Skip to content

BUG: dtype=object should stop conversion from object in frame constructo... #2291

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 3 commits into from
Nov 24, 2012
Merged

BUG: dtype=object should stop conversion from object in frame constructo... #2291

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ade95fc
BUG: dtype=object should stop conversion from object in frame constru…
Nov 19, 2012
f2941c2
CLN: put new kwd at the end
Nov 19, 2012
b5ea387
Get rid of newline. Triggering Travis
changhiskhan Nov 20, 2012
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
33 changes: 19 additions & 14 deletions pandas/core/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -402,8 +402,7 @@ def __init__(self, data=None, index=None, columns=None, dtype=None,
index = _get_names_from_index(data)

if isinstance(data[0], (list, tuple, dict, Series)):
arrays, columns = _to_arrays(data, columns)

arrays, columns = _to_arrays(data, columns, dtype=dtype)
columns = _ensure_index(columns)

if index is None:
Expand Down Expand Up @@ -5159,38 +5158,43 @@ def _rec_to_dict(arr):
return columns, sdict


def _to_arrays(data, columns, coerce_float=False):
def _to_arrays(data, columns, coerce_float=False, dtype=None):
"""
Return list of arrays, columns
"""

if len(data) == 0:
return [], columns if columns is not None else []
if isinstance(data[0], (list, tuple)):
return _list_to_arrays(data, columns, coerce_float=coerce_float)
return _list_to_arrays(data, columns, coerce_float=coerce_float,
dtype=dtype)
elif isinstance(data[0], dict):
return _list_of_dict_to_arrays(data, columns,
coerce_float=coerce_float)
coerce_float=coerce_float,
dtype=dtype)
elif isinstance(data[0], Series):
return _list_of_series_to_arrays(data, columns,
coerce_float=coerce_float)
coerce_float=coerce_float,
dtype=dtype)
else:
# last ditch effort
data = map(tuple, data)
return _list_to_arrays(data, columns, coerce_float=coerce_float)
return _list_to_arrays(data, columns,
coerce_float=coerce_float,
dtype=dtype)


def _list_to_arrays(data, columns, coerce_float=False):
def _list_to_arrays(data, columns, coerce_float=False, dtype=None):
if len(data) > 0 and isinstance(data[0], tuple):
content = list(lib.to_object_array_tuples(data).T)
else:
# list of lists
content = list(lib.to_object_array(data).T)
return _convert_object_array(content, columns,
return _convert_object_array(content, columns, dtype=dtype,
coerce_float=coerce_float)


def _list_of_series_to_arrays(data, columns, coerce_float=False):
def _list_of_series_to_arrays(data, columns, coerce_float=False, dtype=None):
from pandas.core.index import _get_combined_index

if columns is None:
Expand All @@ -5211,13 +5215,13 @@ def _list_of_series_to_arrays(data, columns, coerce_float=False):

if values.dtype == np.object_:
content = list(values.T)
return _convert_object_array(content, columns,
return _convert_object_array(content, columns, dtype=dtype,
coerce_float=coerce_float)
else:
return values.T, columns


def _list_of_dict_to_arrays(data, columns, coerce_float=False):
def _list_of_dict_to_arrays(data, columns, coerce_float=False, dtype=None):
if columns is None:
gen = (x.keys() for x in data)
columns = lib.fast_unique_multiple_list_gen(gen)
Expand All @@ -5228,11 +5232,11 @@ def _list_of_dict_to_arrays(data, columns, coerce_float=False):
for d in data]

content = list(lib.dicts_to_array(data, list(columns)).T)
return _convert_object_array(content, columns,
return _convert_object_array(content, columns, dtype=dtype,
coerce_float=coerce_float)


def _convert_object_array(content, columns, coerce_float=False):
def _convert_object_array(content, columns, coerce_float=False, dtype=None):
if columns is None:
columns = _default_index(len(content))
else:
Expand All @@ -5241,6 +5245,7 @@ def _convert_object_array(content, columns, coerce_float=False):
'columns' % (len(columns), len(content)))

arrays = [lib.maybe_convert_objects(arr, try_float=coerce_float)
if dtype != object and dtype != np.object else arr
for arr in content]

return arrays, columns
Expand Down
6 changes: 6 additions & 0 deletions pandas/tests/test_frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1730,6 +1730,12 @@ def test_constructor_dtype_nocast_view(self):
should_be_view[0][0] = 97
self.assertEqual(df.values[0, 0], 97)

def test_constructor_dtype_list_data(self):
df = DataFrame([[1, '2'],
[None, 'a']], dtype=object)
self.assert_(df.ix[1, 0] is None)
self.assert_(df.ix[0, 1] == '2')

def test_constructor_rec(self):
rec = self.frame.to_records(index=False)

Expand Down