pyarrow.lib.array
File "pyarrow/array.pxi", line 85, in pyarrow.lib._ndarray_to_array
File "pyarrow/error.pxi", line 91, in pyarrow.lib.check_status
pyarrow.lib.ArrowTypeError: Input object was not a NumPy array
>>>
{code}
{code:java}
>>> pd.__version__
'2.2.3'
>>> pa.__version__
'15.0.2'
>>> np.__version__
'2.0.2' {code}
was:
{code:java}
>>> pdf = pd.DataFrame({"a": ["x"], "b": [0]})
>>> pdf
a b
0 x 0
>>> psdf = ps.from_pandas(pdf)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/xinrong.meng/spark/python/pyspark/pandas/namespace.py", line
187, in from_pandas
return DataFrame(pobj)
File "/Users/xinrong.meng/spark/python/pyspark/pandas/frame.py", line 573, in
__init__
internal = InternalFrame.from_pandas(pdf)
File "/Users/xinrong.meng/spark/python/pyspark/pandas/internal.py", line
1480, in from_pandas
) = InternalFrame.prepare_pandas_frame(pdf,
prefer_timestamp_ntz=prefer_timestamp_ntz)
File "/Users/xinrong.meng/spark/python/pyspark/pandas/internal.py", line
1581, in prepare_pandas_frame
spark_type = infer_pd_series_spark_type(reset_index[col], dtype,
prefer_timestamp_ntz)
File "/Users/xinrong.meng/spark/python/pyspark/pandas/typedef/typehints.py",
line 368, in infer_pd_series_spark_type
return from_arrow_type(pa.Array.from_pandas(pser).type,
prefer_timestamp_ntz)
File "pyarrow/array.pxi", line 1115, in pyarrow.lib.Array.from_pandas
File "pyarrow/array.pxi", line 339, in pyarrow.lib.array
File "pyarrow/array.pxi", line 85, in pyarrow.lib._ndarray_to_array
File "pyarrow/error.pxi", line 91, in pyarrow.lib.check_status
pyarrow.lib.ArrowTypeError: Input object was not a NumPy array
>>> {code}
> Arrow fails to infer the schema with string and int column when creating a
> DataFrame
> ------------------------------------------------------------------------------------
>
> Key: SPARK-52266
> URL: https://issues.apache.org/jira/browse/SPARK-52266
> Project: Spark
> Issue Type: Sub-task
> Components: PS
> Affects Versions: 4.1.0
> Reporter: Xinrong Meng
> Priority: Major
>
> {code:java}
> >>> pdf = pd.DataFrame({"a": ["x"], "b": [0]})
> >>> pdf
> a b
> 0 x 0
> >>> psdf = ps.from_pandas(pdf)
> Traceback (most recent call last):
> File "<stdin>", line 1, in <module>
> File "/Users/xinrong.meng/spark/python/pyspark/pandas/namespace.py", line
> 187, in from_pandas
> return DataFrame(pobj)
> File "/Users/xinrong.meng/spark/python/pyspark/pandas/frame.py", line 573,
> in __init__
> internal = InternalFrame.from_pandas(pdf)
> File "/Users/xinrong.meng/spark/python/pyspark/pandas/internal.py", line
> 1480, in from_pandas
> ) = InternalFrame.prepare_pandas_frame(pdf,
> prefer_timestamp_ntz=prefer_timestamp_ntz)
> File "/Users/xinrong.meng/spark/python/pyspark/pandas/internal.py", line
> 1581, in prepare_pandas_frame
> spark_type = infer_pd_series_spark_type(reset_index[col], dtype,
> prefer_timestamp_ntz)
> File
> "/Users/xinrong.meng/spark/python/pyspark/pandas/typedef/typehints.py", line
> 368, in infer_pd_series_spark_type
> return from_arrow_type(pa.Array.from_pandas(pser).type,
> prefer_timestamp_ntz)
> File "pyarrow/array.pxi", line 1115, in pyarrow.lib.Array.from_pandas
> File "pyarrow/array.pxi", line 339, in pyarrow.lib.array
> File "pyarrow/array.pxi", line 85, in pyarrow.lib._ndarray_to_array
> File "pyarrow/error.pxi", line 91, in pyarrow.lib.check_status
> pyarrow.lib.ArrowTypeError: Input object was not a NumPy array
> >>>
> {code}
>
> {code:java}
> >>> pd.__version__
> '2.2.3'
> >>> pa.__version__
> '15.0.2'
> >>> np.__version__
> '2.0.2' {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
