chemotools 0.1.11rc0__py3-none-any.whl → 0.1.17__py3-none-any.whl

chemotools/augmentation/_index_shift.py

@@ -193,7 +193,7 @@ class IndexShift(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
             if pad_left:
                 points = x[: pad_length + 1]  # Take first pad_length+1 points
                 x_coords = np.arange(len(points))
-                slope, intercept, _, _, _ = stats.linregress(x_coords, points)
+                slope, intercept, *_ = stats.linregress(x_coords, points)
 
                 # Generate new points using linear regression
                 new_x = np.arange(-pad_length, 0)
@@ -202,7 +202,7 @@ class IndexShift(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
             else:
                 points = x[-pad_length - 1 :]  # Take last pad_length+1 points
                 x_coords = np.arange(len(points))
-                slope, intercept, _, _, _ = stats.linregress(x_coords, points)
+                slope, intercept, *_ = stats.linregress(x_coords, points)
 
                 # Generate new points using linear regression
                 new_x = np.arange(len(points), len(points) + pad_length)

chemotools/feature_selection/__init__.py

@@ -1,4 +1,6 @@
 from ._index_selector import IndexSelector
 from ._range_cut import RangeCut
+from ._sr_selector import SRSelector
+from ._vip_selector import VIPSelector
 
-__all__ = ["IndexSelector", "RangeCut"]
+__all__ = ["IndexSelector", "RangeCut", "SRSelector", "VIPSelector"]

chemotools/feature_selection/_base.py

@@ -0,0 +1,88 @@
+from abc import ABC, abstractmethod
+from typing import Union
+
+import numpy as np
+
+from sklearn.base import BaseEstimator
+from sklearn.cross_decomposition._pls import _PLS
+from sklearn.feature_selection._base import SelectorMixin
+from sklearn.pipeline import Pipeline
+from sklearn.utils.validation import check_is_fitted
+
+ModelTypes = Union[_PLS, Pipeline]
+
+
+class _PLSFeatureSelectorBase(ABC, BaseEstimator, SelectorMixin):
+    """Feature selection base class for _PLS-like models.
+
+
+    Parameters
+    ----------
+    model : Union[_PLS, Pipeline]
+        A fitted  _PLS models or Pipeline ending with such a model
+
+    threshold : float
+        The threshold for feature selection. Features with importance
+        above this threshold will be selected.
+
+    Attributes
+    ----------
+    estimator_ : ModelTypes
+        The fitted model of type _BasePCA or _PLS
+
+    feature_scores_ : np.ndarray
+        The calculated feature scores based on the selected method.
+
+    support_mask : np.ndarray
+        The boolean mask indicating which features are selected.
+    """
+
+    def __init__(
+        self,
+        model: Union[_PLS, Pipeline],
+    ) -> None:
+        self.estimator_ = _validate_and_extract_model(model)
+
+    @abstractmethod
+    def _calculate_features(self, X: np.ndarray) -> np.ndarray:
+        """Calculate the residuals of the model.
+
+        Returns
+        -------
+        ndarray of shape (n_samples,)
+            The residuals of the model
+        """
+
+
+def _validate_and_extract_model(
+    model: Union[_PLS, Pipeline],
+) -> _PLS:
+    """Validate and extract the model.
+
+    Parameters
+    ----------
+    model : Union[_PLS, Pipeline]
+        A fitted _PLS model or Pipeline ending with such a model
+
+    Returns
+    -------
+    _PLS
+        The extracted estimator
+
+    Raises
+    ------
+    TypeError
+        If the model is not of type _BasePCA or _PLS or a Pipeline ending with one of these types or if the model is not fitted
+    """
+    if isinstance(model, Pipeline):
+        estimator = model[-1]
+    else:
+        estimator = model
+
+    if not isinstance(estimator, _PLS):
+        raise TypeError(
+            "Model not a valid model. Must be of base type _BasePCA or _PLS or a Pipeline ending with one of these types."
+        )
+
+    check_is_fitted(model)
+    return estimator

