Add Devcontainer

.devcontainer/Dockerfile

@@ -0,0 +1,3 @@
+FROM mcr.microsoft.com/vscode/devcontainers/python:3.9
+
+RUN /usr/local/bin/python -m pip install --upgrade pip

.devcontainer/devcontainer.json

@@ -0,0 +1,25 @@
+// For format details, see https://aka.ms/devcontainer.json. 
+{
+	"name": "fseval",
+	"dockerFile": "Dockerfile",
+	"customizations": {
+		"vscode": {
+			"extensions": [
+				"ms-python.python",
+				"ms-python.vscode-pylance",
+				"eamodio.gitlens",
+				"GitHub.vscode-pull-request-github"
+			],
+			"settings": {
+				"python.testing.unittestEnabled": false,
+				"python.testing.pytestEnabled": true,
+				"python.formatting.provider": "black",
+				"python.linting.enabled": true,
+				"python.linting.mypyEnabled": true,
+				"python.envFile": "${workspaceFolder}/.env"
+			}
+		}
+	},
+	"postCreateCommand": "pip install -r requirements.txt && pip install -r .devcontainer/requirements.txt && pip install --upgrade setuptools wheel",
+	"remoteUser": "vscode"
+}

.devcontainer/requirements.txt

@@ -0,0 +1,4 @@
+mypy
+pytest
+pytest-cov
+black

README.md

@@ -1,6 +1,7 @@
 # fseval
 
-[![build status](https://github.com/dunnkers/fseval/actions/workflows/python-app.yml/badge.svg)](https://github.com/dunnkers/fseval/actions/workflows/python-app.yml) [![pypi badge](https://img.shields.io/pypi/v/fseval.svg?maxAge=3600)](https://pypi.org/project/fseval/) [![Black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black) [![Downloads](https://pepy.tech/badge/fseval/month)](https://pepy.tech/project/fseval) ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/fseval) [![codecov](https://codecov.io/gh/dunnkers/fseval/branch/master/graph/badge.svg?token=R5ZXH8UPCI)](https://codecov.io/gh/dunnkers/fseval) [![Language grade: Python](https://img.shields.io/lgtm/grade/python/g/dunnkers/fseval.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/dunnkers/fseval/context:python) ![PyPI - License](https://img.shields.io/pypi/l/hydra-core) [![DOI](https://zenodo.org/badge/274001213.svg)](https://zenodo.org/badge/latestdoi/274001213)
+[![build status](https://github.com/dunnkers/fseval/actions/workflows/python-app.yml/badge.svg)](https://github.com/dunnkers/fseval/actions/workflows/python-app.yml) [![pypi badge](https://img.shields.io/pypi/v/fseval.svg?maxAge=3600)](https://pypi.org/project/fseval/) [![Black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black) [![Downloads](https://pepy.tech/badge/fseval/month)](https://pepy.tech/project/fseval) ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/fseval) [![codecov](https://codecov.io/gh/dunnkers/fseval/branch/master/graph/badge.svg?token=R5ZXH8UPCI)](https://codecov.io/gh/dunnkers/fseval) [![Language grade: Python](https://img.shields.io/lgtm/grade/python/g/dunnkers/fseval.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/dunnkers/fseval/context:python) ![PyPI - License](https://img.shields.io/pypi/l/hydra-core) [![DOI](https://zenodo.org/badge/274001213.svg)](https://zenodo.org/badge/latestdoi/274001213) [![Open in Remote - Containers](https://img.shields.io/static/v1?label=Remote%20-%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/dunnkers/fseval)
+
 
 Benchmarking framework for Feature Selection and Feature Ranking algorithms 🚀
 

requirements.txt

@@ -1,7 +1,7 @@
 hydra-core==1.1.2
 hydra-colorlog==1.1.0
 numpy>=1.19
-pandas>=1
+pandas>=1.1
 scikit-learn>=0.24
 humanfriendly>=9
 shortuuid>=1.0
@@ -10,7 +10,7 @@ types-dataclasses>=0.6
 PyYAML>=6
 types-PyYAML>=6
 SQLAlchemy>=1
-wandb>=0.12
+wandb==0.12.11
 -e git+https://github.com/dunnkers/FeatBoost.git@b81059ea4c5ac49fec075e823491104fae3d12b7#egg=featboost
 -e git+https://github.com/dunnkers/infinite-selection.git@6c9db1d5fe1b12bc34eb2af5893a4f3ca385aaff#egg=infinite_selection
 -e git+https://github.com/dunnkers/stability-selection.git@baf54e7526bbce57d80871fcd93cdfdd67972a43#egg=stability_selection
@@ -22,4 +22,5 @@ skfeature-chappers>=1.0
 skrebate>=0.62
 xgboost>=1
 pytest-dependency
-overrides>=6
+overrides>=6
+protobuf==3.20.0

