upgini 1.1.282__tar.gz → 1.1.282a3418.post1__tar.gz

{upgini-1.1.282 → upgini-1.1.282a3418.post1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.282
+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/
@@ -839,4 +839,4 @@ 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-1.1.282 → upgini-1.1.282a3418.post1}/README.md

@@ -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-1.1.282a3418.post1/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.282a3418-1"

{upgini-1.1.282 → upgini-1.1.282a3418.post1}/src/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-1.1.282 → upgini-1.1.282a3418.post1}/src/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-1.1.282 → upgini-1.1.282a3418.post1}/src/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-1.1.282 → upgini-1.1.282a3418.post1}/src/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-1.1.282 → upgini-1.1.282a3418.post1}/src/upgini/metrics.py

@@ -298,7 +298,6 @@ class EstimatorWrapper:
         scorer = check_scoring(self.estimator, scoring=self.scorer)
 
         if baseline_score_column is not None and self.metric_name == "GINI":
-            self.logger.info("Calculate baseline GINI on passed baseline_score_column and target")
             metric = roc_auc_score(y, x[baseline_score_column])
         else:
             cv_results = cross_validate(

{upgini-1.1.282 → upgini-1.1.282a3418.post1}/src/upgini/utils/sklearn_ext.py

@@ -17,7 +17,7 @@ from sklearn.base import clone, is_classifier
 from sklearn.exceptions import FitFailedWarning, NotFittedError
 from sklearn.metrics import check_scoring
 from sklearn.metrics._scorer import _MultimetricScorer
-from sklearn.model_selection import StratifiedKFold, check_cv
+from sklearn.model_selection import check_cv
 from sklearn.utils.fixes import np_version, parse_version
 from sklearn.utils.validation import indexable
 
@@ -312,34 +312,25 @@ def cross_validate(
                 ret[key] = train_scores_dict[name]
 
         return ret
-    except ValueError as e:
+    except Exception:
         # logging.exception("Failed to execute overriden cross_validate. Fallback to original")
-        if hasattr(e, "args") and len(e.args) > 0 and "Only one class present in y_true" in e.args[0]:
-            # Try change CV to StratifiedKFold and retry
-            if hasattr(cv, "shuffle"):
-                shuffle = cv.shuffle
-            else:
-                shuffle = False
-            if hasattr(cv, "random_state"):
-                random_state = cv.random_state
-            else:
-                random_state = None
-            return cross_validate(
-                estimator,
-                x,
-                y,
-                groups=groups,
-                scoring=scoring,
-                cv=StratifiedKFold(n_splits=cv.get_n_splits(), shuffle=shuffle, random_state=random_state),
-                n_jobs=n_jobs,
-                verbose=verbose,
-                fit_params=fit_params,
-                pre_dispatch=pre_dispatch,
-                return_train_score=return_train_score,
-                return_estimator=return_estimator,
-                error_score=error_score,
-            )
-        raise e
+        raise
+        # fit_params["use_best_model"] = False
+        # return original_cross_validate(
+        #     estimator,
+        #     X,
+        #     y,
+        #     groups=groups,
+        #     scoring=scoring,
+        #     cv=cv,
+        #     n_jobs=n_jobs,
+        #     verbose=verbose,
+        #     fit_params=fit_params,
+        #     pre_dispatch=pre_dispatch,
+        #     return_train_score=return_train_score,
+        #     return_estimator=return_estimator,
+        #     error_score=error_score,
+        # )
 
 
 def _fit_and_score(

upgini-1.1.282/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.282"