upgini 1.2.79a1__py3-none-any.whl → 1.2.80__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.79a1"
+__version__ = "1.2.80"

upgini/features_enricher.py

@@ -1119,7 +1119,7 @@ class FeaturesEnricher(TransformerMixin):
                         self.bundle.get("quality_metrics_rows_header"): _num_samples(fitting_X),
                     }
                     if model_task_type in [ModelTaskType.BINARY, ModelTaskType.REGRESSION] and is_numeric_dtype(
-                        validated_y
+                        y_sorted
                     ):
                         train_metrics[self.bundle.get("quality_metrics_mean_target_header")] = round(
                             # np.mean(validated_y), 4
@@ -1197,7 +1197,7 @@ class FeaturesEnricher(TransformerMixin):
                                 # self.bundle.get("quality_metrics_match_rate_header"): eval_hit_rate,
                             }
                             if model_task_type in [ModelTaskType.BINARY, ModelTaskType.REGRESSION] and is_numeric_dtype(
-                                validated_eval_set[idx][1]
+                                eval_y_sorted
                             ):
                                 eval_metrics[self.bundle.get("quality_metrics_mean_target_header")] = round(
                                     # np.mean(validated_eval_set[idx][1]), 4
@@ -3886,9 +3886,10 @@ if response.status_code == 200:
             if updated_shaps is not None:
                 updating_shap = updated_shaps.get(feature_meta.name)
                 if updating_shap is None:
-                    self.logger.warning(
-                        f"WARNING: Shap value for feature {feature_meta.name} not found and will be set to 0.0"
-                    )
+                    if feature_meta.shap_value != 0.0:
+                        self.logger.warning(
+                            f"WARNING: Shap value for feature {feature_meta.name} not found and will be set to 0.0"
+                        )
                     updating_shap = 0.0
                 feature_meta.shap_value = updating_shap
 

upgini/metrics.py

@@ -99,8 +99,7 @@ LIGHTGBM_REGRESSION_PARAMS = {
     "min_sum_hessian_in_leaf": 0.01,
     "objective": "huber",
     "deterministic": "true",
-    "force_col_wise": "true",
-    "force_row_wise": "true",
+    # "force_col_wise": "true",
     "verbosity": -1,
 }
 
@@ -120,8 +119,7 @@ LIGHTGBM_MULTICLASS_PARAMS = {
     "num_grad_quant_bins": "8",
     "stochastic_rounding": "true",
     "deterministic": "true",
-    "force_col_wise": "true",
-    "force_row_wise": "true",
+    # "force_col_wise": "true",
     "verbosity": -1,
 }
 
@@ -138,8 +136,7 @@ LIGHTGBM_BINARY_PARAMS = {
     "cat_smooth": 18,
     "cat_l2": 8,
     "deterministic": "true",
-    "force_col_wise": "true",
-    "force_row_wise": "true",
+    # "force_col_wise": "true",
     "verbosity": -1,
 }
 
@@ -148,33 +145,33 @@ LIGHTGBM_EARLY_STOPPING_ROUNDS = 20
 N_FOLDS = 5
 BLOCKED_TS_TEST_SIZE = 0.2
 
-NA_VALUES = [
-    "",
-    " ",
-    "   ",
-    "#n/a",
-    "#n/a n/a",
-    "#na",
-    "-1.#ind",
-    "-1.#qnan",
-    "-nan",
-    "1.#ind",
-    "1.#qnan",
-    "n/a",
-    "na",
-    "null",
-    "nan",
-    "n/a",
-    "nan",
-    "none",
-    "-",
-    "undefined",
-    "[[unknown]]",
-    "[not provided]",
-    "[unknown]",
-]
-
-NA_REPLACEMENT = "NA"
+# NA_VALUES = [
+#     "",
+#     " ",
+#     "   ",
+#     "#n/a",
+#     "#n/a n/a",
+#     "#na",
+#     "-1.#ind",
+#     "-1.#qnan",
+#     "-nan",
+#     "1.#ind",
+#     "1.#qnan",
+#     "n/a",
+#     "na",
+#     "null",
+#     "nan",
+#     "n/a",
+#     "nan",
+#     "none",
+#     "-",
+#     "undefined",
+#     "[[unknown]]",
+#     "[not provided]",
+#     "[unknown]",
+# ]
+
+# NA_REPLACEMENT = "NA"
 
