upgini 1.1.307__tar.gz → 1.1.309__tar.gz

{upgini-1.1.307 → upgini-1.1.309}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.307
+Version: 1.1.309
 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-1.1.309/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.309"

{upgini-1.1.307 → upgini-1.1.309}/src/upgini/data_source/data_source_publisher.py

@@ -3,7 +3,7 @@ import time
 import uuid
 from datetime import datetime
 from enum import Enum
-from typing import Dict, List, Optional, Union
+from typing import Dict, List, Literal, Optional, Union
 
 from upgini.errors import HttpError, ValidationError
 from upgini.http import LoggerFactory, get_rest_client
@@ -47,7 +47,9 @@ class DataSourcePublisher:
         self,
         data_table_uri: str,
         search_keys: Dict[str, SearchKey],
-        update_frequency: str,
+        update_frequency: (
+            Literal["Daily"] | Literal["Weekly"] | Literal["Monthly"] | Literal["Quarterly"] | Literal["Annually"]
+        ),
         exclude_from_autofe_generation: Optional[List[str]],
         secondary_search_keys: Optional[Dict[str, SearchKey]] = None,
         sort_column: Optional[str] = None,
@@ -233,11 +235,17 @@ class DataSourcePublisher:
                 self.logger.exception("Failed to register data table")
                 raise
 
-    def remove(self, data_table_ids: List[str]):
+    def remove(self, data_table_ids: List[str] | str):
         trace_id = str(uuid.uuid4())
         with MDC(trace_id=trace_id):
             try:
-                if data_table_ids is None or len(data_table_ids) == 0:
+                if not data_table_ids:
+                    raise ValidationError("Empty data table ids")
+                if isinstance(data_table_ids, str):
+                    data_table_ids = [data_table_ids]
+                if not isinstance(data_table_ids, list):
+                    raise ValidationError("Invalid format of data_table_ids argument")
+                if len(data_table_ids) == 0:
                     raise ValidationError("Empty data table ids")
 
                 for data_table_id in data_table_ids:
@@ -266,16 +274,20 @@ class DataSourcePublisher:
         source_link: Optional[str] = None,
         update_frequency: Optional[str] = None,
         client_emails: Optional[List[str]] = None,
+        date_features: Optional[List[str]] = None,
+        date_vector_features: Optional[List[str]] = None,
     ):
         trace_id = str(uuid.uuid4())
         with MDC(trace_id=trace_id):
             try:
-                if data_table_ids is None or len(data_table_ids) == 0:
+                if data_table_ids is None:
                     raise ValidationError("Empty data table ids")
                 if isinstance(data_table_ids, str):
                     data_table_ids = [data_table_ids]
                 if not isinstance(data_table_ids, list):
                     raise ValidationError("data_table_ids should be string or list of strings")
+                if len(data_table_ids) == 0:
+                    raise ValidationError("Empty data table ids")
                 if update_frequency is not None and update_frequency not in self.ACCEPTABLE_UPDATE_FREQUENCIES:
                     raise ValidationError(
                         f"Invalid update frequency: {update_frequency}. "
@@ -311,6 +323,10 @@ class DataSourcePublisher:
                     request["updateFrequency"] = update_frequency
                 if client_emails is not None:
                     request["clientEmails"] = client_emails
+                if date_features is not None:
+                    request["dateFeatures"] = date_features
+                if date_vector_features is not None:
+                    request["dateVectorFeatures"] = date_vector_features
                 self.logger.info(f"Activating data tables with request {request}")
 
                 self._rest_client.activate_datatables(request, trace_id)

{upgini-1.1.307 → upgini-1.1.309}/src/upgini/features_enricher.py

@@ -90,7 +90,6 @@ from upgini.utils.display_utils import (
 from upgini.utils.email_utils import EmailSearchKeyConverter, EmailSearchKeyDetector
 from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.format import Format
-from upgini.utils.ip_utils import IpToCountrySearchKeyConverter
 from upgini.utils.phone_utils import PhoneSearchKeyDetector
 from upgini.utils.postal_code_utils import PostalCodeSearchKeyDetector
 
