upgini 1.2.120__tar.gz → 1.2.121__tar.gz

{upgini-1.2.120 → upgini-1.2.121}/PKG-INFO

@@ -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-1.2.121/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.121"

{upgini-1.2.120 → upgini-1.2.121}/src/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-1.2.120 → upgini-1.2.121}/src/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-1.2.120 → upgini-1.2.121}/src/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/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.120"