upgini 1.2.68a3832.dev4__tar.gz → 1.2.68a3832.dev6__tar.gz

{upgini-1.2.68a3832.dev4 → upgini-1.2.68a3832.dev6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.68a3832.dev4
+Version: 1.2.68a3832.dev6
 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-1.2.68a3832.dev6/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.68a3832.dev6"

{upgini-1.2.68a3832.dev4 → upgini-1.2.68a3832.dev6}/src/upgini/dataset.py

@@ -388,7 +388,7 @@ class Dataset:  # (pd.DataFrame):
         for col in columns_to_validate:
             self.data[f"{col}_is_valid"] = ~self.data[col].isnull()
             if validate_target and target is not None and col == target:
-                self.data.loc[self.data[target] == np.Inf, f"{col}_is_valid"] = False
+                self.data.loc[self.data[target] == np.inf, f"{col}_is_valid"] = False
 
             if col in mandatory_columns:
                 self.data["valid_mandatory"] = self.data["valid_mandatory"] & self.data[f"{col}_is_valid"]

{upgini-1.2.68a3832.dev4 → upgini-1.2.68a3832.dev6}/src/upgini/metrics.py

@@ -101,6 +101,52 @@ LIGHTGBM_PARAMS = {
     "min_sum_hessian_in_leaf": 0.01,
 }
 
+LIGHTGBM_REGRESSION_PARAMS = {
+  "random_state": DEFAULT_RANDOM_STATE,
+  "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": "huber",
+  "verbosity": 0,
+}
+
+LIGHTGBM_MULTICLASS_PARAMS = {
+    "random_state": DEFAULT_RANDOM_STATE,
+    "n_estimators": 275,
+    "max_depth": 3,
+    "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,
+    "objective": "multiclass",
+    "class_weight": "balanced",
+    "verbosity": 0,
+}
+
+LIGHTGBM_BINARY_PARAMS = {
+    "random_state": DEFAULT_RANDOM_STATE,
+    "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",
+    "verbosity": 0,
+}
+
 N_FOLDS = 5
 BLOCKED_TS_TEST_SIZE = 0.2
 
@@ -441,28 +487,27 @@ class EstimatorWrapper:
         }
         if estimator is None:
             params = {}
-            params["has_time"] = has_date
             # if metric_name.upper() in SUPPORTED_CATBOOST_METRICS:
             #     params["eval_metric"] = SUPPORTED_CATBOOST_METRICS[metric_name.upper()]
             if target_type == ModelTaskType.MULTICLASS:
                 # params = _get_add_params(params, CATBOOST_MULTICLASS_PARAMS)
                 # params = _get_add_params(params, add_params)
                 # estimator = CatBoostWrapper(CatBoostClassifier(**params), **kwargs)
-                params = _get_add_params(params, LIGHTGBM_PARAMS)
+                params = _get_add_params(params, LIGHTGBM_MULTICLASS_PARAMS)
                 params = _get_add_params(params, add_params)
                 estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
             elif target_type == ModelTaskType.BINARY:
                 # params = _get_add_params(params, CATBOOST_BINARY_PARAMS)
                 # params = _get_add_params(params, add_params)
                 # estimator = CatBoostWrapper(CatBoostClassifier(**params), **kwargs)
-                params = _get_add_params(params, LIGHTGBM_PARAMS)
+                params = _get_add_params(params, LIGHTGBM_BINARY_PARAMS)
                 params = _get_add_params(params, add_params)
                 estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
             elif target_type == ModelTaskType.REGRESSION:
                 # params = _get_add_params(params, CATBOOST_REGRESSION_PARAMS)
                 # params = _get_add_params(params, add_params)
                 # estimator = CatBoostWrapper(CatBoostRegressor(**params), **kwargs)
-                params = _get_add_params(params, LIGHTGBM_PARAMS)
+                params = _get_add_params(params, LIGHTGBM_REGRESSION_PARAMS)
                 params = _get_add_params(params, add_params)
                 estimator = LightGBMWrapper(LGBMRegressor(**params), **kwargs)
             else:
@@ -474,6 +519,7 @@ class EstimatorWrapper:
                 estimator_copy = deepcopy(estimator)
             kwargs["estimator"] = estimator_copy
             if is_catboost_estimator(estimator):
+                params["has_time"] = has_date
                 if cat_features is not None:
                     for cat_feature in cat_features:
                         if cat_feature not in x.columns:
@@ -712,6 +758,8 @@ class LightGBMWrapper(EstimatorWrapper):
 
     def _prepare_to_fit(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, pd.Series, np.ndarray, dict]:
         x, y, groups, params = super()._prepare_to_fit(x, y)
+        if self.target_type == ModelTaskType.MULTICLASS:
+            params["num_class"] = y.nunique()
         self.cat_features = _get_cat_features(x)
         x = fill_na_cat_features(x, self.cat_features)
         for feature in self.cat_features:

upgini-1.2.68a3832.dev4/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.68a3832.dev4"