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
|
import sys
import numpy as np
import pandas as pd
import pytest
from pytest_regressions.testing import check_regression_fixture_workflow
@pytest.fixture
def no_regen(dataframe_regression, request):
if dataframe_regression._force_regen or request.config.getoption("force_regen"):
pytest.fail("--force-regen should not be used on this test.")
def test_usage_workflow(pytester, monkeypatch):
monkeypatch.setattr(
sys, "testing_get_data", lambda: {"data": 1.1 * np.ones(50)}, raising=False
)
source = """
import sys
import pandas as pd
def test_1(dataframe_regression):
contents = sys.testing_get_data()
dataframe_regression.check(pd.DataFrame.from_dict(contents))
"""
def get_csv_contents():
filename = pytester.path / "test_file" / "test_1.csv"
frame = pd.read_csv(str(filename))
return {"data": frame["data"].values}
def compare_arrays(obtained, expected):
assert (obtained["data"] == expected["data"]).all()
check_regression_fixture_workflow(
pytester,
source=source,
data_getter=get_csv_contents,
data_modifier=lambda: monkeypatch.setattr(
sys, "testing_get_data", lambda: {"data": 1.2 * np.ones(50)}, raising=False
),
expected_data_1={"data": 1.1 * np.ones(50)},
expected_data_2={"data": 1.2 * np.ones(50)},
compare_fn=compare_arrays,
)
def test_common_cases(dataframe_regression, no_regen):
# Most common case: Data is valid, is present and should pass
data1 = 1.1 * np.ones(5000)
data2 = 2.2 * np.ones(5000)
dataframe_regression.check(pd.DataFrame.from_dict({"data1": data1, "data2": data2}))
# Assertion error case 1: Data has one invalid place
data1 = 1.1 * np.ones(5000)
data2 = 2.2 * np.ones(5000)
data1[500] += 0.1
with pytest.raises(AssertionError) as excinfo:
dataframe_regression.check(
pd.DataFrame.from_dict({"data1": data1, "data2": data2})
)
obtained_error_msg = str(excinfo.value)
expected = "\n".join(
[
"Values are not sufficiently close.",
"To update values, use --force-regen option.",
]
)
assert expected in obtained_error_msg
expected = "\n".join(
[
"data1:",
" obtained_data1 expected_data1 diff",
"500 1.20000000000000018 1.10000000000000009 0.10000000000000009",
]
)
assert expected in obtained_error_msg
# Assertion error case 2: More than one invalid data
data1 = 1.1 * np.ones(5000)
data2 = 2.2 * np.ones(5000)
data1[500] += 0.1
data1[600] += 0.2
data2[700] += 0.3
with pytest.raises(AssertionError) as excinfo:
dataframe_regression.check(
pd.DataFrame.from_dict({"data1": data1, "data2": data2})
)
obtained_error_msg = str(excinfo.value)
expected = "\n".join(
[
"Values are not sufficiently close.",
"To update values, use --force-regen option.",
]
)
assert expected in obtained_error_msg
expected = "\n".join(
[
"data1:",
" obtained_data1 expected_data1 diff",
"500 1.20000000000000018 1.10000000000000009 0.10000000000000009",
"600 1.30000000000000004 1.10000000000000009 0.19999999999999996",
]
)
assert expected in obtained_error_msg
expected = "\n".join(
[
"data2:",
" obtained_data2 expected_data2 diff",
"700 2.5 2.20000000000000018 0.29999999999999982",
]
)
assert expected in obtained_error_msg
# Assertion error case 3: More than one invalid data
data1 = 1.1 * np.ones(5000)
data2 = 2.2 * np.ones(5000)
data1[500] += 0.01
data2[500] += 0.01
with pytest.raises(AssertionError) as excinfo:
dataframe_regression.check(
pd.DataFrame.from_dict({"data1": data1, "data2": data2}),
tolerances={
"data1": dict(atol=1e-1, rtol=1e-17),
"data2": dict(atol=1e-17, rtol=1e-17),
},
)
obtained_error_msg = str(excinfo.value)
assert " data1:" not in obtained_error_msg
assert (
"\n".join(
[
"Values are not sufficiently close.",
"To update values, use --force-regen option.",
]
)
in obtained_error_msg
)
