upgini 1.1.296a3521.dev8__tar.gz → 1.1.296a3521.dev10__tar.gz

{upgini-1.1.296a3521.dev8 → upgini-1.1.296a3521.dev10}/PKG-INFO

@@ -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 → upgini-1.1.296a3521.dev10}/pyproject.toml

@@ -47,6 +47,7 @@ dependencies = [
     "python-json-logger>=2.0.2",
     "requests>=2.8.0",
     "scikit-learn>=1.3.0",
+    "python-bidi==0.4.2",
     "xhtml2pdf==0.2.11",
     "python-bidi==0.4.2",
 ]

upgini-1.1.296a3521.dev10/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.296a3521.dev10"

{upgini-1.1.296a3521.dev8 → upgini-1.1.296a3521.dev10}/src/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-1.1.296a3521.dev8 → upgini-1.1.296a3521.dev10}/src/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-1.1.296a3521.dev8 → upgini-1.1.296a3521.dev10}/src/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-1.1.296a3521.dev8 → upgini-1.1.296a3521.dev10}/src/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-1.1.296a3521.dev8 → upgini-1.1.296a3521.dev10}/src/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/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.296a3521.dev8"