upgini 1.1.316a4__tar.gz → 1.1.317__tar.gz

{upgini-1.1.316a4 → upgini-1.1.317}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.316a4
+Version: 1.1.317
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -29,9 +29,9 @@ Requires-Dist: ipywidgets>=8.1.0
 Requires-Dist: jarowinkler>=2.0.0
 Requires-Dist: levenshtein>=0.25.1
 Requires-Dist: lightgbm>=3.3.2
-Requires-Dist: numpy<=1.26.4,>=1.19.0
+Requires-Dist: numpy>=1.19.0
 Requires-Dist: pandas<3.0.0,>=1.1.0
-Requires-Dist: pydantic<3.0.0,>1.0.0
+Requires-Dist: pydantic<2.0.0,>=1.8.2
 Requires-Dist: pyjwt>=2.8.0
 Requires-Dist: python-bidi==0.4.2
 Requires-Dist: python-dateutil>=2.8.0

{upgini-1.1.316a4 → upgini-1.1.317}/pyproject.toml

@@ -39,9 +39,9 @@ dependencies = [
     "fastparquet>=0.8.1",
     "ipywidgets>=8.1.0",
     "lightgbm>=3.3.2",
-    "numpy>=1.19.0,<=1.26.4",
+    "numpy>=1.19.0",
     "pandas>=1.1.0,<3.0.0",
-    "pydantic>1.0.0,<3.0.0",
+    "pydantic>=1.8.2,<2.0.0",
     "pyjwt>=2.8.0",
     "python-dateutil>=2.8.0",
     "python-json-logger>=2.0.2",
@@ -79,7 +79,7 @@ python = "3.10"
 cov = 'pytest --cov-report=term-missing --cov-config=pyproject.toml --cov=upgini --cov=tests'
 format = "black {args}"
 lint = "ruff check {args}"
-test_all = 'pytest -s -vv tests'
+test_binary = 'pytest -s -vv tests/test_binary_dataset.py'
 
 [[tool.hatch.envs.test.matrix]]
 python = ["3.8"]
@@ -103,7 +103,7 @@ dependencies = [
 #  "pytest-timeout",
   "requests-mock",
   "pytest-datafiles",
-  "pandas~={matrix:pandas}",
+  "pandas~={matrix:pandas}.0",
 ]
 
 [tool.black]
@@ -115,5 +115,4 @@ profile = "black"
 [tool.pytest.ini_options]
 pythonpath = [
   "./src"
-]
-addopts="-n 4"
+]

upgini-1.1.317/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.317"

{upgini-1.1.316a4 → upgini-1.1.317}/src/upgini/autofe/binary.py

@@ -9,32 +9,32 @@ from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
 
 class Min(PandasOperand):
-    name: str = "min"
-    is_binary: bool = True
-    is_symmetrical: bool = True
-    has_symmetry_importance: bool = True
+    name = "min"
+    is_binary = True
+    is_symmetrical = True
+    has_symmetry_importance = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         return np.minimum(left, right)
 
 
 class Max(PandasOperand):
-    name: str = "max"
-    is_binary: bool = True
-    is_symmetrical: bool = True
-    has_symmetry_importance: bool = True
+    name = "max"
+    is_binary = True
+    is_symmetrical = True
+    has_symmetry_importance = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         return np.maximum(left, right)
 
 
 class Add(PandasOperand, VectorizableMixin):
-    name: str = "+"
-    alias: str = "add"
-    is_binary: bool = True
-    is_symmetrical: bool = True
-    has_symmetry_importance: bool = True
-    is_vectorizable: bool = True
+    name = "+"
+    alias = "add"
+    is_binary = True
+    is_symmetrical = True
+    has_symmetry_importance = True
+    is_vectorizable = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         return left + right
@@ -48,12 +48,12 @@ class Add(PandasOperand, VectorizableMixin):
 