@@ -866,13 +865,6 @@ class FeaturesEnricher(TransformerMixin):
                 if X is not None and y is None:
                     raise ValidationError("X passed without y")
 
-                if self.X is None:
-                    self.X = X
-                if self.y is None:
-                    self.y = y
-                if self.eval_set is None:
-                    self.eval_set = effective_eval_set
-
                 validate_scoring_argument(scoring)
 
                 self._validate_baseline_score(effective_X, effective_eval_set)
@@ -889,9 +881,9 @@ class FeaturesEnricher(TransformerMixin):
 
                 prepared_data = self._prepare_data_for_metrics(
                     trace_id=trace_id,
-                    X=effective_X,
-                    y=effective_y,
-                    eval_set=effective_eval_set,
+                    X=X,
+                    y=y,
+                    eval_set=eval_set,
                     exclude_features_sources=exclude_features_sources,
                     importance_threshold=importance_threshold,
                     max_features=max_features,
@@ -1136,6 +1128,13 @@ class FeaturesEnricher(TransformerMixin):
                     elif uplift_col in metrics_df.columns and (metrics_df[uplift_col] < 0).any():
                         self.logger.warning("Uplift is negative")
 
+                    if self.X is None:
+                        self.X = X
+                    if self.y is None:
+                        self.y = y
+                    if self.eval_set is None:
+                        self.eval_set = effective_eval_set
+
                     return metrics_df
             except Exception as e:
                 error_message = "Failed to calculate metrics" + (
@@ -1213,13 +1212,6 @@ class FeaturesEnricher(TransformerMixin):
             converter = EmailSearchKeyConverter(email_column, hem_column, search_keys, [], self.logger)
             extended_X = converter.convert(extended_X)
             generated_features.extend(converter.generated_features)
-        if (
-            self.detect_missing_search_keys
-            and list(search_keys.values()) == [SearchKey.DATE]
-            and self.country_code is None
-        ):
-            converter = IpToCountrySearchKeyConverter(search_keys, self.logger)
-            extended_X = converter.convert(extended_X)
         generated_features = [f for f in generated_features if f in self.fit_generated_features]
 
         return extended_X, search_keys
@@ -1987,13 +1979,6 @@ class FeaturesEnricher(TransformerMixin):
                 df = converter.convert(df)
                 generated_features.extend(converter.generated_features)
                 email_converted_to_hem = converter.email_converted_to_hem
-            if (
-                self.detect_missing_search_keys
-                and list(search_keys.values()) == [SearchKey.DATE]
-                and self.country_code is None
-            ):
-                converter = IpToCountrySearchKeyConverter(search_keys, self.logger)
-                df = converter.convert(df)
             generated_features = [f for f in generated_features if f in self.fit_generated_features]
 
             meaning_types = {col: key.value for col, key in search_keys.items()}
@@ -2342,7 +2327,7 @@ class FeaturesEnricher(TransformerMixin):
                 df = self._add_current_date_as_key(df, self.fit_search_keys, self.logger, self.bundle)
 
         # Checks that need validated date
-        validate_dates_distribution(validated_X, self.fit_search_keys, self.logger, self.bundle, self.warning_counter)
+        validate_dates_distribution(df, self.fit_search_keys, self.logger, self.bundle, self.warning_counter)
 
         if is_numeric_dtype(df[self.TARGET_NAME]) and has_date:
             self._validate_PSI(df.sort_values(by=maybe_date_column))
@@ -2356,14 +2341,6 @@ class FeaturesEnricher(TransformerMixin):
         )
         df = clean_full_duplicates(df, self.logger, bundle=self.bundle)
 
-        if (
-            self.detect_missing_search_keys
-            and list(self.fit_search_keys.values()) == [SearchKey.DATE]
-            and self.country_code is None
-        ):
-            converter = IpToCountrySearchKeyConverter(self.fit_search_keys, self.logger)
-            df = converter.convert(df)
-
         # Explode multiple search keys
         non_feature_columns = [self.TARGET_NAME, EVAL_SET_INDEX] + list(self.fit_search_keys.keys())
         meaning_types = {

upgini-1.1.307/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.307"