Skip to content

Regression raising Error when having dup cols with single dtype for read csv #42030

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

Merged
merged 2 commits into from
Jun 16, 2021
Merged

Regression raising Error when having dup cols with single dtype for read csv #42030

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
0287a25
Regression raising Error when having dup cols with single dtype for r…
phofl Jun 15, 2021
72d1ed4
Use is_dict_like
phofl Jun 15, 2021
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
2 changes: 2 additions & 0 deletions pandas/_libs/parsers.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,6 +108,7 @@ from pandas.core.dtypes.common import (
is_object_dtype,
)
from pandas.core.dtypes.dtypes import CategoricalDtype
from pandas.core.dtypes.inference import is_dict_like

cdef:
float64_t INF = <float64_t>np.inf
Expand Down Expand Up @@ -689,6 +690,7 @@ cdef class TextReader:
count = counts.get(name, 0)
if (
self.dtype is not None
and is_dict_like(self.dtype)
and self.dtype.get(old_name) is not None
and self.dtype.get(name) is None
):
Expand Down
2 changes: 2 additions & 0 deletions pandas/io/parsers/python_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@
)

from pandas.core.dtypes.common import is_integer
from pandas.core.dtypes.inference import is_dict_like

from pandas.io.parsers.base_parser import (
ParserBase,
Expand Down Expand Up @@ -424,6 +425,7 @@ def _infer_columns(self):
cur_count = counts[col]
if (
self.dtype is not None
and is_dict_like(self.dtype)
and self.dtype.get(old_col) is not None
and self.dtype.get(col) is None
):
Expand Down
9 changes: 9 additions & 0 deletions pandas/tests/io/parser/dtypes/test_dtypes_basic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -248,3 +248,12 @@ def test_dtype_mangle_dup_cols(all_parsers, dtypes, exp_value):
result = parser.read_csv(StringIO(data), dtype={"a": str, **dtypes})
expected = DataFrame({"a": ["1"], "a.1": [exp_value]})
tm.assert_frame_equal(result, expected)


def test_dtype_mangle_dup_cols_single_dtype(all_parsers):
# GH#42022
parser = all_parsers
data = """a,a\n1,1"""
result = parser.read_csv(StringIO(data), dtype=str)
expected = DataFrame({"a": ["1"], "a.1": ["1"]})
tm.assert_frame_equal(result, expected)