Первичная версия: стилометрия реплик, LSA и протокол экспериментов

lab1/tests/test_features.py

@@ -0,0 +1,38 @@
+"""Тесты ручных стилометрических признаков."""
+
+from __future__ import annotations
+
+import numpy as np
+
+from stylometry.datasets import load_feature_frame
+from stylometry.features import StylometricVectorizer, feature_dictionary
+
+
+def test_feature_matrix_shape_and_finiteness() -> None:
+    frame = load_feature_frame(verbose=False).head(20)
+    vectorizer = StylometricVectorizer()
+    matrix = vectorizer.fit_transform(frame)
+    names = vectorizer.get_feature_names_out()
+    assert matrix.shape == (20, len(names))
+    assert np.isfinite(matrix).all()
+    assert len(set(names)) == len(names)
+
+
+def test_feature_dictionary() -> None:
+    frame = load_feature_frame(verbose=False).head(2)
+    vectorizer = StylometricVectorizer()
+    vectorizer.fit(frame)
+    dictionary = feature_dictionary(vectorizer.get_feature_names_out())
+    assert len(dictionary) == len(vectorizer.get_feature_names_out())
+    assert {"feature", "group", "description", "status"} <= set(dictionary.columns)
+
+
+def test_group_subset() -> None:
+    frame = load_feature_frame(verbose=False).head(5)
+    vectorizer = StylometricVectorizer(groups=["length", "punctuation"])
+    matrix = vectorizer.fit_transform(frame)
+    assert matrix.shape[0] == 5
+    assert all(
+        name.startswith("len_") or name.startswith("punct_")
+        for name in vectorizer.get_feature_names_out()
+    )