chemotools/feature_selection/_sr_selector.py

@@ -0,0 +1,137 @@
+import numpy as np
+from sklearn.utils.validation import validate_data
+
+from ._base import _PLSFeatureSelectorBase
+
+
+class SRSelector(_PLSFeatureSelectorBase):
+    """
+    This selector is used to select features that contribute significantly
+    to the latent variables in a PLS regression model using the Selectivity
+    Ratio (SR) method.
+
+    Parameters
+    ----------
+    - model: Union[_PLS, Pipeline]
+        The PLS regression model or a pipeline with a PLS regression model as last step.
+
+    - threshold: float, default=1.0
+        The threshold for feature selection. Features with importance
+        above this threshold will be selected.
+
+    Attributes
+    ----------
+    estimator_ : ModelTypes
+        The fitted model of type _BasePCA or _PLS
+
+    feature_scores_ : np.ndarray
+        The calculated feature scores based on the selected method.
+
+    support_mask_ : np.ndarray
+        The boolean mask indicating which features are selected.
+
+    Methods
+    -------
+    fit(X, y=None)
+        Fit the transformer to the input data. It calculates the feature scores and the feature_mask.
+    """
+
+    def __init__(
+        self,
+        model,
+        threshold: float = 1.0,
+    ):
+        self.model = model
+        self.threshold = threshold
+        super().__init__(self.model)
+
+    def fit(self, X: np.ndarray, y=None) -> "SRSelector":
+        """
+        Fit the transformer to calculate the feature scores and the support mask.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The input data to fit the transformer to.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        self : SRSelector
+            The fitted transformer.
+        """
+        # Check that X is a 2D array and has only finite values
+        X = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
+
+        # Calculate the SR scores
+        self.feature_scores_ = self._calculate_features(X)
+
+        # Calculate the support mask
+        self.support_mask_ = self._get_support_mask()
+
+        return self
+
+    def _get_support_mask(self) -> np.ndarray:
+        """
+        Get the support mask based on the feature scores and threshold.
+        Features with scores above the threshold are selected.
+        Parameters
+        ----------
+        self : SRSelector
+            The fitted transformer.
+
+        Returns
+        -------
+        support_mask_ : np.ndarray
+            The boolean mask indicating which features are selected.
+        """
+        return self.feature_scores_ > self.threshold
+
+    def _calculate_features(self, X: np.ndarray) -> np.ndarray:
+        """
+        Vectorized Selectivity Ratio calculation from a fitted _PLS
+        like model.
+
+        Parameters:
+        ----------
+        - self: SRSelector
+            The fitted transformer.
+
+        - X: array-like of shape (n_samples, n_features)
+            The input training data to calculate the feature scores from.
+
+        Returns
+        -------
+        feature_scores_ : np.ndarray
+            The calculated feature scores based on the selected method.
+        """
+        bpls = self.estimator_.coef_
+        bpls_norm = bpls.T / np.linalg.norm(bpls)
+
+        # Handle 1D case correctly
+        if bpls.ndim == 1:
+            bpls_norm = bpls_norm.reshape(-1, 1)
+
+        # Project X onto the regression vector
+        ttp = X @ bpls_norm
+        ptp = X.T @ np.linalg.pinv(ttp).T
+
+        # Predicted part of X
+        X_hat = ttp @ ptp.T
+
+        # Compute squared norms directly
+        total_ss = np.linalg.norm(X, axis=0) ** 2
+        explained_ss = np.linalg.norm(X_hat, axis=0) ** 2
+
+        # Calculate residual sum of squares
+        residual_ss = total_ss - explained_ss
+
+        # Stability: avoid division by zero
+        epsilon = 1e-12
+
+        # Calculate Selectivity Ratio
+        return explained_ss / (residual_ss + epsilon)

