upgini 1.1.275a99__tar.gz → 1.1.277__tar.gz

{upgini-1.1.275a99/src/upgini.egg-info → upgini-1.1.277}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.275a99
+Version: 1.1.277
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.275a99 → upgini-1.1.277}/setup.py

@@ -40,7 +40,7 @@ def send_log(msg: str):
 
 
 here = Path(__file__).parent.resolve()
-version = "1.1.275a99"
+version = "1.1.277"
 try:
     send_log(f"Start setup PyLib version {version}")
     setup(

{upgini-1.1.275a99 → upgini-1.1.277}/src/upgini/ads.py

@@ -5,7 +5,7 @@ from typing import Dict, Optional
 
 import numpy as np
 import pandas as pd
-from pandas.api.types import is_string_dtype
+from pandas.api.types import is_object_dtype, is_string_dtype
 
 from upgini import SearchKey
 from upgini.http import get_rest_client
@@ -34,7 +34,11 @@ def upload_user_ads(name: str, df: pd.DataFrame, search_keys: Dict[str, SearchKe
             if df[column_name].notnull().sum() < min_valid_rows_count:
                 raise ValueError(bundle.get("ads_upload_to_many_empty_rows"))
             meaning_type = search_keys[column_name].value
-            if meaning_type == FileColumnMeaningType.MSISDN and not is_string_dtype(df[column_name]):
+            if (
+                meaning_type == FileColumnMeaningType.MSISDN
+                and not is_string_dtype(df[column_name])
+                and not is_object_dtype(df[column_name])
+            ):
                 df[column_name] = df[column_name].values.astype(np.int64).astype("string")  # type: ignore
         else:
             meaning_type = FileColumnMeaningType.FEATURE

{upgini-1.1.275a99 → upgini-1.1.277}/src/upgini/dataset.py

@@ -17,6 +17,7 @@ from pandas.api.types import (
     is_numeric_dtype,
     is_period_dtype,
     is_string_dtype,
+    is_object_dtype,
 )
 
 from upgini.errors import ValidationError
@@ -219,7 +220,7 @@ class Dataset:  # (pd.DataFrame):
         """Check that string values less than maximum characters for LLM"""
         # self.logger.info("Validate too long string values")
         for col in self.data.columns:
-            if is_string_dtype(self.data[col]):
+            if is_string_dtype(self.data[col]) or is_object_dtype(self.data[col]):
                 max_length: int = self.data[col].astype("str").str.len().max()
                 if max_length > self.MAX_STRING_FEATURE_LENGTH:
                     self.data[col] = self.data[col].astype("str").str.slice(stop=self.MAX_STRING_FEATURE_LENGTH)
@@ -350,7 +351,7 @@ class Dataset:  # (pd.DataFrame):
         if postal_code is not None and postal_code in self.data.columns:
             # self.logger.info("Normalize postal code")
 
-            if is_string_dtype(self.data[postal_code]):
+            if is_string_dtype(self.data[postal_code]) or is_object_dtype(self.data[postal_code]):
                 try:
                     self.data[postal_code] = self.data[postal_code].astype("float64").astype("Int64").astype("string")
                 except Exception:
@@ -821,7 +822,7 @@ class Dataset:  # (pd.DataFrame):
             return DataType.INT
         elif is_float_dtype(pandas_data_type):
             return DataType.DECIMAL
-        elif is_string_dtype(pandas_data_type):
+        elif is_string_dtype(pandas_data_type) or is_object_dtype(pandas_data_type):
             return DataType.STRING
         else:
             msg = self.bundle.get("dataset_invalid_column_type").format(column_name, pandas_data_type)

{upgini-1.1.275a99 → upgini-1.1.277}/src/upgini/features_enricher.py

@@ -21,6 +21,7 @@ from pandas.api.types import (
     is_bool,
     is_datetime64_any_dtype,
     is_numeric_dtype,
+    is_object_dtype,
     is_period_dtype,
     is_string_dtype,
 )
@@ -2982,7 +2983,7 @@ class FeaturesEnricher(TransformerMixin):
 
     def __correct_target(self, df: pd.DataFrame) -> pd.DataFrame:
         target = df[self.TARGET_NAME]
-        if is_string_dtype(target):
+        if is_string_dtype(target) or is_object_dtype(target):
             maybe_numeric_target = pd.to_numeric(target, errors="coerce")
             # If less than 5% is non numeric then leave this rows with NaN target and later it will be dropped
             if maybe_numeric_target.isna().sum() <= _num_samples(df) * 0.05:
@@ -3255,6 +3256,8 @@ class FeaturesEnricher(TransformerMixin):
             descriptions = []
             for m in autofe_meta:
                 autofe_feature = Feature.from_formula(m.formula)
+                orig_to_hashed = {base_column.original_name: base_column.hashed_name for base_column in m.base_columns}
+                autofe_feature.rename_columns(orig_to_hashed)
                 autofe_feature.set_display_index(m.display_index)
                 if autofe_feature.op.is_vector:
                     continue
@@ -3382,7 +3385,8 @@ class FeaturesEnricher(TransformerMixin):
                 valid_search_keys[column_name] = SearchKey.CUSTOM_KEY
             else:
                 if x[column_name].isnull().all() or (
-                    is_string_dtype(x[column_name]) and (x[column_name].astype("string").str.strip() == "").all()
+                    (is_string_dtype(x[column_name]) or is_object_dtype(x[column_name]))
+                    and (x[column_name].astype("string").str.strip() == "").all()
                 ):
                     raise ValidationError(self.bundle.get("empty_search_key").format(column_name))
 

