upgini 1.1.263a1__tar.gz → 1.1.264a1__tar.gz

{upgini-1.1.263a1/src/upgini.egg-info → upgini-1.1.264a1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.263a1
+Version: 1.1.264a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.263a1 → upgini-1.1.264a1}/setup.py

@@ -40,7 +40,7 @@ def send_log(msg: str):
 
 
 here = Path(__file__).parent.resolve()
-version = "1.1.263a1"
+version = "1.1.264a1"
 try:
     send_log(f"Start setup PyLib version {version}")
     setup(

{upgini-1.1.263a1 → upgini-1.1.264a1}/src/upgini/autofe/all_operands.py

@@ -1,4 +1,5 @@
 from typing import Dict
+from upgini.autofe.date import DateDiff, DateDiffType2
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
 from upgini.autofe.unary import Abs, Log, Residual, Sqrt, Square, Sigmoid, Floor, Freq
@@ -35,6 +36,8 @@ ALL_OPERANDS: Dict[str, Operand] = {
         Operand(name="GroupByThenNUnique", output_type="int", is_vectorizable=True, is_grouping=True),
         Operand(name="GroupByThenFreq", output_type="float", is_grouping=True),
         Sim(),
+        DateDiff(),
+        DateDiffType2(),
     ]
 }
 

upgini-1.1.264a1/src/upgini/autofe/date.py

@@ -0,0 +1,53 @@
+from typing import Optional, Union
+import numpy as np
+import pandas as pd
+
+from upgini.autofe.operand import PandasOperand
+
+
+class DateDiffMixin:
+    diff_unit: str = "D"
+    left_unit: Optional[str] = None
+    right_unit: Optional[str] = None
+
+    def _convert_to_date(
+        self, x: Union[pd.DataFrame, pd.Series], unit: Optional[str]
+    ) -> Union[pd.DataFrame, pd.Series]:
+        if isinstance(x, pd.DataFrame):
+            return x.apply(lambda y: self._convert_to_date(y, unit), axis=1)
+
+        return pd.to_datetime(x, unit=unit)
+
+
+class DateDiff(PandasOperand, DateDiffMixin):
+    name = "date_diff"
+    is_binary = True
+    has_symmetry_importance = True
+
+    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)
+        return self.__replace_negative((left - right) / np.timedelta64(1, self.diff_unit))
+
+    def __replace_negative(self, x: Union[pd.DataFrame, pd.Series]):
+        x[x < 0] = None
+        return x
+
+
+class DateDiffType2(PandasOperand, DateDiffMixin):
+    name = "date_diff_type2"
+    is_binary = True
+    has_symmetry_importance = True
+    is_vectorizable = False
+
+    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)
+        future = right + (left.dt.year - right.dt.year).apply(
+            lambda y: np.datetime64("NaT") if np.isnan(y) else pd.tseries.offsets.DateOffset(years=y)
+        )
+        before = future[future < left]
+        future[future < left] = before + pd.tseries.offsets.DateOffset(years=1)
+        diff = (future - left) / np.timedelta64(1, self.diff_unit)
+
+        return diff

{upgini-1.1.263a1 → upgini-1.1.264a1}/src/upgini/autofe/feature.py

@@ -305,7 +305,7 @@ class FeatureGroup:
         grouped_features = []
 
         def groupby_func(f: Feature) -> Tuple[Operand, Union[Column, Feature]]:
-            return (f.op, f.children[0] if f.op.is_unary or f.op.is_vector else f.children[1])
+            return (f.op, f.children[0 if not f.op.is_vectorizable else f.op.group_index])
 
         for op_child, features in itertools.groupby(candidates, groupby_func):
             op, main_child = op_child

{upgini-1.1.263a1 → upgini-1.1.264a1}/src/upgini/autofe/operand.py

@@ -73,6 +73,8 @@ class PandasOperand(Operand, abc.ABC):
 
 
 class VectorizableMixin(Operand):
+    group_index: int = 1
+
     def validate_calculation(self, input_columns: List[str], **kwargs) -> Tuple[str, List[str]]:
         if not kwargs.get(MAIN_COLUMN):
             raise ValueError(f"Expected argument {MAIN_COLUMN} for grouping operator {self.name} not found")

{upgini-1.1.263a1 → upgini-1.1.264a1}/src/upgini/autofe/unary.py

@@ -1,12 +1,13 @@
-from upgini.autofe.operand import PandasOperand
+from upgini.autofe.operand import PandasOperand, VectorizableMixin
 import numpy as np
 import pandas as pd
 
 
-class Abs(PandasOperand):
+class Abs(PandasOperand, VectorizableMixin):
     name = "abs"
     is_unary = True
     is_vectorizable = True
+    group_index = 0
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         return data.abs()
@@ -15,11 +16,12 @@ class Abs(PandasOperand):
         return data.abs()
 
