upgini 1.2.121a1__py3-none-any.whl → 1.2.121a3__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.121a1"
+__version__ = "1.2.121a3"

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

@@ -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.dist-info → upgini-1.2.121a3.dist-info}/METADATA

@@ -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-1.2.121a1.dist-info → upgini-1.2.121a3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=lbqEfhDGdLuugmia7aJpwXt4xpDEZT5h_07_bMMutgk,26
+upgini/__about__.py,sha256=Cxw4BNratannn0d_z-lnfpv2ewsqbgmtVkJj8WoA6x0,26
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=pQ8JQe0cdygD-W9GefJmfE6bnj4EYzXsjlgWdIS9nS8,31578
@@ -38,7 +38,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 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=wkPQlQFK6EQdnOd1MxFCSmb8gEqzCYJX1isLPaeRsgU,4365
+upgini/utils/features_validator.py,sha256=5oNO8UV6SJ03fSkq15CQZARQZo-cii-hT9YbAbxE20o,4732
 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-1.2.121a1.dist-info/METADATA,sha256=8lCLPlcxApmxxhl8DgplSrHe_Z_GHqIiOLB66OCabPo,50745
-upgini-1.2.121a1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.121a1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.121a1.dist-info/RECORD,,
+upgini-1.2.121a3.dist-info/METADATA,sha256=Ej1y42arckLkQQc0FhSuzKTWK6FS8n7I_aSCSm5CPKQ,50745
+upgini-1.2.121a3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.121a3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.121a3.dist-info/RECORD,,