upgini 1.2.65a3818.dev5__tar.gz → 1.2.65a3818.dev7__tar.gz

{upgini-1.2.65a3818.dev5 → upgini-1.2.65a3818.dev7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.65a3818.dev5
+Version: 1.2.65a3818.dev7
 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-1.2.65a3818.dev7/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.65a3818.dev7"

{upgini-1.2.65a3818.dev5 → upgini-1.2.65a3818.dev7}/src/upgini/autofe/feature.py

@@ -6,7 +6,7 @@ import numpy as np
 import pandas as pd
 from pandas._typing import DtypeObj
 
-from upgini.autofe.all_operands import find_op
+from upgini.autofe.all_operators import find_op
 from upgini.autofe.operator import Operator, PandasOperator
 
 
@@ -112,7 +112,7 @@ class Feature:
 
     def get_hash(self) -> str:
         return hashlib.sha256(
-            "_".join([self.op.to_formula()] + [ch.get_display_name() for ch in self.children]).encode("utf-8")
+            "_".join([self.op.get_hash_component()] + [ch.get_display_name() for ch in self.children]).encode("utf-8")
         ).hexdigest()[:8]
 
     def set_alias(self, alias: str) -> "Feature":

{upgini-1.2.65a3818.dev5 → upgini-1.2.65a3818.dev7}/src/upgini/autofe/operator.py

@@ -76,6 +76,9 @@ class Operator(BaseModel, metaclass=OperatorRegistry):
     def to_formula(self) -> str:
         return self.name
 
+    def get_hash_component(self) -> str:
+        return self.to_formula()
+
 
 class ParametrizedOperator(Operator, abc.ABC):
 

{upgini-1.2.65a3818.dev5 → upgini-1.2.65a3818.dev7}/src/upgini/autofe/timeseries/cross.py

@@ -8,7 +8,7 @@ try:
 except ImportError:
     from pydantic import validator  # V1
 
-from upgini.autofe.all_operands import find_op
+from upgini.autofe.all_operators import find_op
 from upgini.autofe.operator import PandasOperator, ParametrizedOperator
 from upgini.autofe.timeseries.base import TimeSeriesBase
 
@@ -95,6 +95,15 @@ class CrossSeriesInteraction(TimeSeriesBase, ParametrizedOperator):
         )
         return res
 
+    def get_hash_component(self) -> str:
+        inner_components = [
+            self.to_formula(),
+            "_".join(str(i) for i in self.descriptor_indices),
+            "_".join(self.left_descriptor),
+            "_".join(self.right_descriptor),
+        ]
+        return "_".join(inner_components)
+
     def _get_interaction_op_name(self) -> str:
         return self.interaction_op.alias or self.interaction_op.to_formula()
 
@@ -113,7 +122,7 @@ class CrossSeriesInteraction(TimeSeriesBase, ParametrizedOperator):
         return res
 
     def _get_mask(self, data: List[pd.Series], descriptor: List[str]) -> pd.Series:
-        mask = np.logical_and.reduce([data[i] == v for i, v in zip(self.descriptor_indices, descriptor)])
+        mask = np.logical_and.reduce([data[i].astype(str) == v for i, v in zip(self.descriptor_indices, descriptor)])
         return mask
 
     def _extract_series(self, data: List[pd.Series], mask: pd.Series) -> pd.Series:

upgini-1.2.65a3818.dev5/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.65a3818.dev5"