File size: 8,209 Bytes
5caedb4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os

import pandas as pd
import pytest

from llm_studio.src.possible_values import (
    Columns,
    DatasetValue,
    Files,
    Number,
    String,
    _scan_dirs,
    _scan_files,
    strip_common_prefix,
)


# Helper function to create a temporary directory structure
@pytest.fixture
def temp_dir_structure(tmp_path):
    base_dir = tmp_path / "test_dir"
    base_dir.mkdir()
    (base_dir / "subdir1").mkdir()
    (base_dir / "subdir2").mkdir()
    (base_dir / "subdir1" / "subsubdir").mkdir()
    (base_dir / "file1.csv").touch()
    (base_dir / "file2.json").touch()
    (base_dir / "__meta_info__train.json").touch()
    (base_dir / "subdir1" / "file3.parquet").touch()
    (base_dir / "subdir1" / "__meta_info__train.pq.csv").touch()
    return base_dir


def test_scan_dirs(temp_dir_structure):
    dirs = _scan_dirs(str(temp_dir_structure))
    expected = [
        str(temp_dir_structure / "subdir1") + "/",
        str(temp_dir_structure / "subdir2") + "/",
        str(temp_dir_structure / "subdir1" / "subsubdir") + "/",
    ]
    assert set(dirs) == set(expected)


def test_scan_files(temp_dir_structure):
    files = _scan_files(str(temp_dir_structure))
    expected = [
        str(temp_dir_structure / "file1.csv"),
        str(temp_dir_structure / "file2.json"),
        str(temp_dir_structure / "subdir1" / "file3.parquet"),
    ]
    assert set(files) == set(expected)


def test_strip_common_prefix():
    paths = ["/a/b/c/file1.txt", "/a/b/c/file2.txt", "/a/b/d/file3.txt"]
    stripped = strip_common_prefix(paths)
    assert stripped == ("c/file1.txt", "c/file2.txt", "d/file3.txt")

    # Test with ignore_set
    paths_with_ignore = paths + ["ignore_this"]
    stripped_with_ignore = strip_common_prefix(
        paths_with_ignore, ignore_set={"ignore_this"}
    )
    assert stripped_with_ignore == (
        "c/file1.txt",
        "c/file2.txt",
        "d/file3.txt",
        "ignore_this",
    )


def test_strip_common_prefix_empty_paths():
    paths = []
    stripped = strip_common_prefix(paths)
    assert stripped == tuple([])


def test_number_slider():
    num = Number(min=0, max=10, step=0.5)
    assert num.min == 0
    assert num.max == 10
    assert num.step == 0.5


def test_number_spinbox():
    num = Number(min=0, step=0.5)
    assert num.min == 0
    assert num.max is None
    assert num.step == 0.5


def test_number_impossible_values():
    with pytest.raises(ValueError):
        Number(min=0, max=10, step="a")

    with pytest.raises(ValueError):
        Number(min=0, max="a", step=0.5)

    with pytest.raises(ValueError):
        Number(min="a", max=10, step=0.5)

    with pytest.raises(ValueError):
        Number(min=0, max=10)

    with pytest.raises(ValueError):
        Number(min=10, max=1, step=1)

    with pytest.raises(ValueError):
        Number(min=10, max=0, step=1)


def test_string_tuple_of_strings():
    s = String(
        values=("a", "b", "c"), allow_custom=True, placeholder="Select an option"
    )
    assert s.values == ("a", "b", "c")
    assert s.allow_custom is True
    assert s.placeholder == "Select an option"


def test_string_tuple_of_tuples():
    s = String(
        values=(("a", "hello there"), ("b", "hello there"), ("c", "hello there")),
        allow_custom=True,
        placeholder="Select an option",
    )
    assert s.values == (
        ("a", "hello there"),
        ("b", "hello there"),
        ("c", "hello there"),
    )
    assert s.allow_custom is True
    assert s.placeholder == "Select an option"


def test_string_impossible_values():
    with pytest.raises(ValueError):
        String(values=("a", "b", "c"), allow_custom="a")

    with pytest.raises(ValueError):
        String(values=("a", "b", "c"), placeholder=True)


class TestDatasetValue:

    def test_get_value(self):
        """
        Test that NotImplementedError is raised when get_value is called directly

        This is a base class and should not be used directly.
        get_value is an abstract method.
        """
        dataset_value = DatasetValue()
        with pytest.raises(NotImplementedError):
            dataset_value.get_value(None, None, None)

    @pytest.mark.parametrize(
        "current_values, possible_values, prefer_with, expected",
        [
            (["a", "b"], ["a", "b", "c"], None, ["a", "b"]),
            (["a", "d"], ["a", "b", "c"], None, ["a"]),
            ([], ["a", "b", "c"], None, ["a"]),
            (["d", "e"], ["a", "b", "c"], None, ["a"]),
            ([], [], None, [""]),
            (["a", "b"], [], None, [""]),
        ],
    )
    def test_compute_current_values_basic(
        self, current_values, possible_values, prefer_with, expected
    ):
        result = DatasetValue._compute_current_values(
            current_values, possible_values, prefer_with
        )
        assert result == expected

    def test_compute_current_values_with_prefer_function(self):
        current_values = []
        possible_values = ["a", "b", "c", "d"]

        def prefer_with(x):
            return x in ["b", "c"]

        result = DatasetValue._compute_current_values(
            current_values, possible_values, prefer_with
        )
        assert result == ["b", "c"]

    def test_compute_current_values_with_prefer_function_single_match(self):
        current_values = []
        possible_values = ["a", "b", "d"]

        def prefer_with(x):
            return x in ["b", "c"]

        result = DatasetValue._compute_current_values(
            current_values, possible_values, prefer_with
        )
        assert result == ["b"]

    def test_compute_current_values_prefer_function_no_match(self):
        current_values = []
        possible_values = ["a", "b", "c"]

        def prefer_with(x):
            return x == "d"

        result = DatasetValue._compute_current_values(
            current_values, possible_values, prefer_with
        )
        assert result == [
            "a"
        ]  # Should return first possible value when no preference matches

    def test_compute_current_values_all_filtered_out(self):
        current_values = ["d", "e"]
        possible_values = ["a", "b", "c"]

        result = DatasetValue._compute_current_values(current_values, possible_values)
        assert result == [
            "a"
        ]  # Should return first possible value when all current values are filtered out

    @pytest.mark.parametrize(
        "current_values, possible_values",
        [
            (["a", "a", "b"], ["a", "b", "c"]),
            (["a", "b", "a"], ["a", "b", "c"]),
            (["a", "b", "a"], ["a", "b", "c", "a"]),
            (["a", "b"], ["a", "a", "b"]),
        ],
    )
    def test_compute_current_values_duplicates(self, current_values, possible_values):
        with pytest.raises(ValueError):
            DatasetValue._compute_current_values(current_values, possible_values)

    def test_compute_current_values_type_check(self):
        current_values = ["a", "b"]
        possible_values = ["a", "b", "c"]
        result = DatasetValue._compute_current_values(current_values, possible_values)
        assert isinstance(result, list)
        assert all(isinstance(item, str) for item in result)


# Mock dataset for testing
@pytest.fixture
def mock_dataset(temp_dir_structure):
    return {
        "path": str(temp_dir_structure),
        "dataframe": pd.DataFrame(
            {"col1": [1, 2, 3], "col2": ["a", "b", "c"], "col3": [True, False, True]}
        ),
    }


@pytest.mark.parametrize(
    "filename", ["file1.csv", "file2.json", "subdir1/file3.parquet", "non-existant"]
)
def test_files(mock_dataset, filename):
    files = Files()
    result, value = files.get_value(mock_dataset, filename, str)
    assert isinstance(result, String)
    assert value == os.path.join(mock_dataset["path"], "file1.csv")


@pytest.mark.parametrize("col", ["col1", "col2", "col3", "non-existant"])
def test_columns(mock_dataset, col):
    cols = Columns()
    result, value = cols.get_value(mock_dataset, col, str)
    assert isinstance(result, String)
    assert set(result.values) == {"col1", "col2", "col3"}
    if col == "non-existant":
        assert value == "col1"
    else:
        assert value == col