upgini 1.2.68a3832.dev4__py3-none-any.whl → 1.2.68a3832.dev6__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.68a3832.dev4"
+__version__ = "1.2.68a3832.dev6"

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/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.dist-info → upgini-1.2.68a3832.dev6.dist-info}/METADATA

@@ -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.dev4.dist-info → upgini-1.2.68a3832.dev6.dist-info}/RECORD

@@ -1,13 +1,13 @@
-upgini/__about__.py,sha256=tA-8e1UEPt8tajFxx1rKXEmQOOfuqGfXLGYhIFUctPM,33
+upgini/__about__.py,sha256=8CoP2d6NQy3RuFamWKCHcwiF2GYkyj5rtk6FIpBm0rI,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=OGjpeFHbj3lWiZTOHTpWEoMMDmFY1FlNC44FKktoZvU,34956
+upgini/dataset.py,sha256=1rb6BzyuiQFGVCTDmKL2wox3UFRNjtNaIJOwQnZ801A,34956
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
 upgini/features_enricher.py,sha256=GXXx14jwf3F26_KrfJ6O40Vcu1hRx5iBjUB_jxy3Xvg,205476
 upgini/http.py,sha256=ud0Cp7h0jNeHuuZGpU_1dAAEiabGoJjGxc1X5oeBQr4,43496
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=Jh6YTaS00m_nbaOY_owvlSyn9zgkErkqu8iTr9ZjKI8,12279
-upgini/metrics.py,sha256=0WIe1IQx9vzUK0pVGv3hODBrOL3zaLDybXbs5S_ntvQ,36991
+upgini/metrics.py,sha256=ZBAjInLCm15BBYWNi9kz6IJs8R0WrF2PkrLnLAodR1Y,38246
 upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -70,7 +70,7 @@ upgini/utils/target_utils.py,sha256=b1GzO8_gMcwXSZ2v98CY50MJJBzKbWHId_BJGybXfkM,
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.68a3832.dev4.dist-info/METADATA,sha256=N1U1IshnQeHVgYDyt_pa2G7SezelEjMUjcdNOQ1KxkQ,49149
-upgini-1.2.68a3832.dev4.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.68a3832.dev4.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.68a3832.dev4.dist-info/RECORD,,
+upgini-1.2.68a3832.dev6.dist-info/METADATA,sha256=UWgAnrn5D5mQT6Js-sXVBCA1wPW7YZU-JEEcnRdUCHU,49149
+upgini-1.2.68a3832.dev6.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.68a3832.dev6.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.68a3832.dev6.dist-info/RECORD,,