upgini 1.2.6a1__tar.gz → 1.2.8__tar.gz

{upgini-1.2.6a1 → upgini-1.2.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.6a1
+Version: 1.2.8
 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-1.2.8/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.8"

{upgini-1.2.6a1 → upgini-1.2.8}/src/upgini/autofe/all_operands.py

@@ -1,3 +1,4 @@
+from copy import deepcopy
 from typing import Dict
 
 from upgini.autofe.binary import (
@@ -83,4 +84,4 @@ ALL_OPERANDS: Dict[str, Operand] = {
 
 
 def find_op(name):
-    return ALL_OPERANDS.get(name)
+    return deepcopy(ALL_OPERANDS.get(name))

{upgini-1.2.6a1 → upgini-1.2.8}/src/upgini/autofe/feature.py

@@ -22,6 +22,9 @@ class Column:
     def set_op_params(self, params: Dict[str, str]) -> "Column":
         return self
 
+    def get_op_params(self, **kwargs):
+        return dict()
+
     def rename_columns(self, mapping: Dict[str, str]) -> "Column":
         self.name = self._unhash(mapping.get(self.name) or self.name)
         return self
@@ -44,6 +47,10 @@ class Column:
     def get_columns(self, **kwargs) -> List[str]:
         return [self.name]
 
+    @property
+    def children(self) -> List[Union["Feature", "Column"]]:
+        return []
+
     def infer_type(self, data: pd.DataFrame) -> DtypeObj:
         return data[self.name].dtype
 
@@ -88,9 +95,30 @@ class Feature:
         self.op.set_params(params)
 
         for child in self.children:
-            child.set_op_params(params)
+            child_params = {
+                k[len(child.get_display_name()) + 1 :]: v
+                for k, v in params.items()
+                if k.startswith(child.get_display_name())
+            }
+            if not child_params:
+                child_params = params
+            child.set_op_params(child_params)
         return self
 
+    def get_op_params(self, **kwargs) -> Dict[str, str]:
+        return {
+            k: str(v)
+            for k, v in dict(
+                (
+                    (f"{child.get_display_name(**kwargs)}_{k}", v)
+                    for child in self.children
+                    for k, v in child.get_op_params(**kwargs).items()
+                ),
+                **(self.op.get_params() or {}),
+            ).items()
+            if v is not None
+        }
+
     def get_hash(self) -> str:
         return hashlib.sha256(
             "_".join([self.op.name] + [ch.get_display_name() for ch in self.children]).encode("utf-8")
@@ -326,24 +354,26 @@ class FeatureGroup:
         return names
 
     def calculate(self, data: pd.DataFrame, is_root=False) -> pd.DataFrame:
-        main_column = None if self.main_column_node is None else self.main_column_node.get_columns()[0]
         if isinstance(self.op, PandasOperand):
-            columns = self.get_columns()
-            lower_order_children = [
+            main_column = None if self.main_column_node is None else self.main_column_node.get_display_name()
+            lower_order_children = []
+            if self.main_column_node is not None:
+                lower_order_children.append(self.main_column_node)
+            lower_order_children.extend(
                 ch for f in self.children for ch in f.children if ch.get_display_name() != main_column
-            ]
+            )
             lower_order_names = [ch.get_display_name() for ch in lower_order_children]
-            if any(isinstance(f, Feature) for f in lower_order_children):
-                child_data = pd.concat(
-                    [data[main_column or []]] + [ch.calculate(data) for ch in lower_order_children],
-                    axis=1,
-                )
-                child_data.columns = ([main_column] if main_column is not None else []) + lower_order_names
-            else:
-                child_data = data[columns]
+            child_data = pd.concat(
+                [ch.calculate(data) for ch in lower_order_children],
+                axis=1,
+            )
+            child_data.columns = lower_order_names
 
             new_data = self.op.calculate_group(child_data, main_column=main_column)
-            new_data.rename(columns=dict(zip(lower_order_names, self.get_display_names())), inplace=True)
+            new_data.rename(
+                columns=dict(zip((n for n in lower_order_names if n != main_column), self.get_display_names())),
+                inplace=True,
+            )
         else:
             raise NotImplementedError(f"Unrecognized operator {self.op.name}.")
 

