Skip to content

Bump pydantic #295

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 12 commits into from
Sep 4, 2024
Merged

Bump pydantic #295

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
3eaf66d
Bump pydantic
c3p0upgini Aug 23, 2024
46dd5af
Bump version
c3p0upgini Aug 23, 2024
4967d07
parallel tests
c3p0upgini Aug 26, 2024
6c111bb
Add back compatibility
c3p0upgini Aug 27, 2024
743f699
Correct migration
c3p0upgini Aug 29, 2024
7b4f54b
Hotfix autofe distance
c3p0upgini Aug 29, 2024
0f36938
Hotfix bounds compatibility
c3p0upgini Aug 30, 2024
14989ee
Refactoring
c3p0upgini Sep 4, 2024
fd4373e
Correct array validator
c3p0upgini Sep 4, 2024
3a5a955
Merge branch 'main' into bump_pydantic
c3p0upgini Sep 4, 2024
2bd92db
Refactoring
c3p0upgini Sep 4, 2024
c6166f7
Bump version
c3p0upgini Sep 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion _config.yml
View file
Open in desktop

This file was deleted.

12 changes: 7 additions & 5 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,9 +39,9 @@ dependencies = [
"fastparquet>=0.8.1",
"ipywidgets>=8.1.0",
"lightgbm>=3.3.2",
"numpy>=1.19.0",
"numpy>=1.19.0,<=1.26.4",
"pandas>=1.1.0,<3.0.0",
"pydantic>=1.8.2,<2.0.0",
"pydantic>1.0.0,<3.0.0",
"pyjwt>=2.8.0",
"python-dateutil>=2.8.0",
"python-json-logger>=2.0.2",
Expand Down Expand Up @@ -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_binary = 'pytest -s -vv tests/test_binary_dataset.py'
test_all = 'pytest -s -vv tests'

[[tool.hatch.envs.test.matrix]]
python = ["3.8"]
Expand All @@ -103,7 +103,8 @@ dependencies = [
# "pytest-timeout",
"requests-mock",
"pytest-datafiles",
"pandas~={matrix:pandas}.0",
"pytest-xdist",
"pandas~={matrix:pandas}",
]

[tool.black]
Expand All @@ -115,4 +116,5 @@ profile = "black"
[tool.pytest.ini_options]
pythonpath = [
"./src"
]
]
addopts="-n 4"
7 changes: 4 additions & 3 deletions requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,9 @@ python-dateutil>=2.8.0
requests>=2.8.0
# pandas>=1.1.0,<2.0.0
pandas>=1.1.0,<3.0.0
numpy>=1.19.0
numpy>=1.19.0,<=1.26.4
scikit-learn>=1.3.0
pydantic>=1.8.2,<2.0.0
pydantic>1.0.0,<3.0.0
fastparquet>=0.8.1
python-json-logger>=2.0.2
catboost>=1.0.3
Expand All @@ -30,4 +30,5 @@ unittest-xml-reporting
pytest-parallel
py
build
twine
twine
pytest-xdist
2 changes: 1 addition & 1 deletion src/upgini/__about__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
__version__ = "1.1.317"
__version__ = "1.2.0"
142 changes: 71 additions & 71 deletions src/upgini/autofe/binary.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,32 +9,32 @@


class Min(PandasOperand):
name = "min"
is_binary = True
is_symmetrical = True
has_symmetry_importance = True
name: str = "min"
is_binary: bool = True
is_symmetrical: bool = True
has_symmetry_importance: bool = True

def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
return np.minimum(left, right)


class Max(PandasOperand):
name = "max"
is_binary = True
is_symmetrical = True
has_symmetry_importance = True
name: str = "max"
is_binary: bool = True
is_symmetrical: bool = True
has_symmetry_importance: bool = True

def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
return np.maximum(left, right)


class Add(PandasOperand, VectorizableMixin):
name = "+"
alias = "add"
is_binary = True
is_symmetrical = True
has_symmetry_importance = True
is_vectorizable = True
name: str = "+"
alias: str = "add"
is_binary: bool = True
is_symmetrical: bool = True
has_symmetry_importance: bool = True
is_vectorizable: bool = True

def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
return left + right
Expand All @@ -48,12 +48,12 @@ def calculate_group(self, data: pd.DataFrame, **kwargs) -> pd.DataFrame:


