Skip to content

Commit

Permalink
recommend from_dict(dict()) and from_dict(OrderedDict())
Browse files Browse the repository at this point in the history
  • Loading branch information
@reidy-p
reidy-p committed Jan 30, 2018
1 parent 4b986b3 commit c25f541
Show file tree
Hide file tree
Showing 7 changed files with 57 additions and 56 deletions.
2 changes: 1 addition & 1 deletion doc/source/whatsnew/v0.23.0.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -329,7 +329,7 @@ Deprecations
- :func:`read_excel` has deprecated the ``skip_footer`` parameter. Use ``skipfooter`` instead (:issue:`18836`)
- The ``is_copy`` attribute is deprecated and will be removed in a future version (:issue:`18801`).
- ``IntervalIndex.from_intervals`` is deprecated in favor of the :class:`IntervalIndex` constructor (:issue:`19263`)
- :func:``DataFrame.from_items`` is deprecated. Use ``DataFrame.from_dict(OrderedDict())`` instead (:issue:`17320`)
- :func:``DataFrame.from_items`` is deprecated. Use :func:``DataFrame.from_dict()`` instead, or :func:``DataFrame.from_dict(OrderedDict())`` if you wish to preserve the key order (:issue:`17320`)

.. _whatsnew_0230.prior_deprecations:

Expand Down
8 changes: 6 additions & 2 deletions pandas/core/frame.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1247,7 +1247,9 @@ def to_records(self, index=True, convert_datetime64=True):
def from_items(cls, items, columns=None, orient='columns'):
"""
DEPRECATED: from_items is deprecated and will be removed in a
future version. Use :meth:`DataFrame(dict())` instead.
future version. Use :meth:`DataFrame.from_dict(dict())`
instead. :meth:`DataFrame.from_dict(OrderedDict(...))` may be used
to preserve the key order.
Convert (key, value) pairs to DataFrame. The keys will be the axis
index (usually the columns, but depends on the specified
Expand All @@ -1271,7 +1273,9 @@ def from_items(cls, items, columns=None, orient='columns'):
"""

warnings.warn("from_items is deprecated. Please use "
"DataFrame(dict()) instead.",
"DataFrame.from_dict(dict()) instead. "
"DataFrame.from_dict(OrderedDict()) may be used to "
"preserve the key order.",
FutureWarning, stacklevel=2)

keys, values = lzip(*items)
Expand Down
12 changes: 4 additions & 8 deletions pandas/io/stata.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1572,8 +1572,7 @@ def read(self, nrows=None, convert_dates=None,
else:
data_formatted.append((col, data[col]))
if requires_type_conversion:
data = DataFrame(OrderedDict(data_formatted),
columns=OrderedDict(data_formatted).keys())
data = DataFrame.from_dict(OrderedDict(data_formatted))
del data_formatted

self._do_convert_missing(data, convert_missing)
Expand Down Expand Up @@ -1611,8 +1610,7 @@ def read(self, nrows=None, convert_dates=None,
convert = True
retyped_data.append((col, data[col].astype(dtype)))
if convert:
data = DataFrame(OrderedDict(retyped_data),
columns=OrderedDict(retyped_data).keys())
data = DataFrame.from_dict(OrderedDict(retyped_data))

if index_col is not None:
data = data.set_index(data.pop(index_col))
Expand Down Expand Up @@ -1725,8 +1723,7 @@ def _do_convert_categoricals(self, data, value_label_dict, lbllist,
cat_converted_data.append((col, cat_data))
else:
cat_converted_data.append((col, data[col]))
data = DataFrame(OrderedDict(cat_converted_data),
columns=OrderedDict(cat_converted_data).keys())
data = DataFrame.from_dict(OrderedDict(cat_converted_data))
return data

def data_label(self):
Expand Down Expand Up @@ -2001,8 +1998,7 @@ def _prepare_categoricals(self, data):
data_formatted.append((col, values))
else:
data_formatted.append((col, data[col]))
return DataFrame(OrderedDict(data_formatted),
columns=OrderedDict(data_formatted).keys())
return DataFrame.from_dict(OrderedDict(data_formatted))

def _replace_nans(self, data):
# return data
Expand Down
4 changes: 2 additions & 2 deletions pandas/tests/frame/test_nonunique_indexes.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -328,8 +328,8 @@ def check(result, expected=None):

df1r = df1.reindex_like(df2)
result = df1r == df2
expected = DataFrame([[False, True], [True, False], [False, False],
[True, False]], columns=['A', 'A'])
expected = DataFrame([[False, True], [True, False], [False, False], [
True, False]], columns=['A', 'A'])
assert_frame_equal(result, expected)