 
 class Subtract(PandasOperand, VectorizableMixin):
-    name: str = "-"
-    alias: str = "sub"
-    is_binary: bool = True
-    is_symmetrical: bool = True
-    has_symmetry_importance: bool = True
-    is_vectorizable: bool = True
+    name = "-"
+    alias = "sub"
+    is_binary = True
+    is_symmetrical = True
+    has_symmetry_importance = True
+    is_vectorizable = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         return left - right
@@ -67,12 +67,12 @@ class Subtract(PandasOperand, VectorizableMixin):
 
 
 class Multiply(PandasOperand, VectorizableMixin):
-    name: str = "*"
-    alias: str = "mul"
-    is_binary: bool = True
-    is_symmetrical: bool = True
-    has_symmetry_importance: bool = True
-    is_vectorizable: bool = True
+    name = "*"
+    alias = "mul"
+    is_binary = True
+    is_symmetrical = True
+    has_symmetry_importance = True
+    is_vectorizable = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         return left * right
@@ -86,12 +86,12 @@ class Multiply(PandasOperand, VectorizableMixin):
 
 
 class Divide(PandasOperand, VectorizableMixin):
-    name: str = "/"
-    alias: str = "div"
-    is_binary: bool = True
-    has_symmetry_importance: bool = True
-    is_vectorizable: bool = True
-    output_type: Optional[str] = "float"
+    name = "/"
+    alias = "div"
+    is_binary = True
+    has_symmetry_importance = True
+    is_vectorizable = True
+    output_type = "float"
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         return left / right.replace(0, np.nan)
@@ -105,10 +105,10 @@ class Divide(PandasOperand, VectorizableMixin):
 
 
 class Combine(PandasOperand):
-    name: str = "Combine"
-    is_binary: bool = True
-    has_symmetry_importance: bool = True
-    output_type: Optional[str] = "object"
+    name = "Combine"
+    is_binary = True
+    has_symmetry_importance = True
+    output_type = "object"
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         temp = left.astype(str) + "_" + right.astype(str)
@@ -117,13 +117,13 @@ class Combine(PandasOperand):
 
 
 class CombineThenFreq(PandasOperand):
-    name: str = "CombineThenFreq"
-    is_binary: bool = True
-    is_symmetrical: bool = True
-    has_symmetry_importance: bool = True
-    output_type: Optional[str] = "float"
-    is_distribution_dependent: bool = True
-    input_type: Optional[str] = "discrete"
+    name = "CombineThenFreq"
+    is_binary = True
+    is_symmetrical = True
+    has_symmetry_importance = True
+    output_type = "float"
+    is_distribution_dependent = True
+    input_type = "discrete"
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         temp = left.astype(str) + "_" + right.astype(str)
@@ -133,15 +133,15 @@ class CombineThenFreq(PandasOperand):
 
 
 class Distance(PandasOperand):
-    name: str = "dist"
-    is_binary: bool = True
-    output_type: Optional[str] = "float"
-    is_symmetrical: bool = True
-    has_symmetry_importance: bool = True
+    name = "dist"
+    is_binary = True
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         return pd.Series(
-            1 - self.__dot(left, right) / (self.__dot(left, left) * self.__dot(right, right)), index=left.index
+            1 - self.__dot(left, right) / (self.__norm(left) * self.__norm(right)), index=left.index
         )
 
     # row-wise dot product
@@ -152,14 +152,17 @@ class Distance(PandasOperand):
         res = res.reindex(left.index.union(right.index))
         return res
 
+    def __norm(self, vector: pd.Series) -> pd.Series:
+        return np.sqrt(self.__dot(vector, vector))
+
 
 # Left for backward compatibility
 class Sim(Distance):
-    name: str = "sim"
-    is_binary: bool = True
-    output_type: Optional[str] = "float"
-    is_symmetrical: bool = True
-    has_symmetry_importance: bool = True
+    name = "sim"
+    is_binary = True
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         return 1 - super().calculate_binary(left, right)
@@ -188,12 +191,12 @@ class StringSim(PandasOperand, abc.ABC):
 
 
 class JaroWinklerSim1(StringSim):
-    name: str = "sim_jw1"
-    is_binary: bool = True
-    input_type: Optional[str] = "string"
-    output_type: Optional[str] = "float"
-    is_symmetrical: bool = True
-    has_symmetry_importance: bool = True
+    name = "sim_jw1"
+    is_binary = True
+    input_type = "string"
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
 
