upgini 1.1.287__py3-none-any.whl → 1.1.287a3232.post1__py3-none-any.whl

upgini/__about__.py

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

upgini/autofe/date.py

@@ -2,6 +2,7 @@ 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
 
@@ -21,6 +22,20 @@ 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"
@@ -41,7 +56,8 @@ 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)
-        return self.__replace_negative((left - right) / np.timedelta64(1, self.diff_unit))
+        diff = self._convert_diff_to_unit(left.dt.date - right.dt.date)
+        return self.__replace_negative(diff)
 
     def __replace_negative(self, x: Union[pd.DataFrame, pd.Series]):
         x[x < 0] = None
@@ -107,12 +123,7 @@ class DateListDiff(PandasOperand, DateDiffMixin):
         return pd.Series(left - right.values).apply(lambda x: self._agg(self._diff(x)))
 
     def _diff(self, x: TimedeltaArray):
-        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)
+        x = self._convert_diff_to_unit(x)
         return x[x > 0]
 
     def _agg(self, x):

upgini/data_source/data_source_publisher.py

@@ -58,7 +58,6 @@ 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:
@@ -117,8 +116,6 @@ 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/features_enricher.py

@@ -2596,6 +2596,9 @@ 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)
@@ -2604,9 +2607,6 @@ 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)))
 

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/IPv6 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 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-1.1.287.dist-info → upgini-1.1.287a3232.post1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.287
+Version: 1.1.287a3232.post1
 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-1.1.287.dist-info → upgini-1.1.287a3232.post1.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=WtxVJq1BW1DUDDaE5gqIzPkiWzy6p8Kcht-f1BAV52I,24
+upgini/__about__.py,sha256=AbRcDfYtBT7CZaikr7-ihUYbwsvTkE9kN2r6HAW5iGs,31
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=7TLVVhGtjgx_9yaiaIUK3kZSe_R9wg5dY0d4F5qCGM4,45636
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=Bfqbzqj3h1Ox3s6hBA4UYXkG7hQDqGPB4JK1YXtxXxw,177530
+upgini/features_enricher.py,sha256=EKngUPR5dpX8bZWrwl8qW61TtzssbxGEVwVO7XM3d3o,177530
 upgini/http.py,sha256=khrYSldpY-HbVLCcApfV1BjBFK6Uyuatb4colKybxgY,42301
 upgini/metadata.py,sha256=qDAIO7NLSSQp_XiXCv3U4XJTLO0KH3YuQ8lvCLYPqzs,9781
 upgini/metrics.py,sha256=DLvA2YLV4f7lnzBCcfZ5T4NkqAv3pbstbjTepavuT7U,30688
@@ -15,21 +15,21 @@ upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operands.py,sha256=7UyvmmqGSqQu4kDgoFwQRKY__b9xKDk3Fpp2-H8A7AA,2399
 upgini/autofe/binary.py,sha256=441BRuqMsxlxuw4c8rMZB6h5EpRdVMk-bVa03U7T5Hg,3973
-upgini/autofe/date.py,sha256=w0C2n261Uzd9sEk3s7QdDrXLZBWv6Vv7EBuv0W1g-LU,6738
+upgini/autofe/date.py,sha256=xy6D4dYvf5efVOzV8xn1H6fzYLIjjTY9MGwfnGcCAzs,7310
 upgini/autofe/feature.py,sha256=_V9B74B3ue7eAYXSOt9JKhVC9klkAKks22MwnBRye_w,12487
 upgini/autofe/groupby.py,sha256=4WjDzQxqpZxB79Ih4ihMMI5GDxaFqiH6ZelfV82ClT4,3091
 upgini/autofe/operand.py,sha256=JjEVT1U3kY9NDjUPMdoki7Oa8hMDG0-_h_NklVjIFyc,2882
 upgini/autofe/unary.py,sha256=v-l3aiE5hj6kurvh6adCQL8W3X9u9a7RVbS_WPR2qlw,3146
 upgini/autofe/vector.py,sha256=dLxfAstJs-gw_OQ1xxoxcM6pVzORlV0HVzdzt7cLXVQ,606
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/data_source/data_source_publisher.py,sha256=B4fJ1owDCF5ZZ0Ca9ywi_CXVt4iPvABh5BGTnXdXmHk,16635
+upgini/data_source/data_source_publisher.py,sha256=taRzyGgrPrTTSGw4Y-Ca5k4bf30aiTa68rxqT9zfqeI,16478
 upgini/mdc/__init__.py,sha256=aM08nIWFc2gWdWUa3_IuEnNND0cQPkBGnYpRMnfFN8k,1019
 upgini/mdc/context.py,sha256=3u1B-jXt7tXEvNcV3qmR9SDCseudnY7KYsLclBdwVLk,1405
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/normalizer/phone_normalizer.py,sha256=EzTaahk6myRv6ZXgbyVFGY4kpo_2VlQgOrm5_lfbmNI,9996
 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=1oHurL4I83P2lXIavx9vSdKM8ZqncAPXH2IZf76bD6g,26292
+upgini/resource_bundle/strings.properties,sha256=1O779a0-Ai0j7W-Z5AznvjuV69YkJvgGhJda-6VMLOQ,26287
 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
@@ -56,7 +56,7 @@ upgini/utils/sklearn_ext.py,sha256=N-eJrfAJxYpDPc85sKQyMFcIeL9Ug2lwlqDyS4jFOdE,4
 upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.287.dist-info/METADATA,sha256=QQ4-zg1aeZceZi65axWevn2a9tU5PEFCmE0hRSXoEzA,48117
-upgini-1.1.287.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.1.287.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.287.dist-info/RECORD,,
+upgini-1.1.287a3232.post1.dist-info/METADATA,sha256=WYI6YVa5RX0B1MNfStn_rU3M9QTg2Z5khzwNHxBzPp4,48128
+upgini-1.1.287a3232.post1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.1.287a3232.post1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.287a3232.post1.dist-info/RECORD,,