upgini 1.1.281__py3-none-any.whl → 1.1.282a3418.post1__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.281"
+__version__ = "1.1.282a3418-1"

upgini/autofe/all_operands.py

@@ -1,7 +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
+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, Sigmoid, Sqrt, Square
@@ -49,6 +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),
+        DatePercentile(),
     ]
 }
 

upgini/autofe/date.py

@@ -1,9 +1,10 @@
-from typing import Any, 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
 
@@ -27,6 +28,17 @@ class DateDiff(PandasOperand, DateDiffMixin):
     is_binary = True
     has_symmetry_importance = True
 
+    def get_params(self) -> Dict[str, Optional[str]]:
+        res = super().get_params()
+        res.update(
+            {
+                "diff_unit": self.diff_unit,
+                "left_unit": self.left_unit,
+                "right_unit": self.right_unit,
+            }
+        )
+        return res
+
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         left = self._convert_to_date(left, self.left_unit)
         right = self._convert_to_date(right, self.right_unit)
@@ -42,6 +54,17 @@ class DateDiffType2(PandasOperand, DateDiffMixin):
     is_binary = True
     has_symmetry_importance = True
 
+    def get_params(self) -> Dict[str, Optional[str]]:
+        res = super().get_params()
+        res.update(
+            {
+                "diff_unit": self.diff_unit,
+                "left_unit": self.left_unit,
+                "right_unit": self.right_unit,
+            }
+        )
+        return res
+
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         left = self._convert_to_date(left, self.left_unit)
         right = self._convert_to_date(right, self.right_unit)
@@ -64,6 +87,15 @@ class DateListDiff(PandasOperand, DateDiffMixin):
     has_symmetry_importance = True
     aggregation: str
 
+    def get_params(self) -> Dict[str, Optional[str]]:
+        res = super().get_params()
+        res.update(
+            {
+                "aggregation": self.aggregation,
+            }
+        )
+        return res
+
     def __init__(self, **data: Any) -> None:
         if "name" not in data:
             data["name"] = f"date_diff_{data.get('aggregation')}"
@@ -116,3 +148,55 @@ 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
+
+    def get_params(self) -> Dict[str, Optional[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, 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 np.nan

upgini/autofe/feature.py

@@ -16,6 +16,12 @@ class Column:
         self.data = data
         self.calculate_all = calculate_all
 
+    def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
+        return self.name
+
+    def set_op_params(self, params: Dict[str, str]) -> "Column":
+        return self
+
     def rename_columns(self, mapping: Dict[str, str]) -> "Column":
         self.name = self._unhash(mapping.get(self.name) or self.name)
         return self
@@ -69,14 +75,20 @@ class Feature:
         self.cached_display_name = cached_display_name
         self.alias = alias
 
-    def set_op_params(self, params: Dict[str, str]) -> "Feature":
+    def set_op_params(self, params: Optional[Dict[str, str]]) -> "Feature":
+        obj_dict = self.op.dict().copy()
+        obj_dict.update(params or {})
+        self.op = self.op.__class__.parse_obj(obj_dict)
         self.op.set_params(params)
+
+        for child in self.children:
+            child.set_op_params(params)
         return self
 
     def get_hash(self) -> str:
-        return hashlib.sha256("_".join([self.op.name] + [ch.name for ch in self.children]).encode("utf-8")).hexdigest()[
-            :8
-        ]
+        return hashlib.sha256(
+            "_".join([self.op.name] + [ch.get_display_name() for ch in self.children]).encode("utf-8")
+        ).hexdigest()[:8]
 
     def set_alias(self, alias: str) -> "Feature":
         self.alias = alias

upgini/autofe/operand.py

@@ -25,8 +25,10 @@ class Operand(BaseModel):
         self.params = params
         return self
 
-    def get_params(self) -> Dict[str, str]:
-        return self.params
+    def get_params(self) -> Dict[str, Optional[str]]:
+        res = {"alias": self.alias}
+        res.update(self.params or {})
+        return res
 
 
 MAIN_COLUMN = "main_column"

{upgini-1.1.281.dist-info → upgini-1.1.282a3418.post1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.281
+Version: 1.1.282a3418.post1
 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-1.1.281.dist-info → upgini-1.1.282a3418.post1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=QXQ0qAoJaXwuS49QdPQRJ572R1Vxd94TndilBoFpK_s,24
+upgini/__about__.py,sha256=GG1GC75bod-mGb53WjhL__a8G9_p00TZYiKG5snDjHQ,31
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=7TLVVhGtjgx_9yaiaIUK3kZSe_R9wg5dY0d4F5qCGM4,45636
@@ -13,12 +13,12 @@ upgini/version_validator.py,sha256=RGg87VweujTNlibgsOuqPLIEiBgIOkuXNVTGuNCD234,1
 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=SyKVU-xGMHgoRZvHrCmba2u2Ygc73c1mXFolNSWe8Uo,2357
+upgini/autofe/all_operands.py,sha256=7UyvmmqGSqQu4kDgoFwQRKY__b9xKDk3Fpp2-H8A7AA,2399
 upgini/autofe/binary.py,sha256=441BRuqMsxlxuw4c8rMZB6h5EpRdVMk-bVa03U7T5Hg,3973
-upgini/autofe/date.py,sha256=Vy1I92fLLYLhuYKJmtuPBMI8cPxE4Uwk40hqE2F2e1A,4224
-upgini/autofe/feature.py,sha256=ChSuuIbRPGIWnPjKAgZbeAEi7Y_PjSVRyxxx41MyFp0,11845
+upgini/autofe/date.py,sha256=XeTJIkPzauYXgI3n5E8h4353PhZRZ7LOpQGHA4DMPx4,6758
+upgini/autofe/feature.py,sha256=x7sumlIZqSE020XAkoykaesUjmmdYhaa0iFPKxBuDXo,12285
 upgini/autofe/groupby.py,sha256=4WjDzQxqpZxB79Ih4ihMMI5GDxaFqiH6ZelfV82ClT4,3091
-upgini/autofe/operand.py,sha256=xgEIZuFCfckc6LpBqVu1OVK3JEabm1O-LHUsp83EHKA,2806
+upgini/autofe/operand.py,sha256=JjEVT1U3kY9NDjUPMdoki7Oa8hMDG0-_h_NklVjIFyc,2882
 upgini/autofe/unary.py,sha256=v-l3aiE5hj6kurvh6adCQL8W3X9u9a7RVbS_WPR2qlw,3146
 upgini/autofe/vector.py,sha256=dLxfAstJs-gw_OQ1xxoxcM6pVzORlV0HVzdzt7cLXVQ,606
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -56,7 +56,7 @@ upgini/utils/sklearn_ext.py,sha256=c23MGSUVfxLnaDWKAxavHgnOtm5dGKkF3YswdWQcFzs,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-1.1.281.dist-info/METADATA,sha256=l6PW4_vWrlqKTTbhXFb9Qsm9FIYMQH5BrU3Vca5WzKo,48118
-upgini-1.1.281.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.1.281.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.281.dist-info/RECORD,,
+upgini-1.1.282a3418.post1.dist-info/METADATA,sha256=XEY5jBcIoE7tG5ivbqU_75frPJwXZeMViN7fKn5wBv0,48129
+upgini-1.1.282a3418.post1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.1.282a3418.post1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.282a3418.post1.dist-info/RECORD,,