upgini 1.2.68a3832.dev7__py3-none-any.whl → 1.2.68a3832.dev9__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.68a3832.dev7"
+__version__ = "1.2.68a3832.dev9"

upgini/metrics.py

@@ -491,26 +491,15 @@ class EstimatorWrapper:
         }
         if estimator is None:
             params = {}
-            # 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_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)
@@ -523,18 +512,19 @@ 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}. "
@@ -761,20 +751,12 @@ 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()
-        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
+        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/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.dev7.dist-info → upgini-1.2.68a3832.dev9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.68a3832.dev7
+Version: 1.2.68a3832.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-1.2.68a3832.dev7.dist-info → upgini-1.2.68a3832.dev9.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=CR4sN9ZhYNXzf0xJ61KtPk3O9k_pn-EljmzdfIfJyoM,33
+upgini/__about__.py,sha256=PUD99JYjzGuY1b4bkoVfexbGcQ412xzz1bitG33oTYM,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=1rb6BzyuiQFGVCTDmKL2wox3UFRNjtNaIJOwQnZ801A,34956
@@ -7,7 +7,7 @@ upgini/features_enricher.py,sha256=GXXx14jwf3F26_KrfJ6O40Vcu1hRx5iBjUB_jxy3Xvg,2
 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=onr-wFpP0idy0SH3Wxv2xnqxT5H5MiP70o44f1PhfFw,38808
+upgini/metrics.py,sha256=5g2N-z7IFH52tkgeOQjOq2-lsn-s1S4PtEWlwoS14jg,37629
 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
@@ -56,7 +56,7 @@ upgini/utils/deduplicate_utils.py,sha256=SMZx9IKIhWI5HqXepfKiQb3uDJrogQZtG6jcWuM
 upgini/utils/display_utils.py,sha256=DsBjJ8jEYAh8BPgfAbzq5imoGFV6IACP20PQ78BQCX0,11964
 upgini/utils/email_utils.py,sha256=pZ2vCfNxLIPUhxr0-OlABNXm12jjU44isBk8kGmqQzA,5277
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
-upgini/utils/feature_info.py,sha256=m1tQcT3hTChPAiXzpk0WQcEqElj8KgeCifEJFa7-gss,7247
+upgini/utils/feature_info.py,sha256=Q9HN6A-fvfVD-irFWrmOqqZG9RsUSvh5MTY_k0xu-tE,7287
 upgini/utils/features_validator.py,sha256=lEfmk4DoxZ4ooOE1HC0ZXtUb_lFKRFHIrnFULZ4_rL8,3746
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
 upgini/utils/ip_utils.py,sha256=TSQ_qDsLlVnm09X1HacpabEf_HNqSWpxBF4Sdc2xs08,6580
@@ -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.dev7.dist-info/METADATA,sha256=LZ6mg6092FrqWu_yNWdMKTMgOC9lYclcPCQFLyMQAW0,49149
-upgini-1.2.68a3832.dev7.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.68a3832.dev7.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.68a3832.dev7.dist-info/RECORD,,
+upgini-1.2.68a3832.dev9.dist-info/METADATA,sha256=zgbDmansWs-GTVIg9WJrS86ZRfIZ4Psx-2Ao7JVFIQs,49149
+upgini-1.2.68a3832.dev9.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.68a3832.dev9.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.68a3832.dev9.dist-info/RECORD,,