upgini 1.2.120__py3-none-any.whl → 1.2.121__py3-none-any.whl

upgini/__about__.py

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

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/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. Use int encoding for correct results of fit.\n{}
 
     # 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)
-
-            # 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)
+            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)
+
+        if one_hot_encoded_features:
+            msg = bundle.get("one_hot_encoded_features").format(one_hot_encoded_features)
+            warnings.append(msg)
 
         columns_renaming = columns_renaming or {}
 
@@ -102,3 +96,41 @@ 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:
+            # All rows should be the same type
+            if series.apply(lambda x: type(x)).nunique() != 1:
+                return False
+
+            # First, handle string representations of True/False
+            series_copy = series.copy()
+            if series_copy.dtype == "object" or series_copy.dtype == "string":
+                # Convert string representations of boolean values to numeric
+                series_copy = series_copy.astype(str).str.strip().str.lower()
+                series_copy = series_copy.replace({"true": "1", "false": "0"})
+
+            # Column contains only 0 and 1 (as strings or numbers or booleans)
+            series_copy = series_copy.astype(float)
+            if set(series_copy.unique()) != {0.0, 1.0}:
+                return False
+
+            series_copy = series_copy.astype(int)
+
+            # Column doesn't contain any NaN, np.NaN, space, null, etc.
+            if not (series_copy.isin([0, 1])).all():
+                return False
+
+            vc = series_copy.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-1.2.120.dist-info → upgini-1.2.121.dist-info}/METADATA

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

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=C4MPkUjPY8txHqkpCAHzv554Bvc9hUrOFMic1aakSTI,24
+upgini/__about__.py,sha256=LnV-34eDiq8p_t9q_FYO9NsfGtCG2wuABJi8Ifyn-H8,24
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=pQ8JQe0cdygD-W9GefJmfE6bnj4EYzXsjlgWdIS9nS8,31578
@@ -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=KcXm1Nl6c3zswL91tIbG0DjuuNpzxUdCg1cY9f2-9cg,29283
 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=A_3AX7X5u5AH7RLgkTiS6dHxaOiq5vm8w4ijQWLGcMY,4871
 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
@@ -74,7 +74,7 @@ upgini/utils/target_utils.py,sha256=GCPn4QeJ83JJ_vyBJ3IhY5fyIRkLC9q9BE59S2FRO1I,
 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-1.2.120.dist-info/METADATA,sha256=KFxeOoYvqFTE347dhf5EmvIskXqWMZvxYWy3AAwOyWI,50743
-upgini-1.2.120.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.120.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.120.dist-info/RECORD,,
+upgini-1.2.121.dist-info/METADATA,sha256=g69OOnXW2VfteF9jYTzpJwahQrMcwbIL0iXBYqyyE4o,50743
+upgini-1.2.121.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.121.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.121.dist-info/RECORD,,