upgini 1.1.280a3418.post2__tar.gz → 1.1.280a3418.post4__tar.gz

{upgini-1.1.280a3418.post2 → upgini-1.1.280a3418.post4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.280a3418.post2
+Version: 1.1.280a3418.post4
 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-1.1.280a3418.post4/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.280a3418-4"

{upgini-1.1.280a3418.post2 → upgini-1.1.280a3418.post4}/src/upgini/autofe/feature.py

@@ -16,6 +16,9 @@ class Column:
         self.data = data
         self.calculate_all = calculate_all
 
+    def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
+        return self.name
+
     def rename_columns(self, mapping: Dict[str, str]) -> "Column":
         self.name = self._unhash(mapping.get(self.name) or self.name)
         return self
@@ -74,9 +77,9 @@ class Feature:
         return self
 
     def get_hash(self) -> str:
-        return hashlib.sha256("_".join([self.op.name] + [ch.name for ch in self.children]).encode("utf-8")).hexdigest()[
-            :8
-        ]
+        return hashlib.sha256(
+            "_".join([self.op.name] + [ch.get_display_name() for ch in self.children]).encode("utf-8")
+        ).hexdigest()[:8]
 
     def set_alias(self, alias: str) -> "Feature":
         self.alias = alias

{upgini-1.1.280a3418.post2 → upgini-1.1.280a3418.post4}/src/upgini/autofe/unary.py

@@ -1,3 +1,4 @@
+from typing import Optional
 import numpy as np
 import pandas as pd
 
@@ -119,13 +120,17 @@ class Bin(PandasOperand):
     output_type = "int"
     input_type = "discrete"
 
-    zero_bound_low: int
-    zero_bound_high: int
-    step: int
+    zero_bound_low: Optional[int]
+    zero_bound_high: Optional[int]
+    step: Optional[int]
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
+        high = self.zero_bound_high if self.zero_bound_high is not None else np.inf
+        low = self.zero_bound_low if self.zero_bound_low is not None else -np.inf
+        step = self.step or 1
+
         res = pd.Series(np.zeros(data.shape), index=data.index, dtype="int")
-        res.update((data[data < self.zero_bound_low] - self.zero_bound_low) // self.step)
-        res.update((data[data >= self.zero_bound_high] - self.zero_bound_high) // self.step + 1)
+        res.update((data[data < low] - low) // step)
+        res.update((data[data >= high] - high) // step + 1)
 
         return res

upgini-1.1.280a3418.post2/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.280a3418-2"