Skip to content

Commit

Permalink
Let initialisation from dicts use insertion order for python >= 3.6 (…
Browse files Browse the repository at this point in the history 
…part II) (pandas-dev#19859)
  • Loading branch information
@topper-123
topper-123 authored and harisbal committed Feb 28, 2018
1 parent f8a3e72 commit ab0bcfc
Show file tree
Hide file tree
Showing 11 changed files with 86 additions and 77 deletions.
16 changes: 8 additions & 8 deletions pandas/tests/groupby/test_groupby.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -99,9 +99,9 @@ def max_value(group):

applied = df.groupby('A').apply(max_value)
result = applied.get_dtype_counts().sort_values()
expected = Series({'object': 2,
'float64': 2,
'int64': 1}).sort_values()
expected = Series({'float64': 2,
'int64': 1,
'object': 2}).sort_values()
assert_series_equal(result, expected)

def test_groupby_return_type(self):
Expand Down Expand Up @@ -244,7 +244,7 @@ def func_with_no_date(batch):
return pd.Series({'c': 2})

def func_with_date(batch):
return pd.Series({'c': 2, 'b': datetime(2015, 1, 1)})
return pd.Series({'b': datetime(2015, 1, 1), 'c': 2})

dfg_no_conversion = df.groupby(by=['a']).apply(func_with_no_date)
dfg_no_conversion_expected = pd.DataFrame({'c': 2}, index=[1])
Expand Down Expand Up @@ -1628,8 +1628,8 @@ def f(g):

def test_apply_with_mixed_dtype(self):
# GH3480, apply with mixed dtype on axis=1 breaks in 0.11
df = DataFrame({'foo1': ['one', 'two', 'two', 'three', 'one', 'two'],
'foo2': np.random.randn(6)})
df = DataFrame({'foo1': np.random.randn(6),
'foo2': ['one', 'two', 'two', 'three', 'one', 'two']})
result = df.apply(lambda x: x, axis=1)
assert_series_equal(df.get_dtype_counts(), result.get_dtype_counts())

Expand Down Expand Up @@ -2113,10 +2113,10 @@ def test_multifunc_sum_bug(self):

def test_handle_dict_return_value(self):
def f(group):
return {'min': group.min(), 'max': group.max()}
return {'max': group.max(), 'min': group.min()}

def g(group):
return Series({'min': group.min(), 'max': group.max()})
return Series({'max': group.max(), 'min': group.min()})

result = self.df.groupby('A')['C'].apply(f)
expected = self.df.groupby('A')['C'].apply(g)
Expand Down
8 changes: 6 additions & 2 deletions pandas/tests/groupby/test_transform.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -519,7 +519,9 @@ def test_cython_transform_frame(self, op, args, targop):
'timedelta': pd.timedelta_range(1, freq='s',
periods=1000),
'string': strings * 50,
'string_missing': strings_missing * 50})
'string_missing': strings_missing * 50},
columns=['float', 'float_missing', 'int', 'datetime',
'timedelta', 'string', 'string_missing'])
df['cat'] = df['string'].astype('category')

df2 = df.copy()
Expand Down Expand Up @@ -552,7 +554,9 @@ def test_cython_transform_frame(self, op, args, targop):
tm.assert_frame_equal(expected,
gb.transform(op, *args).sort_index(
axis=1))
tm.assert_frame_equal(expected, getattr(gb, op)(*args))
tm.assert_frame_equal(
expected,
getattr(gb, op)(*args).sort_index(axis=1))
# individual columns
for c in df:
if c not in ['float', 'int', 'float_missing'
Expand Down
16 changes: 9 additions & 7 deletions pandas/tests/indexing/test_ix.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -53,13 +53,15 @@ def test_ix_loc_setitem_consistency(self):

# GH 8607
# ix setitem consistency
df = DataFrame({'timestamp': [1413840976, 1413842580, 1413760580],
'delta': [1174, 904, 161],
'elapsed': [7673, 9277, 1470]})
expected = DataFrame({'timestamp': pd.to_datetime(
[1413840976, 1413842580, 1413760580], unit='s'),
'delta': [1174, 904, 161],
'elapsed': [7673, 9277, 1470]})
df = DataFrame({'delta': [1174, 904, 161],
'elapsed': [7673, 9277, 1470],
'timestamp': [1413840976, 1413842580, 1413760580]})
expected = DataFrame({'delta': [1174, 904, 161],
'elapsed': [7673, 9277, 1470],
'timestamp': pd.to_datetime(
[1413840976, 1413842580, 1413760580],
unit='s')
})

df2 = df.copy()
df2['timestamp'] = pd.to_datetime(df['timestamp'], unit='s')
Expand Down
12 changes: 6 additions & 6 deletions pandas/tests/io/formats/test_format.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -539,8 +539,8 @@ def test_east_asian_unicode_frame(self):
assert _rep(df) == expected

