-
Notifications
You must be signed in to change notification settings - Fork 4
/
test_utils.py
181 lines (156 loc) · 7.56 KB
/
test_utils.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
import unittest
from typing import cast
import pandas as pd
import pytest
from pandas.testing import assert_frame_equal, assert_series_equal
from pytest_unordered import unordered
import dsp_tools.commands.excel2json.utils as utl
from dsp_tools.commands.excel2json.models.input_error import DuplicatesInColumnProblem
# ruff: noqa: PT009 (pytest-unittest-assertion) (remove this line when pytest is used instead of unittest)
class TestUtils(unittest.TestCase):
def test_clean_data_frame(self) -> None:
original_df = pd.DataFrame(
{
" TitLE of Column 1 ": [1.54, " 0-1 ", "1-n ", " "],
" Title of Column 2 ": ["1", 1, " t ext ", "text"],
"Title of Column 3": ["", pd.NA, None, "text"],
}
)
expected_df = pd.DataFrame(
{
"title of column 1": ["1.54", "0-1", "1-n", pd.NA],
"title of column 2": ["1", "1", "t ext", "text"],
"title of column 3": [pd.NA, pd.NA, pd.NA, "text"],
}
)
returned_df = utl.clean_data_frame(df=original_df)
assert_frame_equal(expected_df, returned_df)
def test_check_contains_required_columns(self) -> None:
original_df = pd.DataFrame(columns=["col1", "col2", "col3", "extra_col"])
required = {"col1", "col2", "col3"}
assert not utl.check_contains_required_columns(df=original_df, required_columns=required)
required = {"col1", "col2", "col3", "col4"}
res = utl.check_contains_required_columns(df=original_df, required_columns=required)
assert res.columns == ["col4"] # type: ignore[union-attr]
def test_check_column_for_duplicate(self) -> None:
original_df = pd.DataFrame(
{
"col_1": ["1.54", "0-1", "1-n", "0-1", "1.54"],
"col_2": ["1.54", "0-1", "1-n", "text", "neu"],
}
)
assert not utl.check_column_for_duplicate(df=original_df, to_check_column="col_2")
result = utl.check_column_for_duplicate(df=original_df, to_check_column="col_1")
res = cast(DuplicatesInColumnProblem, result)
assert res.column == "col_1"
assert unordered(res.duplicate_values) == ["1.54", "0-1"]
def test_check_required_values(self) -> None:
original_df = pd.DataFrame(
{
"col_1": ["1.54", "0-1", "1-n", pd.NA],
"col_2": ["1", "1", pd.NA, "text"],
"col_3": ["1", "1", "1", "text"],
}
)
returned_dict = utl.check_required_values(df=original_df, required_values_columns=["col_1", "col_3"])
assert list(returned_dict.keys()) == ["col_1"]
expected_series = pd.Series([False, False, False, True], name="col_1")
assert_series_equal(returned_dict["col_1"], expected_series)
def test_turn_bool_array_into_index_numbers(self) -> None:
original_series = pd.Series([False, True, False, True])
returned_list = utl.turn_bool_array_into_index_numbers(series=original_series, true_remains=True)
assert unordered(returned_list) == [1, 3]
returned_list = utl.turn_bool_array_into_index_numbers(series=original_series, true_remains=False)
assert unordered(returned_list) == [0, 2]
def test_get_wrong_row_numbers(self) -> None:
original_dict = {
"col_1": pd.Series([False, True, False, True]),
"col_2": pd.Series([False, False, True, False]),
}
expected_dict = {"col_1": [3, 5], "col_2": [4]}
returned_dict = utl.get_wrong_row_numbers(wrong_row_dict=original_dict, true_remains=True)
self.assertDictEqual(expected_dict, returned_dict)
def test_update_dict_if_not_value_none(self) -> None:
original_dict = {0: 0}
original_update_dict = {1: 1, 2: 2, 3: None, 4: pd.NA, 5: "5"}
expected_dict = {0: 0, 1: 1, 2: 2, 5: "5"}
returned_dict = utl.update_dict_if_not_value_none(
additional_dict=original_update_dict, to_update_dict=original_dict
)
self.assertDictEqual(expected_dict, returned_dict)
def test_find_one_full_cell_in_cols(self) -> None:
required_cols = ["label_en", "label_de", "label_fr", "label_it", "label_rm"]
original_df = pd.DataFrame(
{
"label_en": [1, pd.NA, pd.NA, 4],
"label_de": [1, pd.NA, 3, 4],
"label_fr": [1, pd.NA, 3, pd.NA],
"label_it": [1, pd.NA, 3, 4],
"label_rm": [pd.NA, pd.NA, 3, 4],
}
)
expected_array = pd.Series([False, True, False, False])
returned_array = utl.find_one_full_cell_in_cols(df=original_df, required_columns=required_cols)
assert_series_equal(returned_array, expected_array)
def test_find_one_full_cell_none(self) -> None:
required_cols = ["label_en", "label_de", "label_fr", "label_it", "label_rm"]
original_df = pd.DataFrame(
{
"label_en": [1, 2, 3, 4],
"label_de": [1, pd.NA, 3, 4],
"label_fr": [1, pd.NA, 3, pd.NA],
"label_it": [1, pd.NA, 3, 4],
"label_rm": [pd.NA, pd.NA, 3, 4],
}
)
assert not utl.find_one_full_cell_in_cols(df=original_df, required_columns=required_cols)
def test_col_must_or_not_empty_based_on_other_col(self) -> None:
original_df = pd.DataFrame({"substring": ["1", "2", "3", "4", "5", "6"], "check": [1, pd.NA, 3, 4, pd.NA, 6]})
assert not utl.col_must_or_not_empty_based_on_other_col(
df=original_df,
substring_list=["1", "3", "6"],
substring_colname="substring",
check_empty_colname="check",
must_have_value=True,
)
expected_series = pd.Series([True, False, False, False, False, False])
returned_series = utl.col_must_or_not_empty_based_on_other_col(
df=original_df,
substring_list=["1", "2"],
substring_colname="substring",
check_empty_colname="check",
must_have_value=False,
)
assert_series_equal(returned_series, expected_series)
def test_get_labels(self) -> None:
original_df = pd.DataFrame(
{
"label_en": ["text_en", "text_en"],
"label_de": ["text_de", pd.NA],
"label_fr": ["text_fr", pd.NA],
"label_it": ["text_it", pd.NA],
"label_rm": ["text_rm", pd.NA],
}
)
expected_dict = {"de": "text_de", "en": "text_en", "fr": "text_fr", "it": "text_it", "rm": "text_rm"}
returned_dict = utl.get_labels(original_df.loc[0, :])
self.assertDictEqual(expected_dict, returned_dict)
expected_dict = {"en": "text_en"}
returned_dict = utl.get_labels(original_df.loc[1, :])
self.assertDictEqual(expected_dict, returned_dict)
def test_get_comments(self) -> None:
original_df = pd.DataFrame(
{
"comment_en": ["text_en", pd.NA],
"comment_de": ["text_de", pd.NA],
"comment_fr": ["text_fr", pd.NA],
"comment_it": ["text_it", pd.NA],
"comment_rm": ["text_rm", pd.NA],
}
)
expected_dict = {"de": "text_de", "en": "text_en", "fr": "text_fr", "it": "text_it", "rm": "text_rm"}
returned_dict = utl.get_comments(original_df.loc[0, :])
self.assertDictEqual(expected_dict, cast(dict[str, str], returned_dict))
assert not utl.get_comments(original_df.loc[1, :])
if __name__ == "__main__":
pytest.main([__file__])