upgini 1.2.133a1__py3-none-any.whl → 1.2.134__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.133a1"
+__version__ = "1.2.134"

upgini/features_enricher.py

@@ -2938,7 +2938,7 @@ if response.status_code == 200:
         new_columns_on_transform = [c for c in validated_Xy.columns if c not in fit_input_columns]
 
         selected_generated_features = [
-            c for c in generated_features if not self.fit_select_features or c in self.feature_names_
+            c for c in generated_features if c in self.feature_names_
         ]
         if keep_input is True:
             selected_input_columns = [
@@ -3245,7 +3245,7 @@ if response.status_code == 200:
         if fintech_warnings:
             for fintech_warning in fintech_warnings:
                 self.__log_warning(fintech_warning)
-        df, full_duplicates_warning = clean_full_duplicates(df, self.logger, bundle=self.bundle)
+        df, full_duplicates_warning = clean_full_duplicates(df, logger=self.logger, bundle=self.bundle)
         if full_duplicates_warning:
             if len(df) == 0:
                 raise ValidationError(full_duplicates_warning)

upgini/utils/datetime_utils.py

@@ -84,30 +84,31 @@ class DateTimeConverter:
         return parsed is not None and not parsed.isna().all()
 
     def parse_datetime(self, df: pd.DataFrame, raise_errors=True) -> pd.Series | None:
-        df = df.copy()
         if len(df) == 0 or df[self.date_column].isna().all():
             return None
 
+        date_col = df[self.date_column].copy()
+
         try:
-            if df[self.date_column].apply(lambda x: isinstance(x, datetime.datetime)).all():
-                parsed_datetime = df[self.date_column].apply(lambda x: x.replace(tzinfo=None))
-            elif isinstance(df[self.date_column].dropna().values[0], datetime.date):
-                parsed_datetime = pd.to_datetime(df[self.date_column], errors="coerce")
-            elif isinstance(df[self.date_column].dtype, pd.PeriodDtype):
-                parsed_datetime = df[self.date_column].dt.to_timestamp()
-            elif is_numeric_dtype(df[self.date_column]):
+            if date_col.apply(lambda x: isinstance(x, datetime.datetime)).all():
+                parsed_datetime = date_col.apply(lambda x: x.replace(tzinfo=None))
+            elif isinstance(date_col.dropna().values[0], datetime.date):
+                parsed_datetime = pd.to_datetime(date_col, errors="coerce")
+            elif isinstance(date_col.dtype, pd.PeriodDtype):
+                parsed_datetime = date_col.dt.to_timestamp()
+            elif is_numeric_dtype(date_col):
                 # 315532801 - 2524608001    - seconds
                 # 315532801000 - 2524608001000 - milliseconds
                 # 315532801000000 - 2524608001000000 - microseconds
                 # 315532801000000000 - 2524608001000000000 - nanoseconds
-                if df[self.date_column].apply(lambda x: 10**16 < x).all():
-                    parsed_datetime = pd.to_datetime(df[self.date_column], unit="ns")
-                elif df[self.date_column].apply(lambda x: 10**14 < x < 10**16).all():
-                    parsed_datetime = pd.to_datetime(df[self.date_column], unit="us")
-                elif df[self.date_column].apply(lambda x: 10**11 < x < 10**14).all():
-                    parsed_datetime = pd.to_datetime(df[self.date_column], unit="ms")
-                elif df[self.date_column].apply(lambda x: 10**8 < x < 10**11).all():
-                    parsed_datetime = pd.to_datetime(df[self.date_column], unit="s")
+                if date_col.apply(lambda x: 10**16 < x).all():
+                    parsed_datetime = pd.to_datetime(date_col, unit="ns")
+                elif date_col.apply(lambda x: 10**14 < x < 10**16).all():
+                    parsed_datetime = pd.to_datetime(date_col, unit="us")
+                elif date_col.apply(lambda x: 10**11 < x < 10**14).all():
+                    parsed_datetime = pd.to_datetime(date_col, unit="ms")
+                elif date_col.apply(lambda x: 10**8 < x < 10**11).all():
+                    parsed_datetime = pd.to_datetime(date_col, unit="s")
                 else:
                     msg = self.bundle.get("unsupported_date_type").format(self.date_column)
                     if raise_errors:
@@ -115,8 +116,10 @@ class DateTimeConverter:
                     else:
                         return None
             else:
-                df[self.date_column] = df[self.date_column].astype("string").apply(self.clean_date)
-                parsed_datetime = self.parse_string_date(df, raise_errors)
+                date_col = date_col.astype("string")  # .apply(self.clean_date)
+                parsed_datetime = self.parse_string_date(date_col.to_frame(self.date_column), raise_errors)
+                if parsed_datetime.isna().all():
+                    raise ValidationError(self.bundle.get("invalid_date_format").format(self.date_column))
             parsed_datetime = parsed_datetime.dt.tz_localize(None)
             return parsed_datetime
         except Exception as e:

