upgini 1.1.287a3232.post1__tar.gz → 1.1.288a0__tar.gz

{upgini-1.1.287a3232.post1 → upgini-1.1.288a0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.287a3232.post1
+Version: 1.1.288a0
 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-1.1.288a0/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.288a0"

{upgini-1.1.287a3232.post1 → upgini-1.1.288a0}/src/upgini/autofe/date.py

@@ -2,7 +2,6 @@ from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
 import pandas as pd
-import datetime
 from pandas.core.arrays.timedeltas import TimedeltaArray
 from pydantic import BaseModel, validator
 
@@ -22,20 +21,6 @@ class DateDiffMixin(BaseModel):
 
         return pd.to_datetime(x, unit=unit)
 
-    def _convert_diff_to_unit(self, diff: Union[pd.Series, TimedeltaArray]) -> Union[pd.Series, TimedeltaArray]:
-        if self.diff_unit == "M":
-            raise Exception("Unsupported difference unit: Month")
-        elif self.diff_unit == "D":
-            if isinstance(diff, pd.Series) and diff.dtype == "object":
-                return diff.apply(lambda x: None if isinstance(x, float) and np.isnan(x) else x.days)
-            else:
-                return diff / np.timedelta64(1, self.diff_unit)
-        elif self.diff_unit == "Y":
-            if isinstance(diff, TimedeltaArray):
-                return (diff / 365 / 24 / 60 / 60 / 10**9).astype(int)
-            else:
-                return (diff / 365 / 24 / 60 / 60 / 10**9).dt.nanoseconds
-
 
 class DateDiff(PandasOperand, DateDiffMixin):
     name = "date_diff"
@@ -56,8 +41,7 @@ class DateDiff(PandasOperand, DateDiffMixin):
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         left = self._convert_to_date(left, self.left_unit)
         right = self._convert_to_date(right, self.right_unit)
-        diff = self._convert_diff_to_unit(left.dt.date - right.dt.date)
-        return self.__replace_negative(diff)
+        return self.__replace_negative((left - right) / np.timedelta64(1, self.diff_unit))
 
     def __replace_negative(self, x: Union[pd.DataFrame, pd.Series]):
         x[x < 0] = None
@@ -123,7 +107,12 @@ class DateListDiff(PandasOperand, DateDiffMixin):
         return pd.Series(left - right.values).apply(lambda x: self._agg(self._diff(x)))
 
     def _diff(self, x: TimedeltaArray):
-        x = self._convert_diff_to_unit(x)
+        if self.diff_unit == "Y":
+            x = (x / 365 / 24 / 60 / 60 / 10**9).astype(int)
+        elif self.diff_unit == "M":
+            raise Exception("Unsupported difference unit: Month")
+        else:
+            x = x / np.timedelta64(1, self.diff_unit)
         return x[x > 0]
 
     def _agg(self, x):

{upgini-1.1.287a3232.post1 → upgini-1.1.288a0}/src/upgini/data_source/data_source_publisher.py

@@ -58,6 +58,7 @@ class DataSourcePublisher:
         join_date_abs_limit_days: Optional[int] = None,
         features_for_embeddings: Optional[List[str]] = DEFAULT_GENERATE_EMBEDDINGS,
         data_table_id_to_replace: Optional[str] = None,
+        keep_features: Optional[List[str]] = None,
         _force_generation=False,
         _silent=False,
     ) -> str:
@@ -116,6 +117,8 @@ class DataSourcePublisher:
                     request["adsDefinitionIdToReplace"] = data_table_id_to_replace
                 if exclude_from_autofe_generation is not None:
                     request["excludeFromGeneration"] = exclude_from_autofe_generation
+                if keep_features is not None:
+                    request["keepFeatures"] = keep_features
                 self.logger.info(f"Start registering data table {request}")
 
                 task_id = self._rest_client.register_ads(request, trace_id)

{upgini-1.1.287a3232.post1 → upgini-1.1.288a0}/src/upgini/resource_bundle/strings.properties

@@ -81,7 +81,7 @@ date_and_datetime_simultanious=DATE and DATETIME search keys cannot be used simu
 email_and_hem_simultanious=EMAIL and HEM search keys cannot be used simultaneously. Choose one to keep
 postal_code_without_country=COUNTRY search key required if POSTAL_CODE is present
 multiple_search_key=Search key {} passed multiple times
-unregistered_only_personal_keys=Only personal search keys used. Api_key from profile.upgini.com required for EMAIL/HEM, PHONE NUMBER or IPv4 search keys\nSee docs https://github.com/upgini/upgini#-open-up-all-capabilities-of-upgini
+unregistered_only_personal_keys=Only personal search keys used. Api_key from profile.upgini.com required for EMAIL/HEM, PHONE NUMBER or IPv4/IPv6 search keys\nSee docs https://github.com/upgini/upgini#-open-up-all-capabilities-of-upgini
 search_key_not_found=Column `{}` from search_keys was not found in X dataframe: {}
 numeric_search_key_not_found=Index {} in search_keys is out of bounds for {} columns of X dataframe
 unsupported_search_key_type=Unsupported type of key in search_keys: {}

{upgini-1.1.287a3232.post1 → upgini-1.1.288a0}/src/upgini/utils/sklearn_ext.py

@@ -320,7 +320,7 @@ def cross_validate(
                 shuffle = cv.shuffle
             else:
                 shuffle = False
-            if hasattr(cv, "random_state"):
+            if hasattr(cv, "random_state") and shuffle:
                 random_state = cv.random_state
             else:
                 random_state = None

upgini-1.1.287a3232.post1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.287a3232-1"

{upgini-1.1.287a3232.post1 → upgini-1.1.288a0}/src/upgini/features_enricher.py

@@ -2596,9 +2596,6 @@ class FeaturesEnricher(TransformerMixin):
         return validated_X
 
     def _validate_y(self, X: pd.DataFrame, y) -> pd.Series:
-        if _num_samples(y) == 0:
-            raise ValidationError(self.bundle.get("y_is_empty"))
-
         if (
             not isinstance(y, pd.Series)
             and not isinstance(y, pd.DataFrame)
@@ -2607,6 +2604,9 @@ class FeaturesEnricher(TransformerMixin):
         ):
             raise ValidationError(self.bundle.get("unsupported_y_type").format(type(y)))
 
+        if _num_samples(y) == 0:
+            raise ValidationError(self.bundle.get("y_is_empty"))
+
         if _num_samples(X) != _num_samples(y):
             raise ValidationError(self.bundle.get("x_and_y_diff_size").format(_num_samples(X), _num_samples(y)))