upgini 1.2.71a3832.dev7__tar.gz → 1.2.71a3832.dev9__tar.gz

{upgini-1.2.71a3832.dev7 → upgini-1.2.71a3832.dev9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.71a3832.dev7
+Version: 1.2.71a3832.dev9
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

upgini-1.2.71a3832.dev9/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.71a3832.dev9"

{upgini-1.2.71a3832.dev7 → upgini-1.2.71a3832.dev9}/src/upgini/metrics.py

@@ -119,18 +119,16 @@ LIGHTGBM_REGRESSION_PARAMS = {
 
 LIGHTGBM_MULTICLASS_PARAMS = {
     "random_state": DEFAULT_RANDOM_STATE,
-    "deterministic": True,
-    "min_gain_to_split": 0.001,
     "n_estimators": 275,
-    "max_depth": 3,
+    "max_depth": 5,
+    "learning_rate": 0.05,
+    "min_gain_to_split": 0.001,
     "max_cat_threshold": 80,
-    "min_data_per_group": 25,
-    "cat_l2": 10,
-    "cat_smooth": 12,
-    "learning_rate": 0.25,  # CatBoost 0.25
-    "min_sum_hessian_in_leaf": 0.01,
-    "class_weight": "balanced",  # TODO pass dict with weights for each class
+    "min_data_per_group": 20,
+    "cat_smooth": 18,
+    "cat_l2" : 8,
     "objective": "multiclass",
+    "class_weight": "balanced",
     "use_quantized_grad": "true",
     "num_grad_quant_bins": "8",
     "stochastic_rounding": "true",
@@ -139,19 +137,17 @@ LIGHTGBM_MULTICLASS_PARAMS = {
 
 LIGHTGBM_BINARY_PARAMS = {
     "random_state": DEFAULT_RANDOM_STATE,
-    "deterministic": True,
     "min_gain_to_split": 0.001,
     "n_estimators": 275,
     "max_depth": 5,
-    "max_cat_threshold": 80,
-    "min_data_per_group": 25,
-    "cat_l2": 10,
-    "cat_smooth": 12,
     "learning_rate": 0.05,
-    "feature_fraction": 1.0,
-    "min_sum_hessian_in_leaf": 0.01,
     "objective": "binary",
-    "class_weight": "balanced",  # TODO pass dict with weights for each class
+    "class_weight": "balanced",
+    "deterministic": True,
+    "max_cat_threshold": 80,
+    "min_data_per_group": 20,
+    "cat_smooth": 18,
+    "cat_l2" : 8,
     "verbosity": -1,
 }
 
@@ -765,6 +761,8 @@ class LightGBMWrapper(EstimatorWrapper):
         if LIGHTGBM_EARLY_STOPPING_ROUNDS is not None:
             params["callbacks"] = [lgb.early_stopping(stopping_rounds=LIGHTGBM_EARLY_STOPPING_ROUNDS, verbose=False)]
         self.cat_features = _get_cat_features(x)
+        if self.cat_features:
+            params["categorical_feature"] = self.cat_features
         x = fill_na_cat_features(x, self.cat_features)
         for feature in self.cat_features:
             x[feature] = x[feature].astype("category").cat.codes

{upgini-1.2.71a3832.dev7 → upgini-1.2.71a3832.dev9}/src/upgini/utils/sklearn_ext.py

@@ -515,7 +515,7 @@ def _fit_and_score(
             if is_catboost_estimator(estimator):
                 fit_params = fit_params.copy()
                 fit_params["eval_set"] = [(X_test, y_test)]
-            elif is_lightgbm_estimator(estimator) and "callbacks" not in fit_params:
+            elif is_lightgbm_estimator(estimator):
                 fit_params = fit_params.copy()
                 fit_params["eval_set"] = [(X_test, y_test)]
             estimator.fit(X_train, y_train, **fit_params)

upgini-1.2.71a3832.dev7/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.71a3832.dev7"