upgini 1.2.120a1__py3-none-any.whl → 1.2.121a2__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.120a1"
+__version__ = "1.2.121a2"

upgini/data_source/data_source_publisher.py

@@ -519,21 +519,24 @@ class DataSourcePublisher:
         description: str = "",
     ):
         if model_type is not None and model_type not in ["ONNX", "CATBOOST"]:
-            raise ValueError(f"Invalid model type: {model_type}. Available values: ONNX")
+            raise ValueError(f"Invalid model type: {model_type}. Available values: ONNX, CATBOOST")
         metadata = {
             "modelName": name,
             "inputNames": input_names,
             "dateColumn": date_column,
             "scoreName": score_name,
             "searchTaskId": search_id,
-            "modelType": model_type or "ONNX",
+            "modelType": model_type or "CATBOOST",
             "description": description,
         }
 
         trace_id = str(uuid.uuid4())
         with MDC(trace_id=trace_id):
             try:
-                self._rest_client.upload_autofe_model(file_path, metadata, trace_id)
+                result = self._rest_client.upload_autofe_model(file_path, metadata, trace_id)
+                if "ERROR" in result:
+                    raise Exception(result)
+                print(result)
             except Exception:
                 self.logger.exception("Failed to upload autofe model")
                 raise

upgini/dataset.py

@@ -694,9 +694,7 @@ class Dataset:
 
     def prepare_uploading_file(self, base_path: str) -> str:
         parquet_file_path = f"{base_path}/{self.dataset_name}.parquet"
-        print("Before saving parquet file")
         self.data.to_parquet(path=parquet_file_path, index=False, compression="gzip", engine="fastparquet")
-        print("After saving parquet file")
         uploading_file_size = Path(parquet_file_path).stat().st_size
         self.logger.info(f"Size of prepared uploading file: {uploading_file_size}. {len(self.data)} rows")
         if uploading_file_size > self.MAX_UPLOADING_FILE_SIZE:

upgini/features_enricher.py

@@ -1028,13 +1028,7 @@ class FeaturesEnricher(TransformerMixin):
                     columns_renaming,
                     _,
                 ) = prepared_data
-
-                # rename baseline_score_column
-                reversed_renaming = {v: k for k, v in columns_renaming.items()}
-                baseline_score_column = self.baseline_score_column
-                if baseline_score_column is not None:
-                    baseline_score_column = reversed_renaming[baseline_score_column]
-
+                
                 gc.collect()
 
                 if fitting_X.shape[1] == 0 and fitting_enriched_X.shape[1] == 0:
@@ -1089,7 +1083,7 @@ class FeaturesEnricher(TransformerMixin):
                             has_time=has_time,
                         )
                         baseline_cv_result = baseline_estimator.cross_val_predict(
-                            fitting_X, y_sorted, baseline_score_column
+                            fitting_X, y_sorted, self.baseline_score_column
                         )
                         baseline_metric = baseline_cv_result.get_display_metric()
                         if baseline_metric is None:
@@ -1192,7 +1186,7 @@ class FeaturesEnricher(TransformerMixin):
                                     f"on client features: {eval_X_sorted.columns.to_list()}"
                                 )
                                 etalon_eval_results = baseline_estimator.calculate_metric(
-                                    eval_X_sorted, eval_y_sorted, baseline_score_column
+                                    eval_X_sorted, eval_y_sorted, self.baseline_score_column
                                 )
                                 etalon_eval_metric = etalon_eval_results.get_display_metric()
                                 self.logger.info(
@@ -2502,6 +2496,9 @@ if response.status_code == 200:
     ) -> tuple[pd.DataFrame, dict[str, str], list[str], dict[str, SearchKey]]:
         if self._search_task is None:
             raise NotFittedError(self.bundle.get("transform_unfitted_enricher"))
+        features_meta = self._search_task.get_all_features_metadata_v2()
+        if features_meta is None:
+            raise NotFittedError(self.bundle.get("transform_unfitted_enricher"))
 
         start_time = time.time()
         search_id = self.search_id or (self._search_task.search_task_id if self._search_task is not None else None)
@@ -2531,7 +2528,6 @@ if response.status_code == 200:
                 self.__display_support_link(msg)
                 return None, {}, [], self.search_keys
 
