forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathtest_describe.py
300 lines (269 loc) · 10.3 KB
/
test_describe.py
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
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
import numpy as np
import pandas as pd
from pandas import Categorical, DataFrame, Series, Timestamp, date_range
import pandas._testing as tm
class TestDataFrameDescribe:
def test_describe_bool_in_mixed_frame(self):
df = DataFrame(
{
"string_data": ["a", "b", "c", "d", "e"],
"bool_data": [True, True, False, False, False],
"int_data": [10, 20, 30, 40, 50],
}
)
# Integer data are included in .describe() output,
# Boolean and string data are not.
result = df.describe()
expected = DataFrame(
{"int_data": [5, 30, df.int_data.std(), 10, 20, 30, 40, 50]},
index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
)
tm.assert_frame_equal(result, expected)
# Top value is a boolean value that is False
result = df.describe(include=["bool"])
expected = DataFrame(
{"bool_data": [5, 2, False, 3]}, index=["count", "unique", "top", "freq"]
)
tm.assert_frame_equal(result, expected)
def test_describe_empty_object(self):
# GH#27183
df = pd.DataFrame({"A": [None, None]}, dtype=object)
result = df.describe()
expected = pd.DataFrame(
{"A": [0, 0, np.nan, np.nan]},
dtype=object,
index=["count", "unique", "top", "freq"],
)
tm.assert_frame_equal(result, expected)
result = df.iloc[:0].describe()
tm.assert_frame_equal(result, expected)
def test_describe_bool_frame(self):
# GH#13891
df = pd.DataFrame(
{
"bool_data_1": [False, False, True, True],
"bool_data_2": [False, True, True, True],
}
)
result = df.describe()
expected = DataFrame(
{"bool_data_1": [4, 2, True, 2], "bool_data_2": [4, 2, True, 3]},
index=["count", "unique", "top", "freq"],
)
tm.assert_frame_equal(result, expected)
df = pd.DataFrame(
{
"bool_data": [False, False, True, True, False],
"int_data": [0, 1, 2, 3, 4],
}
)
result = df.describe()
expected = DataFrame(
{"int_data": [5, 2, df.int_data.std(), 0, 1, 2, 3, 4]},
index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
)
tm.assert_frame_equal(result, expected)
df = pd.DataFrame(
{"bool_data": [False, False, True, True], "str_data": ["a", "b", "c", "a"]}
)
result = df.describe()
expected = DataFrame(
{"bool_data": [4, 2, True, 2], "str_data": [4, 3, "a", 2]},
index=["count", "unique", "top", "freq"],
)
tm.assert_frame_equal(result, expected)
def test_describe_categorical(self):
df = DataFrame({"value": np.random.randint(0, 10000, 100)})
labels = [f"{i} - {i + 499}" for i in range(0, 10000, 500)]
cat_labels = Categorical(labels, labels)
df = df.sort_values(by=["value"], ascending=True)
df["value_group"] = pd.cut(
df.value, range(0, 10500, 500), right=False, labels=cat_labels
)
cat = df
# Categoricals should not show up together with numerical columns
result = cat.describe()
assert len(result.columns) == 1
# In a frame, describe() for the cat should be the same as for string
# arrays (count, unique, top, freq)
cat = Categorical(
["a", "b", "b", "b"], categories=["a", "b", "c"], ordered=True
)
s = Series(cat)
result = s.describe()
expected = Series([4, 2, "b", 3], index=["count", "unique", "top", "freq"])
tm.assert_series_equal(result, expected)
cat = Series(Categorical(["a", "b", "c", "c"]))
df3 = DataFrame({"cat": cat, "s": ["a", "b", "c", "c"]})
result = df3.describe()
tm.assert_numpy_array_equal(result["cat"].values, result["s"].values)
def test_describe_empty_categorical_column(self):
# GH#26397
# Ensure the index of an an empty categorical DataFrame column
# also contains (count, unique, top, freq)
df = pd.DataFrame({"empty_col": Categorical([])})
result = df.describe()
expected = DataFrame(
{"empty_col": [0, 0, np.nan, np.nan]},
