upgini 1.1.280a3418.post5__tar.gz → 1.1.280a3418.post7__tar.gz

{upgini-1.1.280a3418.post5 → upgini-1.1.280a3418.post7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.280a3418.post5
+Version: 1.1.280a3418.post7
 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.post7/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.280a3418-7"

{upgini-1.1.280a3418.post5 → upgini-1.1.280a3418.post7}/src/upgini/autofe/date.py

@@ -1,9 +1,10 @@
-from typing import Any, List, Optional, Union
+from datetime import date
+from typing import Any, Dict, 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
 
@@ -123,14 +124,35 @@ class DatePercentile(PandasOperand):
     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
 
+    def get_params(self) -> Dict[str, str]:
+        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,
+                "step": self.step,
+            }
+        )
+        return res
+
+    @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)
+        left = pd.to_datetime(left, unit=self.date_unit)
         months = left.dt.month
         years = left.dt.year
 
@@ -146,4 +168,4 @@ class DatePercentile(PandasOperand):
         if hit.size > 0:
             return np.max(hit) * 10
         else:
-            return None
+            return np.nan

{upgini-1.1.280a3418.post5 → upgini-1.1.280a3418.post7}/src/upgini/autofe/operand.py

@@ -26,7 +26,9 @@ class Operand(BaseModel):
         return self
 
     def get_params(self) -> Dict[str, str]:
-        return self.params
+        res = {"alias": self.alias}
+        res.update(self.params)
+        return res
 
 
 MAIN_COLUMN = "main_column"

upgini-1.1.280a3418.post5/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.280a3418-5"