use uv instead of poetry as dependency manager

Author: cod3licious

notebooks/autofeat_benchmark_classification.ipynb

@@ -9,15 +9,16 @@
     "import os\n",
     "import sys\n",
     "import warnings\n",
+    "\n",
     "import numpy as np\n",
     "import pandas as pd\n",
-    "from sklearn.datasets import load_iris, load_wine, load_breast_cancer\n",
-    "from sklearn.model_selection import train_test_split, GridSearchCV\n",
+    "from sklearn.datasets import load_breast_cancer, load_iris, load_wine\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "from sklearn.linear_model import LogisticRegression\n",
     "from sklearn.metrics import accuracy_score\n",
+    "from sklearn.model_selection import GridSearchCV, train_test_split\n",
     "from sklearn.preprocessing import StandardScaler\n",
-    "from sklearn.linear_model import LogisticRegression\n",
     "from sklearn.svm import SVC\n",
-    "from sklearn.ensemble import RandomForestClassifier\n",
     "\n",
     "from autofeat import AutoFeatClassifier\n",
     "\n",

notebooks/autofeat_benchmark_regression.ipynb

@@ -9,15 +9,16 @@
     "import os\n",
     "import sys\n",
     "import warnings\n",
+    "\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "from sklearn.datasets import fetch_california_housing, load_diabetes\n",
-    "from sklearn.model_selection import train_test_split, GridSearchCV\n",
+    "from sklearn.ensemble import RandomForestRegressor\n",
+    "from sklearn.linear_model import Ridge\n",
     "from sklearn.metrics import mean_squared_error, r2_score\n",
+    "from sklearn.model_selection import GridSearchCV, train_test_split\n",
     "from sklearn.preprocessing import StandardScaler\n",
-    "from sklearn.linear_model import Ridge\n",
     "from sklearn.svm import SVR\n",
-    "from sklearn.ensemble import RandomForestRegressor\n",
     "\n",
     "from autofeat import AutoFeatRegressor\n",
     "\n",

notebooks/autofeat_examples.ipynb

@@ -6,11 +6,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
     "import pandas as pd\n",
-    "import matplotlib.pyplot as plt\n",
     "\n",
-    "from autofeat import FeatureSelector, AutoFeatRegressor\n",
+    "from autofeat import AutoFeatRegressor, FeatureSelector\n",
     "\n",
     "%load_ext autoreload\n",
     "%autoreload 2"

notebooks/featsel_benchmark_linearmodels.ipynb

@@ -23,15 +23,16 @@
    "source": [
     "import colorsys\n",
     "import warnings\n",
+    "from time import time\n",
+    "\n",
     "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "import sklearn.linear_model as lm\n",
-    "from time import time\n",
     "from sklearn import svm\n",
-    "from sklearn.preprocessing import StandardScaler\n",
     "from sklearn.datasets import make_classification\n",
     "from sklearn.model_selection import GridSearchCV\n",
+    "from sklearn.preprocessing import StandardScaler\n",
     "\n",
     "from autofeat import AutoFeatModel\n",
     "\n",

pyproject.toml

@@ -1,41 +1,47 @@
 [build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"
 
