New tests and his starting scripts

lab1/configs/tune_block_weights.toml

@@ -0,0 +1,13 @@
+# Ослабить потенциально шумные блоки после L2-нормировки.
+
+[cv]
+folds = 5
+repeats = 3
+seed = 42
+
+[features.block_weights]
+stylo = 1.0
+char = 0.5
+pos = 0.7
+lsa_word = 0.3
+lsa_pos = 0.5

lab1/configs/tune_char_narrow.toml

@@ -0,0 +1,13 @@
+# Более короткие char n-граммы, меньше признаков, строже min_df.
+
+[cv]
+folds = 5
+repeats = 3
+seed = 42
+
+[features]
+char_ngram_range = [2, 4]
+char_max_features = 3000
+pos_ngram_range = [1, 3]
+pos_max_features = 500
+min_df = 5

lab1/configs/tune_char_wide.toml

@@ -0,0 +1,13 @@
+# Более длинные n-граммы и больше признаков: риск переобучения.
+
+[cv]
+folds = 5
+repeats = 3
+seed = 42
+
+[features]
+char_ngram_range = [2, 6]
+char_max_features = 8000
+pos_ngram_range = [1, 4]
+pos_max_features = 800
+min_df = 2

lab1/configs/tune_lsa_k150.toml

@@ -0,0 +1,7 @@
+[cv]
+folds = 5
+repeats = 3
+seed = 42
+
+[features]
+lsa_components = 150

lab1/configs/tune_lsa_k300.toml

@@ -0,0 +1,7 @@
+[cv]
+folds = 5
+repeats = 3
+seed = 42
+
+[features]
+lsa_components = 300

lab1/configs/tune_no_vocab_readability.toml

@@ -0,0 +1,20 @@
+# Без нестабильных групп на коротких репликах.
+# Остальные поля пресета (n-граммы, LSA) не переопределяются.
+
+[cv]
+folds = 5
+repeats = 3
+seed = 42
+
+[features]
+groups = [
+    "length",
+    "lexical",
+    "characters",
+    "punctuation",
+    "function_words",
+    "pronouns",
+    "pos",
+    "syntax",
+    "dialogue",
+]

lab1/configs/tune_no_vocab_readability_length.toml

@@ -0,0 +1,18 @@
+# То же + без length: проверка, не объясняется ли сигнал длиной реплики.
+
+[cv]
+folds = 5
+repeats = 3
+seed = 42
+
+[features]
+groups = [
+    "lexical",
+    "characters",
+    "punctuation",
+    "function_words",
+    "pronouns",
+    "pos",
+    "syntax",
+    "dialogue",
+]