8000 DEPR: DataFrame.get_dtype_counts by mroeschke · Pull Request #27145 · pandas-dev/pandas · GitHub
[go: up one dir, main page]
Skip to content

DEPR: DataFrame.get_dtype_counts #27145

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 27 commits into from
Jul 3, 2019
Merged

DEPR: DataFrame.get_dtype_counts #27145

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
27 commits
Select commit Hold shift + click to select a range
2fe603d
DEPR: get_dtype_values
Jun 30, 2019
735a2fd
Add test and whatsnew note:
Jun 30, 2019
8473885
Flake8
Jun 30, 2019
faeb972
Start converting tests to compare np dtypes
Jun 30, 2019
95a7075
keys --> keys(), first pass at converting tests
Jun 30, 2019
eb5213c
Change more tests
Jul 1, 2019
06af7fc
Change more tests
Jul 1, 2019
879485b
More progress
Jul 1, 2019
0c82f16
convert more tests
Jul 1, 2019
525fe51
Converting
Jul 1, 2019
592659f
Convert more tests
Jul 1, 2019
0df4dd9
convert tests
Jul 1, 2019
eba5396
flake8
Jul 1, 2019
eeba8a4
Merge remote-tracking branch 'upstream/master' into deprecate_get_dty…
Jul 1, 2019 8000
4419114
Merge remote-tracking branch 'upstream/master' into deprecate_get_dty…
Jul 1, 2019
4ce1194
update docstring
Jul 1, 2019
cb6c8bd
Address some failures
Jul 1, 2019
b3b839a
Merge remote-tracking branch 'upstream/master' into deprecate_get_dty…
Jul 1, 2019
abe310c
typo
Jul 1, 2019
aa172d6
Merge remote-tracking branch 'upstream/master' into deprecate_get_dty…
Jul 2, 2019
6cb5d13
isort
Jul 2, 2019
ca70a46
Fix doc warnings
Jul 2, 2019
86c0a08
Edit tests for dict sorting and platform ints
Jul 2, 2019
523ab60
Merge remote-tracking branch 'upstream/master' into deprecate_get_dty…
Jul 2, 2019
852bd64
Add alternative method
Jul 2, 2019
e700c63
Add doc note
Jul 2, 2019
475e361
Merge branch 'master' into PR_TOOL_MERGE_PR_27145
jreback Jul 3, 2019
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
Prev Previous commit
Next Next commit
convert tests
  • Loading branch information
Matt Roeschke committed Jul 1, 2019
commit 0df4dd946402d21308a4b9f248a0a235c60676cc
25 changes: 15 additions & 10 deletions pandas/tests/frame/test_dtypes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -836,23 +836,28 @@ def test_timedeltas(self):
df = DataFrame(dict(A=Series(date_range('2012-1-1', periods=3,
freq='D')),
B=Series([timedelta(days=i) for i in range(3)])))
result = Series(df._data.get_dtype_counts()).sort_index()
expected = Series(
{'datetime64[ns]': 1, 'timedelta64[ns]': 1}).sort_index()
result = df.dtypes
expected = Series([np.dtype('datetime64[ns]'),
np.dtype('timedelta64[ns]')],
index=list("AB"))
assert_series_equal(result, expected)

df['C'] = df['A'] + df['B']
expected = Series(
{'datetime64[ns]': 2, 'timedelta64[ns]': 1}).sort_values()
result = Series(df._data.get_dtype_counts()).sort_values()
result = df.dtypes
expected = Series([np.dtype('datetime64[ns]'),
np.dtype('timedelta64[ns]'),
np.dtype('datetime64[ns]')],
index=list("ABC"))
assert_series_equal(result, expected)

# mixed int types
df['D'] = 1
expected = Series({'datetime64[ns]': 2,
'timedelta64[ns]': 1,
'int64': 1}).sort_values()
result = Series(df._data.get_dtype_counts()).sort_values()
result = df.dtypes
expected = Series([np.dtype('datetime64[ns]'),
np.dtype('timedelta64[ns]'),
np.dtype('datetime64[ns]'),
np.dtype('int64')],
index=list("ABCD"))
assert_series_equal(result, expected)

def test_arg_for_errors_in_astype(self):
Expand Down
35 changes: 25 additions & 10 deletions pandas/tests/frame/test_indexing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -300,15 +300,23 @@ def test_getitem_boolean_casting(self, datetime_frame):
df['F1'] = df['F'].copy()

casted = df[df > 0]
result = Series(casted._data.get_dtype_counts())
expected = Series({'float64': 4, 'int32': 2, 'int64': 2})
result = casted.dtypes
expected = Series([np.dtype('float64')] * 4 +
[np.dtype('int32')] * 2 +
[np.dtype('int64')] * 2,
index=['A', 'B', 'C', 'D', 'E', 'E1', 'F', 'F1'])
assert_series_equal(result, expected)

# int block splitting
df.loc[df.index[1:3], ['E1', 'F1']] = 0
casted = df[df > 0]
result = Series(casted._data.get_dtype_counts())
expected = Series({'float64': 6, 'int32': 1, 'int64': 1})
result = casted.dtypes
expected = Series([np.dtype('float64')] * 4 +
[np.dtype('int32')] +
[np.dtype('float64')] +
[np.dtype('int64')] +
[np.dtype('float64')],
index=['A', 'B', 'C', 'D', 'E', 'E1', 'F', 'F1'])
assert_series_equal(result, expected)

# where dtype conversions
Expand Down Expand Up @@ -615,8 +623,9 @@ def test_setitem_cast(self, float_frame):
df = DataFrame(np.random.rand(30, 3), columns=tuple('ABC'))
df['event'] = np.nan
df.loc[10, 'event'] = 'foo'
result = Series(df._data.get_dtype_counts()).sort_values()
expected = Series({'float64': 3, 'object': 1}).sort_values()
result = df.dtypes
expected = Series([np.dtype('float64')] * 3 + [np.dtype('object')],
index=['A', 'B', 'C', 'event'])
assert_series_equal(result, expected)

# Test that data type is preserved . #5782
Expand Down Expand Up @@ -1614,8 +1623,10 @@ def test_setitem_single_column_mixed_datetime(self):
df['timestamp'] = Timestamp('20010102')

# check our dtypes
result = Series(df._data.get_dtype_counts())
expected = Series({'float64': 3, 'datetime64[ns]': 1})
result = df.dtypes
expected = Series([np.dtype('float64')] * 3 +
[np.dtype('datetime64[ns]')],
index=['foo', 'bar', 'baz', 'timestamp'])
assert_series_equal(result, expected)

# set an allowable datetime64 type
Expand Down Expand Up @@ -2637,13 +2648,17 @@ def _check_get(df, cond, check_dtypes=True):
for c in ['float32', 'float64',
'int32', 'int64']})
df.iloc[1, :] = 0
result = Series(df.where(df >= 0)._data.get_dtype_counts())
result = df.dtypes
expected = Series([np.dtype('float32'),
np.dtype('float64'),
np.dtype('int32'),
np.dtype('int64')],
index=['float32', 'float64', 'int32', 'int64'])

# when we don't preserve boolean casts
#
# expected = Series({ 'float32' : 1, 'float64' : 3 })

expected = Series({'float32': 1, 'float64': 1, 'int32': 1, 'int64': 1})
assert_series_equal(result, expected)

# aligning
Expand Down
0