Skip to content

Commit 1081716

Browse files
reidy-preidy-p
committed
clean up and parametrize mode tests and add versionadded
1 parent 4b1b564 commit 1081716

File tree

6 files changed

+173
-177
lines changed

6 files changed

+173
-177
lines changed

‎pandas/core/algorithms.py‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -809,6 +809,8 @@ def mode(values, dropna=True):
809809
dropna : boolean, default True
810810
Don't consider counts of NaN/NaT.
811811
812+
.. versionadded:: 0.23.0
813+
812814
Returns
813815
-------
814816
mode : Series

‎pandas/core/arrays/categorical.py‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2128,6 +2128,8 @@ def mode(self, dropna=True):
21282128
dropna : boolean, default True
21292129
Don't consider counts of NaN/NaT.
21302130
2131+
.. versionadded:: 0.23.0
2132+
21312133
Returns
21322134
-------
21332135
modes : `Categorical` (sorted)

‎pandas/core/frame.py‎

Lines changed: 2 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -7059,6 +7059,8 @@ def mode(self, axis=0, numeric_only=False, dropna=True):
70597059
dropna : boolean, default True
70607060
Don't consider counts of NaN/NaT.
70617061
7062+
.. versionadded:: 0.23.0
7063+
70627064
Returns
70637065
-------
70647066
modes : DataFrame (sorted)
@@ -7126,10 +7128,6 @@ def quantile(self, q=0.5, axis=0, numeric_only=True,
71267128
a b
71277129
0.1 1.3 3.7
71287130
0.5 2.5 55.0
7129-
7130-
See Also
7131-
--------
7132-
pandas.core.window.Rolling.quantile
71337131
"""
71347132
self._check_percentile(q)
71357133

‎pandas/core/series.py‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1441,6 +1441,8 @@ def mode(self, dropna=True):
14411441
dropna : boolean, default True
14421442
Don't consider counts of NaN/NaT.
14431443
1444+
.. versionadded:: 0.23.0
1445+
14441446
Returns
14451447
-------
14461448
modes : Series (sorted)

‎pandas/tests/frame/test_analytics.py‎

Lines changed: 55 additions & 81 deletions
Original file line numberDiff line numberDiff line change
@@ -20,7 +20,6 @@
2020
import pandas as pd
2121
import pandas.core.nanops as nanops
2222
import pandas.core.algorithms as algorithms
23-
import pandas.io.formats.printing as printing
2423

2524
import pandas.util.testing as tm
2625
import pandas.util._test_decorators as td
@@ -841,87 +840,62 @@ def wrapper(x):
841840
expected = pd.Series(unit, index=r1.index, dtype=r1.dtype)
842841
tm.assert_series_equal(r1, expected)
843842