-            features_meta = self._search_task.get_all_features_metadata_v2()
             online_api_features = [fm.name for fm in features_meta if fm.from_online_api and fm.shap_value > 0]
             if len(online_api_features) > 0:
                 self.logger.warning(
@@ -3382,6 +3378,7 @@ if response.status_code == 200:
             except KeyboardInterrupt as e:
                 print(self.bundle.get("search_stopping"))
                 self.rest_client.stop_search_task_v2(trace_id, self._search_task.search_task_id)
+                self._search_task = None
                 self.logger.warning(f"Search {self._search_task.search_task_id} stopped by user")
                 print(self.bundle.get("search_stopped"))
                 raise e

upgini/http.py

@@ -426,26 +426,19 @@ class _RestClient:
     ) -> SearchTaskResponse:
         api_path = self.INITIAL_SEARCH_URI_FMT_V2
 
-        print("Before getting track metrics")
         track_metrics = get_track_metrics(self.client_ip, self.client_visitorid)
-        print("After getting track metrics")
 
         def open_and_send():
             md5_hash = hashlib.md5()
-            print("Before opening file to calculate hashes")
             with open(file_path, "rb") as file:
                 content = file.read()
                 md5_hash.update(content)
                 digest = md5_hash.hexdigest()
                 metadata_with_md5 = pydantic_copy_method(metadata)(update={"checksumMD5": digest})
-            print("After calculating md5")
 
-            print("Before calculating sha256")
             digest_sha256 = file_hash(file_path)
-            print("After calculating sha256")
             metadata_with_md5 = pydantic_copy_method(metadata_with_md5)(update={"digest": digest_sha256})
 
-            print("Before opening file to send")
             with open(file_path, "rb") as file:
                 files = {
                     "metadata": (
@@ -473,12 +466,9 @@ class _RestClient:
                     )
                 additional_headers = {self.SEARCH_KEYS_HEADER_NAME: ",".join(self.search_keys_meaning_types(metadata))}
 
-                print("Before sending request for initial search")
-                response = self._send_post_file_req_v2(
+                return self._send_post_file_req_v2(
                     api_path, files, trace_id=trace_id, additional_headers=additional_headers
                 )
-                print("After sending request")
-                return response
 
         response = self._with_unauth_retry(open_and_send)
         return SearchTaskResponse(response)

upgini/resource_bundle/strings.properties

@@ -155,7 +155,7 @@ target_outliers_warning=We detected {} outliers in your sample.\nExamples of out
     # features validation
 empty_or_contant_features=Columns {} has value with frequency more than 99%, removed from X
 high_cardinality_features=Columns {} has high cardinality (>90% unique values), removed from X
-# one_hot_encoded_features=One hot encoded features detected. Use int encoding for correct results of fit.\n{}
+one_hot_encoded_features=One hot encoded features detected: {}
 
     # Dataset validation
 dataset_too_few_rows=X size should be at least {} rows after validation

upgini/utils/features_validator.py

@@ -24,7 +24,7 @@ class FeaturesValidator:
         features_for_generate: Optional[List[str]] = None,
         columns_renaming: Optional[Dict[str, str]] = None,
     ) -> Tuple[List[str], List[str]]:
-        # one_hot_encoded_features = []
+        one_hot_encoded_features = []
         empty_or_constant_features = []
         high_cardinality_features = []
         warnings = []
@@ -36,23 +36,17 @@ class FeaturesValidator:
             value_counts = column.value_counts(dropna=False, normalize=True)
             most_frequent_percent = value_counts.iloc[0]
 
-            if most_frequent_percent >= 0.99:
+            if len(value_counts) == 1:
                 empty_or_constant_features.append(f)
+            elif most_frequent_percent >= 0.99:
+                if self.is_one_hot_encoded(column):
+                    one_hot_encoded_features.append(f)
+                else:
+                    empty_or_constant_features.append(f)
 
