AlenkaF commented on a change in pull request #12311:
URL: https://github.com/apache/arrow/pull/12311#discussion_r800638755
##########
File path: python/pyarrow/table.pxi
##########
@@ -1779,15 +1796,41 @@ cdef class Table(_PandasConvertible):
<pyarrow.lib.Table object at 0x7f05d1fb1b40>
"""
from pyarrow.pandas_compat import dataframe_to_arrays
- arrays, schema = dataframe_to_arrays(
+ arrays, schema, n_rows = dataframe_to_arrays(
df,
schema=schema,
preserve_index=preserve_index,
nthreads=nthreads,
columns=columns,
safe=safe
)
- return cls.from_arrays(arrays, schema=schema)
+
+ cdef:
+ vector[shared_ptr[CChunkedArray]] arr
+ shared_ptr[CSchema] c_schema
+ # If df is empty but row index is not, create empty Table with rows >0
+ if n_rows:
+ names = None
+ metadata = None
+ converted_arrays = _sanitize_arrays(arrays, names, schema,
metadata,
+ &c_schema)
+ arr.reserve(0)
+ for item in converted_arrays:
+ if isinstance(item, Array):
+ arr.push_back(
+ make_shared[CChunkedArray](
+ (<Array> item).sp_array
+ )
+ )
+ elif isinstance(item, ChunkedArray):
+ arr.push_back((<ChunkedArray> item).sp_chunked_array)
+ else:
+ raise TypeError(type(item))
Review comment:
Creating an empty cython vector and converting schema to cython is
simplified now, thank you for the live help!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