chemotools/feature_selection/_vip_selector.py

@@ -0,0 +1,129 @@
+import numpy as np
+from sklearn.utils.validation import validate_data
+
+from ._base import _PLSFeatureSelectorBase
+
+
+class VIPSelector(_PLSFeatureSelectorBase):
+    """
+    This selector is used to select features that contribute significantly
+    to the latent variables in a PLS regression model using the Variables
+    Importance in Projection (VIP) method.
+
+    Parameters
+    ----------
+    - model: Union[_PLS, Pipeline]
+        The PLS regression model or a pipeline with a PLS regression model as last step.
+
+    - threshold: float, default=1.0
+        The threshold for feature selection. Features with importance
+        above this threshold will be selected.
+
+    Attributes
+    ----------
+    estimator_ : ModelTypes
+        The fitted model of type _BasePCA or _PLS
+
+    feature_scores_ : np.ndarray
+        The calculated feature scores based on the selected method.
+
+    support_mask_ : np.ndarray
+        The boolean mask indicating which features are selected.
+
+    Methods
+    -------
+    fit(X, y=None)
+        Fit the transformer to the input data. It calculates the feature scores and the feature_mask.
+    """
+
+    def __init__(
+        self,
+        model,
+        threshold: float = 1.0,
+    ):
+        self.model = model
+        self.threshold = threshold
+        super().__init__(self.model)
+
+    def fit(self, X: np.ndarray, y=None) -> "VIPSelector":
+        """
+        Fit the transformer to calculate the feature scores and the support mask.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The input data to fit the transformer to.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        self : VIPSelector
+            The fitted transformer.
+        """
+        # Check that X is a 2D array and has only finite values
+        X = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
+
+        # Calculate the VIP scores
+        self.feature_scores_ = self._calculate_features(X)
+
+        # Calculate the support mask
+        self.support_mask_ = self._get_support_mask()
+
+        return self
+
+    def _get_support_mask(self) -> np.ndarray:
+        """
+        Get the support mask based on the feature scores and threshold.
+        Features with scores above the threshold are selected.
+        Parameters
+        ----------
+        self : VIPSelector
+            The fitted transformer.
+
+        Returns
+        -------
+        support_mask_ : np.ndarray
+            The boolean mask indicating which features are selected.
+        """
+        return self.feature_scores_ > self.threshold
+
+    def _calculate_features(self, X: np.ndarray) -> np.ndarray:
+        """
+        Calculate the VIP scores based on the fitted model.
+
+        Parameters
+        ----------
+        self : VIPSelector
+            The fitted transformer.
+
+        Returns
+        -------
+        feature_scores_ : np.ndarray
+            The calculated feature scores based on the selected method.
+        """
+        # Calculate sum of squares of y_loadings and x_scores
+        sum_of_squares_y_loadings = (
+            np.linalg.norm(self.estimator_.y_loadings_, ord=2, axis=0) ** 2
+        )
+        sum_of_squares_x_scores = (
+            np.linalg.norm(self.estimator_.x_scores_, ord=2, axis=0) ** 2
+        )
+
+        # Calculate the sum of squares
+        sum_of_squares = sum_of_squares_y_loadings * sum_of_squares_x_scores
+
+        # Calculate the numerator
+        numerator = self.estimator_.n_features_in_ * np.sum(
+            sum_of_squares * self.estimator_.x_weights_**2,
+            axis=1,
+        )
+
+        # Calculate the denominator
+        denominator = np.sum(sum_of_squares, axis=0)
+
+        # Calculate the VIP scores
+        return np.sqrt(numerator / denominator)