     def _prepare_value(self, value: Optional[str]) -> Optional[str]:
         return value
@@ -203,12 +206,12 @@ class JaroWinklerSim1(StringSim):
 
 
 class JaroWinklerSim2(StringSim):
-    name: str = "sim_jw2"
-    is_binary: bool = True
-    input_type: Optional[str] = "string"
-    output_type: Optional[str] = "float"
-    is_symmetrical: bool = True
-    has_symmetry_importance: bool = True
+    name = "sim_jw2"
+    is_binary = True
+    input_type = "string"
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
 
     def _prepare_value(self, value: Optional[str]) -> Optional[str]:
         return value[::-1] if value is not None else None
@@ -218,12 +221,12 @@ class JaroWinklerSim2(StringSim):
 
 
 class LevenshteinSim(StringSim):
-    name: str = "sim_lv"
-    is_binary: bool = True
-    input_type: Optional[str] = "string"
-    output_type: Optional[str] = "float"
-    is_symmetrical: bool = True
-    has_symmetry_importance: bool = True
+    name = "sim_lv"
+    is_binary = True
+    input_type = "string"
+    output_type = "float"
+    is_symmetrical = True
+    has_symmetry_importance = True
 
     def _prepare_value(self, value: Optional[str]) -> Optional[str]:
         return value

{upgini-1.1.316a4 → upgini-1.1.317}/src/upgini/autofe/date.py

@@ -1,4 +1,5 @@
 import abc
+import json
 from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
@@ -38,10 +39,10 @@ class DateDiffMixin(BaseModel):
 
 
 class DateDiff(PandasOperand, DateDiffMixin):
-    name: str = "date_diff"
-    alias: Optional[str] = "date_diff_type1"
-    is_binary: bool = True
-    has_symmetry_importance: bool = True
+    name = "date_diff"
+    alias = "date_diff_type1"
+    is_binary = True
+    has_symmetry_importance = True
 
     replace_negative: bool = False
 
@@ -70,9 +71,9 @@ class DateDiff(PandasOperand, DateDiffMixin):
 
 
 class DateDiffType2(PandasOperand, DateDiffMixin):
-    name: str = "date_diff_type2"
-    is_binary: bool = True
-    has_symmetry_importance: bool = True
+    name = "date_diff_type2"
+    is_binary = True
+    has_symmetry_importance = True
 
     def get_params(self) -> Dict[str, Optional[str]]:
         res = super().get_params()
@@ -104,8 +105,8 @@ _count_aggregations = ["nunique", "count"]
 
 
 class DateListDiff(PandasOperand, DateDiffMixin):
-    is_binary: bool = True
-    has_symmetry_importance: bool = True
+    is_binary = True
+    has_symmetry_importance = True
 
     aggregation: str
     replace_negative: bool = False
@@ -165,8 +166,8 @@ class DateListDiff(PandasOperand, DateDiffMixin):
 
 
 class DateListDiffBounded(DateListDiff):
-    lower_bound: Optional[int] = None
-    upper_bound: Optional[int] = None
+    lower_bound: Optional[int]
+    upper_bound: Optional[int]
 
     def __init__(self, **data: Any) -> None:
         if "name" not in data:
@@ -191,8 +192,8 @@ class DateListDiffBounded(DateListDiff):
 
 
 class DatePercentileBase(PandasOperand, abc.ABC):
-    is_binary: bool = True
-    output_type: Optional[str] = "float"
+    is_binary = True
+    output_type = "float"
 
     date_unit: Optional[str] = None
 
@@ -226,12 +227,12 @@ class DatePercentileBase(PandasOperand, abc.ABC):
 
 
 class DatePercentile(DatePercentileBase):
-    name: str = "date_per"
-    alias: Optional[str] = "date_per_method1"
+    name = "date_per"
+    alias = "date_per_method1"
 
-    zero_month: Optional[int] = None
-    zero_year: Optional[int] = None
-    zero_bounds: Optional[List[float]] = 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]]:
@@ -246,12 +247,12 @@ class DatePercentile(DatePercentileBase):
         )
         return res
 
