upgini 1.2.121a1__tar.gz → 1.2.121a3__tar.gz

{upgini-1.2.121a1 → upgini-1.2.121a3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.121a1
+Version: 1.2.121a3
 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-1.2.121a3/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.121a3"

{upgini-1.2.121a1 → upgini-1.2.121a3}/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: {}
 
     # Dataset validation
 dataset_too_few_rows=X size should be at least {} rows after validation

{upgini-1.2.121a1 → upgini-1.2.121a3}/src/upgini/utils/features_validator.py

@@ -36,9 +36,6 @@ class FeaturesValidator:
             value_counts = column.value_counts(dropna=False, normalize=True)
             most_frequent_percent = value_counts.iloc[0]
 
-            if most_frequent_percent >= 0.99:
-                empty_or_constant_features.append(f)
-
             if len(value_counts) == 1:
                 empty_or_constant_features.append(f)
             elif most_frequent_percent >= 0.99:
@@ -103,18 +100,25 @@ class FeaturesValidator:
     @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}:
+            # 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 = series.astype(int)
+            series_copy = series_copy.astype(int)
 
             # Column doesn't contain any NaN, np.NaN, space, null, etc.
-            if not (series.isin([0, 1])).all():
+            if not (series_copy.isin([0, 1])).all():
                 return False
 
-            vc = series.value_counts()
+            vc = series_copy.value_counts()
             # Column should contain both 0 and 1
             if len(vc) != 2:
                 return False

upgini-1.2.121a1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.121a1"