index=["count", "unique", "top", "freq"],
dtype="object",
)
tm.assert_frame_equal(result, expected)
# ensure NaN, not None
assert np.isnan(result.iloc[2, 0])
assert np.isnan(result.iloc[3, 0])
def test_describe_categorical_columns(self):
# GH#11558
columns = pd.CategoricalIndex(["int1", "int2", "obj"], ordered=True, name="XXX")
df = DataFrame(
{
"int1": [10, 20, 30, 40, 50],
"int2": [10, 20, 30, 40, 50],
"obj": ["A", 0, None, "X", 1],
},
columns=columns,
)
result = df.describe()
exp_columns = pd.CategoricalIndex(
["int1", "int2"],
categories=["int1", "int2", "obj"],
ordered=True,
name="XXX",
)
expected = DataFrame(
{
"int1": [5, 30, df.int1.std(), 10, 20, 30, 40, 50],
"int2": [5, 30, df.int2.std(), 10, 20, 30, 40, 50],
},
index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
columns=exp_columns,
)
tm.assert_frame_equal(result, expected)
tm.assert_categorical_equal(result.columns.values, expected.columns.values)
def test_describe_datetime_columns(self):
columns = pd.DatetimeIndex(
["2011-01-01", "2011-02-01", "2011-03-01"],
freq="MS",
tz="US/Eastern",
name="XXX",
)
df = DataFrame(
{
0: [10, 20, 30, 40, 50],
1: [10, 20, 30, 40, 50],
2: ["A", 0, None, "X", 1],
}
)
df.columns = columns
result = df.describe()
exp_columns = pd.DatetimeIndex(
["2011-01-01", "2011-02-01"], freq="MS", tz="US/Eastern", name="XXX"
)
expected = DataFrame(
{
0: [5, 30, df.iloc[:, 0].std(), 10, 20, 30, 40, 50],
1: [5, 30, df.iloc[:, 1].std(), 10, 20, 30, 40, 50],
},
index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
)
expected.columns = exp_columns
tm.assert_frame_equal(result, expected)
assert result.columns.freq == "MS"
assert result.columns.tz == expected.columns.tz
def test_describe_timedelta_values(self):
# GH#6145
t1 = pd.timedelta_range("1 days", freq="D", periods=5)
t2 = pd.timedelta_range("1 hours", freq="H", periods=5)
df = pd.DataFrame({"t1": t1, "t2": t2})
expected = DataFrame(
{
"t1": [
5,
pd.Timedelta("3 days"),
df.iloc[:, 0].std(),
pd.Timedelta("1 days"),
pd.Timedelta("2 days"),
pd.Timedelta("3 days"),
pd.Timedelta("4 days"),
pd.Timedelta("5 days"),
],
"t2": [
5,
pd.Timedelta("3 hours"),
df.iloc[:, 1].std(),
pd.Timedelta("1 hours"),
pd.Timedelta("2 hours"),
pd.Timedelta("3 hours"),
pd.Timedelta("4 hours"),
pd.Timedelta("5 hours"),
],
},
index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
)
result = df.describe()
tm.assert_frame_equal(result, expected)
exp_repr = (
" t1 t2\n"
"count 5 5\n"
"mean 3 days 00:00:00 0 days 03:00:00\n"
"std 1 days 13:56:50.394919273 0 days 01:34:52.099788303\n"
"min 1 days 00:00:00 0 days 01:00:00\n"
"25% 2 days 00:00:00 0 days 02:00:00\n"
"50% 3 days 00:00:00 0 days 03:00:00\n"
"75% 4 days 00:00:00 0 days 04:00:00\n"
"max 5 days 00:00:00 0 days 05:00:00"
)
assert repr(result) == exp_repr
def test_describe_tz_values(self, tz_naive_fixture):
# GH#21332
tz = tz_naive_fixture
s1 = Series(range(5))
start = Timestamp(2018, 1, 1)
end = Timestamp(2018, 1, 5)
s2 = Series(date_range(start, end, tz=tz))
df = pd.DataFrame({"s1": s1, "s2": s2})
expected = DataFrame(
{
"s1": [5, 2, 0, 1, 2, 3, 4, 1.581139],
"s2": [
5,
Timestamp(2018, 1, 3).tz_localize(tz),
start.tz_localize(tz),
s2[1],
s2[2],
s2[3],
end.tz_localize(tz),
np.nan,
],
},
index=["count", "mean", "min", "25%", "50%", "75%", "max", "std"],
)
result = df.describe(include="all")
tm.assert_frame_equal(result, expected)
def test_describe_percentiles_integer_idx(self):
# GH#26660
df = pd.DataFrame({"x": [1]})
pct = np.linspace(0, 1, 10 + 1)
result = df.describe(percentiles=pct)
expected = DataFrame(
{"x": [1.0, 1.0, np.NaN, 1.0, *[1.0 for _ in pct], 1.0]},
index=[
"count",
"mean",
"std",
"min",
"0%",
"10%",
"20%",
"30%",
"40%",
"50%",
"60%",
"70%",
"80%",
"90%",
"100%",
"max",
],
)
tm.assert_frame_equal(result, expected)