upgini 1.2.68a3832.dev8__tar.gz → 1.2.68a3832.dev10__tar.gz

{upgini-1.2.68a3832.dev8 → upgini-1.2.68a3832.dev10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.68a3832.dev8
+Version: 1.2.68a3832.dev10
 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.dev10/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.68a3832.dev10"

{upgini-1.2.68a3832.dev8 → upgini-1.2.68a3832.dev10}/src/upgini/metrics.py

@@ -127,8 +127,11 @@ LIGHTGBM_MULTICLASS_PARAMS = {
     "cat_smooth": 12,
     "learning_rate": 0.25,  # CatBoost 0.25
     "min_sum_hessian_in_leaf": 0.01,
-    "objective": "softmax",
     "class_weight": "balanced",  # TODO pass dict with weights for each class
+    "objective": "multiclass",
+    "use_quantized_grad": "true",
+    "num_grad_quant_bins": "8",
+    "stochastic_rounding": "true",
     "verbosity": -1,
 }
 
@@ -491,30 +494,15 @@ class EstimatorWrapper:
         }
         if estimator is None:
             params = {}
-            # emb_pattern = r"(.+)_emb\d+"
-            # emb_features = [c for c in x.columns if re.match(emb_pattern, c) and is_numeric_dtype(x[c])]
-            # max_bin_by_feature_type = {
-            #     feature: 63 if feature in emb_features else 255 for feature in x.columns
-            # }
-            # params["max_bin_by_feature_type"] = max_bin_by_feature_type
             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_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_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_REGRESSION_PARAMS)
                 params = _get_add_params(params, add_params)
                 estimator = LightGBMWrapper(LGBMRegressor(**params), **kwargs)
@@ -527,18 +515,19 @@ 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:
                             logger.error(
                                 f"Client cat_feature `{cat_feature}` not found in x columns: {x.columns.to_list()}"
                             )
-                    estimator_copy.set_params(cat_features=cat_features)
+                    estimator_copy.set_params(cat_features=cat_features, has_time=has_date)
                 estimator = CatBoostWrapper(**kwargs)
             else:
                 if isinstance(estimator, (LGBMClassifier, LGBMRegressor)):
                     estimator = LightGBMWrapper(**kwargs)
+                elif is_catboost_estimator(estimator):
+                    estimator = CatBoostWrapper(**kwargs)
                 else:
                     logger.warning(
                         f"Unexpected estimator is used for metrics: {estimator}. "
@@ -765,14 +754,12 @@ class LightGBMWrapper(EstimatorWrapper):
         self.cat_features = None
 
     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()
+        x, y_numpy, groups, params = super()._prepare_to_fit(x, y)
         self.cat_features = _get_cat_features(x)
         x = fill_na_cat_features(x, self.cat_features)
         for feature in self.cat_features:
             x[feature] = x[feature].astype("category").cat.codes
-        if not is_numeric_dtype(y):
+        if not is_numeric_dtype(y_numpy):
             y = correct_string_target(y)
 
         return x, y, groups, params

{upgini-1.2.68a3832.dev8 → upgini-1.2.68a3832.dev10}/src/upgini/utils/feature_info.py

@@ -90,7 +90,8 @@ class FeatureInfo:
 def _get_feature_sample(feature_meta: FeaturesMetadataV2, data: Optional[pd.DataFrame]) -> str:
     if data is not None and len(data) > 0 and feature_meta.name in data.columns:
         if len(data) > 3:
-            feature_sample = np.random.choice(data[feature_meta.name].dropna().unique(), 3).tolist()
+            rand = np.random.RandomState(42)
+            feature_sample = rand.choice(data[feature_meta.name].dropna().unique(), 3).tolist()
         else:
             feature_sample = data[feature_meta.name].dropna().unique().tolist()
         if len(feature_sample) > 0 and isinstance(feature_sample[0], float):

upgini-1.2.68a3832.dev8/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.68a3832.dev8"