Первичная версия: стилометрия реплик, LSA и протокол экспериментов

lab1/tests/test_io.py

@@ -0,0 +1,52 @@
+"""Тесты чтения и валидации корпуса."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import pandas as pd
+
+from stylometry.io import (
+    DEFAULT_DATA_PATH,
+    compare_with_stats,
+    corpus_fingerprint,
+    read_corpus,
+    read_stats,
+    validate_corpus,
+)
+
+
+def test_read_corpus_shape() -> None:
+    frame = read_corpus()
+    assert len(frame) == 2005
+    assert frame["character"].nunique() == 34
+    assert {"line_id", "text", "character", "text_raw", "placeholder_count"} <= set(frame.columns)
+    assert frame["text"].str.len().gt(0).all()
+
+
+def test_corpus_is_cp1251() -> None:
+    raw = DEFAULT_DATA_PATH.read_bytes()
+    assert raw.decode("cp1251").startswith("Реплика;Персонаж")
+
+
+def test_validate_corpus() -> None:
+    frame = read_corpus()
+    stats = validate_corpus(frame)
+    assert stats["n_lines"] == 2005
+    assert stats["n_characters"] == 34
+    assert stats["n_duplicate_texts"] == 0
+    assert stats["n_words"] > 30_000
+
+
+def test_compare_with_stats() -> None:
+    frame = read_corpus()
+    comparison = compare_with_stats(frame, read_stats())
+    assert not comparison.empty
+    assert (comparison["difference"] == 0).all()
+
+
+def test_fingerprint_is_stable() -> None:
+    first = corpus_fingerprint()
+    second = corpus_fingerprint()
+    assert first == second
+    assert len(first) == 64