Добавлены параметры моделей, веса блоков и руководство по настройке

lab1/stylometry/pipelines.py

@@ -45,6 +45,9 @@ class FeatureConfig:
     lsa_components: int = 100
     stylo_scaler: str = "standard"  # standard | minmax | none
     stylo_normalize: bool = True
+    # Веса блоков в FeatureUnion: stylo, char, pos, lsa_word, lsa_pos и т.д.
+    # Пустой словарь означает равный вес блоков.
+    block_weights: dict[str, float] = field(default_factory=dict)
     include_stylo: bool = True
     include_lsa: bool = True
     char_max_features: int = 5000
@@ -150,7 +153,18 @@ def build_feature_union(config: FeatureConfig) -> Any:
 
     if len(branches) == 1:
         return branches[0][1]
-    return FeatureUnion(branches)
+
+    union_kwargs: dict[str, Any] = {}
+    if config.block_weights:
+        branch_names = {name for name, _ in branches}
+        unknown = set(config.block_weights) - branch_names
+        if unknown:
+            raise ValueError(
+                f"Неизвестные блоки в block_weights: {sorted(unknown)}. "
+                f"Доступны: {sorted(branch_names)}"
+            )
+        union_kwargs["transformer_weights"] = dict(config.block_weights)
+    return FeatureUnion(branches, **union_kwargs)
 
 
 def make_classifier(name: str, **params: Any) -> Any:
@@ -159,19 +173,24 @@ def make_classifier(name: str, **params: Any) -> Any:
         strategy = params.pop("strategy", "most_frequent")
         return DummyClassifier(strategy=strategy)
     if name == "multinomial_nb":
-        return MultinomialNB(alpha=params.pop("alpha", 1.0))
+        return MultinomialNB(
+            alpha=params.pop("alpha", 1.0),
+            fit_prior=params.pop("fit_prior", True),
+        )
     if name == "logreg":
         return LogisticRegression(
             C=params.pop("C", 1.0),
-            solver="lbfgs",
-            max_iter=5000,
-            class_weight="balanced",
+            solver=params.pop("solver", "lbfgs"),
+            max_iter=params.pop("max_iter", 5000),
+            class_weight=params.pop("class_weight", "balanced"),
         )
     if name == "linear_svc":
         return LinearSVC(
             C=params.pop("C", 1.0),
-            class_weight="balanced",
-            max_iter=20_000,
+            loss=params.pop("loss", "squared_hinge"),
+            tol=params.pop("tol", 1e-4),
+            class_weight=params.pop("class_weight", "balanced"),
+            max_iter=params.pop("max_iter", 20_000),
             dual="auto",
         )
     if name == "random_forest":
@@ -179,7 +198,9 @@ def make_classifier(name: str, **params: Any) -> Any:
             n_estimators=params.pop("n_estimators", 400),
             max_depth=params.pop("max_depth", None),
             min_samples_leaf=params.pop("min_samples_leaf", 1),
-            class_weight="balanced_subsample",
+            min_samples_split=params.pop("min_samples_split", 2),
+            max_features=params.pop("max_features", "sqrt"),
+            class_weight=params.pop("class_weight", "balanced_subsample"),
             n_jobs=-1,
             random_state=params.pop("random_state", 42),
         )
@@ -188,7 +209,9 @@ def make_classifier(name: str, **params: Any) -> Any:
             n_estimators=params.pop("n_estimators", 400),
             max_depth=params.pop("max_depth", None),
             min_samples_leaf=params.pop("min_samples_leaf", 1),
-            class_weight="balanced",
+            min_samples_split=params.pop("min_samples_split", 2),
+            max_features=params.pop("max_features", "sqrt"),
+            class_weight=params.pop("class_weight", "balanced"),
             n_jobs=-1,
             random_state=params.pop("random_state", 42),
         )