Первичная версия: стилометрия реплик, LSA и протокол экспериментов

lab1/tests/test_delta.py

@@ -0,0 +1,41 @@
+"""Тесты дельты Барроуза."""
+
+from __future__ import annotations
+
+import numpy as np
+import pandas as pd
+
+from stylometry.delta import DeltaClassifier, MFWVectorizer
+
+
+def _toy_frame() -> pd.DataFrame:
+    texts = [
+        "the cat sat on the mat",
+        "the cat sat on the mat again",
+        "the dog sat on the log",
+        "the dog sat on the log again",
+        "a cat and a dog",
+        "a cat and a dog again",
+    ]
+    labels = ["cat", "cat", "dog", "dog", "cat", "dog"]
+    return pd.DataFrame({"text": texts, "character": labels})
+
+
+def test_mfw_vectorizer_shape() -> None:
+    frame = _toy_frame()
+    vectorizer = MFWVectorizer(n_features=5)
+    matrix = vectorizer.fit_transform(frame)
+    assert matrix.shape == (6, 5)
+    assert np.isfinite(matrix).all()
+
+
+def test_delta_fit_predict() -> None:
+    frame = _toy_frame()
+    classifier = DeltaClassifier(n_features=5, metric="manhattan")
+    classifier.fit(frame, frame["character"].values)
+    predictions = classifier.predict(frame)
+    assert len(predictions) == len(frame)
+    assert set(predictions) <= {"cat", "dog"}
+    probabilities = classifier.predict_proba(frame)
+    assert probabilities.shape == (len(frame), 2)
+    assert np.allclose(probabilities.sum(axis=1), 1.0)