upgini 1.1.295__tar.gz → 1.1.296a3511.dev1__tar.gz

{upgini-1.1.295 → upgini-1.1.296a3511.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.295
+Version: 1.1.296a3511.dev1
 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.dev1/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.296a3511.dev1"

{upgini-1.1.295 → upgini-1.1.296a3511.dev1}/src/upgini/autofe/all_operands.py

@@ -1,8 +1,22 @@
 from typing import Dict
 
-from upgini.autofe.binary import Add, Divide, Max, Min, Multiply, Sim, Subtract
+from upgini.autofe.binary import (
+    Add,
+    Combine,
+    CombineThenFreq,
+    Distance,
+    Divide,
+    JaroWinklerSim1,
+    JaroWinklerSim2,
+    LevenshteinSim,
+    Max,
+    Min,
+    Multiply,
+    Sim,
+    Subtract,
+)
 from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded, DatePercentile
-from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
+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.vector import Mean, Sum
@@ -32,10 +46,10 @@ ALL_OPERANDS: Dict[str, Operand] = {
         GroupByThenAgg(name="GroupByThenMedian", agg="median"),
         GroupByThenAgg(name="GroupByThenStd", output_type="float", agg="std"),
         GroupByThenRank(),
-        Operand(name="Combine", has_symmetry_importance=True, output_type="object", is_categorical=True),
-        Operand(name="CombineThenFreq", has_symmetry_importance=True, output_type="float"),
-        Operand(name="GroupByThenNUnique", output_type="int", is_vectorizable=True, is_grouping=True),
-        Operand(name="GroupByThenFreq", output_type="float", is_grouping=True),
+        Combine(),
+        CombineThenFreq(),
+        GroupByThenNUnique(),
+        GroupByThenFreq(),
         Sim(),
         DateDiff(),
         DateDiffType2(),
@@ -51,6 +65,10 @@ ALL_OPERANDS: Dict[str, Operand] = {
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
         DatePercentile(),
         Norm(),
+        JaroWinklerSim1(),
+        JaroWinklerSim2(),
+        LevenshteinSim(),
+        Distance(),
     ]
 }
 

{upgini-1.1.295 → upgini-1.1.296a3511.dev1}/src/upgini/autofe/binary.py

@@ -1,7 +1,11 @@
+import abc
+from typing import Optional
+import Levenshtein
 import numpy as np
 import pandas as pd
 from numpy import dot
 from numpy.linalg import norm
+from jarowinkler import jarowinkler_similarity
 
 from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
@@ -130,8 +134,8 @@ class CombineThenFreq(PandasOperand):
         self._loc(temp, value_counts)
 
 
-class Sim(PandasOperand):
-    name = "sim"
+class Distance(PandasOperand):
+    name = "dist"
     is_binary = True
     output_type = "float"
     is_symmetrical = True
@@ -139,3 +143,78 @@ class Sim(PandasOperand):
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         return dot(left, right) / (norm(left) * norm(right))
+
+
+class Sim(Distance):
+    name = "sim"
+    is_binary = True
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
+
+
+class StringSim(PandasOperand, abc.ABC):
+    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        sims = []
+        for i in left.index:
+            left_i = self._prepare_value(left.get(i))
+            right_i = self._prepare_value(right.get(i))
+            if left_i is not None and right_i is not None:
+                sims.append(self._similarity(left_i, right_i))
+            else:
+                sims.append(None)
+
+        return pd.Series(sims, index=left.index)
+
+    @abc.abstractmethod
+    def _prepare_value(self, value: Optional[str]) -> Optional[str]:
+        pass
+
+    @abc.abstractmethod
+    def _similarity(self, left: str, right: str) -> float:
+        pass
+
+
+class JaroWinklerSim1(StringSim):
+    name = "sim_jw1"
+    is_binary = True
+    input_type = "string"
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
+
+    def _prepare_value(self, value: Optional[str]) -> Optional[str]:
+        return value
+
+    def _similarity(self, left: str, right: str) -> float:
+        return jarowinkler_similarity(left, right)
+
+
+class JaroWinklerSim2(StringSim):
+    name = "sim_jw2"
+    is_binary = True
+    input_type = "string"
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
+
+    def _prepare_value(self, value: Optional[str]) -> Optional[str]:
+        return value[::-1] if value is not None else None
+
+    def _similarity(self, left: str, right: str) -> float:
+        return jarowinkler_similarity(left, right)
+
+
+class LevenshteinSim(StringSim):
+    name = "sim_lv"
+    is_binary = True
+    input_type = "string"
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
+
+    def _prepare_value(self, value: Optional[str]) -> Optional[str]:
+        return value
+
+    def _similarity(self, left: str, right: str) -> float:
+        return 1 - Levenshtein.distance(left, right) / max(len(left), len(right))

upgini-1.1.295/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.295"