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

upgini/__about__.py

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

upgini/features_enricher.py

@@ -3,7 +3,6 @@ import datetime
 import gc
 import hashlib
 import itertools
-import json
 import logging
 import numbers
 import os
@@ -60,7 +59,6 @@ from upgini.metadata import (
     CVType,
     FeaturesMetadataV2,
     FileColumnMeaningType,
-    FileColumnMetadata,
     ModelTaskType,
     RuntimeParameters,
     SearchKey,
@@ -2154,7 +2152,7 @@ class FeaturesEnricher(TransformerMixin):
             trace_id = trace_id or uuid.uuid4()
             return search_task.get_progress(trace_id)
 
-    def display_transactional_transform_api(self, only_online_sources=False):
+    def get_transactional_transform_api(self, only_online_sources=False):
         if self.api_key is None:
             raise ValidationError(self.bundle.get("transactional_transform_unregistered"))
         if self._search_task is None:
@@ -2180,36 +2178,20 @@ class FeaturesEnricher(TransformerMixin):
             return "test_value"
 
         file_metadata = self._search_task.get_file_metadata(str(uuid.uuid4()))
-
-        def get_column_meta(column_name: str) -> FileColumnMetadata:
-            for c in file_metadata.columns:
-                if c.name == column_name:
-                    return c
-
         search_keys = file_metadata.search_types()
         if SearchKey.IPV6_ADDRESS in search_keys:
             search_keys.pop(SearchKey.IPV6_ADDRESS, None)
-
-        search_keys_with_values = dict()
-        for sk_type, sk_name in search_keys.items():
-            if sk_type == SearchKey.IPV6_ADDRESS:
-                continue
-
-            sk_meta = get_column_meta(sk_name)
-            if sk_meta is None:
-                search_keys_with_values[sk_type.name] = [{"name": sk_name, "value": key_example(sk_type)}]
-            else:
-                if sk_meta.isUnnest:
-                    search_keys_with_values[sk_type.name] = [
-                        {"name": name, "value": key_example(sk_type)} for name in sk_meta.unnestKeyNames
-                    ]
-                else:
-                    search_keys_with_values[sk_type.name] = [{
-                        "name": sk_meta.originalName,
-                        "value": key_example(sk_type),
-                    }]
-
-        keys_section = json.dumps(search_keys_with_values)
+        original_names = {c.name: c.originalName for c in file_metadata.columns}
+        keys = (
+            "{"
+            + ", ".join(
+                [
+                    f'"{key.name}": {{"name": "{original_names.get(name, name)}", "value": "{key_example(key)}"}}'
+                    for key, name in search_keys.items()
+                ]
+            )
+            + "}"
+        )
         features_for_transform = self._search_task.get_features_for_transform()
         if features_for_transform:
             original_features_for_transform = [
@@ -2230,7 +2212,7 @@ class FeaturesEnricher(TransformerMixin):
 curl 'https://search.upgini.com/online/api/http_inference_trigger?search_id={search_id}' \\
     -H 'Authorization: {self.api_key}' \\
     -H 'Content-Type: application/json' \\
-    -d '{{"search_keys": {keys_section}{features_section}, "only_online_sources": {str(only_online_sources).lower()}}}'
+    -d '{{"search_keys": {keys}{features_section}, "only_online_sources": {str(only_online_sources).lower()}}}'
 
 {Format.BOLD}Python{Format.END}:
 
@@ -2239,12 +2221,13 @@ import requests
 response = requests.post(
     url='https://search.upgini.com/online/api/http_inference_trigger?search_id={search_id}',
     headers={{'Authorization': '{self.api_key}'}},
-    json={{"search_keys": {keys_section}{features_section}, "only_online_sources": {only_online_sources}}}
+    json={{"search_keys": {keys}{features_section}, "only_online_sources": {only_online_sources}}}
 )
 if response.status_code == 200:
     print(response.json())
 """
-        print(api_example)
+
+        return api_example
 
     def _get_copy_of_runtime_parameters(self) -> RuntimeParameters:
         return RuntimeParameters(properties=self.runtime_parameters.properties.copy())
@@ -2305,7 +2288,7 @@ if response.status_code == 200:
                 msg = self.bundle.get("online_api_features_transform").format(online_api_features)
                 self.logger.warning(msg)
                 print(msg)
-                self.display_transactional_transform_api(only_online_sources=True)
+                print(self.get_transactional_transform_api(only_online_sources=True))
 
             if not metrics_calculation:
                 transform_usage = self.rest_client.get_current_transform_usage(trace_id)

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

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

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=GQcOPY8MByuUtzBlWgL-5Ml2KS1SWi19jFLxrEPAY_Q,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
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=G0qbRPdlWe9p6cwYF3khP99-0kgAO8N0A2sfQxSLgmM,213446
+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-1.2.85.dist-info/METADATA,sha256=cEtUjRx8eUntASmye2LUmZX78RCWtrMm43z2ZCWyhW8,49162
-upgini-1.2.85.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.85.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.85.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-1.2.85.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