# column name
df = DataFrame({u'あああああ': [1, 222, 33333, 4],
'b': [u'あ', u'いいい', u'う', u'ええええええ']},
df = DataFrame({'b': [u'あ', u'いいい', u'う', u'ええええええ'],
u'あああああ': [1, 222, 33333, 4]},
index=['a', 'bb', 'c', 'ddd'])
expected = (u" b あああああ\na あ 1\n"
u"bb いいい 222\nc う 33333\n"
Expand Down Expand Up @@ -647,8 +647,8 @@ def test_east_asian_unicode_frame(self):
assert _rep(df) == expected

# column name
df = DataFrame({u'あああああ': [1, 222, 33333, 4],
'b': [u'あ', u'いいい', u'う', u'ええええええ']},
df = DataFrame({'b': [u'あ', u'いいい', u'う', u'ええええええ'],
u'あああああ': [1, 222, 33333, 4]},
index=['a', 'bb', 'c', 'ddd'])
expected = (u" b あああああ\n"
u"a あ 1\n"
Expand Down Expand Up @@ -733,8 +733,8 @@ def test_east_asian_unicode_frame(self):
assert _rep(df) == expected

# ambiguous unicode
df = DataFrame({u'あああああ': [1, 222, 33333, 4],
'b': [u'あ', u'いいい', u'¡¡', u'ええええええ']},
df = DataFrame({'b': [u'あ', u'いいい', u'¡¡', u'ええええええ'],
u'あああああ': [1, 222, 33333, 4]},
index=['a', 'bb', 'c', '¡¡¡'])
expected = (u" b あああああ\n"
u"a あ 1\n"
Expand Down
21 changes: 11 additions & 10 deletions pandas/tests/io/formats/test_to_latex.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -115,17 +115,18 @@ def test_to_latex_empty(self):
assert result == expected

def test_to_latex_with_formatters(self):
df = DataFrame({'int': [1, 2, 3],
df = DataFrame({'datetime64': [datetime(2016, 1, 1),
datetime(2016, 2, 5),
datetime(2016, 3, 3)],
'float': [1.0, 2.0, 3.0],
'int': [1, 2, 3],
'object': [(1, 2), True, False],
'datetime64': [datetime(2016, 1, 1),
datetime(2016, 2, 5),
datetime(2016, 3, 3)]})
})

formatters = {'int': lambda x: '0x{x:x}'.format(x=x),
formatters = {'datetime64': lambda x: x.strftime('%Y-%m'),
'float': lambda x: '[{x: 4.1f}]'.format(x=x),
'int': lambda x: '0x{x:x}'.format(x=x),
'object': lambda x: '-{x!s}-'.format(x=x),
'datetime64': lambda x: x.strftime('%Y-%m'),
'__index__': lambda x: 'index: {x}'.format(x=x)}
result = df.to_latex(formatters=dict(formatters))

Expand Down Expand Up @@ -347,10 +348,10 @@ def test_to_latex_escape(self):
a = 'a'
b = 'b'

test_dict = {u('co^l1'): {a: "a",
b: "b"},
u('co$e^x$'): {a: "a",
b: "b"}}
test_dict = {u('co$e^x$'): {a: "a",
b: "b"},
u('co^l1'): {a: "a",
b: "b"}}

unescaped_result = DataFrame(test_dict).to_latex(escape=False)
escaped_result = DataFrame(test_dict).to_latex(
Expand Down
2 changes: 1 addition & 1 deletion pandas/tests/io/json/test_pandas.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -553,7 +553,7 @@ def __str__(self):

def test_label_overflow(self):
# GH14256: buffer length not checked when writing label
df = pd.DataFrame({'foo': [1337], 'bar' * 100000: [1]})
df = pd.DataFrame({'bar' * 100000: [1], 'foo': [1337]})
assert df.to_json() == \
'{{"{bar}":{{"0":1}},"foo":{{"0":1337}}}}'.format(
bar=('bar' * 100000))
Expand Down
43 changes: 22 additions & 21 deletions pandas/tests/reshape/merge/test_merge.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -588,18 +588,18 @@ def test_merge_on_datetime64tz(self):
result = pd.merge(left, right, on='key', how='outer')
assert_frame_equal(result, expected)