-            # TODO implement one-hot encoding check
-            # if len(value_counts) == 1:
-            #     empty_or_constant_features.append(f)
-            # elif most_frequent_percent >= 0.99:
-            #     empty_or_constant_features.append(f)
-            #     if set(value_counts.index.to_list()) == {0, 1}:
-            #         one_hot_encoded_features.append(f)
-            #     else:
-            #         empty_or_constant_features.append(f)
-            #     continue
-
-        # if one_hot_encoded_features:
-        #     msg = bundle.get("one_hot_encoded_features").format(one_hot_encoded_features)
-        #     warnings.append(msg)
+        if one_hot_encoded_features:
+            msg = bundle.get("one_hot_encoded_features").format(one_hot_encoded_features)
+            self.logger.info(msg)
 
         columns_renaming = columns_renaming or {}
 
@@ -102,3 +96,30 @@ class FeaturesValidator:
     @staticmethod
     def find_constant_features(df: pd.DataFrame) -> List[str]:
         return [i for i in df if df[i].nunique() <= 1]
+
+    @staticmethod
+    def is_one_hot_encoded(series: pd.Series) -> bool:
+        try:
+            # Column contains only 0 and 1 (as strings or numbers)
+            series = series.astype(float)
+            if set(series.unique()) != {0.0, 1.0}:
+                return False
+
+            series = series.astype(int)
+
+            # Column doesn't contain any NaN, np.NaN, space, null, etc.
+            if not (series.isin([0, 1])).all():
+                return False
+
+            vc = series.value_counts()
+            # Column should contain both 0 and 1
+            if len(vc) != 2:
+                return False
+
+            # Minority class is 1
+            if vc[1] >= vc[0]:
+                return False
+
+            return True
+        except ValueError:
+            return False

upgini/utils/sklearn_ext.py

@@ -1301,6 +1301,7 @@ def _encode_cat_features(X_train, y_train, X_test, y_test, cat_features, estimat
             encoder = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1)
             encoder.fit(X_train[cat_features], y_train)
 
+            # OrdinalEncoder doesn't support progressive encoding with target
             X_train[cat_features] = encoder.transform(X_train[cat_features]).astype(int)
             X_test[cat_features] = encoder.transform(X_test[cat_features]).astype(int)
 
@@ -1314,10 +1315,8 @@ def _encode_cat_features(X_train, y_train, X_test, y_test, cat_features, estimat
             encoder = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1)
             encoder.fit(X_train[cat_features], y_train)
 
-            # Progressive encoding on train (using y)
-            X_train[cat_features] = encoder.transform(X_train[cat_features], y_train).astype(int)
-
-            # Static encoding on validation (no y)
+            # OrdinalEncoder doesn't support progressive encoding with target
+            X_train[cat_features] = encoder.transform(X_train[cat_features]).astype(int)
             X_test[cat_features] = encoder.transform(X_test[cat_features]).astype(int)
 
             return X_train, y_train, X_test, y_test, [], encoder

{upgini-1.2.120a1.dist-info → upgini-1.2.121a2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.120a1
+Version: 1.2.121a2
 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-1.2.120a1.dist-info → upgini-1.2.121a2.dist-info}/RECORD

