upgini 1.1.296a3521.dev8__py3-none-any.whl → 1.1.296a3521.dev10__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.296a3521.dev8"
+__version__ = "1.1.296a3521.dev10"

upgini/autofe/all_operands.py

@@ -7,7 +7,7 @@ from upgini.autofe.date import (
     DateListDiff,
     DateListDiffBounded,
     DatePercentile,
-    DatePercentileType2,
+    DatePercentileMethod2,
 )
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
@@ -57,7 +57,7 @@ ALL_OPERANDS: Dict[str, Operand] = {
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=45, upper_bound=60),
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
         DatePercentile(),
-        DatePercentileType2(),
+        DatePercentileMethod2(),
         Norm(),
     ]
 }

upgini/autofe/date.py

@@ -39,6 +39,7 @@ class DateDiffMixin(BaseModel):
 
 class DateDiff(PandasOperand, DateDiffMixin):
     name = "date_diff"
+    alias = "date_diff_type1"
     is_binary = True
     has_symmetry_importance = True
 
@@ -197,6 +198,7 @@ class DatePercentileBase(PandasOperand, abc.ABC):
 
 class DatePercentile(DatePercentileBase):
     name = "date_per"
+    alias = "date_per_method1"
 
     zero_month: Optional[int]
     zero_year: Optional[int]
@@ -232,8 +234,8 @@ class DatePercentile(DatePercentileBase):
         )
 
 
-class DatePercentileType2(DatePercentileBase):
-    name = "date_per_type2"
+class DatePercentileMethod2(DatePercentileBase):
+    name = "date_per_method2"
 
     def _get_bounds(self, date_col: pd.Series) -> pd.Series:
         pass

upgini/autofe/feature.py

@@ -134,9 +134,6 @@ class Feature:
         for child in self.children:
             child.delete_data()
 
-    def get_name_component(self, **kwargs) -> str:
-        return "_".join(ch.get_name_component(**kwargs) for ch in self.children) + "_" + self.get_op_display_name()
-
     def get_op_display_name(self) -> str:
         return self.op.alias or self.op.name.lower()
 
@@ -149,8 +146,7 @@ class Feature:
         elif shorten and not self.op.is_unary:
             components = ["f_autofe", self.get_op_display_name()]
         else:
-            child_components = [ch.get_name_component(**kwargs) for ch in self.children]
-            components = ["f_" + "_f_".join(child_components)] + [
+            components = ["f_" + "_f_".join(self.get_columns(**kwargs))] + [
                 "autofe",
                 self.get_op_display_name(),
             ]

upgini/data_source/data_source_publisher.py

@@ -59,9 +59,35 @@ class DataSourcePublisher:
         features_for_embeddings: Optional[List[str]] = DEFAULT_GENERATE_EMBEDDINGS,
         data_table_id_to_replace: Optional[str] = None,
         keep_features: Optional[List[str]] = None,
+        date_features: Optional[List[str]] = None,
+        date_vector_features: Optional[List[str]] = None,
         _force_generation=False,
         _silent=False,
     ) -> str:
+        """Register new ADS
+
+        Parameters
+        ----------
+        data_table_uri - str - table name in format {project_id}.{datasource_name}.{table_name}
+
+        search_keys - dict with column names as keys and SearchKey as value
+
+        update_frequency - str - (Monthly, Weekly, Daily, Annually, Quarterly)
+
+        exclude_from_autofe_generation - optional list of features that should be excluded from AutoFE
+
+        secondary_search_keys - optional dict of secondary search keys
+
+        sort_column - optional str - name of unique column that could be used for sort
+
+        date_format - optional str - format of date if it is present in search keys
+
+        ...
+
+        data_table_id_to_replace - optional str - id of registered ADS that should be replaced by new table
+
+        keep_features - optional list - features that should not be removed from ADS (even if they are personal)
+        """
         trace_id = str(uuid.uuid4())
 
         with MDC(trace_id=trace_id):
@@ -124,6 +150,14 @@ class DataSourcePublisher:
                     request["excludeFromGeneration"] = exclude_from_autofe_generation
                 if keep_features is not None:
                     request["keepFeatures"] = keep_features
+                if date_features is not None:
+                    if date_format is None:
+                        raise ValidationError("date_format should be presented if you use date features")
+                    request["dateFeatures"] = date_features
+                if date_vector_features is not None:
+                    if date_format is None:
+                        raise ValidationError("date_format should be presented if you use date vector features")
+                    request["dateVectorFeatures"] = date_vector_features
                 self.logger.info(f"Start registering data table {request}")
 
                 task_id = self._rest_client.register_ads(request, trace_id)
@@ -181,6 +215,9 @@ class DataSourcePublisher:
                 msg = f"Data table successfully registered with id: {data_table_id}"
                 self.logger.info(msg)
                 print(msg)
+                if "warnings" in status_response and status_response["warnings"]:
+                    self.logger.warning(status_response["warnings"])
+                    print(status_response["warnings"])
                 return data_table_id
             except KeyboardInterrupt:
                 if task_id is not None:

upgini/features_enricher.py

@@ -2870,7 +2870,7 @@ class FeaturesEnricher(TransformerMixin):
                 self.logger.info(f"Dates interval is ({min_date}, {max_date})")
 
         except Exception:
-            self.logger.exception("Failed to log debug information")
+            self.logger.warning("Failed to log debug information", exc_info=True)
 
     def __handle_index_search_keys(self, df: pd.DataFrame, search_keys: Dict[str, SearchKey]) -> pd.DataFrame:
         index_names = df.index.names if df.index.names != [None] else [DEFAULT_INDEX]

