upgini 1.2.53__py3-none-any.whl → 1.2.55a1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.53"
+__version__ = "1.2.55a1"

upgini/dataset.py

@@ -587,15 +587,23 @@ class Dataset:  # (pd.DataFrame):
         if (
             runtime_parameters is not None
             and runtime_parameters.properties is not None
-            and "generate_features" in runtime_parameters.properties
         ):
-            generate_features = runtime_parameters.properties["generate_features"].split(",")
-            renamed_generate_features = []
-            for f in generate_features:
-                for new_column, orig_column in self.columns_renaming.items():
-                    if f == orig_column:
-                        renamed_generate_features.append(new_column)
-            runtime_parameters.properties["generate_features"] = ",".join(renamed_generate_features)
+            if "generate_features" in runtime_parameters.properties:
+                generate_features = runtime_parameters.properties["generate_features"].split(",")
+                renamed_generate_features = []
+                for f in generate_features:
+                    for new_column, orig_column in self.columns_renaming.items():
+                        if f == orig_column:
+                            renamed_generate_features.append(new_column)
+                runtime_parameters.properties["generate_features"] = ",".join(renamed_generate_features)
+            if "columns_for_online_api" in runtime_parameters.properties:
+                columns_for_online_api = runtime_parameters.properties["columns_for_online_api"].split(",")
+                renamed_columns_for_online_api = []
+                for f in columns_for_online_api:
+                    for new_column, orig_column in self.columns_renaming.items():
+                        if f == orig_column:
+                            renamed_columns_for_online_api.append(new_column)
+                runtime_parameters.properties["columns_for_online_api"] = ",".join(renamed_columns_for_online_api)
 
         return runtime_parameters
 

upgini/features_enricher.py

@@ -222,6 +222,7 @@ class FeaturesEnricher(TransformerMixin):
         loss: Optional[str] = None,
         detect_missing_search_keys: bool = True,
         generate_features: Optional[List[str]] = None,
+        columns_for_online_api: Optional[List[str]] = None,
         round_embeddings: Optional[int] = None,
         logs_enabled: bool = True,
         raise_validation_error: bool = True,
@@ -268,7 +269,7 @@ class FeaturesEnricher(TransformerMixin):
         self.eval_set: Optional[List[Tuple]] = None
         self.autodetected_search_keys: Dict[str, SearchKey] = {}
         self.imbalanced = False
-        self.fit_select_features = False
+        self.fit_select_features = True
         self.__cached_sampled_datasets: Dict[str, Tuple[pd.DataFrame, pd.DataFrame, pd.Series, Dict, Dict, Dict]] = (
             dict()
         )
@@ -345,6 +346,9 @@ class FeaturesEnricher(TransformerMixin):
                     self.logger.error(msg)
                     raise ValidationError(msg)
                 self.runtime_parameters.properties["round_embeddings"] = round_embeddings
+        self.columns_for_online_api = columns_for_online_api
+        if columns_for_online_api is not None:
+            self.runtime_parameters.properties["columns_for_online_api"] = ",".join(columns_for_online_api)
         maybe_downsampling_limit = self.runtime_parameters.properties.get("downsampling_limit")
         if maybe_downsampling_limit is not None:
             Dataset.FIT_SAMPLE_THRESHOLD = int(maybe_downsampling_limit)
@@ -2608,17 +2612,18 @@ if response.status_code == 200:
             checked_generate_features = []
             for gen_feature in self.generate_features:
                 if gen_feature not in x_columns:
-                    if gen_feature == self._get_phone_column(self.search_keys):
-                        raise ValidationError(
-                            self.bundle.get("missing_generate_feature").format(gen_feature, x_columns)
-                        )
-                    else:
-                        self.__log_warning(self.bundle.get("missing_generate_feature").format(gen_feature, x_columns))
+                    msg = self.bundle.get("missing_generate_feature").format(gen_feature, x_columns)
+                    self.__log_warning(msg)
                 else:
                     checked_generate_features.append(gen_feature)
             self.generate_features = checked_generate_features
             self.runtime_parameters.properties["generate_features"] = ",".join(self.generate_features)
 
+        if self.columns_for_online_api is not None and len(self.columns_for_online_api) > 0:
+            for column in self.columns_for_online_api:
+                if column not in validated_X.columns:
+                    raise ValidationError(self.bundle.get("missing_column_for_online_api").format(column))
+
         if self.id_columns is not None:
             for id_column in self.id_columns:
                 if id_column not in validated_X.columns:

upgini/resource_bundle/strings.properties

@@ -111,6 +111,7 @@ x_is_empty=X is empty
 y_is_empty=y is empty
 x_contains_reserved_column_name=Column name {} is reserved. Please rename column and try again
 missing_generate_feature=Feature {} specified in `generate_features` is not present in input columns: {}
+missing_column_for_online_api=Column {} specified in `columns_for_online_api` is not present in input columns: {}
 x_unstable_by_date=Your training sample is unstable in number of rows per date. It is recommended to redesign the training sample
 train_unstable_target=Your training sample contains an unstable target event, PSI = {}. This will lead to unstable scoring on deferred samples. It is recommended to redesign the training sample
 eval_unstable_target=Your training and evaluation samples have a difference in target distribution. PSI = {}. The results will be unstable. It is recommended to redesign the training and evaluation samples

upgini/utils/email_utils.py

@@ -116,17 +116,17 @@ class EmailSearchKeyConverter:
         else:
             df[self.hem_column] = df[self.hem_column].astype("string").str.lower()
 