{upgini-1.2.133a1.dist-info → upgini-1.2.134.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: upgini
-Version: 1.2.133a1
+Version: 1.2.134
 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-1.2.133a1.dist-info → upgini-1.2.134.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=2J0xRzQRVTKW9-UjHayhhp4WFFpAteaH5RVfrXavaz0,26
+upgini/__about__.py,sha256=MT6QELtgqY26TnKAbjjKik1_WtJtBfrKgI7IxYRg6F0,24
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=Nm2ZmwyQqvTnymYpGUwyJWy7y2ebXlHMyYmGeGcyA_s,31652
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=Na-W1f5xQVUKF4_m2Bw8mM29kLD8N3U7p9-FU0J9bi8,234415
+upgini/features_enricher.py,sha256=lnog1Ox6bE6ADBBwLk63w6VNOV_rnQfagi8CnpuPBbU,234390
 upgini/http.py,sha256=-J_wOpnwVnT0ebPC6sOs6fN3AWtCD0LJLu6nlYmxaqk,44348
 upgini/metadata.py,sha256=H3wiN37k-yqWZgbPD0tJzx8DzaCIkgmX5cybhByQWLg,12619
 upgini/metrics.py,sha256=KCPE_apPN-9BIdv6GqASbJVaB_gBcy8wzNApAcyaGo4,46020
@@ -52,7 +52,7 @@ upgini/utils/config.py,sha256=zFdnjchykfp_1Tm3Qep7phLzXBpXIOzr2tIuXchRBLw,1754
 upgini/utils/country_utils.py,sha256=lY-eXWwFVegdVENFttbvLcgGDjFO17Sex8hd2PyJaRk,6937
 upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDcqVNY,3857
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
-upgini/utils/datetime_utils.py,sha256=l85UzSQLhtMeI2G6m-m8y8bCColCLSXNHb2-G6fKpLM,16988
+upgini/utils/datetime_utils.py,sha256=aHeX0iJwPNCj12z_3uDUP_pjVR7bWGeUc-dtxrtM3Q8,17002
 upgini/utils/deduplicate_utils.py,sha256=CLX0QapRxB-ZVQT7yGvv1vSd2zac5SwRjCJavujdCps,11332
 upgini/utils/display_utils.py,sha256=MoTqXZJvC6pAqgOaI3V0FG-IU_LnMfrn4TDcNvUqsdg,13316
 upgini/utils/email_utils.py,sha256=pZ2vCfNxLIPUhxr0-OlABNXm12jjU44isBk8kGmqQzA,5277
@@ -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-1.2.133a1.dist-info/METADATA,sha256=oveLN_pPi2K1BqqAnu5ZnGXVMl7TeD65Jg1biA1drE0,51135
-upgini-1.2.133a1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.133a1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.133a1.dist-info/RECORD,,
+upgini-1.2.134.dist-info/METADATA,sha256=obO7_PRcJM6erbGiU4G8fXumU7Ekozv2xcvBqcP3lCk,51133
+upgini-1.2.134.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+upgini-1.2.134.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.134.dist-info/RECORD,,

{upgini-1.2.133a1.dist-info → upgini-1.2.134.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.25.0
+Generator: hatchling 1.27.0
 Root-Is-Purelib: true
 Tag: py3-none-any