 
-class Log(PandasOperand):
+class Log(PandasOperand, VectorizableMixin):
     name = "log"
     is_unary = True
     is_vectorizable = True
     output_type = "float"
+    group_index = 0
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         return self._round_value(np.log(np.abs(data.replace(0, np.nan))), 10)
@@ -28,11 +30,12 @@ class Log(PandasOperand):
         return self._round_value(np.log(data.replace(0, np.nan).abs()), 10)
 
 
-class Sqrt(PandasOperand):
+class Sqrt(PandasOperand, VectorizableMixin):
     name = "sqrt"
     is_unary = True
     is_vectorizable = True
     output_type = "float"
+    group_index = 0
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         return self._round_value(np.sqrt(np.abs(data)))
@@ -41,10 +44,11 @@ class Sqrt(PandasOperand):
         return self._round_value(np.sqrt(data.abs()))
 
 
-class Square(PandasOperand):
+class Square(PandasOperand, VectorizableMixin):
     name = "square"
     is_unary = True
     is_vectorizable = True
+    group_index = 0
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         return np.square(data)
@@ -53,11 +57,12 @@ class Square(PandasOperand):
         return np.square(data)
 
 
-class Sigmoid(PandasOperand):
+class Sigmoid(PandasOperand, VectorizableMixin):
     name = "sigmoid"
     is_unary = True
     is_vectorizable = True
     output_type = "float"
+    group_index = 0
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         return self._round_value(1 / (1 + np.exp(-data)))
@@ -66,12 +71,13 @@ class Sigmoid(PandasOperand):
         return self._round_value(1 / (1 + np.exp(-data)))
 
 
-class Floor(PandasOperand):
+class Floor(PandasOperand, VectorizableMixin):
     name = "floor"
     is_unary = True
     is_vectorizable = True
     output_type = "int"
     input_type = "continuous"
+    group_index = 0
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         return np.floor(data)
@@ -80,11 +86,12 @@ class Floor(PandasOperand):
         return np.floor(data)
 
 
-class Residual(PandasOperand):
+class Residual(PandasOperand, VectorizableMixin):
     name = "residual"
     is_unary = True
     is_vectorizable = True
     input_type = "continuous"
+    group_index = 0
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         return data - np.floor(data)

{upgini-1.1.263a1 → upgini-1.1.264a1}/src/upgini/autofe/vector.py

@@ -1,20 +1,22 @@
 from typing import List
 import pandas as pd
-from upgini.autofe.operand import PandasOperand
+from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
 
-class Mean(PandasOperand):
+class Mean(PandasOperand, VectorizableMixin):
     name = "mean"
     output_type = "float"
     is_vector = True
+    group_index = 0
 
     def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
         return pd.DataFrame(data).T.fillna(0).mean(axis=1)
 
 
-class Sum(PandasOperand):
+class Sum(PandasOperand, VectorizableMixin):
     name = "sum"
     is_vector = True
+    group_index = 0
 
     def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
         return pd.DataFrame(data).T.fillna(0).sum(axis=1)

{upgini-1.1.263a1 → upgini-1.1.264a1/src/upgini.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.263a1
+Version: 1.1.264a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.263a1 → upgini-1.1.264a1}/src/upgini.egg-info/SOURCES.txt

@@ -24,6 +24,7 @@ src/upgini/ads_management/ads_manager.py
 src/upgini/autofe/__init__.py
 src/upgini/autofe/all_operands.py
 src/upgini/autofe/binary.py
+src/upgini/autofe/date.py
 src/upgini/autofe/feature.py
 src/upgini/autofe/groupby.py
 src/upgini/autofe/operand.py
@@ -64,6 +65,7 @@ src/upgini/utils/sklearn_ext.py
 src/upgini/utils/target_utils.py
 src/upgini/utils/track_info.py
 src/upgini/utils/warning_counter.py
+tests/test_autofe_operands.py
 tests/test_binary_dataset.py
 tests/test_blocked_time_series.py
 tests/test_categorical_dataset.py

upgini-1.1.264a1/tests/test_autofe_operands.py

@@ -0,0 +1,27 @@
+import pandas as pd
+from upgini.autofe.date import DateDiff, DateDiffType2
+
+from datetime import datetime
+from pandas.testing import assert_series_equal
+
+
+def test_date_diff():
+    df = pd.DataFrame(
+        [[datetime(1993, 12, 10), datetime(2022, 10, 10)], [datetime(2023, 10, 10), datetime(2022, 10, 10)]],
+        columns=["date1", "date2"],
+    )
+
+    operand = DateDiff()
+    expected_result = pd.Series([10531, None])
+    assert_series_equal(operand.calculate_binary(df.date2, df.date1), expected_result)
+
+
+def test_date_diff_future():
+    df = pd.DataFrame(
+        [[datetime(1993, 12, 10), datetime(2022, 10, 10)], [datetime(1993, 4, 10), datetime(2022, 10, 10)]],
+        columns=["date1", "date2"],
+    )
+
+    operand = DateDiffType2()
+    expected_result = pd.Series([61.0, 182.0])
+    assert_series_equal(operand.calculate_binary(df.date2, df.date1), expected_result)