-        del self.search_keys[self.email_column]
-        if self.email_column in self.unnest_search_keys:
-            self.unnest_search_keys.remove(self.email_column)
+        # del self.search_keys[self.email_column]
+        # if self.email_column in self.unnest_search_keys:
+        #     self.unnest_search_keys.remove(self.email_column)
 
         one_domain_name = self.email_column + self.ONE_DOMAIN_SUFFIX
         df[one_domain_name] = df[self.email_column].apply(self._email_to_one_domain)
         self.columns_renaming[one_domain_name] = original_email_column
         self.search_keys[one_domain_name] = SearchKey.EMAIL_ONE_DOMAIN
 
-        if self.email_converted_to_hem:
-            df = df.drop(columns=self.email_column)
-            del self.columns_renaming[self.email_column]
+        # if self.email_converted_to_hem:
+        #     df = df.drop(columns=self.email_column)
+        #     del self.columns_renaming[self.email_column]
 
         return df

{upgini-1.2.53.dist-info → upgini-1.2.55a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.53
+Version: 1.2.55a1
 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-1.2.53.dist-info → upgini-1.2.55a1.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=X7WSWc7i6nvghhrqNxUUTAI8_CLJ7jRVdust93y4RdY,23
+upgini/__about__.py,sha256=86s5f_R4jUHavxr1KulObYZALbZX82z6GRJ0aiY88oY,25
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=vT4JyHmafLNbj54SySXr93f5hNS6-t94aFslbBy-7No,33535
+upgini/dataset.py,sha256=NP5vHqEfZQ1HWz3TcNAa_OhXG8wiMRdydm26D6UBiRU,34166
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=mDpz2NcNBItvfdE2EllEetnv7-ApODXg0FQleYrGIfg,200628
+upgini/features_enricher.py,sha256=ZYBLKxkFZB-b94-7oiAqZ0b4sbA1wXKClfkxVU529e0,200957
 upgini/http.py,sha256=ud0Cp7h0jNeHuuZGpU_1dAAEiabGoJjGxc1X5oeBQr4,43496
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=-bulW4ay0qxOxR4_5oDvENtgKiZgZI-QnU2stGHrKhg,12130
@@ -30,7 +30,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/normalize_utils.py,sha256=Ft2MwSgVoBilXAORAOYAuwPD79GOLfwn4qQE3IUFzzg,7218
 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=0_KAExIi1u48N1CQ13LKJS3bgDlRs-MPOyU3VxcE-qY,27350
+upgini/resource_bundle/strings.properties,sha256=UXMiaFP3p-WdiXyZJN3O_OZstb-F33BWVDxDiofyxd4,27464
 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=7GpjYqjOp58vYcJLiX__1R5wjUlyQbxvHJ2klFnup_M,6389
@@ -46,7 +46,7 @@ upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
 upgini/utils/datetime_utils.py,sha256=RVAk4_rakK8X9zjybK3-rj0to0e3elye8tnBuA4wTWU,13491
 upgini/utils/deduplicate_utils.py,sha256=SMZx9IKIhWI5HqXepfKiQb3uDJrogQZtG6jcWuMo5Z4,8855
 upgini/utils/display_utils.py,sha256=DsBjJ8jEYAh8BPgfAbzq5imoGFV6IACP20PQ78BQCX0,11964
-upgini/utils/email_utils.py,sha256=GbnhHJn1nhUBytmK6PophYqaoq4t7Lp6i0-O0Gd3RV8,5265
+upgini/utils/email_utils.py,sha256=pZ2vCfNxLIPUhxr0-OlABNXm12jjU44isBk8kGmqQzA,5277
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
 upgini/utils/feature_info.py,sha256=0rOXSyCj-sw-8migWP0ge8qrOzGU50dQvH0JUJUrDfQ,6766
 upgini/utils/features_validator.py,sha256=lEfmk4DoxZ4ooOE1HC0ZXtUb_lFKRFHIrnFULZ4_rL8,3746
@@ -59,7 +59,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=RlpKGss9kMibVSlA8iZuO_qxmyeplqzn7X8g6hiGGGs,14341
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.53.dist-info/METADATA,sha256=evVuEI0gOJIoXMeba7eYScAMZgUenOcRlc4myty3n4w,49055
-upgini-1.2.53.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.53.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.53.dist-info/RECORD,,
+upgini-1.2.55a1.dist-info/METADATA,sha256=uESME_SjmqafjB1XBhRSZWYFrv4rPx5F1pKSxEKKsNs,49057
+upgini-1.2.55a1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.55a1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.55a1.dist-info/RECORD,,