-[tool.poetry]
+[project]
 name = "autofeat"
 version = "2.1.3"
 description = "Automatic Feature Engineering and Selection Linear Prediction Model"
-authors = ["Franziska Horn <[email protected]>"]
+authors = [{ name = "Franziska Horn", email = "[email protected]" }]
 readme = "README.md"
-packages = [{include = "autofeat", from = "src"}]
 license = "MIT"
 keywords = ["automl", "feature engineering", "feature selection", "linear model"]
-repository = "https://github.com/cod3licious/autofeat"
-homepage = "https://franziskahorn.de/autofeat"
-
-[tool.poetry.dependencies]
-python = "^3.8.1,<3.13"
-numpy = "^1.20.3"
-numba = ">=0.53.1"
-joblib = "^1.2.0"
-pandas = ">=1.3.5,<3.0.0"
-pint = ">=0.17,<1.0"
-scipy = "^1.7.3"
-scikit-learn = "^1.2.0"
-sympy = "^1.7.1"
-
-[tool.poetry.group.dev.dependencies]
-bandit = "^1.7.7"
-ipython = ">=8.0.0"
-notebook = "^6.5.0"
-matplotlib = "^3.7.2"
-mkdocs-material = "^9.5.28"
-mypy = "^1.7.1"
-poethepoet = ">=0.24.4"
-pytest = "^7.4.0"
-pyupgrade = "^3.9.0"
-ruff = ">=0.2.1"
+requires-python = ">=3.8.1,<3.13"
+dependencies = [
+    "joblib>=1.2.0",
+    "numba>=0.53.1",
+    "numpy>=1.21.0,<2.0",
+    "pandas>=1.3.5,<3.0",
+    "pint>=0.17,<1.0",
+    "scikit-learn>=1.2.0,<1.6",
+    "scipy>=1.7.3",
+    "sympy>=1.7.1",
+]
+
+[dependency-groups]
+dev = [
+    "bandit>=1.7.7",
+    "ipython>=8.0.0",
+    "matplotlib>=3.7.2",
+    "mkdocs-material>=9.5.28",
+    "mypy>=1.7.1",
+    "notebook>=6.5.0,<7.0",
+    "poethepoet>=0.24.4",
+    "pytest>=7.4.0",
+    "pyupgrade>=3.9.0",
+    "ruff>=0.2.1",
+]
+
+[project.urls]
+Repository = "https://github.com/cod3licious/autofeat"
+Documentation = "https://franziskahorn.de/autofeat"
+
+[tool.uv]
+required-version = ">=0.5.31"
 
 
 [tool.poe.tasks]
@@ -63,6 +69,7 @@ exclude = [
     "__pycache__",
     "build",
     "dist",
+    "*.ipynb",
 ]
 
 [tool.ruff.lint]
@@ -86,6 +93,7 @@ ignore = ["E501", # Line too long
     "D203", "D204", "D205", # required blank lines
     "G004", # Logging statement uses f-string
     "PIE790", # Unnecessary `pass` statement
+    "PLC0206", # Extracting value from dictionary without calling `.items()`
     "PLR2004", # Magic value used in comparison, consider replacing 0.999 with a constant variable
     "PLR09", # Too many arguments to function call
     "COM812", # trailing comma - don't use together with formatter

src/autofeat/autofeat.py

@@ -162,15 +162,15 @@ def _apply_pi_theorem(self, df: pd.DataFrame) -> pd.DataFrame:
             for i, r in enumerate(pi_theorem_results, 1):
                 if self.verbose:
                     logging.info(f"[AutoFeat] Pi Theorem {i}: ")
-                    logging.info(pint.formatter(r.items()))
+                    logging.info(pint.formatter(r.items(), denominator=[]))
                 # compute the final result by multiplying and taking the power of
                 cols = sorted(r)
                 # only use data points where non of the affected columns are NaNs
                 not_na_idx = df[cols].notna().all(axis=1)
                 ptr = df[cols[0]].to_numpy()[not_na_idx] ** r[cols[0]]
                 for c in cols[1:]:
                     ptr *= df[c].to_numpy()[not_na_idx] ** r[c]
-                df.loc[not_na_idx, f"PT{i}_{pint.formatter(r.items()).replace(' ', '')}"] = ptr
+                df.loc[not_na_idx, f"PT{i}_{pint.formatter(r.items(), denominator=[]).replace(' ', '')}"] = ptr
         return df
 
     def _generate_features(self, df: pd.DataFrame, new_feat_cols: list) -> pd.DataFrame:

src/autofeat/feateng.py

@@ -45,7 +45,7 @@ def ncr(n: int, r: int) -> int:
 
 def n_cols_generated(n_features: int, max_steps: int, n_transformations: int = 7, n_combinations: int = 4) -> int:
     """
-    computes the upper bound of how many features will be generated based on n_features to start with
+    Computes the upper bound of how many features will be generated based on n_features to start with
     and max_steps feateng steps.
     """
     # n_transformations is 1-len(func_transform) because either abs() or sqrt and log will be applied