left = pd.DataFrame({'value': pd.date_range('20151010', periods=2,
tz='US/Eastern'),
'key': [1, 2]})
right = pd.DataFrame({'value': pd.date_range('20151011', periods=2,
tz='US/Eastern'),
'key': [2, 3]})
left = pd.DataFrame({'key': [1, 2],
'value': pd.date_range('20151010', periods=2,
tz='US/Eastern')})
right = pd.DataFrame({'key': [2, 3],
'value': pd.date_range('20151011', periods=2,
tz='US/Eastern')})
expected = DataFrame({
'key': [1, 2, 3],
'value_x': list(pd.date_range('20151010', periods=2,
tz='US/Eastern')) + [pd.NaT],
'value_y': [pd.NaT] + list(pd.date_range('20151011', periods=2,
tz='US/Eastern')),
'key': [1, 2, 3]})
tz='US/Eastern'))})
result = pd.merge(left, right, on='key', how='outer')
assert_frame_equal(result, expected)
assert result['value_x'].dtype == 'datetime64[ns, US/Eastern]'
Expand Down Expand Up @@ -632,31 +632,32 @@ def test_merge_on_periods(self):
result = pd.merge(left, right, on='key', how='outer')
assert_frame_equal(result, expected)

left = pd.DataFrame({'value': pd.period_range('20151010', periods=2,
freq='D'),
'key': [1, 2]})
right = pd.DataFrame({'value': pd.period_range('20151011', periods=2,
freq='D'),
'key': [2, 3]})
left = pd.DataFrame({'key': [1, 2],
'value': pd.period_range('20151010', periods=2,
freq='D')})
right = pd.DataFrame({'key': [2, 3],
'value': pd.period_range('20151011', periods=2,
freq='D')})

exp_x = pd.period_range('20151010', periods=2, freq='D')
exp_y = pd.period_range('20151011', periods=2, freq='D')
expected = DataFrame({'value_x': list(exp_x) + [pd.NaT],
'value_y': [pd.NaT] + list(exp_y),
'key': [1, 2, 3]})
expected = DataFrame({'key': [1, 2, 3],
'value_x': list(exp_x) + [pd.NaT],
'value_y': [pd.NaT] + list(exp_y)})
result = pd.merge(left, right, on='key', how='outer')
assert_frame_equal(result, expected)
assert result['value_x'].dtype == 'object'
assert result['value_y'].dtype == 'object'

def test_indicator(self):
# PR #10054. xref #7412 and closes #8790.
df1 = DataFrame({'col1': [0, 1], 'col_left': [
'a', 'b'], 'col_conflict': [1, 2]})
df1 = DataFrame({'col1': [0, 1], 'col_conflict': [1, 2],
'col_left': ['a', 'b']})
df1_copy = df1.copy()

df2 = DataFrame({'col1': [1, 2, 3, 4, 5], 'col_right': [2, 2, 2, 2, 2],
'col_conflict': [1, 2, 3, 4, 5]})
df2 = DataFrame({'col1': [1, 2, 3, 4, 5],
'col_conflict': [1, 2, 3, 4, 5],
'col_right': [2, 2, 2, 2, 2]})
df2_copy = df2.copy()

df_result = DataFrame({
Expand Down
5 changes: 3 additions & 2 deletions pandas/tests/reshape/merge/test_merge_ordered.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -83,9 +83,10 @@ def test_empty_sequence_concat(self):
pd.concat([pd.DataFrame(), None])

def test_doc_example(self):
left = DataFrame({'key': ['a', 'c', 'e', 'a', 'c', 'e'],
left = DataFrame({'group': list('aaabbb'),
'key': ['a', 'c', 'e', 'a', 'c', 'e'],
'lvalue': [1, 2, 3] * 2,
'group': list('aaabbb')})
})

right = DataFrame({'key': ['b', 'c', 'd'],
'rvalue': [1, 2, 3]})
Expand Down
8 changes: 4 additions & 4 deletions pandas/tests/reshape/test_concat.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1542,10 +1542,10 @@ def test_concat_bug_2972(self):
def test_concat_bug_3602(self):

