upgini 1.2.60a3792.dev1__tar.gz → 1.2.60a3792.dev2__tar.gz

{upgini-1.2.60a3792.dev1 → upgini-1.2.60a3792.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.60a3792.dev1
+Version: 1.2.60a3792.dev2
 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-1.2.60a3792.dev2/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.60a3792.dev2"

{upgini-1.2.60a3792.dev1 → upgini-1.2.60a3792.dev2}/src/upgini/dataset.py

@@ -40,7 +40,6 @@ from upgini.utils.email_utils import EmailSearchKeyConverter
 from upgini.utils.target_utils import (
     balance_undersample,
     balance_undersample_forced,
-    balance_undersample_time_series,
     balance_undersample_time_series_trunc,
 )
 
@@ -304,12 +303,12 @@ class Dataset:  # (pd.DataFrame):
                 )
 
         # Resample over fit threshold
-        if not self.imbalanced and EVAL_SET_INDEX in self.data.columns:
-            sample_threshold = self.FIT_SAMPLE_WITH_EVAL_SET_THRESHOLD
-            sample_rows = self.FIT_SAMPLE_WITH_EVAL_SET_ROWS
-        elif self.cv_type is not None and self.cv_type.is_time_series():
+        if self.cv_type is not None and self.cv_type.is_time_series():
             sample_threshold = self.FIT_SAMPLE_THRESHOLD_TS
             sample_rows = self.FIT_SAMPLE_ROWS_TS
+        elif not self.imbalanced and EVAL_SET_INDEX in self.data.columns:
+            sample_threshold = self.FIT_SAMPLE_WITH_EVAL_SET_THRESHOLD
+            sample_rows = self.FIT_SAMPLE_WITH_EVAL_SET_ROWS
         else:
             sample_threshold = self.FIT_SAMPLE_THRESHOLD
             sample_rows = self.FIT_SAMPLE_ROWS

{upgini-1.2.60a3792.dev1 → upgini-1.2.60a3792.dev2}/src/upgini/utils/target_utils.py

@@ -313,7 +313,7 @@ def balance_undersample_time_series_trunc(
 
     if time_unit < time_unit_threshold:
         for trunc_length in highfreq_trunc_lengths:
-            sampled_df = trunc_datetime(dates_df, id_columns, date_column, trunc_length)
+            sampled_df = trunc_datetime(dates_df, id_columns, date_column, trunc_length, logger=logger)
             if len(sampled_df) <= sample_size:
                 break
         if len(sampled_df) > sample_size:
@@ -322,7 +322,7 @@ def balance_undersample_time_series_trunc(
             )
     else:
         for trunc_length in lowfreq_trunc_lengths:
-            sampled_df = trunc_datetime(dates_df, id_columns, date_column, trunc_length)
+            sampled_df = trunc_datetime(dates_df, id_columns, date_column, trunc_length, logger=logger)
             if len(sampled_df) <= sample_size:
                 break
         if len(sampled_df) > sample_size:

upgini-1.2.60a3792.dev1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.60a3792.dev1"