upgini 1.1.296a3521.dev10__py3-none-any.whl → 1.1.297__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.296a3521.dev10"
+__version__ = "1.1.297"

upgini/autofe/all_operands.py

@@ -1,14 +1,7 @@
 from typing import Dict
 
 from upgini.autofe.binary import Add, Divide, Max, Min, Multiply, Sim, Subtract
-from upgini.autofe.date import (
-    DateDiff,
-    DateDiffType2,
-    DateListDiff,
-    DateListDiffBounded,
-    DatePercentile,
-    DatePercentileMethod2,
-)
+from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded, DatePercentile
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
 from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Norm, Sigmoid, Sqrt, Square
@@ -57,7 +50,6 @@ 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(),
-        DatePercentileMethod2(),
         Norm(),
     ]
 }

upgini/autofe/date.py

@@ -1,4 +1,3 @@
-import abc
 from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
@@ -39,7 +38,6 @@ class DateDiffMixin(BaseModel):
 
 class DateDiff(PandasOperand, DateDiffMixin):
     name = "date_diff"
-    alias = "date_diff_type1"
     is_binary = True
     has_symmetry_importance = True
 
@@ -161,45 +159,12 @@ class DateListDiffBounded(DateListDiff):
         return super()._agg(x)
 
 
-class DatePercentileBase(PandasOperand, abc.ABC):
+class DatePercentile(PandasOperand):
+    name = "date_per"
     is_binary = True
     output_type = "float"
 
     date_unit: Optional[str] = None
-
-    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
-
-    def get_params(self) -> Dict[str, Optional[str]]:
-        res = super().get_params()
-        res.update(
-            {
-                "date_unit": self.date_unit,
-            }
-        )
-        return res
-
-
-class DatePercentile(DatePercentileBase):
-    name = "date_per"
-    alias = "date_per_method1"
-
     zero_month: Optional[int]
     zero_year: Optional[int]
     zero_bounds: Optional[List[float]]
@@ -209,6 +174,7 @@ class DatePercentile(DatePercentileBase):
         res = super().get_params()
         res.update(
             {
+                "date_unit": self.date_unit,
                 "zero_month": self.zero_month,
                 "zero_year": self.zero_year,
                 "zero_bounds": self.zero_bounds,
@@ -224,18 +190,22 @@ class DatePercentile(DatePercentileBase):
         elif isinstance(value, str):
             return value[1:-1].split(", ")
 
-    def _get_bounds(self, date_col: pd.Series) -> pd.Series:
-        months = date_col.dt.month
-        years = date_col.dt.year
+    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
 
         month_diffs = 12 * (years - (self.zero_year or 0)) + (months - (self.zero_month or 0))
-        return month_diffs.apply(
+        bounds = 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]))
 
-class DatePercentileMethod2(DatePercentileBase):
-    name = "date_per_method2"
-
-    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

upgini/autofe/feature.py

@@ -16,9 +16,6 @@ class Column:
         self.data = data
         self.calculate_all = calculate_all
 
-    def get_name_component(self, **kwargs) -> str:
-        return self.name
-
     def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
         return self.name
 
@@ -44,7 +41,7 @@ class Column:
     def get_column_nodes(self) -> List["Column"]:
         return [self]
 
-    def get_columns(self, **kwargs) -> List[str]:
+    def get_columns(self) -> List[str]:
         return [self.name]
 
     def infer_type(self, data: pd.DataFrame) -> DtypeObj:
@@ -60,12 +57,6 @@ class Column:
     def to_pretty_formula(self) -> str:
         return self.to_formula()
 
-    def __eq__(self, value: object) -> bool:
-        if not isinstance(value, Column):
-            return False
-        else:
-            return self.name == value.name and self.calculate_all == value.calculate_all
-
 
