upgini 1.2.142a1__tar.gz → 1.2.143__tar.gz

{upgini-1.2.142a1 → upgini-1.2.143}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: upgini
-Version: 1.2.142a1
+Version: 1.2.143
 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-1.2.143/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.143"

{upgini-1.2.142a1 → upgini-1.2.143}/src/upgini/features_enricher.py

@@ -2553,9 +2553,7 @@ if response.status_code == 200:
 
         self.__validate_search_keys(search_keys, self.search_id)
 
-        validated_X, validated_y, validated_eval_set = self._validate_train_eval(
-            X, y, eval_set=None, is_transform=True
-        )
+        validated_X, validated_y, validated_eval_set = self._validate_train_eval(X, y, eval_set=None, is_transform=True)
         df = self.__combine_train_and_eval_sets(validated_X, validated_y, validated_eval_set)
 
         validated_Xy = df.copy()
@@ -3239,6 +3237,7 @@ if response.status_code == 200:
         )
         self.fit_columns_renaming = normalizer.columns_renaming
         if normalizer.removed_datetime_features:
+            self.fit_dropped_features.update(normalizer.removed_datetime_features)
             original_removed_datetime_features = [
                 self.fit_columns_renaming.get(f, f) for f in normalizer.removed_datetime_features
             ]
@@ -4783,7 +4782,7 @@ if response.status_code == 200:
         maybe_date = [k for k, v in valid_search_keys.items() if v in [SearchKey.DATE, SearchKey.DATETIME]]
         if (self.cv is None or self.cv == CVType.k_fold) and len(maybe_date) > 0 and not silent_mode:
             date_column = next(iter(maybe_date))
-            if x[date_column].nunique() > 0.9 * _num_samples(x):
+            if x[date_column].nunique() > 0.9 * _num_samples(x) and not is_transform:
                 msg = self.bundle.get("date_search_without_time_series")
                 self.__log_warning(msg)
 
@@ -5024,7 +5023,9 @@ if response.status_code == 200:
                                 f"File x.parquet was already uploaded with digest {x_digest_sha256}, skipping"
                             )
                         else:
-                            self.rest_client.dump_input_file(f"{tmp_dir}/x.parquet", "x.parquet", x_digest_sha256)
+                            self.rest_client.dump_input_file(
+                                trace_id_, f"{tmp_dir}/x.parquet", "x.parquet", x_digest_sha256
+                            )
 
                         if y_ is not None:
                             if isinstance(y_, pd.Series):

{upgini-1.2.142a1 → upgini-1.2.143}/src/upgini/utils/datetime_utils.py

@@ -282,10 +282,13 @@ class DateTimeConverter:
                     warnings.filterwarnings("ignore", message="Could not infer format")
                     return pd.to_datetime(df[self.date_column])
             except ValueError:
-                if raise_errors:
-                    raise ValidationError(self.bundle.get("invalid_date_format").format(self.date_column))
-                else:
-                    return None
+                try:
+                    return pd.to_datetime(df[self.date_column], format="mixed", errors="raise")
+                except ValueError:
+                    if raise_errors:
+                        raise ValidationError(self.bundle.get("invalid_date_format").format(self.date_column))
+                    else:
+                        return None
 
     def clean_old_dates(self, df: pd.DataFrame) -> pd.DataFrame:
         condition = df[self.date_column] <= self.MIN_SUPPORTED_DATE_TS

{upgini-1.2.142a1 → upgini-1.2.143}/src/upgini/utils/postal_code_utils.py

@@ -4,16 +4,45 @@ from pandas.api.types import (
     is_object_dtype,
     is_string_dtype,
 )
+import re
 
 from upgini.utils.base_search_key_detector import BaseSearchKeyDetector
 
 
 class PostalCodeSearchKeyDetector(BaseSearchKeyDetector):
+    postal_pattern = re.compile(r'^[A-Za-z0-9][A-Za-z0-9\s\-]{1,9}$')
+
     def _is_search_key_by_name(self, column_name: str) -> bool:
-        return str(column_name).lower() in ["zip", "zipcode", "zip_code", "postal_code", "postalcode"]
+        return "zip" in str(column_name).lower() or "postal" in str(column_name).lower()
 
     def _is_search_key_by_values(self, column: pd.Series) -> bool:
-        return False
+        """
+        # Fast two-step check whether the column looks like a postal code.
+        # Returns True if, after removing missing values, values remain,
+        # and all of them match the common characteristics of a postal code.
+        """
+        s = column.copy().dropna().astype(str).str.strip()
+        s = s[s != ""]  # remove empty strings
+        if s.empty:
+            return False
+
+        # remove suffix ".0" (often after float)
+        s = s.str.replace(r"\.0$", "", regex=True)
+
+        # --- Step 1: fast filtering ---
+        mask_len = s.str.len().between(2, 10)
+        mask_digit = s.str.contains(r'\d', regex=True)
+        mask_chars = ~s.str.contains(r'[^A-Za-z0-9\s\-]', regex=True)
+        fast_mask = mask_len & mask_digit & mask_chars
+
+        # if any of them failed the fast check, return False
+        if not fast_mask.all():
+            return False
+
+        # --- Step 2: regex check ---
+        # only if the first step passed
+        valid_mask = s.apply(lambda x: bool(self.postal_pattern.fullmatch(x)))
+        return valid_mask.all()
 
 
 class PostalCodeSearchKeyConverter:

upgini-1.2.142a1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.142a1"