{upgini-1.1.275a99 → upgini-1.1.277}/src/upgini/utils/__init__.py

@@ -2,7 +2,7 @@ import itertools
 from typing import List, Tuple
 
 import pandas as pd
-from pandas.api.types import is_string_dtype
+from pandas.api.types import is_string_dtype, is_object_dtype
 
 
 def combine_search_keys(search_keys: List[str]) -> List[Tuple[str]]:
@@ -20,5 +20,6 @@ def find_numbers_with_decimal_comma(df: pd.DataFrame) -> pd.DataFrame:
     return [
         col
         for col in tmp.columns
-        if is_string_dtype(tmp[col]) and tmp[col].astype("string").str.match("^[0-9]+,[0-9]*$").any()
+        if (is_string_dtype(tmp[col]) or is_object_dtype(tmp[col]))
+        and tmp[col].astype("string").str.match("^[0-9]+,[0-9]*$").any()
     ]

{upgini-1.1.275a99 → upgini-1.1.277}/src/upgini/utils/country_utils.py

@@ -1,5 +1,5 @@
 import pandas as pd
-from pandas.api.types import is_string_dtype
+from pandas.api.types import is_string_dtype, is_object_dtype
 
 from upgini.utils.base_search_key_detector import BaseSearchKeyDetector
 
@@ -9,7 +9,7 @@ class CountrySearchKeyDetector(BaseSearchKeyDetector):
         return "country" in str(column_name).lower()
 
     def _is_search_key_by_values(self, column: pd.Series) -> bool:
-        if not is_string_dtype(column):
+        if not is_string_dtype(column) and not is_object_dtype(column):
             return False
 
         all_count = len(column)

{upgini-1.1.275a99 → upgini-1.1.277}/src/upgini/utils/datetime_utils.py

@@ -6,7 +6,10 @@ from typing import Dict, List, Optional
 import numpy as np
 import pandas as pd
 from dateutil.relativedelta import relativedelta
-from pandas.api.types import is_numeric_dtype, is_period_dtype, is_string_dtype
+from pandas.api.types import (
+    is_numeric_dtype,
+    is_period_dtype,
+)
 
 from upgini.errors import ValidationError
 from upgini.metadata import SearchKey
@@ -78,9 +81,6 @@ class DateTimeSearchKeyConverter:
             df[self.date_column] = df[self.date_column].apply(lambda x: x.replace(tzinfo=None))
         elif isinstance(df[self.date_column].values[0], datetime.date):
             df[self.date_column] = pd.to_datetime(df[self.date_column], errors="coerce")
-        elif is_string_dtype(df[self.date_column]):
-            df[self.date_column] = df[self.date_column].apply(self.clean_date)
-            df[self.date_column] = self.parse_date(df)
         elif is_period_dtype(df[self.date_column]):
             df[self.date_column] = pd.to_datetime(df[self.date_column].astype("string"))
         elif is_numeric_dtype(df[self.date_column]):
@@ -249,7 +249,8 @@ def validate_dates_distribution(
             if col in search_keys:
                 continue
             try:
-                pd.to_datetime(X[col])
+                # Format mixed to avoid massive warnings
+                pd.to_datetime(X[col], format="mixed")
                 maybe_date_col = col
                 break
             except Exception:

{upgini-1.1.275a99 → upgini-1.1.277}/src/upgini/utils/email_utils.py

@@ -4,7 +4,7 @@ from hashlib import sha256
 from typing import Dict, List, Optional
 
 import pandas as pd
-from pandas.api.types import is_string_dtype
+from pandas.api.types import is_string_dtype, is_object_dtype
 from upgini.resource_bundle import bundle
 
 from upgini.metadata import SearchKey
@@ -18,7 +18,7 @@ class EmailSearchKeyDetector(BaseSearchKeyDetector):
         return str(column_name).lower() in ["email", "e_mail", "e-mail"]
 
     def _is_search_key_by_values(self, column: pd.Series) -> bool:
-        if not is_string_dtype(column):
+        if not is_string_dtype(column) and not is_object_dtype:
             return False
         if not column.astype("string").str.contains("@").any():
             return False

{upgini-1.1.275a99 → upgini-1.1.277}/src/upgini/utils/target_utils.py

@@ -107,7 +107,7 @@ def balance_undersample(
     min_class_count = vc[min_class_value]
 
     min_class_percent = imbalance_threshold / target_classes_count
-    min_class_threshold = min_class_percent * count
+    min_class_threshold = int(min_class_percent * count)
 
     resampled_data = df
     df = df.copy().sort_values(by=SYSTEM_RECORD_ID)

{upgini-1.1.275a99 → upgini-1.1.277/src/upgini.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.275a99
+Version: 1.1.277
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers