1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
| import datetime as dt
| from string import ascii_lowercase
|
| import numpy as np
| import pytest
|
| import pandas as pd
| from pandas import (
| DataFrame,
| MultiIndex,
| NaT,
| Series,
| Timestamp,
| date_range,
| )
| import pandas._testing as tm
|
|
| @pytest.mark.slow
| @pytest.mark.parametrize("n", 10 ** np.arange(2, 6))
| @pytest.mark.parametrize("m", [10, 100, 1000])
| @pytest.mark.parametrize("sort", [False, True])
| @pytest.mark.parametrize("dropna", [False, True])
| def test_series_groupby_nunique(n, m, sort, dropna):
| def check_nunique(df, keys, as_index=True):
| original_df = df.copy()
| gr = df.groupby(keys, as_index=as_index, sort=sort)
| left = gr["julie"].nunique(dropna=dropna)
|
| gr = df.groupby(keys, as_index=as_index, sort=sort)
| right = gr["julie"].apply(Series.nunique, dropna=dropna)
| if not as_index:
| right = right.reset_index(drop=True)
|
| if as_index:
| tm.assert_series_equal(left, right, check_names=False)
| else:
| tm.assert_frame_equal(left, right, check_names=False)
| tm.assert_frame_equal(df, original_df)
|
| days = date_range("2015-08-23", periods=10)
|
| frame = DataFrame(
| {
| "jim": np.random.choice(list(ascii_lowercase), n),
| "joe": np.random.choice(days, n),
| "julie": np.random.randint(0, m, n),
| }
| )
|
| check_nunique(frame, ["jim"])
| check_nunique(frame, ["jim", "joe"])
|
| frame.loc[1::17, "jim"] = None
| frame.loc[3::37, "joe"] = None
| frame.loc[7::19, "julie"] = None
| frame.loc[8::19, "julie"] = None
| frame.loc[9::19, "julie"] = None
|
| check_nunique(frame, ["jim"])
| check_nunique(frame, ["jim", "joe"])
| check_nunique(frame, ["jim"], as_index=False)
| check_nunique(frame, ["jim", "joe"], as_index=False)
|
|
| def test_nunique():
| df = DataFrame({"A": list("abbacc"), "B": list("abxacc"), "C": list("abbacx")})
|
| expected = DataFrame({"A": list("abc"), "B": [1, 2, 1], "C": [1, 1, 2]})
| result = df.groupby("A", as_index=False).nunique()
| tm.assert_frame_equal(result, expected)
|
| # as_index
| expected.index = list("abc")
| expected.index.name = "A"
| expected = expected.drop(columns="A")
| result = df.groupby("A").nunique()
| tm.assert_frame_equal(result, expected)
|
| # with na
| result = df.replace({"x": None}).groupby("A").nunique(dropna=False)
| tm.assert_frame_equal(result, expected)
|
| # dropna
| expected = DataFrame({"B": [1] * 3, "C": [1] * 3}, index=list("abc"))
| expected.index.name = "A"
| result = df.replace({"x": None}).groupby("A").nunique()
| tm.assert_frame_equal(result, expected)
|
|
| def test_nunique_with_object():
| # GH 11077
| data = DataFrame(
| [
| [100, 1, "Alice"],
| [200, 2, "Bob"],
| [300, 3, "Charlie"],
| [-400, 4, "Dan"],
| [500, 5, "Edith"],
| ],
| columns=["amount", "id", "name"],
| )
|
| result = data.groupby(["id", "amount"])["name"].nunique()
| index = MultiIndex.from_arrays([data.id, data.amount])
| expected = Series([1] * 5, name="name", index=index)
| tm.assert_series_equal(result, expected)
|
|
| def test_nunique_with_empty_series():
| # GH 12553
| data = Series(name="name", dtype=object)
| result = data.groupby(level=0).nunique()
| expected = Series(name="name", dtype="int64")
| tm.assert_series_equal(result, expected)
|
|
| def test_nunique_with_timegrouper():
| # GH 13453
| test = DataFrame(
| {
| "time": [
| Timestamp("2016-06-28 09:35:35"),
| Timestamp("2016-06-28 16:09:30"),
| Timestamp("2016-06-28 16:46:28"),
| ],
| "data": ["1", "2", "3"],
| }
| ).set_index("time")
| result = test.groupby(pd.Grouper(freq="h"))["data"].nunique()
| expected = test.groupby(pd.Grouper(freq="h"))["data"].apply(Series.nunique)
| tm.assert_series_equal(result, expected)
|
|
| @pytest.mark.parametrize(
| "key, data, dropna, expected",
| [
| (
| ["x", "x", "x"],
| [Timestamp("2019-01-01"), NaT, Timestamp("2019-01-01")],
| True,
| Series([1], index=pd.Index(["x"], name="key"), name="data"),
| ),
| (
| ["x", "x", "x"],
| [dt.date(2019, 1, 1), NaT, dt.date(2019, 1, 1)],
| True,
| Series([1], index=pd.Index(["x"], name="key"), name="data"),
| ),
| (
| ["x", "x", "x", "y", "y"],
| [dt.date(2019, 1, 1), NaT, dt.date(2019, 1, 1), NaT, dt.date(2019, 1, 1)],
| False,
| Series([2, 2], index=pd.Index(["x", "y"], name="key"), name="data"),
| ),
| (
| ["x", "x", "x", "x", "y"],
| [dt.date(2019, 1, 1), NaT, dt.date(2019, 1, 1), NaT, dt.date(2019, 1, 1)],
| False,
| Series([2, 1], index=pd.Index(["x", "y"], name="key"), name="data"),
| ),
| ],
| )
| def test_nunique_with_NaT(key, data, dropna, expected):
| # GH 27951
| df = DataFrame({"key": key, "data": data})
| result = df.groupby(["key"])["data"].nunique(dropna=dropna)
| tm.assert_series_equal(result, expected)
|
|
| def test_nunique_preserves_column_level_names():
| # GH 23222
| test = DataFrame([1, 2, 2], columns=pd.Index(["A"], name="level_0"))
| result = test.groupby([0, 0, 0]).nunique()
| expected = DataFrame([2], index=np.array([0]), columns=test.columns)
| tm.assert_frame_equal(result, expected)
|
|
| def test_nunique_transform_with_datetime():
| # GH 35109 - transform with nunique on datetimes results in integers
| df = DataFrame(date_range("2008-12-31", "2009-01-02"), columns=["date"])
| result = df.groupby([0, 0, 1])["date"].transform("nunique")
| expected = Series([2, 2, 1], name="date")
| tm.assert_series_equal(result, expected)
|
|
| def test_empty_categorical(observed):
| # GH#21334
| cat = Series([1]).astype("category")
| ser = cat[:0]
| gb = ser.groupby(ser, observed=observed)
| result = gb.nunique()
| if observed:
| expected = Series([], index=cat[:0], dtype="int64")
| else:
| expected = Series([0], index=cat, dtype="int64")
| tm.assert_series_equal(result, expected)
|
|
