Первичная версия: стилометрия реплик, LSA и протокол экспериментов

lab1/tests/test_cv.py

@@ -0,0 +1,35 @@
+"""Тесты кросс-валидации на синтетических данных."""
+
+from __future__ import annotations
+
+import numpy as np
+import pandas as pd
+
+from stylometry.cv import run_repeated_cv
+
+
+def test_repeated_cv_runs_and_has_all_predictions() -> None:
+    rng = np.random.default_rng(0)
+    n_samples = 60
+    n_classes = 3
+    X = pd.DataFrame(
+        {
+            "feature_1": rng.normal(size=n_samples),
+            "feature_2": rng.normal(size=n_samples),
+        }
+    )
+    y = np.repeat([f"c{index}" for index in range(n_classes)], 20)
+    from sklearn.linear_model import LogisticRegression
+    from sklearn.pipeline import Pipeline
+    from sklearn.preprocessing import StandardScaler
+
+    pipeline = Pipeline(
+        [("scale", StandardScaler()), ("model", LogisticRegression(max_iter=1000))]
+    )
+    result = run_repeated_cv(
+        pipeline, X, y, n_splits=3, n_repeats=2, seed=42, verbose=False
+    )
+    assert len(result.oof) == n_samples * 2
+    assert set(result.oof["y_true"]) == set(y)
+    assert result.fold_metrics["macro_f1"].between(0, 1).all()
+    assert result.labels.tolist() == ["c0", "c1", "c2"]