File size: 6,089 Bytes
2c29579
 
1120492
2c29579
1120492
2c29579
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
807485b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1120492
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import json
import math
import os

from infra.database import DatasetModel, ExperimentRun, JobModel
from tests.conftest import TestingSessionLocal


def test_health_check(client):
    response = client.get("/health")
    assert response.status_code == 200
    assert response.json()["status"] == "ok"


def test_get_jobs_empty(client):
    # Depending on DB setup, it might be empty
    response = client.get("/api/jobs")
    assert response.status_code == 200
    assert isinstance(response.json(), list)


def test_get_experiments(client):
    response = client.get("/api/experiments")
    assert response.status_code == 200
    assert isinstance(response.json(), list)


def test_get_leaderboard(client):
    response = client.get("/api/leaderboard")
    assert response.status_code == 200
    assert isinstance(response.json(), list)


def test_404_not_found(client):
    response = client.get("/api/this_does_not_exist")
    assert response.status_code == 404


def test_status_endpoint_sanitizes_nan_payloads(client):
    with TestingSessionLocal() as db:
        db.add(
            JobModel(
                id="job-with-nan",
                dataset_id="ds-1",
                status="completed",
                history_json=json.dumps([{"time": "Final", "metric": math.nan}]),
                results_json='{"best_model":"LGBM","score":NaN,"leaderboard":[{"model":"LGBM","score":NaN}]}',
                insights_json='{"confidence":NaN}',
                reasoning_json=json.dumps(["done"]),
            )
        )
        db.commit()

    response = client.get("/api/status/job-with-nan")

    assert response.status_code == 200
    body = response.json()
    assert body["history"] == [{"time": "Final", "metric": None}]
    assert body["results"]["score"] == 0.0
    assert body["results"]["leaderboard"] == [{"model": "LGBM", "score": None}]
    assert body["insights"] == {"confidence": None}


def test_experiments_endpoint_sanitizes_nan_payloads(client):
    with TestingSessionLocal() as db:
        db.add(
            ExperimentRun(
                id="exp-with-nan",
                job_id="job-exp-nan",
                dataset_id="ds-1",
                model_name="LGBM",
                metric_name="Accuracy",
                score=math.nan,
                task_type="classification",
                mode="Balanced",
                goal="Performance",
                feature_count=5,
                row_count=100,
                hyperparams_json='{"depth": 8, "lr": NaN}',
                metrics_json='{"precision": NaN, "recall": 88.1}',
                leaderboard_json='[{"model":"LGBM","score":NaN}]',
            )
        )
        db.commit()

    response = client.get("/api/experiments")

    assert response.status_code == 200
    rows = response.json()
    target = next(row for row in rows if row["id"] == "exp-with-nan")
    assert target["score"] is None
    assert target["hyperparams"] == {"depth": 8, "lr": None}
    assert target["metrics"] == {"precision": None, "recall": 88.1}
    assert target["leaderboard"] == [{"model": "LGBM", "score": None}]


def test_workspace_latest_restores_dataset_and_job(client, tmp_path):
    csv_path = tmp_path / "workspace.csv"
    csv_path.write_text("feature,target\n1,yes\n2,no\n", encoding="utf-8")

    with TestingSessionLocal() as db:
        db.add(
            DatasetModel(
                id="workspace-ds",
                file_path=os.fspath(csv_path),
                profile_json=json.dumps(
                    {
                        "rows": 2,
                        "cols": 2,
                        "columns": ["feature", "target"],
                        "suggested_target": "target",
                        "task_type": "classification",
                    }
                ),
                source_type="upload",
            )
        )
        db.add(
            JobModel(
                id="workspace-job",
                dataset_id="workspace-ds",
                status="completed",
                history_json=json.dumps([{"time": "Final", "metric": 93.2}]),
                results_json=json.dumps({"best_model": "LiteGBM", "score": 93.2}),
            )
        )
        db.commit()

    response = client.get("/api/workspace/latest")

    assert response.status_code == 200
    body = response.json()
    assert body["dataset"]["id"] == "workspace-ds"
    assert body["dataset"]["profile"]["suggested_target"] == "target"
    assert body["dataset"]["preview_records"][0]["feature"] == 1
    assert body["job"]["id"] == "workspace-job"


def test_workspace_restore_honors_explicit_job_id(client):
    with TestingSessionLocal() as db:
        if not db.query(DatasetModel).filter(DatasetModel.id == "workspace-ds").first():
            db.add(
                DatasetModel(
                    id="workspace-ds",
                    file_path="tests/data/dummy_data.csv",
                    profile_json=json.dumps(
                        {
                            "rows": 2,
                            "cols": 2,
                            "columns": ["feature", "target"],
                            "suggested_target": "target",
                            "task_type": "classification",
                        }
                    ),
                    source_type="upload",
                )
            )
        if not db.query(JobModel).filter(JobModel.id == "workspace-job").first():
            db.add(
                JobModel(
                    id="workspace-job",
                    dataset_id="workspace-ds",
                    status="completed",
                    history_json=json.dumps([{"time": "Final", "metric": 93.2}]),
                    results_json=json.dumps({"best_model": "LiteGBM", "score": 93.2}),
                )
            )
        db.commit()

    response = client.get("/api/workspace/restore", params={"job_id": "workspace-job"})

    assert response.status_code == 200
    body = response.json()
    assert body["job"]["id"] == "workspace-job"
    assert body["dataset"]["id"] == "workspace-ds"