Add run_analysis/tests/test_core.py

run_analysis/tests/test_core.py

@@ -0,0 +1,65 @@
+import json
+import pytest
+from pathlib import Path
+
+import run_analysis.core as core
+
+@pytest.fixture()
+def sample_run_data():
+    # Representative dataset including negative and non-negative visibility_lag
+    return [
+        {"corr_id": "a1", "expires_at_dist_hours": 0.5, "visibility_lag": -2.3},
+        {"corr_id": "b2", "expires_at_dist_hours": 1.0, "visibility_lag": 0.0},
+        {"corr_id": "c3", "expires_at_dist_hours": 2.0, "visibility_lag": -0.5},
+        {"corr_id": "d4", "expires_at_dist_hours": 3.5, "visibility_lag": 1.2}
+    ]
+
+
+def test_analyze_run_data_basic(sample_run_data):
+    result = core.analyze_run_data(sample_run_data)
+
+    assert isinstance(result, dict), "Result should be a dictionary"
+    assert "total_count" in result
+    assert "negative_dt_count" in result
+    assert "negative_corr_ids" in result
+
+    assert result["total_count"] == len(sample_run_data)
+    assert result["negative_dt_count"] == 2, "Should detect exactly two negative cases"
+    assert set(result["negative_corr_ids"]) == {"a1", "c3"}
+
+    # optional mean values should be numbers or None
+    for key in ["mean_expires_at_dist_hours_neg", "mean_visibility_lag_neg"]:
+        val = result.get(key)
+        assert val is None or isinstance(val, (int, float))
+
+
+def test_analyze_run_data_no_negatives():
+    data = [
+        {"corr_id": "p1", "expires_at_dist_hours": 0.1, "visibility_lag": 0.2},
+        {"corr_id": "p2", "expires_at_dist_hours": 5.0, "visibility_lag": 1.0}
+    ]
+    result = core.analyze_run_data(data)
+    assert result["negative_dt_count"] == 0
+    assert result["negative_corr_ids"] == []
+
+
+def test_analyze_run_data_invalid_input():
+    # Missing field should trigger validation error
+    invalid_data = [{"corr_id": "z1", "expires_at_dist_hours": 1.0}]
+    with pytest.raises((KeyError, AssertionError, TypeError)):
+        core.analyze_run_data(invalid_data)
+
+
+def test_analyze_run_data_from_json_file(tmp_path):
+    data_path = tmp_path / "test_run_data.json"
+    input_data = [
+        {"corr_id": "x1", "expires_at_dist_hours": 2.0, "visibility_lag": -1.0},
+        {"corr_id": "x2", "expires_at_dist_hours": 3.0, "visibility_lag": 2.0}
+    ]
+    data_path.write_text(json.dumps(input_data))
+
+    run_data = json.loads(data_path.read_text())
+    result = core.analyze_run_data(run_data)
+
+    assert result["negative_dt_count"] == 1
+    assert result["negative_corr_ids"] == ["x1"]