844-
def test_mode(self):
845-
df = pd.DataFrame({"A": [12, 12, 11, 12, 19, 11],
846-
"B": [10, 10, 10, np.nan, 3, 4],
847-
"C": [8, 8, 8, 9, 9, 9],
848-
"D": np.arange(6, dtype='int64'),
849-
"E": [8, 8, 1, 1, 3, 3]})
850-
tm.assert_frame_equal(df[["A"]].mode(),
851-
pd.DataFrame({"A": [12]}))
852-
expected = pd.Series([0, 1, 2, 3, 4, 5], dtype='int64', name='D').\
853-
to_frame()
854-
tm.assert_frame_equal(df[["D"]].mode(), expected)
855-
expected = pd.Series([1, 3, 8], dtype='int64', name='E').to_frame()
856-
tm.assert_frame_equal(df[["E"]].mode(), expected)
857-
tm.assert_frame_equal(df[["A", "B"]].mode(),
858-
pd.DataFrame({"A": [12], "B": [10.]}))
859-
tm.assert_frame_equal(df.mode(),
860-
pd.DataFrame({"A": [12, np.nan, np.nan, np.nan,
861-
np.nan, np.nan],
862-
"B": [10, np.nan, np.nan, np.nan,
863-
np.nan, np.nan],
864-
"C": [8, 9, np.nan, np.nan, np.nan,
865-
np.nan],
866-
"D": [0, 1, 2, 3, 4, 5],
867-
"E": [1, 3, 8, np.nan, np.nan,
868-
np.nan]}))
869-
870-
# outputs in sorted order
871-
df["C"] = list(reversed(df["C"]))
872-
printing.pprint_thing(df["C"])
873-
printing.pprint_thing(df["C"].mode())
874-
a, b = (df[["A", "B", "C"]].mode(),
875-
pd.DataFrame({"A": [12, np.nan],
876-
"B": [10, np.nan],
877-
"C": [8, 9]}))
878-
printing.pprint_thing(a)
879-
printing.pprint_thing(b)
880-
tm.assert_frame_equal(a, b)
881-
# should work with heterogeneous types
882-
df = pd.DataFrame({"A": np.arange(6, dtype='int64'),
883-
"B": pd.date_range('2011', periods=6),
884-
"C": list('abcdef')})
885-
exp = pd.DataFrame({"A": pd.Series(np.arange(6, dtype='int64'),
886-
dtype=df["A"].dtype),
887-
"B": pd.Series(pd.date_range('2011', periods=6),
888-
dtype=df["B"].dtype),
889-
"C": pd.Series(list('abcdef'),
890-
dtype=df["C"].dtype)})
891-
tm.assert_frame_equal(df.mode(), exp)
892-
893-
def test_mode_dropna(self):
894-
# GH 17534
895-
# Test the dropna=False parameter for mode
896-
897-
df = pd.DataFrame({"A": [1, np.nan, np.nan, np.nan],
898-
"B": [np.nan, np.nan, 'a', np.nan],
899-
"C": Categorical([np.nan, np.nan, 'a', np.nan]),
900-
"D": to_datetime(['NaT', '2000-1-2', 'NaT', 'NaT']),
901-
"E": to_timedelta(['1 days', 'nan', 'nan', 'nan']),
902-
"F": [1, 1, np.nan, np.nan],
903-
"G": [np.nan, np.nan, 'a', 'a'],
904-
"H": Categorical(['a', np.nan, 'a', np.nan]),
905-
"I": to_datetime(['2000-1-2', '2000-1-2',
843+
@pytest.mark.parametrize("dropna, expected", [
844+
(True, {'A': [12],
845+
'B': [10.0],
846+
'C': [1.0],
847+
'D': ['a'],
848+
'E': Categorical(['a'], categories=['a']),
849+
'F': to_datetime(['2000-1-2']),
850+
'G': to_timedelta(['1 days'])}),
851+
(False, {'A': [12],
852+
'B': [10.0],
853+
'C': [np.nan],
854+
'D': np.array([np.nan], dtype=object),
855+
'E': Categorical([np.nan], categories=['a']),
856+
'F': [pd.NaT],
857+
'G': to_timedelta([pd.NaT])}),
858+
(True, {'H': [8, 9, np.nan, np.nan],
859+
'I': [8, 9, np.nan, np.nan],
860+
'J': [1, np.nan, np.nan, np.nan],
861+
'K': ['a', np.nan, np.nan, np.nan],
862+
'L': Categorical(['a', np.nan, np.nan, np.nan],
863+
categories=['a']),
864+
'M': to_datetime(['2000-1-2', 'NaT', 'NaT', 'NaT']),
865+
'N': to_timedelta(['1 days', 'nan', 'nan', 'nan']),
866+
'O': [0, 1, 2, 3]}),
867+
(False, {'H': [8, 9, np.nan, np.nan],
868+
'I': [8, 9, np.nan, np.nan],
869+
'J': [1, np.nan, np.nan, np.nan],
870+
'K': [np.nan, 'a', np.nan, np.nan],
871+
'L': Categorical([np.nan, 'a', np.nan, np.nan],
872+
categories=['a']),
873+
'M': to_datetime(['NaT', '2000-1-2', 'NaT', 'NaT']),
874+
'N': to_timedelta(['nan', '1 days', 'nan', 'nan']),
875+
'O': [0, 1, 2, 3]})
876+
])
877+
def test_mode_dropna(self, dropna, expected):
878+
879+
df = pd.DataFrame({"A": [12, 12, 19, 11],
880+
"B": [10, 10, np.nan, 3],
881+
"C": [1, np.nan, np.nan, np.nan],
882+
"D": [np.nan, np.nan, 'a', np.nan],
883+
"E": Categorical([np.nan, np.nan, 'a', np.nan]),
884+
"F": to_datetime(['NaT', '2000-1-2', 'NaT', 'NaT']),
885+
"G": to_timedelta(['1 days', 'nan', 'nan', 'nan']),
886+
"H": [8, 8, 9, 9],
887+
"I": [9, 9, 8, 8],
888+
"J": [1, 1, np.nan, np.nan],
889+
"K": [np.nan, np.nan, 'a', 'a'],
890+
"L": Categorical(['a', np.nan, 'a', np.nan]),
891+
"M": to_datetime(['2000-1-2', '2000-1-2',
906892
'NaT', 'NaT']),
907-
"J": to_timedelta(['1 days', 'nan',
908-
'1 days', 'nan'])})
909-
910-
result = df.loc[:, 'A':'E'].mode(dropna=False)
911-
expected = pd.DataFrame({'A': [np.nan],
912-
'B': np.array([np.nan], dtype=object),
913-
'C': Categorical([np.nan], categories=['a']),
914-
'D': [pd.NaT],
915-
'E': to_timedelta([pd.NaT])})
916-
tm.assert_frame_equal(result, expected)
917-
918-
result = df.loc[:, 'F':'J'].mode(dropna=False)
919-
expected = pd.DataFrame({'F': [1, np.nan],
920-
'G': [np.nan, 'a'],
921-
'H': Categorical([np.nan, 'a'],
922-
categories=['a']),
923-
'I': to_datetime(['NaT', '2000-1-2']),
924-
'J': to_timedelta(['nan', '1 days'])})
893+
"N": to_timedelta(['1 days', 'nan',
894+
'1 days', 'nan']),
895+
"O": np.arange(4, dtype='int64')})
896+
897+
result = df[sorted(list(expected.keys()))].mode(dropna=dropna)
898+
expected = pd.DataFrame(expected)
925899
tm.assert_frame_equal(result, expected)
926900

927901
def test_operators_timedelta64(self):

0 commit comments

Comments
 (0)