-    @validator("zero_bounds", pre="true")
+    @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(", ")
+            return json.loads(value)
 
     def _get_bounds(self, date_col: pd.Series) -> pd.Series:
         months = date_col.dt.month
@@ -264,7 +265,7 @@ class DatePercentile(DatePercentileBase):
 
 
 class DatePercentileMethod2(DatePercentileBase):
-    name: str = "date_per_method2"
+    name = "date_per_method2"
 
     def _get_bounds(self, date_col: pd.Series) -> pd.Series:
         pass

{upgini-1.1.316a4 → upgini-1.1.317}/src/upgini/autofe/groupby.py

@@ -7,9 +7,9 @@ from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
 class GroupByThenAgg(PandasOperand, VectorizableMixin):
     agg: Optional[str]
-    is_vectorizable: bool = True
-    is_grouping: bool = True
-    is_distribution_dependent: bool = True
+    is_vectorizable = True
+    is_grouping = True
+    is_distribution_dependent = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         temp = left.groupby(right).agg(self.agg)
@@ -24,17 +24,17 @@ class GroupByThenAgg(PandasOperand, VectorizableMixin):
 
 
 class GroupByThenMedian(GroupByThenAgg):
-    name: str = "GroupByThenMedian"
-    pandas_agg: str = "median"
-    is_distribution_dependent: bool = True
+    name = "GroupByThenMedian"
+    pandas_agg = "median"
+    is_distribution_dependent = True
 
 
 class GroupByThenRank(PandasOperand, VectorizableMixin):
-    name: str = "GroupByThenRank"
-    is_vectorizable: bool = True
-    is_grouping: bool = True
-    output_type: Optional[str] = "float"
-    is_distribution_dependent: bool = True
+    name = "GroupByThenRank"
+    is_vectorizable = True
+    is_grouping = True
+    output_type = "float"
+    is_distribution_dependent = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         temp = pd.DataFrame(left[~right.isna()].groupby(right).rank(ascending=True, pct=True)).reset_index()
@@ -49,12 +49,12 @@ class GroupByThenRank(PandasOperand, VectorizableMixin):
 
 
 class GroupByThenNUnique(PandasOperand, VectorizableMixin):
-    name: str = "GroupByThenNUnique"
-    is_vectorizable: bool = True
-    is_grouping: bool = True
-    output_type: Optional[str] = "int"
-    is_distribution_dependent: bool = True
-    input_type: Optional[str] = "discrete"
+    name = "GroupByThenNUnique"
+    is_vectorizable = True
+    is_grouping = True
+    output_type = "int"
+    is_distribution_dependent = True
+    input_type = "discrete"
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         nunique = left.groupby(right).nunique()
@@ -69,11 +69,11 @@ class GroupByThenNUnique(PandasOperand, VectorizableMixin):
 
 
 class GroupByThenFreq(PandasOperand):
-    name: str = "GroupByThenFreq"
-    is_grouping: bool = True
-    output_type: Optional[str] = "float"
-    is_distribution_dependent: bool = True
-    input_type: Optional[str] = "discrete"
+    name = "GroupByThenFreq"
+    is_grouping = True
+    output_type = "float"
+    is_distribution_dependent = True
+    input_type = "discrete"
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         def _f(x):

{upgini-1.1.316a4 → upgini-1.1.317}/src/upgini/autofe/operand.py

@@ -8,19 +8,19 @@ from pydantic import BaseModel
 
 class Operand(BaseModel):
     name: str
-    alias: Optional[str] = None
+    alias: Optional[str]
     is_unary: bool = False
     is_symmetrical: bool = False
     has_symmetry_importance: bool = False
-    input_type: Optional[str] = None
-    output_type: Optional[str] = None
+    input_type: Optional[str]
+    output_type: Optional[str]
     is_categorical: bool = False
     is_vectorizable: bool = False
     is_grouping: bool = False
     is_binary: bool = False
     is_vector: bool = False
     is_distribution_dependent: bool = False
-    params: Optional[Dict[str, str]] = None
+    params: Optional[Dict[str, str]]
 
