upgini 1.1.296a3511.dev5__tar.gz → 1.1.296a3521.dev2__tar.gz

{upgini-1.1.296a3511.dev5 → upgini-1.1.296a3521.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.296a3511.dev5
+Version: 1.1.296a3521.dev2
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -26,8 +26,6 @@ Requires-Python: <3.11,>=3.8
 Requires-Dist: catboost>=1.0.3
 Requires-Dist: fastparquet>=0.8.1
 Requires-Dist: ipywidgets>=8.1.0
-Requires-Dist: jarowinkler>=2.0.0
-Requires-Dist: levenshtein>=0.25.1
 Requires-Dist: lightgbm>=3.3.2
 Requires-Dist: numpy>=1.19.0
 Requires-Dist: pandas<3.0.0,>=1.1.0

{upgini-1.1.296a3511.dev5 → upgini-1.1.296a3521.dev2}/pyproject.toml

@@ -48,8 +48,6 @@ dependencies = [
     "requests>=2.8.0",
     "scikit-learn>=1.3.0",
     "xhtml2pdf==0.2.11",
-    "jarowinkler>=2.0.0",
-    "levenshtein>=0.25.1",
 ]
 
 [project.urls]

upgini-1.1.296a3521.dev2/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.296a3521.dev2"

{upgini-1.1.296a3511.dev5 → upgini-1.1.296a3521.dev2}/src/upgini/autofe/all_operands.py

@@ -1,24 +1,17 @@
 from typing import Dict
 
-from upgini.autofe.binary import (
-    Add,
-    Combine,
-    CombineThenFreq,
-    Distance,
-    Divide,
-    JaroWinklerSim1,
-    JaroWinklerSim2,
-    LevenshteinSim,
-    Max,
-    Min,
-    Multiply,
-    Sim,
-    Subtract,
+from upgini.autofe.binary import Add, Divide, Max, Min, Multiply, Sim, Subtract
+from upgini.autofe.date import (
+    DateDiff,
+    DateDiffType2,
+    DateListDiff,
+    DateListDiffBounded,
+    DatePercentile,
+    DatePercentileType2,
 )
-from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded, DatePercentile
-from upgini.autofe.groupby import GroupByThenAgg, GroupByThenFreq, GroupByThenNUnique, GroupByThenRank
+from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
-from upgini.autofe.unary import Abs, Embeddings, Floor, Freq, Log, Residual, Norm, Sigmoid, Sqrt, Square
+from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Norm, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
 
 ALL_OPERANDS: Dict[str, Operand] = {
@@ -46,10 +39,10 @@ ALL_OPERANDS: Dict[str, Operand] = {
         GroupByThenAgg(name="GroupByThenMedian", agg="median"),
         GroupByThenAgg(name="GroupByThenStd", output_type="float", agg="std"),
         GroupByThenRank(),
-        Combine(),
-        CombineThenFreq(),
-        GroupByThenNUnique(),
-        GroupByThenFreq(),
+        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),
         Sim(),
         DateDiff(),
         DateDiffType2(),
@@ -64,12 +57,8 @@ ALL_OPERANDS: Dict[str, Operand] = {
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=45, upper_bound=60),
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
         DatePercentile(),
+        DatePercentileType2(),
         Norm(),
-        JaroWinklerSim1(),
-        JaroWinklerSim2(),
-        LevenshteinSim(),
-        Distance(),
-        Embeddings(),
     ]
 }
 

{upgini-1.1.296a3511.dev5 → upgini-1.1.296a3521.dev2}/src/upgini/autofe/binary.py

@@ -1,11 +1,7 @@
-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
 
@@ -134,25 +130,7 @@ class CombineThenFreq(PandasOperand):
         self._loc(temp, value_counts)
 
 
-class Distance(PandasOperand):
-    name = "dist"
-    is_binary = True
-    output_type = "float"
-    is_symmetrical = True
-    has_symmetry_importance = True
-
-    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
-        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):
+class Sim(PandasOperand):
     name = "sim"
     is_binary = True
     output_type = "float"
@@ -160,71 +138,4 @@ class Sim(Distance):
     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:
-        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))
+        return dot(left, right) / (norm(left) * norm(right))

{upgini-1.1.296a3511.dev5 → upgini-1.1.296a3521.dev2}/src/upgini/autofe/date.py

@@ -1,3 +1,4 @@
+import abc
 from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
@@ -41,8 +42,6 @@ class DateDiff(PandasOperand, DateDiffMixin):
     is_binary = True
     has_symmetry_importance = True
 