class Subtract(PandasOperand, VectorizableMixin):
name = "-"
alias = "sub"
is_binary = True
is_symmetrical = True
has_symmetry_importance = True
is_vectorizable = True
name: str = "-"
alias: str = "sub"
is_binary: bool = True
is_symmetrical: bool = True
has_symmetry_importance: bool = True
is_vectorizable: bool = True

def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
return left - right
Expand All @@ -67,12 +67,12 @@ def calculate_group(self, data: pd.DataFrame, **kwargs) -> pd.DataFrame:


class Multiply(PandasOperand, VectorizableMixin):
name = "*"
alias = "mul"
is_binary = True
is_symmetrical = True
has_symmetry_importance = True
is_vectorizable = True
name: str = "*"
alias: str = "mul"
is_binary: bool = True
is_symmetrical: bool = True
has_symmetry_importance: bool = True
is_vectorizable: bool = True

def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
return left * right
Expand All @@ -86,12 +86,12 @@ def calculate_group(self, data: pd.DataFrame, **kwargs) -> pd.DataFrame:


class Divide(PandasOperand, VectorizableMixin):
name = "/"
alias = "div"
is_binary = True
has_symmetry_importance = True
is_vectorizable = True
output_type = "float"
name: str = "/"
alias: str = "div"
is_binary: bool = True
has_symmetry_importance: bool = True
is_vectorizable: bool = True
output_type: Optional[str] = "float"

def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
return left / right.replace(0, np.nan)
Expand All @@ -105,10 +105,10 @@ def calculate_group(self, data: pd.DataFrame, **kwargs) -> pd.DataFrame:


class Combine(PandasOperand):
name = "Combine"
is_binary = True
has_symmetry_importance = True
output_type = "object"
name: str = "Combine"
is_binary: bool = True
has_symmetry_importance: bool = True
output_type: Optional[str] = "object"

def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
temp = left.astype(str) + "_" + right.astype(str)
Expand All @@ -117,13 +117,13 @@ def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:


class CombineThenFreq(PandasOperand):
name = "CombineThenFreq"
is_binary = True
is_symmetrical = True
has_symmetry_importance = True
output_type = "float"
is_distribution_dependent = True
input_type = "discrete"
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"

def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
temp = left.astype(str) + "_" + right.astype(str)
Expand All @@ -133,11 +133,11 @@ def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:


class Distance(PandasOperand):
name = "dist"
is_binary = True
output_type = "float"
is_symmetrical = True
has_symmetry_importance = True
name: str = "dist"
is_binary: bool = True
output_type: Optional[str] = "float"
is_symmetrical: bool = True
has_symmetry_importance: bool = True

def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
return pd.Series(
Expand All @@ -158,11 +158,11 @@ def __norm(self, vector: pd.Series) -> pd.Series:

# Left for backward compatibility
class Sim(Distance):
name = "sim"
is_binary = True
output_type = "float"
is_symmetrical = True
has_symmetry_importance = True
name: str = "sim"
is_binary: bool = True
output_type: Optional[str] = "float"
is_symmetrical: bool = True
has_symmetry_importance: bool = True

def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
return 1 - super().calculate_binary(left, right)
Expand Down Expand Up @@ -191,12 +191,12 @@ def _similarity(self, left: str, right: str) -> float:


class JaroWinklerSim1(StringSim):
name = "sim_jw1"
is_binary = True
input_type = "string"
output_type = "float"
is_symmetrical = True
has_symmetry_importance = True
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

def _prepare_value(self, value: Optional[str]) -> Optional[str]:
return value
Expand All @@ -206,12 +206,12 @@ def _similarity(self, left: str, right: str) -> float:


class JaroWinklerSim2(StringSim):
name = "sim_jw2"
is_binary = True
input_type = "string"
output_type = "float"
is_symmetrical = True
has_symmetry_importance = True
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

def _prepare_value(self, value: Optional[str]) -> Optional[str]:
return value[::-1] if value is not None else None
Expand All @@ -221,12 +221,12 @@ def _similarity(self, left: str, right: str) -> float:


class LevenshteinSim(StringSim):
name = "sim_lv"
is_binary = True
input_type = "string"
output_type = "float"
is_symmetrical = True
has_symmetry_importance = True
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

def _prepare_value(self, value: Optional[str]) -> Optional[str]:
return value
Expand Down
Loading