 SUPPORTED_CATBOOST_METRICS = {
     s.upper(): s
@@ -761,8 +758,8 @@ class LightGBMWrapper(EstimatorWrapper):
             params["callbacks"] = [lgb.early_stopping(stopping_rounds=LIGHTGBM_EARLY_STOPPING_ROUNDS, verbose=False)]
         self.cat_features = _get_cat_features(x)
         if self.cat_features:
-            x = fill_na_cat_features(x, self.cat_features)
-            encoder = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1)
+            # x = fill_na_cat_features(x, self.cat_features)
+            encoder = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=np.nan)
             encoded = pd.DataFrame(
                 encoder.fit_transform(x[self.cat_features]), columns=self.cat_features, dtype="category"
             )
@@ -776,7 +773,7 @@ class LightGBMWrapper(EstimatorWrapper):
     def _prepare_to_calculate(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, dict]:
         x, y_numpy, params = super()._prepare_to_calculate(x, y)
         if self.cat_features is not None:
-            x = fill_na_cat_features(x, self.cat_features)
+            # x = fill_na_cat_features(x, self.cat_features)
             if self.cat_encoder is not None:
                 x[self.cat_features] = pd.DataFrame(
                     self.cat_encoder.transform(x[self.cat_features]), columns=self.cat_features, dtype="category"
@@ -860,7 +857,7 @@ class OtherEstimatorWrapper(EstimatorWrapper):
         self.cat_features = _get_cat_features(x)
         num_features = [col for col in x.columns if col not in self.cat_features]
         x[num_features] = x[num_features].fillna(-999)
-        x = fill_na_cat_features(x, self.cat_features)
+        # x = fill_na_cat_features(x, self.cat_features)
         # TODO use one-hot encoding if cardinality is less 50
         for feature in self.cat_features:
             x[feature] = x[feature].astype("category").cat.codes
@@ -873,7 +870,7 @@ class OtherEstimatorWrapper(EstimatorWrapper):
         if self.cat_features is not None:
             num_features = [col for col in x.columns if col not in self.cat_features]
             x[num_features] = x[num_features].fillna(-999)
-            x = fill_na_cat_features(x, self.cat_features)
+            # x = fill_na_cat_features(x, self.cat_features)
             # TODO use one-hot encoding if cardinality is less 50
             for feature in self.cat_features:
                 x[feature] = x[feature].astype("category").cat.codes
@@ -1059,10 +1056,10 @@ def _ext_mean_squared_log_error(y_true, y_pred, *, sample_weight=None, multioutp
     return mse if squared else np.sqrt(mse)
 
 
-def fill_na_cat_features(df: pd.DataFrame, cat_features: List[str]) -> pd.DataFrame:
-    for c in cat_features:
-        if c in df.columns:
-            df[c] = df[c].astype("string").fillna(NA_REPLACEMENT).astype(str)
-            na_filter = df[c].str.lower().isin(NA_VALUES)
-            df.loc[na_filter, c] = NA_REPLACEMENT
-    return df
+# def fill_na_cat_features(df: pd.DataFrame, cat_features: List[str]) -> pd.DataFrame:
+#     for c in cat_features:
+#         if c in df.columns:
+#             df[c] = df[c].astype("string").fillna(NA_REPLACEMENT).astype(str)
+#             na_filter = df[c].str.lower().isin(NA_VALUES)
+#             df.loc[na_filter, c] = NA_REPLACEMENT
+#     return df

{upgini-1.2.79a1.dist-info → upgini-1.2.80.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.79a1
+Version: 1.2.80
 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-1.2.79a1.dist-info → upgini-1.2.80.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=h3pHSW7QFH3c863fq8fxK5FCQiwhFda3blWAzoxplSE,25
+upgini/__about__.py,sha256=CoguueQtsTfVbd91MeGXrmsF-vGq7K1xnwf9nFL4qz0,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=_UkJS35uGaYtI7dR6Xd9Q28nmiPzTjhK3y8v3IjJTfQ,208245
+upgini/features_enricher.py,sha256=MQZ01u-7jR8nSTlsyvMzUt-FvsbsBjds2TvQZG5F4vM,208296
 upgini/http.py,sha256=UH7nswcZ221un3O_VW9limCBO5oRsyg1eKUHiVslRPs,43737
 upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
-upgini/metrics.py,sha256=l7r4cM-xrftcgOTv4uMQBHC_Sd820Z6umw5bIpP5wDI,39384
+upgini/metrics.py,sha256=pv3LELb8QObiaKcUco5YUfM_rP2c7hseK2qtjKmjBGk,39378
 upgini/search_task.py,sha256=RcvAE785yksWTsTNWuZFVNlk32jHElMoEna1T_C5N8Q,17823
 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=P0cCVRaakWLydYwFjk3TEaQfr0p0hfsJCvKRD8qcxiE,
 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-1.2.79a1.dist-info/METADATA,sha256=49MF6sCtAqdDrgL7s0hY2fm7T0ma0A5yeJQ6oIokZDo,49093
-upgini-1.2.79a1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.79a1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.79a1.dist-info/RECORD,,
+upgini-1.2.80.dist-info/METADATA,sha256=szsz09LH3Kv4SMNG8Ogut33IDG0Tzqln2JsrLiEXPBc,49091
+upgini-1.2.80.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.80.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.80.dist-info/RECORD,,