# mixed column selection
Expand Down
6 changes: 4 additions & 2 deletions pandas/tests/io/parser/common.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
import re
import sys
from datetime import datetime
from collections import OrderedDict

import pytest
import numpy as np
Expand Down Expand Up @@ -924,8 +925,9 @@ def test_float_parser(self):

def test_scientific_no_exponent(self):
# see gh-12215
df = DataFrame({'w': ['2e'], 'x': ['3E'],
'y': ['42e'], 'z': ['632E']})
df = DataFrame.from_dict(OrderedDict([('w', ['2e']), ('x', ['3E']),
('y', ['42e']),
('z', ['632E'])]))
data = df.to_csv(index=False)
for prec in self.float_precision_choices:
df_roundtrip = self.read_csv(
Expand Down
79 changes: 39 additions & 40 deletions pandas/tests/io/test_excel.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
from distutils.version import LooseVersion
from functools import partial
from warnings import catch_warnings
from collections import OrderedDict

import numpy as np
import pytest
Expand Down Expand Up @@ -315,19 +316,17 @@ def test_excel_table(self):

def test_reader_special_dtypes(self):

expected = DataFrame({
"IntCol": [1, 2, -3, 4, 0],
"FloatCol": [1.25, 2.25, 1.83, 1.92, 0.0000000005],
"BoolCol": [True, False, True, True, False],
"StrCol": [1, 2, 3, 4, 5],
expected = DataFrame.from_dict(OrderedDict([
("IntCol", [1, 2, -3, 4, 0]),
("FloatCol", [1.25, 2.25, 1.83, 1.92, 0.0000000005]),
("BoolCol", [True, False, True, True, False]),
("StrCol", [1, 2, 3, 4, 5]),
# GH5394 - this is why convert_float isn't vectorized
"Str2Col": ["a", 3, "c", "d", "e"],
"DateCol": [datetime(2013, 10, 30), datetime(2013, 10, 31),
datetime(1905, 1, 1), datetime(2013, 12, 14),
datetime(2015, 3, 14)]
}, columns=["IntCol", "FloatCol", "BoolCol",
"StrCol", "Str2Col", "DateCol"])

("Str2Col", ["a", 3, "c", "d", "e"]),
("DateCol", [datetime(2013, 10, 30), datetime(2013, 10, 31),
datetime(1905, 1, 1), datetime(2013, 12, 14),
datetime(2015, 3, 14)])
]))
basename = 'test_types'

# should read in correctly and infer types
Expand Down Expand Up @@ -364,12 +363,12 @@ def test_reader_converters(self):

basename = 'test_converters'

expected = DataFrame({
"IntCol": [1, 2, -3, -1000, 0],
"FloatCol": [12.5, np.nan, 18.3, 19.2, 0.000000005],
"BoolCol": ['Found', 'Found', 'Found', 'Not found', 'Found'],
"StrCol": ['1', np.nan, '3', '4', '5'],
}, columns=['IntCol', 'FloatCol', 'BoolCol', 'StrCol'])
expected = DataFrame.from_dict(OrderedDict([
("IntCol", [1, 2, -3, -1000, 0]),
("FloatCol", [12.5, np.nan, 18.3, 19.2, 0.000000005]),
("BoolCol", ['Found', 'Found', 'Found', 'Not found', 'Found']),
("StrCol", ['1', np.nan, '3', '4', '5']),
]))

converters = {'IntCol': lambda x: int(x) if x != '' else -1000,
'FloatCol': lambda x: 10 * x if x else np.nan,
Expand Down Expand Up @@ -719,30 +718,30 @@ def test_reader_seconds(self):

if LooseVersion(xlrd.__VERSION__) >= LooseVersion("0.9.3"):
# Xlrd >= 0.9.3 can handle Excel milliseconds.
expected = DataFrame({"Time": [time(1, 2, 3),
time(2, 45, 56, 100000),
time(4, 29, 49, 200000),
time(6, 13, 42, 300000),
time(7, 57, 35, 400000),
time(9, 41, 28, 500000),
time(11, 25, 21, 600000),
time(13, 9, 14, 700000),
time(14, 53, 7, 800000),
time(16, 37, 0, 900000),
time(18, 20, 54)]})
expected = DataFrame.from_dict({"Time": [time(1, 2, 3),
time(2, 45, 56, 100000),
time(4, 29, 49, 200000),
time(6, 13, 42, 300000),
time(7, 57, 35, 400000),
time(9, 41, 28, 500000),
time(11, 25, 21, 600000),
time(13, 9, 14, 700000),
time(14, 53, 7, 800000),
time(16, 37, 0, 900000),
time(18, 20, 54)]})
else:
# Xlrd < 0.9.3 rounds Excel milliseconds.
expected = DataFrame({"Time": [time(1, 2, 3),
time(2, 45, 56),
time(4, 29, 49),
time(6, 13, 42),
time(7, 57, 35),
time(9, 41, 29),
time(11, 25, 22),
time(13, 9, 15),
time(14, 53, 8),
time(16, 37, 1),
time(18, 20, 54)]})
expected = DataFrame.from_dict({"Time": [time(1, 2, 3),
time(2, 45, 56),
time(4, 29, 49),
time(6, 13, 42),
time(7, 57, 35),
time(9, 41, 29),
time(11, 25, 22),
time(13, 9, 15),
time(14, 53, 8),
time(16, 37, 1),
time(18, 20, 54)]})

actual = self.get_exceldf('times_1900', 'Sheet1')
tm.assert_frame_equal(actual, expected)
Expand Down
2 changes: 1 addition & 1 deletion pandas/tests/io/test_stata.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -946,7 +946,7 @@ def test_categorical_order(self, file):
cols.append((col, pd.Categorical.from_codes(codes, labels)))
else:
cols.append((col, pd.Series(labels, dtype=np.float32)))
expected = DataFrame(dict(cols), columns=OrderedDict(cols).keys())
expected = DataFrame.from_dict(OrderedDict(cols))

# Read with and with out categoricals, ensure order is identical
file = getattr(self, file)
Expand Down

0 comments on commit c25f541

Please sign in to comment.