setup.py

@@ -28,8 +28,8 @@
         },
         include_package_data=True,
         install_requires=[
-            "hydra-core>=1.1.0",
-            "hydra-colorlog>=1.1.0",
+            "hydra-core==1.1.2",
+            "hydra-colorlog==1.1.0",
             "numpy>=1.19",
             "pandas>=1.1",
             "scikit-learn>=0.24",

tests/integration/pipelines/test_rank_and_validate.py

@@ -3,11 +3,6 @@
 import numpy as np
 import pandas as pd
 import pytest
-from hydra.core.config_store import ConfigStore
-from hydra.utils import instantiate
-from omegaconf import DictConfig, open_dict
-from sklearn.base import BaseEstimator
-
 from fseval.config import (
     CrossValidatorConfig,
     DatasetConfig,
@@ -16,8 +11,13 @@
     ResampleConfig,
 )
 from fseval.pipeline.dataset import Dataset, DatasetLoader
-from fseval.types import AbstractAdapter, IncompatibilityError, Task
+from fseval.types import AbstractAdapter, Task
 from fseval.utils.hydra_utils import get_config
+from hydra.core.config_store import ConfigStore
+from hydra.errors import InstantiationException
+from hydra.utils import instantiate
+from omegaconf import DictConfig, open_dict
+from sklearn.base import BaseEstimator
 
 cs = ConfigStore.instance()
 
@@ -67,7 +67,6 @@ def get_data(self) -> Tuple[List, List]:
 
 ranker: EstimatorConfig = EstimatorConfig(
     name="Random Ranker",
-    task=Task.classification,
     estimator=random_estimator,
     _estimator_type="classifier",
     is_multioutput_dataset=False,
@@ -207,7 +206,7 @@ def test_with_ranker_gt_no_importances_substitution(cfg: PipelineConfig):
 
 
 def test_validator_incompatibility_check(cfg: PipelineConfig):
-    with pytest.raises(IncompatibilityError):
+    with pytest.raises(InstantiationException):
         cfg.dataset.n = 5
         cfg.dataset.p = 5
         cfg.dataset.multioutput = False
@@ -216,7 +215,7 @@ def test_validator_incompatibility_check(cfg: PipelineConfig):
 
 
 def test_ranker_incompatibility_check(cfg: PipelineConfig):
-    with pytest.raises(IncompatibilityError):
+    with pytest.raises(InstantiationException):
         cfg.dataset.n = 5
         cfg.dataset.p = 5
         cfg.dataset.multioutput = False

tests/integration/test_main.py

@@ -7,6 +7,7 @@
 from fseval.types import IncompatibilityError
 from fseval.utils.hydra_utils import get_config
 from hydra.conf import ConfigStore
+from hydra.errors import InstantiationException
 
 
 @pytest.fixture
@@ -66,7 +67,7 @@ def test_pipeline_incompatibility(incompatible_cfg: PipelineConfig):
     """Pipeline should throw IncompatibilityError when trying to run a classification
     method on a regression dataset."""
 
-    with pytest.raises(IncompatibilityError):
+    with pytest.raises(InstantiationException):
         run_pipeline(incompatible_cfg, raise_incompatibility_errors=True)
 
 

tests/unit/pipeline/test_estimator.py

@@ -3,13 +3,14 @@
 
 import pytest
 from hydra.utils import instantiate
+from hydra.errors import InstantiationException
 from omegaconf import OmegaConf
 from sklearn.base import BaseEstimator
 
 from fseval.config import EstimatorConfig
 from fseval.pipeline.estimator import Estimator
 from fseval.storage.local import LocalStorage
-from fseval.types import CacheUsage, IncompatibilityError, Task
+from fseval.types import CacheUsage, Task
 
 
 @pytest.fixture
@@ -79,23 +80,23 @@ def test_incompatibility(estimator_cfg: EstimatorConfig):
     # classification estimator, but regression task
     estimator_cfg._estimator_type = "classifier"
     estimator_cfg.task = Task.regression
-    with pytest.raises(IncompatibilityError):
+    with pytest.raises(InstantiationException):
         instantiate(estimator_cfg)
 
     # multioutput, but estimator does not support it (`multioutput=False`)
     estimator_cfg._estimator_type = "classifier"
     estimator_cfg.task = Task.classification
     estimator_cfg.multioutput = False
     estimator_cfg.is_multioutput_dataset = True
-    with pytest.raises(IncompatibilityError):
+    with pytest.raises(InstantiationException):
         instantiate(estimator_cfg)
 
     # multioutput only, but
     estimator_cfg._estimator_type = "classifier"
     estimator_cfg.task = Task.classification
     estimator_cfg.multioutput_only = True
     estimator_cfg.is_multioutput_dataset = False
-    with pytest.raises(IncompatibilityError):
+    with pytest.raises(InstantiationException):
         instantiate(estimator_cfg)