Первичная версия: стилометрия реплик, LSA и протокол экспериментов

lab1/tests/test_metadata.py

@@ -0,0 +1,36 @@
+"""Тесты анализа по метаданным персонажей."""
+
+from __future__ import annotations
+
+import pandas as pd
+
+from stylometry.metadata import (
+    group_confusions,
+    load_character_metadata,
+    subgroup_report,
+)
+
+
+def test_metadata_table() -> None:
+    metadata = load_character_metadata()
+    assert len(metadata) == 34
+    assert {"character", "gender", "age_group", "species", "role"} <= set(metadata.columns)
+
+
+def test_subgroup_report() -> None:
+    metadata = load_character_metadata()
+    y_true = ["Abigail", "Abigail", "Alex", "Alex"]
+    y_pred = ["Abigail", "Alex", "Alex", "Alex"]
+    labels = ["Abigail", "Alex"]
+    report = subgroup_report(y_true, y_pred, labels, metadata, "gender")
+    assert {"group", "weighted_f1", "n_samples"} <= set(report.columns)
+    assert report["n_samples"].sum() == 4
+
+
+def test_group_confusions() -> None:
+    metadata = load_character_metadata()
+    y_true = ["Abigail", "Abigail", "Alex", "Alex"]
+    y_pred = ["Abigail", "Alex", "Alex", "Abigail"]
+    table = group_confusions(y_true, y_pred, metadata, "gender")
+    assert not table.empty
+    assert {"true_group", "pred_group", "count"} <= set(table.columns)