chemotools-0.1.17.dist-info/METADATA

@@ -0,0 +1,105 @@
+Metadata-Version: 2.4
+Name: chemotools
+Version: 0.1.17
+Summary: chemotools: A Python Package that Integrates Chemometrics and scikit-learn
+Author: Pau Cabaneros
+License-Expression: MIT
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: numpy<3,>=2.0.0
+Requires-Dist: pandas<3,>=2.0.0
+Requires-Dist: polars<2,>=1.17.0
+Requires-Dist: pyarrow<21,>=18
+Requires-Dist: scikit-learn<2,>=1.4.0
+Provides-Extra: dev
+Requires-Dist: cyclonedx-bom>=7.1.0; extra == 'dev'
+Requires-Dist: mypy<2,>=1.13.0; extra == 'dev'
+Requires-Dist: pandas-stubs<3,>=2.2.3.241126; extra == 'dev'
+Requires-Dist: pytest-cov>=6.3.0; extra == 'dev'
+Requires-Dist: pytest<9,>=8.3.0; extra == 'dev'
+Requires-Dist: ruff<0.9,>=0.8.0; extra == 'dev'
+Requires-Dist: scipy-stubs<2,>=1.15.1.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+![chemotools](assets/images/banner_dark.png)
+
+# chemotools
+
+
+[![PyPI](https://img.shields.io/pypi/v/chemotools)](https://pypi.org/project/chemotools)
+[![Python Versions](https://img.shields.io/pypi/pyversions/chemotools)](https://pypi.org/project/chemotools)
+[![License](https://img.shields.io/pypi/l/chemotools)](https://github.com/paucablop/chemotools/blob/main/LICENSE)
+[![Coverage](https://codecov.io/github/paucablop/chemotools/branch/main/graph/badge.svg?token=D7JUJM89LN)](https://codecov.io/github/paucablop/chemotools)
+[![Downloads](https://static.pepy.tech/badge/chemotools)](https://pepy.tech/project/chemotools)
+[![DOI](https://joss.theoj.org/papers/10.21105/joss.06802/status.svg)](https://doi.org/10.21105/joss.06802)
+
+---
+
+`chemotools` is a Python library that brings **chemometric preprocessing tools** into the [`scikit-learn`](https://scikit-learn.org/) ecosystem.  
+
+It provides modular transformers for spectral data, designed to plug seamlessly into your ML workflows.
+
+## Features
+
+- Preprocessing for spectral data (baseline correction, smoothing, scaling, derivatization, scatter correction).  
+- Fully compatible with `scikit-learn` pipelines and transformers.  
+- Simple, modular API for flexible workflows.  
+- Open-source, actively maintained, and published on [PyPI](https://pypi.org/project/chemotools/) and [Conda](https://anaconda.org/conda-forge/chemotools).  
+
+## Installation
+
+Install from PyPI:
+
+```bash
+pip install chemotools
+````
+
+Install from Conda:
+
+```bash
+conda install -c conda-forge chemotools
+```
+
+## Usage
+
+Example: preprocessing pipeline with scikit-learn:
+
+```python
+from sklearn.preprocessing import StandardScaler
+from sklearn.pipeline import make_pipeline
+
+from chemotools.baseline import AirPls
+from chemotools.scatter import MultiplicativeScatterCorrection
+
+preprocessing = make_pipeline(
+    AirPls(),
+    MultiplicativeScatterCorrection(),
+    StandardScaler(with_std=False),
+)
+
+spectra_transformed = preprocessing.fit_transform(spectra)
+```
+
+➡️ See the [documentation](https://paucablop.github.io/chemotools/) for full details.
+
+## Development
+
+This project uses [uv](https://github.com/astral-sh/uv) for dependency management and [Task](https://taskfile.dev) to simplify common development workflows.
+You can get started quickly by using the predefined [Taskfile](./Taskfile.yml), which provides handy shortcuts such as:
+
+```bash
+task install     # install all dependencies
+task check       # run formatting, linting, typing, and tests
+task coverage    # run tests with coverage reporting
+task build       # build the package for distribution
+```
+
+## Contributing
+
+Contributions are welcome!
+Check out the [contributing guide](CONTRIBUTING.md) and the [project board](https://github.com/users/paucablop/projects/4).
+
+## License
+
+Released under the [MIT License](LICENSE).
+

