upgini 1.1.296a3511.dev2__tar.gz → 1.1.296a3511.dev4__tar.gz

{upgini-1.1.296a3511.dev2 → upgini-1.1.296a3511.dev4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.296a3511.dev2
+Version: 1.1.296a3511.dev4
 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-1.1.296a3511.dev4/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.296a3511.dev4"

{upgini-1.1.296a3511.dev2 → upgini-1.1.296a3511.dev4}/src/upgini/autofe/all_operands.py

@@ -18,7 +18,7 @@ from upgini.autofe.binary import (
 from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded, DatePercentile
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenFreq, GroupByThenNUnique, GroupByThenRank
 from upgini.autofe.operand import Operand
-from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Norm, Sigmoid, Sqrt, Square
+from upgini.autofe.unary import Abs, Embeddings, Floor, Freq, Log, Residual, Norm, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
 
 ALL_OPERANDS: Dict[str, Operand] = {
@@ -69,6 +69,7 @@ ALL_OPERANDS: Dict[str, Operand] = {
         JaroWinklerSim2(),
         LevenshteinSim(),
         Distance(),
+        Embeddings(),
     ]
 }
 

{upgini-1.1.296a3511.dev2 → upgini-1.1.296a3511.dev4}/src/upgini/autofe/binary.py

@@ -142,9 +142,16 @@ class Distance(PandasOperand):
     has_symmetry_importance = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
-        return dot(left, right) / (norm(left) * norm(right))
+        return pd.Series(
+            1 - self.__dot(left, right) / (self.__dot(left, left) * self.__dot(right, right)), index=left.index
+        )
 
+    # row-wise dot product
+    def __dot(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        return (left * right).apply(np.sum)
 
+
+# Left for backward compatibility
 class Sim(Distance):
     name = "sim"
     is_binary = True
@@ -152,6 +159,9 @@ class Sim(Distance):
     is_symmetrical = True
     has_symmetry_importance = True
 
+    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        return 1 - super().calculate_binary(left, right)
+
 
 class StringSim(PandasOperand, abc.ABC):
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:

{upgini-1.1.296a3511.dev2 → upgini-1.1.296a3511.dev4}/src/upgini/autofe/unary.py

@@ -125,3 +125,10 @@ class Norm(PandasOperand):
         normalized_data = pd.Series(normalized_data[:, 0], index=data_dropna.index, name=data.name)
         normalized_data = normalized_data.reindex(data.index)
         return normalized_data
+
+
+class Embeddings(PandasOperand):
+    name = "emb"
+    is_unary = True
+    input_type = "string"
+    output_type = "vector"

upgini-1.1.296a3511.dev2/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.296a3511.dev2"