upgini 1.1.296a3521.dev3__tar.gz → 1.1.296a3521.dev5__tar.gz

{upgini-1.1.296a3521.dev3 → upgini-1.1.296a3521.dev5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.296a3521.dev3
+Version: 1.1.296a3521.dev5
 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.dev5/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.296a3521.dev5"

{upgini-1.1.296a3521.dev3 → upgini-1.1.296a3521.dev5}/src/upgini/autofe/date.py

@@ -172,13 +172,13 @@ class DatePercentileBase(PandasOperand, abc.ABC):
 
         bounds = self._get_bounds(left)
 
-        return right.index.to_series().apply(lambda i: self.__perc(right[i], bounds[i]))
+        return right.index.to_series().apply(lambda i: self._perc(right[i], bounds[i]))
 
     @abc.abstractmethod
     def _get_bounds(self, date_col: pd.Series) -> pd.Series:
         pass
 
-    def __perc(self, f, bounds):
+    def _perc(self, f, bounds):
         hit = np.where(f >= bounds)[0]
         if hit.size > 0:
             return np.max(hit) + 1

{upgini-1.1.296a3521.dev3 → upgini-1.1.296a3521.dev5}/src/upgini/autofe/feature.py

@@ -16,6 +16,9 @@ class Column:
         self.data = data
         self.calculate_all = calculate_all
 
+    def get_name_component(self, **kwargs) -> str:
+        return self.name
+
     def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
         return self.name
 
@@ -41,7 +44,7 @@ class Column:
     def get_column_nodes(self) -> List["Column"]:
         return [self]
 
-    def get_columns(self) -> List[str]:
+    def get_columns(self, **kwargs) -> List[str]:
         return [self.name]
 
     def infer_type(self, data: pd.DataFrame) -> DtypeObj:
@@ -57,6 +60,12 @@ class Column:
     def to_pretty_formula(self) -> str:
         return self.to_formula()
 
+    def __eq__(self, value: object) -> bool:
+        if not isinstance(value, Column):
+            return False
+        else:
+            return self.name == value.name and self.calculate_all == value.calculate_all
+
 
 class Feature:
     def __init__(
@@ -125,6 +134,12 @@ 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()
+
     def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
         if self.cached_display_name is not None and cache:
             return self.cached_display_name
@@ -132,11 +147,12 @@ class Feature:
         if self.alias:
             components = ["f_autofe", self.alias]
         elif shorten and not self.op.is_unary:
-            components = ["f_autofe", self.op.alias or self.op.name.lower()]
+            components = ["f_autofe", self.get_op_display_name()]
         else:
-            components = ["f_" + "_f_".join(self.get_columns(**kwargs))] + [
+            child_components = [ch.get_name_component(**kwargs) for ch in self.children]
+            components = ["f_" + "_f_".join(child_components)] + [
                 "autofe",
-                self.op.alias or self.op.name.lower(),
+                self.get_op_display_name(),
             ]
         components.extend([str(self.display_index)] if self.display_index is not None else [])
         display_name = "_".join(components)
@@ -306,8 +322,20 @@ class FeatureGroup:
         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()
-            new_data = self.op.calculate_group(data[columns], main_column=main_column)
-            new_data.rename(columns=dict(zip(columns, self.get_display_names())), inplace=True)
+            lower_order_children = [
+                ch for f in self.children for ch in f.children if ch.get_display_name() != main_column
+            ]
+            if any(isinstance(f, Feature) for f in lower_order_children):
+                child_data = pd.concat(
+                    [data[main_column]] + [ch.calculate(data) for ch in lower_order_children], axis=1
+                )
+            else:
+                child_data = data[columns]
+
+            new_data = self.op.calculate_group(child_data, main_column=main_column)
+            new_data.rename(
+                columns=dict(zip((c for c in columns if c != main_column), self.get_display_names())), inplace=True
+            )
         else:
             raise NotImplementedError(f"Unrecognized operator {self.op.name}.")
 

upgini-1.1.296a3521.dev3/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.296a3521.dev3"