-    replace_negative: bool = False
-
     def get_params(self) -> Dict[str, Optional[str]]:
         res = super().get_params()
         res.update(
@@ -50,7 +49,6 @@ class DateDiff(PandasOperand, DateDiffMixin):
                 "diff_unit": self.diff_unit,
                 "left_unit": self.left_unit,
                 "right_unit": self.right_unit,
-                "replace_negative": self.replace_negative,
             }
         )
         return res
@@ -62,8 +60,7 @@ class DateDiff(PandasOperand, DateDiffMixin):
         return self.__replace_negative(diff)
 
     def __replace_negative(self, x: Union[pd.DataFrame, pd.Series]):
-        if self.replace_negative:
-            x[x < 0] = None
+        x[x < 0] = None
         return x
 
 
@@ -103,19 +100,13 @@ _ext_aggregations = {"nunique": (lambda x: len(np.unique(x)), 0), "count": (len,
 class DateListDiff(PandasOperand, DateDiffMixin):
     is_binary = True
     has_symmetry_importance = True
-
     aggregation: str
-    replace_negative: bool = False
 
     def get_params(self) -> Dict[str, Optional[str]]:
         res = super().get_params()
         res.update(
             {
                 "aggregation": self.aggregation,
-                "diff_unit": self.diff_unit,
-                "left_unit": self.left_unit,
-                "right_unit": self.right_unit,
-                "replace_negative": self.replace_negative,
             }
         )
         return res
@@ -133,7 +124,7 @@ class DateListDiff(PandasOperand, DateDiffMixin):
 
     def _diff(self, x: TimedeltaArray):
         x = self._convert_diff_to_unit(x)
-        return x[x > 0] if self.replace_negative else x
+        return x[x > 0]
 
     def _agg(self, x):
         method = getattr(np, self.aggregation, None)
@@ -169,11 +160,33 @@ class DateListDiffBounded(DateListDiff):
         return super()._agg(x)
 
 
-class DatePercentile(PandasOperand):
-    name = "date_per"
+class DatePercentileBase(PandasOperand, abc.ABC):
     is_binary = True
     output_type = "float"
 
+    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        # Assuming that left is a date column, right is a feature column
+        left = pd.to_datetime(left, unit=self.date_unit)
+
+        bounds = self._get_bounds(left)
+
+        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):
+        hit = np.where(f >= bounds)[0]
+        if hit.size > 0:
+            return np.max(hit) + 1
+        else:
+            return np.nan
+
+
+class DatePercentile(DatePercentileBase):
+    name = "date_per"
+
     date_unit: Optional[str] = None
     zero_month: Optional[int]
     zero_year: Optional[int]
@@ -200,22 +213,18 @@ class DatePercentile(PandasOperand):
         elif isinstance(value, str):
             return value[1:-1].split(", ")
 
-    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
-        # Assuming that left is a date column, right is a feature column
-        left = pd.to_datetime(left, unit=self.date_unit)
-        months = left.dt.month
-        years = left.dt.year
+    def _get_bounds(self, date_col: pd.Series) -> pd.Series:
+        months = date_col.dt.month
+        years = date_col.dt.year
 
         month_diffs = 12 * (years - (self.zero_year or 0)) + (months - (self.zero_month or 0))
-        bounds = month_diffs.apply(
+        return month_diffs.apply(
             lambda d: np.array(self.zero_bounds if self.zero_bounds is not None else []) + d * self.step
         )
 
-        return right.index.to_series().apply(lambda i: self.__perc(right[i], bounds[i]))
 
-    def __perc(self, f, bounds):
-        hit = np.where(f >= bounds)[0]
-        if hit.size > 0:
-            return np.max(hit) + 1
-        else:
-            return np.nan
+class DatePercentileType2(DatePercentileBase):
+    name = "date_per_type2"
+
+    def _get_bounds(self, date_col: pd.Series) -> pd.Series:
+        pass

{upgini-1.1.296a3511.dev5 → upgini-1.1.296a3521.dev2}/src/upgini/autofe/feature.py

@@ -125,22 +125,18 @@ class Feature:
         for child in self.children:
             child.delete_data()
 
-    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
 
         if self.alias:
             components = ["f_autofe", self.alias]
-        elif shorten and not (self.op.is_unary and all(isinstance(c, Column) for c in self.children)):
-            prev_name = [self.children[0].get_op_display_name()] if self.op.is_unary else []
-            components = ["f_autofe"] + prev_name + [self.get_op_display_name()]
+        elif shorten and not self.op.is_unary:
+            components = ["f_autofe", self.op.alias or self.op.name.lower()]
         else:
             components = ["f_" + "_f_".join(self.get_columns(**kwargs))] + [
                 "autofe",
-                self.get_op_display_name(),
+                self.op.alias or self.op.name.lower(),
             ]
         components.extend([str(self.display_index)] if self.display_index is not None else [])
         display_name = "_".join(components)

{upgini-1.1.296a3511.dev5 → upgini-1.1.296a3521.dev2}/src/upgini/autofe/unary.py

@@ -125,10 +125,3 @@ 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.dev5/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.296a3511.dev5"