assert (
"\n".join(
[
"data2:",
" obtained_data2 expected_data2 diff",
"500 2.20999999999999996 2.20000000000000018 0.00999999999999979",
]
)
in obtained_error_msg
)
def test_different_data_types(dataframe_regression, no_regen):
# Original CSV file contains integer data
data1 = np.array([True] * 10)
with pytest.raises(
AssertionError,
match="Data type for data data1 of obtained and expected are not the same.",
):
dataframe_regression.check(pd.DataFrame.from_dict({"data1": data1}))
class Foo:
def __init__(self, bar):
self.bar = bar
@pytest.mark.parametrize(
"array", [[np.random.randint(10, 99, 6)] * 6, [Foo(i) for i in range(4)]]
)
def test_non_numeric_data(dataframe_regression, array, no_regen):
data1 = pd.DataFrame()
data1["data1"] = array
with pytest.raises(
AssertionError,
match="Only numeric data is supported on dataframe_regression fixture.\n"
" *Array with type '%s' was given." % (str(data1["data1"].dtype),),
):
dataframe_regression.check(data1)
def test_arrays_with_different_sizes(dataframe_regression, no_regen):
data1 = np.ones(10, dtype=np.float64)
with pytest.raises(
AssertionError, match="Obtained and expected data shape are not the same."
):
dataframe_regression.check(pd.DataFrame.from_dict({"data1": data1}))
def test_nonrange_index(dataframe_regression, no_regen):
data1 = pd.DataFrame({"b": ["a", "b", "c"]}, index=pd.Index([90, 91, 92], name="a"))
dataframe_regression.check(data1)
def test_integer_values_smoke_test(dataframe_regression, no_regen):
data1 = np.ones(11, dtype=int)
dataframe_regression.check(pd.DataFrame.from_dict({"data1": data1}))
def test_number_formats(dataframe_regression, no_regen):
data1 = np.array([1.2345678e50, 1.2345678e-50, 0.0])
dataframe_regression.check(pd.DataFrame.from_dict({"data1": data1}))
def test_bool_array(dataframe_regression, no_regen):
data1 = np.array([True, True, True], dtype=bool)
with pytest.raises(AssertionError) as excinfo:
dataframe_regression.check(pd.DataFrame.from_dict({"data1": data1}))
obtained_error_msg = str(excinfo.value)
expected = "\n".join(
[
"Values are not sufficiently close.",
"To update values, use --force-regen option.",
]
)
assert expected in obtained_error_msg
expected = "\n".join(
[
"data1:",
" obtained_data1 expected_data1 diff",
"0 True False True",
"1 True False True",
"2 True False True",
]
)
assert expected in obtained_error_msg
def test_arrays_of_same_size(dataframe_regression):
same_size_int_arrays = {
"hello": np.zeros((1,), dtype=int),
"world": np.zeros((1,), dtype=int),
}
dataframe_regression.check(pd.DataFrame.from_dict(same_size_int_arrays))
def test_string_array(dataframe_regression):
data1 = {"potato": ["delicious", "nutritive", "yummy"]}
dataframe_regression.check(pd.DataFrame.from_dict(data1))
data1 = {"potato": ["delicious", "nutritive", "yikes"]}
with pytest.raises(AssertionError) as excinfo:
dataframe_regression.check(pd.DataFrame.from_dict(data1))
obtained_error_msg = str(excinfo.value)
assert "Values are not sufficiently close." in obtained_error_msg
assert "To update values, use --force-regen option." in obtained_error_msg
assert "2 yikes yummy ?" in obtained_error_msg
assert (
"WARNING: diffs for this kind of data type cannot be computed"
in obtained_error_msg
)
def test_non_pandas_dataframe(dataframe_regression):
data = np.ones(shape=(10, 10))
with pytest.raises(
AssertionError,
match="Only pandas DataFrames are supported on dataframe_regression fixture.\n"
" *Object with type '%s' was given." % (str(type(data)),),
):
dataframe_regression.check(data)
def test_dataframe_with_empty_strings(dataframe_regression):
df = pd.DataFrame.from_records(
[
{"a": "a", "b": "b"},
{"a": "a1", "b": ""},
]
)
dataframe_regression.check(df)
|
