upgini 1.2.38a3769.dev2__py3-none-any.whl → 1.2.38a3769.dev3__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.38a3769.dev2"
+__version__ = "1.2.38a3769.dev3"

upgini/utils/target_utils.py

@@ -306,7 +306,7 @@ def balance_undersample_time_series(
     id_counts.index = [ensure_tuple(i) for i in id_counts.index]
     id_counts = id_counts.sort_index(key=lambda x: [ids_sort[y] for y in x], ascending=False).cumsum()
     id_counts = id_counts[id_counts <= sample_size]
-    min_different_ids = int(len(df[id_columns].drop_duplicates()) * min_different_ids_ratio)
+    min_different_ids = max(int(len(df[id_columns].drop_duplicates()) * min_different_ids_ratio), 1)
 
     def id_mask(sample_index: pd.Index) -> pd.Index:
         if isinstance(sample_index, pd.MultiIndex):
@@ -317,10 +317,10 @@ def balance_undersample_time_series(
     if len(id_counts) < min_different_ids:
         if logger is not None:
             logger.info(
-                f"Different ids count {len(id_counts)} is less than min different ids {min_different_ids}, sampling time window"
+                f"Different ids count {len(id_counts)} for sample size {sample_size} is less than min different ids {min_different_ids}, sampling time window"
             )
         date_counts = df.groupby(id_columns)[date_column].nunique().sort_values(ascending=False)
-        ids_to_sample = date_counts.index[:min_different_ids]
+        ids_to_sample = date_counts.index[:min_different_ids] if len(id_counts) > 0 else date_counts.index
         mask = id_mask(ids_to_sample)
         df = df[mask]
         sample_date_counts = df[date_column].value_counts().sort_index(ascending=False).cumsum()

{upgini-1.2.38a3769.dev2.dist-info → upgini-1.2.38a3769.dev3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.38a3769.dev2
+Version: 1.2.38a3769.dev3
 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-1.2.38a3769.dev2.dist-info → upgini-1.2.38a3769.dev3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=Pi7t905kMODW13sjgsQdvH0UCQF5An8AOCl5peng2eA,33
+upgini/__about__.py,sha256=sQ7NNr0lfG3UfxCnX2sMNRntUVR0zW-NHhIgizLV7ls,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=zYPSQ73ch6k5EWxZlh1KrjL0gMkmAwl7Nkgrz6zxywY,33161
@@ -56,10 +56,10 @@ upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,1
 upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
 upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,44511
-upgini/utils/target_utils.py,sha256=AosrXCtfbNEUbc7fzyt1udKIZ-vvt-ngwx9SkOclWWQ,14200
+upgini/utils/target_utils.py,sha256=i_EsluRZG3LKrqv9NmhvEha9Uwp8JQjRUmokeo240Is,14283
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.38a3769.dev2.dist-info/METADATA,sha256=CifOyMPTP6xdb1WljZK3BuIb5FomL6xgRGbrq1sC_04,48604
-upgini-1.2.38a3769.dev2.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.38a3769.dev2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.38a3769.dev2.dist-info/RECORD,,
+upgini-1.2.38a3769.dev3.dist-info/METADATA,sha256=AeaVPfRIc-RCuzozwXSgurTpHXE21yR_tpsBjCra3KA,48604
+upgini-1.2.38a3769.dev3.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.38a3769.dev3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.38a3769.dev3.dist-info/RECORD,,