Первичная версия: стилометрия реплик, LSA и протокол экспериментов

lab1/tests/test_lsa.py

@@ -0,0 +1,45 @@
+"""Тесты TF-IDF и LSA."""
+
+from __future__ import annotations
+
+import numpy as np
+
+from stylometry.datasets import load_feature_frame
+from stylometry.lsa import (
+    make_char_ngram_vectorizer,
+    make_lsa_vectorizer,
+    make_pos_ngram_vectorizer,
+    make_text_vectorizer,
+)
+
+
+def test_lsa_word_shape_and_variance() -> None:
+    frame = load_feature_frame(verbose=False).head(100)
+    vectorizer = make_lsa_vectorizer("word", n_components=10)
+    matrix = vectorizer.fit_transform(frame)
+    assert matrix.shape == (100, 10)
+    assert np.isfinite(matrix).all()
+    assert 0 <= vectorizer.cumulative_explained_variance_[-1] <= 1.0
+    assert len(vectorizer.top_terms(5)) == 10
+
+
+def test_lsa_pos_and_char() -> None:
+    frame = load_feature_frame(verbose=False).head(100)
+    for variant in ("pos", "char"):
+        vectorizer = make_lsa_vectorizer(variant, n_components=5)
+        matrix = vectorizer.fit_transform(frame)
+        assert matrix.shape[0] == 100
+        assert matrix.shape[1] == 5
+        assert np.isfinite(matrix).all()
+
+
+def test_text_vectorizers() -> None:
+    frame = load_feature_frame(verbose=False).head(50)
+    for vectorizer in (
+        make_text_vectorizer("word"),
+        make_pos_ngram_vectorizer(),
+        make_char_ngram_vectorizer(),
+    ):
+        matrix = vectorizer.fit_transform(frame)
+        assert matrix.shape[0] == 50
+        assert matrix.shape[1] > 0