{chemotools-0.1.11rc0.dist-info → chemotools-0.1.17.dist-info}/RECORD

@@ -4,7 +4,7 @@ chemotools/augmentation/_add_noise.py,sha256=fkTJfIYtZXezcjy6Vz8asIhpBoVp4oaIifp
 chemotools/augmentation/_baseline_shift.py,sha256=kIlYvmKS9pu9vh_-eZ7PSHPuH_58V9mgYbSJt6Gq3BA,3476
 chemotools/augmentation/_fractional_shift.py,sha256=dJ0Vuc-U02HhjKkOwc48qnOksZYgbHwL2ko7tWCZTQU,6916
 chemotools/augmentation/_gaussian_broadening.py,sha256=dJsPlTKqpecKaCDU3vOvedIb-t_HyCkQprxNv0DmYZQ,4236
-chemotools/augmentation/_index_shift.py,sha256=BTtadweDvvMtiF8t7ldwsE6Kl6FmKLCkVJjSzSWyIDs,6904
+chemotools/augmentation/_index_shift.py,sha256=NeN9Nc212wIF4R1dSoWFIrSuP3OWO1GPTPJ_Ql_SKzw,6894
 chemotools/augmentation/_spectrum_scale.py,sha256=hMsmzXpssbI7tGm_YnQn9wjbByso3CgVxd3Hs8kfLS8,3442
 chemotools/baseline/__init__.py,sha256=VzoblGg8Hx_FkTc_n7a-ZjGvtKP8JE_NwJKWenGFQkM,584
 chemotools/baseline/_air_pls.py,sha256=eotXuIEsus7Z-c17oLx8UbiwOHM7DzQJ6rruHnwCGPQ,5067
@@ -27,9 +27,12 @@ chemotools/datasets/data/train_spectra.csv,sha256=iVF19W52NHlbqq8BbLomn8n47kSPT0
 chemotools/derivative/__init__.py,sha256=FkckdzO30jrRWPGpIU3cfnaTtxPtNT5Tb2G9F9PmVTw,134
 chemotools/derivative/_norris_william.py,sha256=rMY_yntpiB5fbSM1tPph4AaGmF1k-HqJp7o48ijePBs,4958
 chemotools/derivative/_savitzky_golay.py,sha256=CuCrKoLmrB1YmJ4ihIykgkL3tO3frqkStMogtsVhO3A,3632
-chemotools/feature_selection/__init__.py,sha256=1_i28hIxijjwhMypTy1w2fLbzXXVkKD5IYzzY8ZSuHw,117
+chemotools/feature_selection/__init__.py,sha256=e_GFVawlDNEQv3EqrGSXUr5cvDN1jckoxe2C2jRwVl8,222
+chemotools/feature_selection/_base.py,sha256=SIH6kl9AePVWTByL0OvJFfc2j3idqs7lm_7Zi1YMp4Y,2311
 chemotools/feature_selection/_index_selector.py,sha256=lNTP2b7P3doWl30KiAr3Xd2HOMxeUmj24MuqoXl4Voc,3556
 chemotools/feature_selection/_range_cut.py,sha256=lVVVC30ZsK2z9jsDGb_z6l8Ty2I89yM05_dIDbMP73Q,3564
+chemotools/feature_selection/_sr_selector.py,sha256=OaXkt3t_NvymgDy6R15ig87jhcb-vM7i63LgtsNdfZo,3969
+chemotools/feature_selection/_vip_selector.py,sha256=ZK3bhdpl3nBYt6xmuHq2IvWtpgJ8ZdElH06xnCFA-Xs,3835
 chemotools/outliers/__init__.py,sha256=wpdlyqU34n1Pb9kGCM4idhcok35WAakxEhzP0xeKaZw,272
 chemotools/outliers/_base.py,sha256=zl0LhRKjpvj5IbYc3su6zEZ7YZ0pDSR3yqNWt2qBjNA,5374
 chemotools/outliers/dmodx.py,sha256=sgizal_BDlqWTZNT8y2D_ImcKAJejXt6vqvFYk4Vqi0,5152
@@ -53,7 +56,7 @@ chemotools/smooth/_median_filter.py,sha256=9ndTJCwrZirWlvDNldiigMddy79KIGq9OwwYN
 chemotools/smooth/_savitzky_golay_filter.py,sha256=27iFUWxdL9_7oZabR0R5L0ZTpBmYfVUjx2XCTukihBE,3509
 chemotools/smooth/_whittaker_smooth.py,sha256=lpLAyf4GdyDW4ulT1nyEoK6xQEl2cVUKquawQdGWbHU,3571
 chemotools/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chemotools-0.1.11rc0.dist-info/LICENSE,sha256=qtyOy2wDQVX9hxp58h3T-6Lmfv-mSCHoSRkcLUdM9bg,1070
-chemotools-0.1.11rc0.dist-info/METADATA,sha256=lhDYugMDLS5dHu86xGNho2mAj25vfFucPMEQAHmhfpA,5243
-chemotools-0.1.11rc0.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
-chemotools-0.1.11rc0.dist-info/RECORD,,
+chemotools-0.1.17.dist-info/METADATA,sha256=hxxeamc9RNFVB7ukM7Srm8PGZzwJi1gI3jMghUD00hc,3652
+chemotools-0.1.17.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+chemotools-0.1.17.dist-info/licenses/LICENSE,sha256=qtyOy2wDQVX9hxp58h3T-6Lmfv-mSCHoSRkcLUdM9bg,1070
+chemotools-0.1.17.dist-info/RECORD,,

{chemotools-0.1.11rc0.dist-info → chemotools-0.1.17.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.1.2
+Generator: hatchling 1.27.0
 Root-Is-Purelib: true
 Tag: py3-none-any

