upgini 1.1.297__tar.gz → 1.1.298__tar.gz

{upgini-1.1.297 → upgini-1.1.298}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.297
+Version: 1.1.298
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -131,7 +131,7 @@ Description-Content-Type: text/markdown
 |Consumer Confidence index| 44 |22|-|Monthly|date, country|No
 |World economic indicators|191 |41|-|Monthly|date, country|No
 |Markets data|-|17|-|Monthly|date, datetime|No
-|World mobile & fixed broadband network coverage and perfomance |167|-|3|Monthly|country, postal/ZIP code|No
+|World mobile & fixed broadband network coverage and performance |167|-|3|Monthly|country, postal/ZIP code|No
 |World demographic data |90|-|2|Annual|country, postal/ZIP code|No
 |World house prices |44|-|3|Annual|country, postal/ZIP code|No
 |Public social media profile data |104|-|-|Monthly|date, email/HEM, phone |Yes
@@ -840,4 +840,4 @@ Some convenient ways to start contributing are:
 - [More perks for registered users](https://profile.upgini.com)
 
 <sup>😔 Found mistype or a bug in code snippet? Our bad! <a href="https://github.com/upgini/upgini/issues/new?assignees=&title=readme%2Fbug">
-Please report it here</a></sup>
+Please report it here</a></sup>

{upgini-1.1.297 → upgini-1.1.298}/README.md

@@ -90,7 +90,7 @@
 |Consumer Confidence index| 44 |22|-|Monthly|date, country|No
 |World economic indicators|191 |41|-|Monthly|date, country|No
 |Markets data|-|17|-|Monthly|date, datetime|No
-|World mobile & fixed broadband network coverage and perfomance |167|-|3|Monthly|country, postal/ZIP code|No
+|World mobile & fixed broadband network coverage and performance |167|-|3|Monthly|country, postal/ZIP code|No
 |World demographic data |90|-|2|Annual|country, postal/ZIP code|No
 |World house prices |44|-|3|Annual|country, postal/ZIP code|No
 |Public social media profile data |104|-|-|Monthly|date, email/HEM, phone |Yes
@@ -799,4 +799,4 @@ Some convenient ways to start contributing are:
 - [More perks for registered users](https://profile.upgini.com)
 
 <sup>😔 Found mistype or a bug in code snippet? Our bad! <a href="https://github.com/upgini/upgini/issues/new?assignees=&title=readme%2Fbug">
-Please report it here</a></sup>
+Please report it here</a></sup>

upgini-1.1.298/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.298"

{upgini-1.1.297 → upgini-1.1.298}/src/upgini/autofe/all_operands.py

@@ -1,7 +1,14 @@
 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
+from upgini.autofe.date import (
+    DateDiff,
+    DateDiffType2,
+    DateListDiff,
+    DateListDiffBounded,
+    DatePercentile,
+    DatePercentileMethod2,
+)
 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
@@ -50,6 +57,7 @@ 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-1.1.297 → upgini-1.1.298}/src/upgini/autofe/date.py

@@ -1,3 +1,4 @@
+import abc
 from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
@@ -38,6 +39,7 @@ class DateDiffMixin(BaseModel):
 
 class DateDiff(PandasOperand, DateDiffMixin):
     name = "date_diff"
+    alias = "date_diff_type1"
     is_binary = True
     has_symmetry_importance = True
 
@@ -159,12 +161,45 @@ class DateListDiffBounded(DateListDiff):
         return super()._agg(x)
 
 
-class DatePercentile(PandasOperand):
-    name = "date_per"
+class DatePercentileBase(PandasOperand, abc.ABC):
     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]]
@@ -174,7 +209,6 @@ class DatePercentile(PandasOperand):
         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,
@@ -190,22 +224,18 @@ 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 DatePercentileMethod2(DatePercentileBase):
+    name = "date_per_method2"
+
+    def _get_bounds(self, date_col: pd.Series) -> pd.Series:
+        pass

{upgini-1.1.297 → upgini-1.1.298}/src/upgini/autofe/feature.py

@@ -41,7 +41,7 @@ class Column:
     def get_column_nodes(self) -> List["Column"]:
         return [self]
 
-    def get_columns(self) -> List[str]:
+    def get_columns(self, **kwargs) -> List[str]:
         return [self.name]
 
     def infer_type(self, data: pd.DataFrame) -> DtypeObj:
@@ -57,6 +57,12 @@ 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__(
@@ -125,6 +131,9 @@ 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
@@ -132,11 +141,11 @@ class Feature:
         if self.alias:
             components = ["f_autofe", self.alias]
         elif shorten and not self.op.is_unary:
-            components = ["f_autofe", self.op.alias or self.op.name.lower()]
+            components = ["f_autofe", self.get_op_display_name()]
         else:
             components = ["f_" + "_f_".join(self.get_columns(**kwargs))] + [
                 "autofe",
-                self.op.alias or self.op.name.lower(),
+                self.get_op_display_name(),
             ]
         components.extend([str(self.display_index)] if self.display_index is not None else [])
         display_name = "_".join(components)
@@ -306,8 +315,21 @@ 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()
-            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)
+            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)
         else:
             raise NotImplementedError(f"Unrecognized operator {self.op.name}.")
 

upgini-1.1.297/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.297"