upgini 1.2.91a3884.dev5__py3-none-any.whl → 1.2.92__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.91a3884.dev5"
+__version__ = "1.2.92"

upgini/dataset.py

@@ -52,8 +52,6 @@ class Dataset:
     MIN_ROWS_COUNT = 100
     MAX_ROWS = 200_000
     IMBALANCE_THESHOLD = 0.6
-    BINARY_BOOTSTRAP_LOOPS = 5
-    MULTICLASS_BOOTSTRAP_LOOPS = 2
     MIN_TARGET_CLASS_ROWS = 100
     MAX_MULTICLASS_CLASS_COUNT = 100
     MIN_SUPPORTED_DATE_TS = 946684800000  # 2000-01-01

upgini/features_enricher.py

@@ -5,7 +5,6 @@ import hashlib
 import itertools
 import json
 import logging
-import numbers
 import os
 import sys
 import tempfile
@@ -303,6 +302,7 @@ class FeaturesEnricher(TransformerMixin):
         self.metrics: Optional[pd.DataFrame] = None
         self.feature_names_ = []
         self.external_source_feature_names = []
+        self.zero_shap_client_features = []
         self.feature_importances_ = []
         self.search_id = search_id
         self.disable_force_downsampling = disable_force_downsampling
@@ -2049,8 +2049,7 @@ class FeaturesEnricher(TransformerMixin):
         for idx, eval_pair in enumerate(eval_set):
             eval_x, eval_y = eval_pair
             eval_df_with_index = eval_x.copy()
-            if eval_y is not None:
-                eval_df_with_index[TARGET] = eval_y
+            eval_df_with_index[TARGET] = eval_y
             eval_df_with_index[EVAL_SET_INDEX] = idx + 1
             df = pd.concat([df, eval_df_with_index])
 
@@ -2669,7 +2668,7 @@ if response.status_code == 200:
             selecting_columns = [
                 c
                 for c in itertools.chain(validated_Xy.columns.tolist(), selected_generated_features)
-                if c not in self.external_source_feature_names or c in (self.id_columns or [])
+                if c not in self.zero_shap_client_features or c in (self.id_columns or [])
             ]
             selecting_columns.extend(c for c in result.columns if c in filtered_columns and c not in selecting_columns)
             if add_fit_system_record_id:
@@ -3296,7 +3295,7 @@ if response.status_code == 200:
         is_transform: bool = False,
     ) -> Tuple[pd.DataFrame, pd.Series, Optional[List[Tuple[pd.DataFrame, pd.Series]]]]:
         validated_X = self._validate_X(X, is_transform)
-        validated_y = self._validate_y(validated_X, y)
+        validated_y = self._validate_y(validated_X, y, enforce_y=not is_transform)
         validated_eval_set = self._validate_eval_set(validated_X, eval_set)
         return validated_X, validated_y, validated_eval_set
 
@@ -3380,8 +3379,8 @@ if response.status_code == 200:
 
         return validated_X
 
-    def _validate_y(self, X: pd.DataFrame, y) -> Optional[pd.Series]:
-        if y is None:
+    def _validate_y(self, X: pd.DataFrame, y, enforce_y: bool = True) -> Optional[pd.Series]:
+        if y is None and not enforce_y:
             return None
         if (
             not isinstance(y, pd.Series)
@@ -4064,6 +4063,7 @@ if response.status_code == 200:
 
         self.feature_names_ = []
         self.external_source_feature_names = []
+        self.zero_shap_client_features = []
         self.feature_importances_ = []
         features_info = []
         features_info_without_links = []
@@ -4099,6 +4099,8 @@ if response.status_code == 200:
 
             # TODO make a decision about selected features based on special flag from mlb
             if original_shaps.get(feature_meta.name, 0.0) == 0.0:
+                if is_client_feature and self.fit_select_features:
+                    self.zero_shap_client_features.append(original_name)
                 continue
 
