upgini 1.2.71a3832.dev7__py3-none-any.whl → 1.2.71a3832.dev9__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.71a3832.dev7"
+__version__ = "1.2.71a3832.dev9"

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/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.dist-info → upgini-1.2.71a3832.dev9.dist-info}/METADATA

@@ -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.dev7.dist-info → upgini-1.2.71a3832.dev9.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=OM1SdEE1I5fkWcKRuW6LMCMJ-zfyOStMB1G7AONAIvI,33
+upgini/__about__.py,sha256=9j3uTsEOnjsLQKejDMGIw2xcYlikwx_zlJRLURdTIkE,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
@@ -6,7 +6,7 @@ upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
 upgini/features_enricher.py,sha256=Z6RSjqcqneGwWflsq1Q5rjf83awPNYqKpAgHRh7jils,204680
 upgini/http.py,sha256=RvzcShpDXssLs6ycGN8xilkKi8ZV9XGUrrk8bwdUzbw,43607
 upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
-upgini/metrics.py,sha256=cY9exGDlpmNcdvblhPVwBmBSlD_JyrgzMUMgh2r9r08,38440
+upgini/metrics.py,sha256=PlyjxL82AtUWgbCWRv_0r4NiPwmflO5ItIPlKb4nxcs,38293
 upgini/search_task.py,sha256=EuCGp0iCWz2fpuJgN6M47aP_CtIi3Oq9zw78w0mkKiU,17595
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -64,13 +64,13 @@ upgini/utils/mstats.py,sha256=u3gQVUtDRbyrOQK6V1UJ2Rx1QbkSNYGjXa6m3Z_dPVs,6286
 upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,10432
 upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
-upgini/utils/sklearn_ext.py,sha256=w27qbgzp5H-4W0LOHHzPUjtcVSchvJHw5sv5BFxNkt8,45076
+upgini/utils/sklearn_ext.py,sha256=HpaNQaKJisgNE7IZ71n7uswxTj7kbPglU2G3s1sORAc,45042
 upgini/utils/sort.py,sha256=8uuHs2nfSMVnz8GgvbOmgMB1PgEIZP1uhmeRFxcwnYw,7039
 upgini/utils/target_utils.py,sha256=b1GzO8_gMcwXSZ2v98CY50MJJBzKbWHId_BJGybXfkM,16579
 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-1.2.71a3832.dev7.dist-info/METADATA,sha256=BqO8gwjY5CjKw0UkrCOczYJQfbwyKlarV3WYCMbEBog,49101
-upgini-1.2.71a3832.dev7.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.71a3832.dev7.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.71a3832.dev7.dist-info/RECORD,,
+upgini-1.2.71a3832.dev9.dist-info/METADATA,sha256=MMv6QMrMxHQ50ISC1VoKtdK00hxtsgnz-IuuHuKUh7M,49101
+upgini-1.2.71a3832.dev9.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.71a3832.dev9.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.71a3832.dev9.dist-info/RECORD,,