{upgini-1.1.296a3521.dev8.dist-info → upgini-1.1.296a3521.dev10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.296a3521.dev8
+Version: 1.1.296a3521.dev10
 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-1.1.296a3521.dev8.dist-info → upgini-1.1.296a3521.dev10.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=X95_CDUy3kiapPYM43NYNLU3VWKYuc_yIZssoiW6W-w,34
+upgini/__about__.py,sha256=JKvS85WNogY-2YIe8YIQ4nIWCAaaPwBgVr2LGrQzI7g,35
 upgini/__init__.py,sha256=ObEtjFkIssl83qeKNMLpIQygfwK8TzztwiI43YTsAP0,353
 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=rLy6BwhL94VkRCp8W4RxJ0lBb7sZqTOsz-bUVI8nXZU,177530
+upgini/features_enricher.py,sha256=HQFLw3VyEsZfAt4xFnIYOnp3fzQSHAsyHzIm0gTJpOI,177543
 upgini/http.py,sha256=bp6jWl422Icy3AhHMdCcJv5NjExE45gSMmzMTPJjPuk,42600
 upgini/lazy_import.py,sha256=EwoM0msNGbSmWBhGbrLDny1DSnOlvTxCjmMKPxYlDms,610
 upgini/metadata.py,sha256=qDAIO7NLSSQp_XiXCv3U4XJTLO0KH3YuQ8lvCLYPqzs,9781
@@ -14,16 +14,16 @@ upgini/version_validator.py,sha256=ddSKUK_-eGJB3NgrqOMoWJU-OxQ253WsNLp8aqJkaIM,1
 upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9JvfkvgE,50
 upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo-R-nGdw,2648
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/autofe/all_operands.py,sha256=WJOiNVNVyrWc3vYGMvJtrpGRrLEQ237YMTsWnkUbLNw,2502
+upgini/autofe/all_operands.py,sha256=XbvgX2IU4aee9rJZ--d5MdmrfKhON_emle5-RU1qlEY,2506
 upgini/autofe/binary.py,sha256=8FXPJxN7fnC5wphO0Dp1tQCa0lFMSDGQGvBMkSIVAcE,4155
-upgini/autofe/date.py,sha256=CgzkV86ua5nN0SOxF5VF-90rI3Snz5lamgCicpG7FHQ,7878
-upgini/autofe/feature.py,sha256=OBR0K_pLYlowmSe54knhv5nwFBjTXiDdW_r9BT9ZxiU,13747
+upgini/autofe/date.py,sha256=8zYVhjl7jVS4xt-IjCgk9px2LHnACX2YlMlmDELlRTc,7943
+upgini/autofe/feature.py,sha256=nV1oJCT65nsAYFfXYCXYNYXZPaZVpqKJ09iCMTldooc,13500
 upgini/autofe/groupby.py,sha256=4WjDzQxqpZxB79Ih4ihMMI5GDxaFqiH6ZelfV82ClT4,3091
 upgini/autofe/operand.py,sha256=MKEsl3zxpWzRDpTkE0sNJxTu62U20sWOvEKhPjUWS6s,2915
 upgini/autofe/unary.py,sha256=ZWjLd-CUkNt_PpM8YuWLLipW1v_RdBlsl4JxXIVo9aM,3652
 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=6paupnciqagACnSzjGSkA2a5i-c9ETvZheLqBYOJemk,17810
+upgini/data_source/data_source_publisher.py,sha256=1cQZrK630VztwGGDp41ec9gqIeUtkefaqSSQEitVWiM,19581
 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
@@ -57,7 +57,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,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-1.1.296a3521.dev8.dist-info/METADATA,sha256=rKyU_Qddi5-pnSSRqotXi6vWWVRcIcCeMN1DHE6myMI,48161
-upgini-1.1.296a3521.dev8.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.1.296a3521.dev8.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.296a3521.dev8.dist-info/RECORD,,
+upgini-1.1.296a3521.dev10.dist-info/METADATA,sha256=RZTVD4L0dwwznJDxfpxjmCTZGzSQjE8lX1fw5CjP9ZA,48162
+upgini-1.1.296a3521.dev10.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.1.296a3521.dev10.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.296a3521.dev10.dist-info/RECORD,,