             # Use only important features

upgini/utils/feature_info.py

@@ -155,7 +155,7 @@ def _get_internal_source(feature_meta: FeaturesMetadataV2, is_client_feature: bo
             and not feature_meta.name.endswith("_postal_code")
             and not is_client_feature
             else ""
-            )
+        )
 
 
 def _list_or_single(lst: List[str], single: str):
@@ -179,7 +179,7 @@ def _make_links(names: List[str], links: List[str]) -> str:
 
 
 def _round_shap_value(shap: float) -> float:
-    if shap > 0.0 and shap < 0.0001:
+    if shap >= 0.0 and shap < 0.0001:
         return 0.0001
     else:
         return round(shap, 4)

upgini/utils/sample_utils.py

@@ -173,7 +173,8 @@ def sample_time_series_train_eval(
                 logger=logger,
                 **kwargs,
             )
-        logger.info(f"Eval set size: {len(eval_df)}")
+        if logger is not None:
+            logger.info(f"Eval set size: {len(eval_df)}")
         df = pd.concat([train_df, eval_df])
 
     elif len(train_df) > max_rows:
@@ -189,7 +190,8 @@ def sample_time_series_train_eval(
     else:
         df = train_df
 
-    logger.info(f"Train set size: {len(df)}")
+    if logger is not None:
+        logger.info(f"Train set size: {len(df)}")
 
     return df
 

{upgini-1.2.91a3884.dev5.dist-info → upgini-1.2.92.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.91a3884.dev5
+Version: 1.2.92
 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-1.2.91a3884.dev5.dist-info → upgini-1.2.92.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=tqdF5EG5u2XotiGWCSnsQ61GODo019Lr-s097ItdAHs,33
+upgini/__about__.py,sha256=wXo9Q87kBdNAVEzs4oUkI_3AmrQDgiMvfXa7xRn9cOE,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=MituLJZTDdIwSk-Ia5G1pS52PERNHQ2P99FgCH2kTjQ,32790
+upgini/dataset.py,sha256=e6JDYTZ2AwC5aF-dqclKZKkiKrHo2f6cFmMQO2ZZmjM,32724
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=udQdXpqVO4YAwEHjUzS195k2jxe5_CtZ-KTpWRicjfs,218225
+upgini/features_enricher.py,sha256=wFeqZ30Dkhiyath--Jg6uVVoTwCdPJ42Rbe_smr1ue4,218465
 upgini/http.py,sha256=4i7fQwrwU3WzDUOWzrgR-4C8eJwj_5dBwRAR-UjUtlc,44345
 upgini/metadata.py,sha256=vsbbHyPCP3Rs8WkeDgQg99uAA_zmsbDStAT-NwDYhO4,12455
 upgini/metrics.py,sha256=Bc1L9DUmEL8OWwNvIEjPjw5EyHSZbiu3v2hWyBmedis,45313
@@ -56,7 +56,7 @@ upgini/utils/deduplicate_utils.py,sha256=EpBVCov42-FJIAPfa4jY_ZRct3N2MFaC7i-oJNZ
 upgini/utils/display_utils.py,sha256=hAeWEcJtPDg8fAVcMNrNB-azFD2WJp1nvbPAhR7SeP4,12071
 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=Q9HN6A-fvfVD-irFWrmOqqZG9RsUSvh5MTY_k0xu-tE,7287
+upgini/utils/feature_info.py,sha256=b3RvAeOHSEu-ZXWTrf42Dll_3ZUBL0pw7sdk7hgUKD0,7284
 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
@@ -64,14 +64,14 @@ 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/sample_utils.py,sha256=jQ1em2FRnMFLul9ujuBgs5XZ9jAZ4eM4FHT3aDSjOy8,15351
+upgini/utils/sample_utils.py,sha256=ETLPKQU_YngiYbdlnEoF2h7QS-3oN8et54q3Qs2ZAbA,15417
 upgini/utils/sklearn_ext.py,sha256=jLJWAKkqQinV15Z4y1ZnsN3c-fKFwXTsprs00COnyVU,49315
 upgini/utils/sort.py,sha256=8uuHs2nfSMVnz8GgvbOmgMB1PgEIZP1uhmeRFxcwnYw,7039
 upgini/utils/target_utils.py,sha256=i3Xt5l9ybB2_nF_ma5cfPuL3OeFTs2dY2xDI0p4Azpg,9049
 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-1.2.91a3884.dev5.dist-info/METADATA,sha256=A9MDv_VCFrWDDw2Xyo7Wsx3ps6ECwTul36gmw-wujgI,49546
-upgini-1.2.91a3884.dev5.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.91a3884.dev5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.91a3884.dev5.dist-info/RECORD,,
+upgini-1.2.92.dist-info/METADATA,sha256=yXqDsCwRNGqlytVFuoBL04Swo6xYo5lsk9_YHj-6PfQ,49536
+upgini-1.2.92.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.92.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.92.dist-info/RECORD,,