{upgini-1.2.6a1 → upgini-1.2.8}/src/upgini/data_source/data_source_publisher.py

@@ -64,6 +64,7 @@ class DataSourcePublisher:
         date_features: Optional[List[str]] = None,
         date_vector_features: Optional[List[str]] = None,
         generate_runtime_embeddings: Optional[List[str]] = None,
+        exclude_raw: Optional[List[str]] = None,
         _force_generation=False,
         _silent=False,
     ) -> str:
@@ -88,6 +89,8 @@ class DataSourcePublisher:
         features_for_embeddings - optional list of str - list of features that should be used for GPT features
             generation
 
+        exclude_raw - optional list of str - list of features that should NOT be used as raw features
+
         ...
 
         data_table_id_to_replace - optional str - id of registered ADS that should be replaced by new table
@@ -166,6 +169,8 @@ class DataSourcePublisher:
                     request["dateVectorFeatures"] = date_vector_features
                 if generate_runtime_embeddings is not None:
                     request["generateRuntimeEmbeddingsFeatures"] = generate_runtime_embeddings
+                if exclude_raw is not None:
+                    request["excludeRaw"] = exclude_raw
                 self.logger.info(f"Start registering data table {request}")
 
                 task_id = self._rest_client.register_ads(request, trace_id)
@@ -281,6 +286,7 @@ class DataSourcePublisher:
         date_vector_features: Optional[List[str]] = None,
         exclude_from_autofe_generation: Optional[List[str]] = None,
         generate_runtime_embeddings: Optional[List[str]] = None,
+        exclude_raw: Optional[List[str]] = None,
     ):
         trace_id = str(uuid.uuid4())
         with MDC(trace_id=trace_id):
@@ -336,6 +342,8 @@ class DataSourcePublisher:
                     request["excludeFromGenerationFeatures"] = exclude_from_autofe_generation
                 if generate_runtime_embeddings is not None:
                     request["generateRuntimeEmbeddingsFeatures"] = generate_runtime_embeddings
+                if exclude_raw is not None:
+                    request["excludeRaw"] = exclude_raw
                 self.logger.info(f"Activating data tables with request {request}")
 
                 self._rest_client.activate_datatables(request, trace_id)
@@ -378,7 +386,6 @@ class DataSourcePublisher:
                 search_keys = [k.value.value for k in search_keys] if search_keys else None
                 request = {"bqTableId": bq_table_id, "searchKeys": search_keys}
                 task_id = self._rest_client.upload_online(request, trace_id)
-                print(f"Start polling management task_id={task_id} with trace_id={trace_id}")
                 with Spinner():
                     status_response = self._rest_client.poll_ads_management_task_status(task_id, trace_id)
                     while status_response["status"] not in self.FINAL_STATUSES:

{upgini-1.2.6a1 → upgini-1.2.8}/src/upgini/features_enricher.py

@@ -2095,7 +2095,9 @@ class FeaturesEnricher(TransformerMixin):
             features_not_to_pass = [
                 c
                 for c in df.columns
-                if c not in search_keys.keys() and c not in features_for_transform and c != ENTITY_SYSTEM_RECORD_ID
+                if c not in search_keys.keys()
+                and c not in features_for_transform
+                and c not in [ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST]
             ]
 
             if add_fit_system_record_id:
@@ -3235,7 +3237,6 @@ class FeaturesEnricher(TransformerMixin):
                 ]
             )
 
-            # TODO some columns not exists
             all_other_columns = sorted_other_keys + other_columns
 
             search_keys_hash = "search_keys_hash"

{upgini-1.2.6a1 → upgini-1.2.8}/src/upgini/utils/ip_utils.py

@@ -104,7 +104,7 @@ class IpSearchKeyConverter:
         del self.search_keys[self.ip_column]
         del self.columns_renaming[self.ip_column]
         self.search_keys[ipv6] = SearchKey.IPV6_ADDRESS
-        self.columns_renaming[ipv6] = original_ip  # could be upgini_ip_unnest...
+        self.columns_renaming[ipv6] = original_ip  # could be __unnest_ip...
 
         return df
 

upgini-1.2.6a1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.6a1"