     def set_params(self, params: Dict[str, str]):
         self.params = params

{upgini-1.1.316a4 → upgini-1.1.317}/src/upgini/autofe/unary.py

@@ -1,4 +1,3 @@
-from typing import Optional
 import numpy as np
 import pandas as pd
 from sklearn.preprocessing import Normalizer
@@ -7,10 +6,10 @@ from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
 
 class Abs(PandasOperand, VectorizableMixin):
-    name: str = "abs"
-    is_unary: bool = True
-    is_vectorizable: bool = True
-    group_index: int = 0
+    name = "abs"
+    is_unary = True
+    is_vectorizable = True
+    group_index = 0
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         return data.abs()
@@ -20,11 +19,11 @@ class Abs(PandasOperand, VectorizableMixin):
 
 
 class Log(PandasOperand, VectorizableMixin):
-    name: str = "log"
-    is_unary: bool = True
-    is_vectorizable: bool = True
-    output_type: Optional[str] = "float"
-    group_index: int = 0
+    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)
@@ -34,11 +33,11 @@ class Log(PandasOperand, VectorizableMixin):
 
 
 class Sqrt(PandasOperand, VectorizableMixin):
-    name: str = "sqrt"
-    is_unary: bool = True
-    is_vectorizable: bool = True
-    output_type: Optional[str] = "float"
-    group_index: int = 0
+    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)))
@@ -48,10 +47,10 @@ class Sqrt(PandasOperand, VectorizableMixin):
 
 
 class Square(PandasOperand, VectorizableMixin):
-    name: str = "square"
-    is_unary: bool = True
-    is_vectorizable: bool = True
-    group_index: int = 0
+    name = "square"
+    is_unary = True
+    is_vectorizable = True
+    group_index = 0
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         return np.square(data)
@@ -61,11 +60,11 @@ class Square(PandasOperand, VectorizableMixin):
 
 
 class Sigmoid(PandasOperand, VectorizableMixin):
-    name: str = "sigmoid"
-    is_unary: bool = True
-    is_vectorizable: bool = True
-    output_type: Optional[str] = "float"
-    group_index: int = 0
+    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)))
@@ -75,12 +74,12 @@ class Sigmoid(PandasOperand, VectorizableMixin):
 
 
 class Floor(PandasOperand, VectorizableMixin):
-    name: str = "floor"
-    is_unary: bool = True
-    is_vectorizable: bool = True
-    output_type: Optional[str] = "int"
-    input_type: Optional[str] = "continuous"
-    group_index: int = 0
+    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)
@@ -90,11 +89,11 @@ class Floor(PandasOperand, VectorizableMixin):
 
 
 class Residual(PandasOperand, VectorizableMixin):
-    name: str = "residual"
-    is_unary: bool = True
-    is_vectorizable: bool = True
-    input_type: Optional[str] = "continuous"
-    group_index: int = 0
+    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)
@@ -104,11 +103,11 @@ class Residual(PandasOperand, VectorizableMixin):
 
 
 class Freq(PandasOperand):
-    name: str = "freq"
-    is_unary: bool = True
-    output_type: Optional[str] = "float"
-    is_distribution_dependent: bool = True
-    input_type: Optional[str] = "discrete"
+    name = "freq"
+    is_unary = True
+    output_type = "float"
+    is_distribution_dependent = True
+    input_type = "discrete"
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         value_counts = data.value_counts(normalize=True)
@@ -116,9 +115,9 @@ class Freq(PandasOperand):
 
 
 class Norm(PandasOperand):
-    name: str = "norm"
-    is_unary: bool = True
-    output_type: Optional[str] = "float"
+    name = "norm"
+    is_unary = True
+    output_type = "float"
 
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         data_dropna = data.dropna()
@@ -132,7 +131,7 @@ class Norm(PandasOperand):
 
 
 class Embeddings(PandasOperand):
-    name: str = "emb"
-    is_unary: bool = True
-    input_type: Optional[str] = "string"
-    output_type: Optional[str] = "vector"
+    name = "emb"
+    is_unary = True
+    input_type = "string"
+    output_type = "vector"