upgini 1.2.117__py3-none-any.whl → 1.2.118__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.117"
+__version__ = "1.2.118"

upgini/features_enricher.py

@@ -1423,8 +1423,15 @@ class FeaturesEnricher(TransformerMixin):
         # Find latest eval set or earliest if all eval sets are before train set
         date_column = self._get_date_column(search_keys)
 
-        # Get minimum date from main dataset X
-        main_min_date = X[date_column].dropna().min()
+        x_date = X[date_column].dropna()
+        if not is_numeric_dtype(x_date):
+            x_date = pd.to_datetime(x_date).dt.floor("D").astype(np.int64) / 10**6
+        main_min_date = x_date.min()
+
+        for eval_x, _ in eval_set:
+            eval_x_date = eval_x[date_column].dropna()
+            if not is_numeric_dtype(eval_x_date):
+                eval_x[date_column] = pd.to_datetime(eval_x_date).dt.floor("D").astype(np.int64) / 10**6
 
         # Find minimum date for each eval_set and compare with main dataset
         eval_dates = []
@@ -1433,8 +1440,11 @@ class FeaturesEnricher(TransformerMixin):
                 if len(eval_x) < 1000:
                     self.logger.warning(f"Eval_set {i} has less than 1000 rows. It will be ignored for stability check")
                     continue
-                eval_min_date = eval_x[date_column].dropna().min()
-                eval_max_date = eval_x[date_column].dropna().max()
+                eval_x_date = eval_x[date_column].dropna()
+                if not is_numeric_dtype(eval_x_date):
+                    eval_x_date = pd.to_datetime(eval_x_date).dt.floor("D").astype(np.int64) / 10**6
+                eval_min_date = eval_x_date.min()
+                eval_max_date = eval_x_date.max()
                 eval_dates.append((i, eval_min_date, eval_max_date))
 
         if not eval_dates:
@@ -1460,6 +1470,10 @@ class FeaturesEnricher(TransformerMixin):
         checking_eval_set_df = checking_eval_set_df.copy()
 
         checking_eval_set_df[date_column] = eval_set_dates[selected_eval_set_idx]
+        if not is_numeric_dtype(checking_eval_set_df[date_column]):
+            checking_eval_set_df[date_column] = (
+                pd.to_datetime(checking_eval_set_df[date_column]).dt.floor("D").astype(np.int64) / 10**6
+            )
 
         psi_values_sparse = calculate_sparsity_psi(
             checking_eval_set_df, cat_features, date_column, self.logger, model_task_type
@@ -3708,6 +3722,25 @@ if response.status_code == 200:
             else:
                 raise ValidationError(self.bundle.get("eval_x_and_x_diff_shape"))
 
+        if any(validated_eval_X.dtypes != X.dtypes):
+            x_types = X.dtypes
+            eval_types = validated_eval_X.dtypes
+            # Find columns with different types
+            diff_cols = [
+                (col, x_types[col], eval_types[col])
+                for col in x_types.index
+                if x_types[col] != eval_types[col]
+            ]
+            diff_col_names = [col for col, _, _ in diff_cols]
+            # print columns with different types
+            print("Columns with different types:")
+            for col, x_type, eval_type in diff_cols:
+                print("-" * 50)
+                print(f"Column: {col}")
+                print(f"X type:        {x_type}")
+                print(f"Eval_set type: {eval_type}")
+            raise ValidationError(self.bundle.get("eval_x_and_x_diff_dtypes").format(diff_col_names))
+
         if _num_samples(validated_eval_X) != _num_samples(eval_y):
             raise ValidationError(
                 self.bundle.get("x_and_y_diff_size_eval_set").format(
@@ -4420,7 +4453,8 @@ if response.status_code == 200:
 
         if len(features_info) > 0:
             self.features_info = pd.DataFrame(features_info)
-            if self.features_info[self.bundle.get("features_info_psi")].isna().all():
+            # If all psi values are 0 or null, drop psi column
+            if self.features_info[self.bundle.get("features_info_psi")].fillna(0.0).eq(0.0).all():
                 self.features_info.drop(columns=[self.bundle.get("features_info_psi")], inplace=True)
             self._features_info_without_links = pd.DataFrame(features_info_without_links)
             self._internal_features_info = pd.DataFrame(internal_features_info)