 class Feature:
     def __init__(
@@ -134,9 +125,6 @@ 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
@@ -144,11 +132,11 @@ class Feature:
         if self.alias:
             components = ["f_autofe", self.alias]
         elif shorten and not self.op.is_unary:
-            components = ["f_autofe", self.get_op_display_name()]
+            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)
@@ -318,21 +306,8 @@ class FeatureGroup:
         main_column = None if self.main_column_node is None else self.main_column_node.get_columns()[0]
         if isinstance(self.op, PandasOperand):
             columns = self.get_columns()
-            lower_order_children = [
-                ch for f in self.children for ch in f.children if ch.get_display_name() != main_column
-            ]
-            lower_order_names = [ch.get_display_name() for ch in lower_order_children]
-            if any(isinstance(f, Feature) for f in lower_order_children):
-                child_data = pd.concat(
-                    [data[main_column]] + [ch.calculate(data) for ch in lower_order_children],
-                    axis=1,
-                )
-                child_data.columns = [main_column] + lower_order_names
-            else:
-                child_data = data[columns]
-
-            new_data = self.op.calculate_group(child_data, main_column=main_column)
-            new_data.rename(columns=dict(zip(lower_order_names, self.get_display_names())), inplace=True)
+            new_data = self.op.calculate_group(data[columns], main_column=main_column)
+            new_data.rename(columns=dict(zip(columns, self.get_display_names())), inplace=True)
         else:
             raise NotImplementedError(f"Unrecognized operator {self.op.name}.")
 

{upgini-1.1.296a3521.dev10.dist-info → upgini-1.1.297.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.296a3521.dev10
+Version: 1.1.297
 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-1.1.296a3521.dev10.dist-info → upgini-1.1.297.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=JKvS85WNogY-2YIe8YIQ4nIWCAaaPwBgVr2LGrQzI7g,35
+upgini/__about__.py,sha256=wXLUjYbwCXLCqMCPB8OqSFq3oPafpNboNnGSVzAPaUk,24
 upgini/__init__.py,sha256=ObEtjFkIssl83qeKNMLpIQygfwK8TzztwiI43YTsAP0,353
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=7TLVVhGtjgx_9yaiaIUK3kZSe_R9wg5dY0d4F5qCGM4,45636
@@ -14,10 +14,10 @@ upgini/version_validator.py,sha256=ddSKUK_-eGJB3NgrqOMoWJU-OxQ253WsNLp8aqJkaIM,1
 upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9JvfkvgE,50
 upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo-R-nGdw,2648
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/autofe/all_operands.py,sha256=XbvgX2IU4aee9rJZ--d5MdmrfKhON_emle5-RU1qlEY,2506
+upgini/autofe/all_operands.py,sha256=cpwUfhZWF9QBfrUyJ0xZ72iGYyt1eXIZQ46FB-7ZDI4,2421
 upgini/autofe/binary.py,sha256=8FXPJxN7fnC5wphO0Dp1tQCa0lFMSDGQGvBMkSIVAcE,4155
-upgini/autofe/date.py,sha256=8zYVhjl7jVS4xt-IjCgk9px2LHnACX2YlMlmDELlRTc,7943
-upgini/autofe/feature.py,sha256=nV1oJCT65nsAYFfXYCXYNYXZPaZVpqKJ09iCMTldooc,13500
+upgini/autofe/date.py,sha256=qzk0NT332Q0vR1eRwTuNiMSrGE3ulh6Ic3QLBZqSdvw,7284
+upgini/autofe/feature.py,sha256=_V9B74B3ue7eAYXSOt9JKhVC9klkAKks22MwnBRye_w,12487
 upgini/autofe/groupby.py,sha256=4WjDzQxqpZxB79Ih4ihMMI5GDxaFqiH6ZelfV82ClT4,3091
 upgini/autofe/operand.py,sha256=MKEsl3zxpWzRDpTkE0sNJxTu62U20sWOvEKhPjUWS6s,2915
 upgini/autofe/unary.py,sha256=ZWjLd-CUkNt_PpM8YuWLLipW1v_RdBlsl4JxXIVo9aM,3652
@@ -57,7 +57,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.296a3521.dev10.dist-info/METADATA,sha256=RZTVD4L0dwwznJDxfpxjmCTZGzSQjE8lX1fw5CjP9ZA,48162
-upgini-1.1.296a3521.dev10.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.1.296a3521.dev10.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.296a3521.dev10.dist-info/RECORD,,
+upgini-1.1.297.dist-info/METADATA,sha256=RwOihmiasIoIOFrOuY-WcLPOc4Fgt5QlztJGwCg5QQ8,48151
+upgini-1.1.297.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.1.297.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.297.dist-info/RECORD,,

{upgini-1.1.296a3521.dev10.dist-info → upgini-1.1.297.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.24.2
+Generator: hatchling 1.25.0
 Root-Is-Purelib: true
 Tag: py3-none-any