upgini 1.1.280a3418.post4__tar.gz → 1.1.280a3418.post6__tar.gz

{upgini-1.1.280a3418.post4 → upgini-1.1.280a3418.post6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.280a3418.post4
+Version: 1.1.280a3418.post6
 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-1.1.280a3418.post6/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.280a3418-6"

{upgini-1.1.280a3418.post4 → upgini-1.1.280a3418.post6}/src/upgini/autofe/all_operands.py

@@ -1,10 +1,10 @@
 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
+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, Bin, Floor, Freq, Log, Residual, Sigmoid, Sqrt, Square
+from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
 
 ALL_OPERANDS: Dict[str, Operand] = {
@@ -49,7 +49,7 @@ ALL_OPERANDS: Dict[str, Operand] = {
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=30, upper_bound=45),
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=45, upper_bound=60),
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
-        Bin(),
+        DatePercentile(),
     ]
 }
 

{upgini-1.1.280a3418.post4 → upgini-1.1.280a3418.post6}/src/upgini/autofe/date.py

@@ -1,9 +1,10 @@
-from typing import Any, Optional, Union
+from datetime import date
+from typing import Any, List, Optional, Union
 
 import numpy as np
 import pandas as pd
 from pandas.core.arrays.timedeltas import TimedeltaArray
-from pydantic import BaseModel
+from pydantic import BaseModel, validator
 
 from upgini.autofe.operand import PandasOperand
 
@@ -116,3 +117,42 @@ class DateListDiffBounded(DateListDiff):
     def _agg(self, x):
         x = x[(x >= (self.lower_bound or -np.inf)) & (x < (self.upper_bound or np.inf))]
         return super()._agg(x)
+
+
+class DatePercentile(PandasOperand):
+    name = "date_per"
+    is_binary = True
+    output_type = "float"
+
+    date_unit: Optional[str] = None
+    zero_month: Optional[int]
+    zero_year: Optional[int]
+    zero_bounds: Optional[List[float]]
+    step: int = 30
+
+    @validator("zero_bounds", pre=True)
+    def validate_bounds(cls, value):
+        if value is None or isinstance(value, list):
+            return value
+        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
+
+        month_diffs = 12 * (years - (self.zero_year or 0)) + (months - (self.zero_month or 0))
+        bounds = month_diffs.apply(
+            lambda d: np.array(self.zero_bounds if self.zero_bounds is not None else []) + d * 30
+        )
+
+        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) * 10
+        else:
+            return None

{upgini-1.1.280a3418.post4 → upgini-1.1.280a3418.post6}/src/upgini/autofe/unary.py

@@ -1,4 +1,3 @@
-from typing import Optional
 import numpy as np
 import pandas as pd
 
@@ -112,25 +111,3 @@ class Freq(PandasOperand):
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         value_counts = data.value_counts(normalize=True)
         return self._loc(data, value_counts)
-
-
-class Bin(PandasOperand):
-    name = "bin"
-    is_unary = True
-    output_type = "int"
-    input_type = "discrete"
-
-    zero_bound_low: Optional[int]
-    zero_bound_high: Optional[int]
-    step: Optional[int]
-
-    def calculate_unary(self, data: pd.Series) -> pd.Series:
-        high = self.zero_bound_high if self.zero_bound_high is not None else np.inf
-        low = self.zero_bound_low if self.zero_bound_low is not None else -np.inf
-        step = self.step or 1
-
-        res = pd.Series(np.zeros(data.shape), index=data.index, dtype="int")
-        res.update((data[data < low] - low) // step)
-        res.update((data[data >= high] - high) // step + 1)
-
-        return res

upgini-1.1.280a3418.post4/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.280a3418-4"