upgini/resource_bundle/strings.properties

@@ -123,6 +123,7 @@ unsupported_type_eval_set=Unsupported type of eval_set: {}. It should be list of
 eval_set_invalid_tuple_size=eval_set contains a tuple of size {}. It should contain only pairs of X and y or X only
 unsupported_x_type_eval_set=Unsupported type of X in eval_set: {}. Use pandas.DataFrame, pandas.Series or numpy.ndarray or list.
 eval_x_and_x_diff_shape=The column set in eval_set are differ from the column set in X
+eval_x_and_x_diff_dtypes=The column types in eval_set are different from the column types in X: {}
 unsupported_y_type_eval_set=Unsupported type of y in eval_set: {}. Use pandas.Series, numpy.ndarray or list
 y_is_constant_eval_set=y in eval_set is a constant. Relevant feature search requires a non-constant y
 x_and_y_diff_size_eval_set=X and y in eval_set contain different number of rows: {}, {}

upgini/utils/psi.py

@@ -82,9 +82,6 @@ def calculate_features_psi(
 ) -> dict[str, float]:
     empty_res = {col: 0.0 for col in df.columns if col not in [TARGET, date_column]}
 
-    if not is_numeric_dtype(df[date_column]):
-        df[date_column] = pd.to_datetime(df[date_column]).dt.floor("D").astype(np.int64) / 10**6
-
     # Filter out rows with missing dates
     df = df[df[date_column].notna()].copy()
 

{upgini-1.2.117.dist-info → upgini-1.2.118.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.117
+Version: 1.2.118
 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-1.2.117.dist-info → upgini-1.2.118.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=MY7Fho70n94XaciDTteAp4gxVleTVF6idcG3aECjijI,24
+upgini/__about__.py,sha256=q02CtZPV2DVtBrD7C_RFfsbI15l7QGmxfUzcCx5UykM,24
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=pQ8JQe0cdygD-W9GefJmfE6bnj4EYzXsjlgWdIS9nS8,31578
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=iYay-Ye5WGntieg3X7uyg9W3x_1FUELrmhJnJIvQMeI,228897
+upgini/features_enricher.py,sha256=zGWU8l6dWZwV1fsQD-j9tTKP9X6mUO9HPnwcGrJFS8o,230596
 upgini/http.py,sha256=-J_wOpnwVnT0ebPC6sOs6fN3AWtCD0LJLu6nlYmxaqk,44348
 upgini/metadata.py,sha256=VzgtgEbPPtNxTrj9LM5qSDP3DujHwAXqbUSKBjPcb9c,12477
 upgini/metrics.py,sha256=KCPE_apPN-9BIdv6GqASbJVaB_gBcy8wzNApAcyaGo4,46020
@@ -38,7 +38,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/normalize_utils.py,sha256=mDh2mBW3aQMB4EFP2aHbf2dGMVkOcWnp4sKKvKDBh8w,8511
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=VbfRqgg2kuWqmUyieGNxuY5dy0TpOQ-L3fHlWB7o2_w,29186
+upgini/resource_bundle/strings.properties,sha256=cNeVkWZMyjGCYGqmOOeJqisqPSEBtmfIw_U1rmgQw4w,29285
 upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=Fva2FEhLiNRPZ9Q6uOtJRtRzwsayjv7aphalAZO_4lc,6452
@@ -66,7 +66,7 @@ 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/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
-upgini/utils/psi.py,sha256=vuVAo5-4HplpblQA7BP8bouI8VQDEb___MW98WQ6ik8,11258
+upgini/utils/psi.py,sha256=vw8QEktXSx29IiMJMxmDeFU_4lJInJBXt_XL5Muekzo,11114
 upgini/utils/sample_utils.py,sha256=xpfYaZ2cYP7I2JrcooVc13QNBFawB81cJRuh38451Q4,15123
 upgini/utils/sklearn_ext.py,sha256=jLJWAKkqQinV15Z4y1ZnsN3c-fKFwXTsprs00COnyVU,49315
 upgini/utils/sort.py,sha256=8uuHs2nfSMVnz8GgvbOmgMB1PgEIZP1uhmeRFxcwnYw,7039
@@ -74,7 +74,7 @@ upgini/utils/target_utils.py,sha256=GCPn4QeJ83JJ_vyBJ3IhY5fyIRkLC9q9BE59S2FRO1I,
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.117.dist-info/METADATA,sha256=3onXIkh96-rh_Q0DIuHUihe07upcEFukS5WsVS1R2yc,50743
-upgini-1.2.117.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.117.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.117.dist-info/RECORD,,
+upgini-1.2.118.dist-info/METADATA,sha256=fEdGQaho0hyf9dXC_fL1AxuJFI46-zCMvm_U_O6hOec,50743
+upgini-1.2.118.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.118.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.118.dist-info/RECORD,,