upgini 1.2.84__py3-none-any.whl → 1.2.85a3857.dev1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.84"
+__version__ = "1.2.85a3857.dev1"

upgini/metrics.py

@@ -391,9 +391,7 @@ class EstimatorWrapper:
                     self.converted_to_int.append(c)
                     self.cat_features.remove(c)
                 elif is_float_dtype(x[c]) or (x[c].dtype == "category" and is_float_dtype(x[c].cat.categories)):
-                    self.logger.info(
-                        f"Convert float cat feature {c} to string"
-                    )
+                    self.logger.info(f"Convert float cat feature {c} to string")
                     x[c] = x[c].astype(str)
                     self.converted_to_str.append(c)
                 elif x[c].dtype not in ["category", "int64"]:
@@ -694,7 +692,15 @@ class CatBoostWrapper(EstimatorWrapper):
                     x[c] = x[c].fillna(np.nan)
                 elif x[c].dtype != "category":
                     x[c] = x[c].fillna("NA")
-            params["cat_features"] = self.cat_features
+            if isinstance(self.cv, TimeSeriesSplit) or isinstance(self.cv, BlockedTimeSeriesSplit):
+                self.logger.info("Using time-aware encoder for CatBoost")
+                encoder = CatBoostEncoder(random_state=DEFAULT_RANDOM_STATE, cols=self.cat_features, return_df=True)
+                encoded = encoder.fit_transform(x[self.cat_features].astype("object"), y)
+                x[self.cat_features] = encoded
+                self.cat_encoder = encoder
+            else:
+                self.cat_encoder = None
+                params["cat_features"] = self.cat_features
 
         return x, y, groups, params
 
@@ -738,7 +744,16 @@ class CatBoostWrapper(EstimatorWrapper):
                     x[c] = x[c].fillna(np.nan)
                 elif x[c].dtype != "category":
                     x[c] = x[c].fillna("NA")
-            params["cat_features"] = self.cat_features
+            if (
+                isinstance(self.cv, TimeSeriesSplit)
+                or isinstance(self.cv, BlockedTimeSeriesSplit)
+                and self.cat_encoder is not None
+            ):
+                self.logger.info("Using time-aware encoder for CatBoost")
+                encoded = self.cat_encoder.transform(x[self.cat_features].astype("object"), y)
+                x[self.cat_features] = encoded
+            else:
+                params["cat_features"] = self.cat_features
 
         return x, y, params
 

{upgini-1.2.84.dist-info → upgini-1.2.85a3857.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.84
+Version: 1.2.85a3857.dev1
 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-1.2.84.dist-info → upgini-1.2.85a3857.dev1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=aeTule-I84yrLN0UOJAi64jLCLq3VVYxtUewFZihoH8,23
+upgini/__about__.py,sha256=fECI7PUZQG8IW2eHjUqgqHVtT40sMjfMgzLhuxKuQFA,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=fRtqSkXNONLnPe6cCL967GMt349FTIpXzy_u8LUKncw,35354
@@ -6,7 +6,7 @@ upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
 upgini/features_enricher.py,sha256=2ryADtOVEEebuUBhimusvnBzGxUkdTaqpEh2F1PqHSs,212719
 upgini/http.py,sha256=AfaJ3c8z_tK2hZFEehNybDKE0mp1tYcyAP_l0_p8bLQ,43933
 upgini/metadata.py,sha256=zt_9k0iQbWXuiRZcel4ORNPdQKt6Ou69ucZD_E1Q46o,12341
-upgini/metrics.py,sha256=3cip0_L6-OFew74KsRwzxJDU6UFq05h2v7IsyHLcMRc,43164
+upgini/metrics.py,sha256=zRrRpNqjSTubsyKPi0_jbHjE8QO_YqyHWtt1B5MfVH8,44086
 upgini/search_task.py,sha256=Q5HjBpLIB3OCxAD1zNv5yQ3ZNJx696WCK_-H35_y7Rs,17912
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -70,7 +70,7 @@ upgini/utils/target_utils.py,sha256=LRN840dzx78-wg7ftdxAkp2c1eu8-JDvkACiRThm4HE,
 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-1.2.84.dist-info/METADATA,sha256=jn2nCo_PdZx_hdSQYi9RFAFY7XyzgLlvz-U-WSY9Hm0,49162
-upgini-1.2.84.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.84.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.84.dist-info/RECORD,,
+upgini-1.2.85a3857.dev1.dist-info/METADATA,sha256=XycmCsMeqC_7hsO0YzR0E8b4eGnIcD-MBzuFvB4T24s,49172
+upgini-1.2.85a3857.dev1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.85a3857.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.85a3857.dev1.dist-info/RECORD,,

{upgini-1.2.84.dist-info → upgini-1.2.85a3857.dev1.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.25.0
+Generator: hatchling 1.24.2
 Root-Is-Purelib: true
 Tag: py3-none-any