# GH 3602, duplicate columns
df1 = DataFrame({'firmNo': [0, 0, 0, 0], 'stringvar': [
'rrr', 'rrr', 'rrr', 'rrr'], 'prc': [6, 6, 6, 6]})
df2 = DataFrame({'misc': [1, 2, 3, 4], 'prc': [
6, 6, 6, 6], 'C': [9, 10, 11, 12]})
df1 = DataFrame({'firmNo': [0, 0, 0, 0], 'prc': [6, 6, 6, 6],
'stringvar': ['rrr', 'rrr', 'rrr', 'rrr']})
df2 = DataFrame({'C': [9, 10, 11, 12], 'misc': [1, 2, 3, 4],
'prc': [6, 6, 6, 6]})
expected = DataFrame([[0, 6, 'rrr', 9, 1, 6],
[0, 6, 'rrr', 10, 2, 6],
[0, 6, 'rrr', 11, 3, 6],
Expand Down
8 changes: 4 additions & 4 deletions pandas/tests/reshape/test_melt.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -589,11 +589,11 @@ def test_nonnumeric_suffix(self):

def test_mixed_type_suffix(self):
df = pd.DataFrame({
'treatment_1': [1.0, 2.0],
'treatment_foo': [3.0, 4.0],
'result_foo': [5.0, 6.0],
'A': ['X1', 'X2'],
'result_1': [0, 9],
'A': ['X1', 'X2']})
'result_foo': [5.0, 6.0],
'treatment_1': [1.0, 2.0],
'treatment_foo': [3.0, 4.0]})
expected = pd.DataFrame({
'A': ['X1', 'X2', 'X1', 'X2'],
'colname': ['1', '1', 'foo', 'foo'],
Expand Down
24 changes: 12 additions & 12 deletions pandas/tests/reshape/test_reshape.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -100,8 +100,8 @@ def test_basic_types(self, sparse, dtype):
expected_counts = {'int64': 1, 'object': 1}
expected_counts[dtype_name] = 3 + expected_counts.get(dtype_name, 0)

expected = Series(expected_counts).sort_values()
tm.assert_series_equal(result.get_dtype_counts().sort_values(),
expected = Series(expected_counts).sort_index()
tm.assert_series_equal(result.get_dtype_counts().sort_index(),
expected)

def test_just_na(self, sparse):
Expand Down Expand Up @@ -212,10 +212,10 @@ def test_dataframe_dummies_prefix_str(self, df, sparse):
def test_dataframe_dummies_subset(self, df, sparse):
result = get_dummies(df, prefix=['from_A'], columns=['A'],
sparse=sparse)
expected = DataFrame({'from_A_a': [1, 0, 1],
'from_A_b': [0, 1, 0],
'B': ['b', 'b', 'c'],
'C': [1, 2, 3]}, dtype=np.uint8)
expected = DataFrame({'B': ['b', 'b', 'c'],
'C': [1, 2, 3],
'from_A_a': [1, 0, 1],
'from_A_b': [0, 1, 0]}, dtype=np.uint8)
expected[['C']] = df[['C']]
assert_frame_equal(result, expected)

Expand Down Expand Up @@ -249,16 +249,16 @@ def test_dataframe_dummies_prefix_sep_bad_length(self, df, sparse):

def test_dataframe_dummies_prefix_dict(self, sparse):
prefixes = {'A': 'from_A', 'B': 'from_B'}
df = DataFrame({'A': ['a', 'b', 'a'],
'B': ['b', 'b', 'c'],
'C': [1, 2, 3]})
df = DataFrame({'C': [1, 2, 3],
'A': ['a', 'b', 'a'],
'B': ['b', 'b', 'c']})
result = get_dummies(df, prefix=prefixes, sparse=sparse)

expected = DataFrame({'from_A_a': [1, 0, 1],
expected = DataFrame({'C': [1, 2, 3],
'from_A_a': [1, 0, 1],
'from_A_b': [0, 1, 0],
'from_B_b': [1, 1, 0],
'from_B_c': [0, 0, 1],
'C': [1, 2, 3]})
'from_B_c': [0, 0, 1]})

columns = ['from_A_a', 'from_A_b', 'from_B_b', 'from_B_c']
expected[columns] = expected[columns].astype(np.uint8)
Expand Down

0 comments on commit ab0bcfc

Please sign in to comment.