@@ -1,10 +1,10 @@
-upgini/__about__.py,sha256=J4ou6xfTwIgzTXi7mnxG9WD4vn49_cFGZVdB8RZEIPM,26
+upgini/__about__.py,sha256=Dv8DzHbPAHs_fY_MACW4HNqnYW7CilejShdVPFkTaYM,26
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=9xYeqp-Ti3-QcsucyxlDFOHQef6ZQsBX7bOZMCyT2rM,31665
+upgini/dataset.py,sha256=pQ8JQe0cdygD-W9GefJmfE6bnj4EYzXsjlgWdIS9nS8,31578
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=C9pZKusj_QnG9coPVAa1a_88VC-lLR4Tre4uC10yt04,231852
-upgini/http.py,sha256=CzDgSrYH6-R14G0d8xPyLalb-w42fjj9XOHVXh7leyM,44835
+upgini/features_enricher.py,sha256=Du1S72F55cqyKbHT3VGSPnJO3XicWABFVkA2-G3chdA,231696
+upgini/http.py,sha256=-J_wOpnwVnT0ebPC6sOs6fN3AWtCD0LJLu6nlYmxaqk,44348
 upgini/metadata.py,sha256=VzgtgEbPPtNxTrj9LM5qSDP3DujHwAXqbUSKBjPcb9c,12477
 upgini/metrics.py,sha256=KCPE_apPN-9BIdv6GqASbJVaB_gBcy8wzNApAcyaGo4,46020
 upgini/search_task.py,sha256=SAiUd1AytbA2Q6PSnnztr7oTRKpud1wQZ5YtKjsmQHU,18256
@@ -31,14 +31,14 @@ upgini/autofe/timeseries/roll.py,sha256=zADKXU-eYWQnQ5R3am1yEal8uU6Tm0jLAixwPb_a
 upgini/autofe/timeseries/trend.py,sha256=K1_iw2ko_LIUU8YCUgrvN3n0MkHtsi7-63-8x9er1k4,2129
 upgini/autofe/timeseries/volatility.py,sha256=SvZfhM_ZAWCNpTf87WjSnZsnlblARgruDlu4By4Zvhc,8078
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/data_source/data_source_publisher.py,sha256=suRmAF1i7yiZ8vJjpEKdVr5Wqtr7o1_vjAhaN9B4DU0,26518
+upgini/data_source/data_source_publisher.py,sha256=qXQUYErhCmkWHm2FWgTL0FYZ2aJbxtSDV94OCM3eqUU,26653
 upgini/mdc/__init__.py,sha256=iHJlXQg6xRM1-ZOUtaPSJqw5SpQDszvxp4LyqviNLIQ,1027
 upgini/mdc/context.py,sha256=3u1B-jXt7tXEvNcV3qmR9SDCseudnY7KYsLclBdwVLk,1405
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/normalizer/normalize_utils.py,sha256=mDh2mBW3aQMB4EFP2aHbf2dGMVkOcWnp4sKKvKDBh8w,8511
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=cNeVkWZMyjGCYGqmOOeJqisqPSEBtmfIw_U1rmgQw4w,29285
+upgini/resource_bundle/strings.properties,sha256=Kmc6ZHpo0hK-bEQuoQkU0SPIQCnIDYRKqkfN3a_gvRU,29237
 upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=Fva2FEhLiNRPZ9Q6uOtJRtRzwsayjv7aphalAZO_4lc,6452
@@ -58,7 +58,7 @@ upgini/utils/display_utils.py,sha256=uSG3JwpwCIgRJXsp-8ktuJ0Dh-WFti7IrRLMUfHfoDc
 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=6vihytwKma_TlXtTn4l6Aj4kqlOj0ouLy-yWVV6VUw8,7551
-upgini/utils/features_validator.py,sha256=lEfmk4DoxZ4ooOE1HC0ZXtUb_lFKRFHIrnFULZ4_rL8,3746
+upgini/utils/features_validator.py,sha256=RAnfX80GBFcz6-SlTSR0DF6BZzf7A7IL8dlIqEoSz_s,4265
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
 upgini/utils/hash_utils.py,sha256=mP2yHyzvDNdpa5g3B4MHzulxBeEz_ZSoGl1YF_VnAyE,5538
 upgini/utils/ip_utils.py,sha256=wmnnwVQdjX9o1cNQw6VQMk6maHhvsq6hNsZBYf9knrw,6585
@@ -68,13 +68,13 @@ upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
 upgini/utils/psi.py,sha256=vw8QEktXSx29IiMJMxmDeFU_4lJInJBXt_XL5Muekzo,11114
 upgini/utils/sample_utils.py,sha256=xpfYaZ2cYP7I2JrcooVc13QNBFawB81cJRuh38451Q4,15123
-upgini/utils/sklearn_ext.py,sha256=jLJWAKkqQinV15Z4y1ZnsN3c-fKFwXTsprs00COnyVU,49315
+upgini/utils/sklearn_ext.py,sha256=Pcy8sWD6f4YcE5Bu0UmXD4j0ICmXtrT8DJlTArM-_a0,49356
 upgini/utils/sort.py,sha256=8uuHs2nfSMVnz8GgvbOmgMB1PgEIZP1uhmeRFxcwnYw,7039
 upgini/utils/target_utils.py,sha256=GCPn4QeJ83JJ_vyBJ3IhY5fyIRkLC9q9BE59S2FRO1I,10882
 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-1.2.120a1.dist-info/METADATA,sha256=Ai4c0bpRvXFgEYB78zVltQNbWv6HpPdc96IAw85kPJI,50745
-upgini-1.2.120a1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.120a1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.120a1.dist-info/RECORD,,
+upgini-1.2.121a2.dist-info/METADATA,sha256=1XVh2jWKC2I3ElN4ftyEveTny9C1pU5z69Osnp6q7_s,50745
+upgini-1.2.121a2.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.121a2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.121a2.dist-info/RECORD,,