chemotools-0.1.11rc0.dist-info/METADATA

@@ -1,105 +0,0 @@
-Metadata-Version: 2.3
-Name: chemotools
-Version: 0.1.11rc0
-Summary: chemotools: A Python Package that Integrates Chemometrics and scikit-learn
-License: MIT
-Author: Pau Cabaneros
-Requires-Python: >=3.10,<4.0
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: numpy (>=2.0.0,<3.0.0)
-Requires-Dist: pandas (>=2.0.0,<3.0.0)
-Requires-Dist: polars (>=1.17.0,<2.0.0)
-Requires-Dist: pyarrow (>=18.0.0,<19.0.0)
-Requires-Dist: scikit-learn (>=1.4.0,<2.0.0)
-Description-Content-Type: text/markdown
-
-![chemotools](assets/images/logo_pixel.png)
-
-
-[![pypi](https://img.shields.io/pypi/v/chemotools)](https://pypi.org/project/chemotools)
-[![pypi](https://img.shields.io/pypi/pyversions/chemotools)](https://pypi.org/project/chemotools)
-[![pypi](https://img.shields.io/pypi/l/chemotools)](https://github.com/paucablop/chemotools/blob/main/LICENSE)
-[![codecov](https://codecov.io/github/paucablop/chemotools/branch/main/graph/badge.svg?token=D7JUJM89LN)](https://codecov.io/github/paucablop/chemotools)
-[![Downloads](https://static.pepy.tech/badge/chemotools)](https://pepy.tech/project/chemotools)
-[![DOI](https://joss.theoj.org/papers/10.21105/joss.06802/status.svg)](https://doi.org/10.21105/joss.06802)
-
-
-# __chemotools__
-
-Welcome to Chemotools, a Python package that integrates chemometrics with Scikit-learn.
-
-## Note
-
-Since I released Chemotools, I have received a fantastic response from the community. I am really happy for the interest in the project 🤗. This also means that I have received a lot of good feedback and suggestions for improvements. I have been intensively working on releasing new versions of Chemotools to address the feedback and suggestions. If you use Chemotools, __make sure you are using the latest version__ (see installation), which will be aligned with the documentation. 
-
-👉👉 Check the [latest version](https://pypi.org/project/chemotools/) and make sure you don't miss out on cool new features.
-
-👉👉 Check the [documentation](https://paucablop.github.io/chemotools/) for a full description on how to use chemotools.
-
-## Description
-
-Chemotools is a Python package that provides a collection of preprocessing tools and utilities for working with spectral data. It is built on top of popular scientific libraries and is designed to be highly modular, easy to use, and compatible with Scikit-learn transformers.
-
-If you are interested in learning more about chemotools, please visit the [documentation](https://paucablop.github.io/chemotools/) page.
-
-Benefits:
-- Provides a collection of preprocessing tools and utilities for working with spectral data
-- Highly modular and compatible with Scikit-learn transformers
-- Can perform popular preprocessing tasks such as baseline correction, smoothing, scaling, derivatization, and scattering correction
-- Open source and available on PyPI
-
-Applications:
-- Analyzing and processing spectral data in chemistry, biology, and other fields
-- Developing machine learning models for predicting properties or classifying samples based on spectral data
-- Teaching and learning about chemometrics and data preprocessing in Python
-
-## Installation
-
-Chemotools is distributed via PyPI and can be easily installed using pip:
-
-```bash
-pip install chemotools
-```
-
-Upgrading to the latest version is as simple as:
-
-```bash
-pip install chemotools --upgrade
-```
-
-## Usage
-
-Chemotools is designed to be used in conjunction with Scikit-learn. It follows the same API as other Scikit-learn transformers, so you can easily integrate it into your existing workflow. For example, you can use chemotools to build pipelines that include transformers from chemotools and Scikit-learn:
-
-```python
-from sklearn.preprocessing import StandardScaler
-from sklearn.pipeline import make_pipeline
-
-from chemotools.baseline import AirPls
-from chemotools.scatter import MultiplicativeScatterCorrection
-
-preprocessing = make_pipeline(AirPls(), MultiplicativeScatterCorrection(), StandardScaler(with_std=False)) 
-spectra_transformed = preprocessing.fit_transform(spectra)
-```
-
-Check the [documentation](https://paucablop.github.io/chemotools/) for more information on how to use chemotools.
-
-
-## Contributing
-
-We welcome contributions to Chemotools from anyone interested in improving the package. Whether you have ideas for new features, bug reports, or just want to help improve the code, we appreciate your contributions! You are also welcome to see the [Project Board](https://github.com/users/paucablop/projects/4) to see what we are currently working on.
-
-To contribute to Chemotools, please follow the [contributing guidelines](CONTRIBUTING.md).
-
-## License
-
-This package is distributed under the MIT license. See the [LICENSE](LICENSE) file for more information.
-
-## Credits
-
-AirPLS baseline correction is based on the implementation by [Zhang et al.](https://pubs.rsc.org/is/content/articlelanding/2010/an/b922045c). The current implementation is based on the Python implementation by [zmzhang](https://github.com/zmzhang/airPLS).