upgini 1.2.142a2__py3-none-any.whl → 1.2.143__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.142a2"
+__version__ = "1.2.143"

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()
@@ -4784,7 +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)
 
@@ -5025,7 +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/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-1.2.142a2.dist-info → upgini-1.2.143.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: upgini
-Version: 1.2.142a2
+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-1.2.142a2.dist-info → upgini-1.2.143.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=dSeNLAH450Diequ6QaqtlfmtTqZqHt2ymoZ_4jsnfj0,26
+upgini/__about__.py,sha256=TkxQ31o1wT_libI5BqRH2rhpiwyfbBiFlzZY9cCcBfw,24
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=bkUpUC1sdhCQcLPysB7BC8WiFDPfjiJj1SztExpv0nA,33735
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=07decijgeSDaN6A1qVf71ZETu9nXVhNRWUTPWZeNpJo,234667
+upgini/features_enricher.py,sha256=KTSNUaJ_j6fBiCFnFfqY92kfSqGMXdgoIO2L7dyYM68,234739
 upgini/http.py,sha256=y26x4TQVYuEM3jz8JdASxSyBtvBemUkFf-FmX25sx-s,44356
 upgini/metadata.py,sha256=iYlL91g2PMHjiPIySIZb4IzIIUsPaAMIiV2It95GAjA,12866
 upgini/metrics.py,sha256=KCPE_apPN-9BIdv6GqASbJVaB_gBcy8wzNApAcyaGo4,46020
@@ -64,7 +64,7 @@ upgini/utils/hash_utils.py,sha256=mP2yHyzvDNdpa5g3B4MHzulxBeEz_ZSoGl1YF_VnAyE,55
 upgini/utils/ip_utils.py,sha256=wmnnwVQdjX9o1cNQw6VQMk6maHhvsq6hNsZBYf9knrw,6585
 upgini/utils/mstats.py,sha256=u3gQVUtDRbyrOQK6V1UJ2Rx1QbkSNYGjXa6m3Z_dPVs,6286
 upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,10432
-upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
+upgini/utils/postal_code_utils.py,sha256=sxdk32CTLvey6zqBbay_HtNzLqcn2eAYUJL-sNmJuDg,2840
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
 upgini/utils/psi.py,sha256=D_DMMBVkU4nwMospTwdMpYzNFACDxhqTuNesDngPwyY,11068
 upgini/utils/sample_utils.py,sha256=xpfYaZ2cYP7I2JrcooVc13QNBFawB81cJRuh38451Q4,15123
@@ -74,7 +74,7 @@ upgini/utils/target_utils.py,sha256=CihpV6SC95HwtlMH60rGAUzVDa4Id0Bva8ySprmNHlE,
 upgini/utils/track_info.py,sha256=NDKeQTUlZaYp15UoP-xLKGoDoJQ0drbDMwB0g9R0PUg,6427
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.142a2.dist-info/METADATA,sha256=WCW6AUmnuZ1JnKGHmjZhdAzyJv4AVOtPleHTz7ewAfY,51166
-upgini-1.2.142a2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-upgini-1.2.142a2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.142a2.dist-info/RECORD,,
+upgini-1.2.143.dist-info/METADATA,sha256=rabfdtvLV7EsidthqGBubCvVp8zWDjqDf7_Nur_1Dro,51164
+upgini-1.2.143.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+upgini-1.2.143.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.143.dist-info/RECORD,,