chemotools 0.0.22__py3-none-any.whl → 0.1.6__py3-none-any.whl

chemotools/augmentation/__init__.py

@@ -0,0 +1,16 @@
+from .baseline_shift import BaselineShift
+from .exponential_noise import ExponentialNoise
+from .normal_noise import NormalNoise
+from .index_shift import IndexShift
+from .spectrum_scale import SpectrumScale
+from .uniform_noise import UniformNoise
+
+
+__all__ = [
+    "BaselineShift",
+    "ExponentialNoise",
+    "NormalNoise",
+    "IndexShift",
+    "SpectrumScale",
+    "UniformNoise",
+]

chemotools/augmentation/baseline_shift.py

@@ -0,0 +1,119 @@
+from typing import Optional
+
+import numpy as np
+from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
+from sklearn.utils.validation import check_is_fitted, validate_data
+
+
+class BaselineShift(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
+    """
+    Adds a constant baseline to the data. The baseline is drawn from a one-sided
+    uniform distribution between 0 and 0 + scale.
+
+    Parameters
+    ----------
+    scale : float, default=0.0
+        Range of the uniform distribution to draw the baseline factor from.
+
+    random_state : int, default=None
+        The random state to use for the random number generator.
+
+    Attributes
+    ----------
+    n_features_in_ : int
+        The number of features in the input data.
+
+    _is_fitted : bool
+        Whether the transformer has been fitted to data.
+
+    Methods
+    -------
+    fit(X, y=None)
+        Fit the transformer to the input data.
+
+    transform(X, y=0, copy=True)
+        Transform the input data by adding a baseline the spectrum.
+    """
+
+    def __init__(self, scale: float = 0.0, random_state: Optional[int] = None):
+        self.scale = scale
+        self.random_state = random_state
+
+    def fit(self, X: np.ndarray, y=None) -> "BaselineShift":
+        """
+        Fit the transformer to the input data.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to fit the transformer to.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        self : BaselineShift
+            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
+        )
+        # Set the number of features
+        self.n_features_in_ = X.shape[1]
+
+        # Set the fitted attribute to True
+        self._is_fitted = True
+
+        # Instantiate the random number generator
+        self._rng = np.random.default_rng(self.random_state)
+
+        return self
+
+    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
+        """
+        Transform the input data by adding a baseline to the spectrum.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to transform.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        X_ : np.ndarray of shape (n_samples, n_features)
+            The transformed data.
+        """
+        # Check that the estimator is fitted
+        check_is_fitted(self, "_is_fitted")
+
+        # Check that X is a 2D array and has only finite values
+        X_ = validate_data(
+            self,
+            X,
+            y="no_validation",
+            ensure_2d=True,
+            copy=True,
+            reset=False,
+            dtype=np.float64,
+        )
+
+        # Check that the number of features is the same as the fitted data
+        if X_.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"Expected {self.n_features_in_} features but got {X_.shape[1]}"
+            )
+
+        # Calculate the scaled spectrum
+        for i, x in enumerate(X_):
+            X_[i] = self._add_baseline(x)
+
+        return X_.reshape(-1, 1) if X_.ndim == 1 else X_
+
+    def _add_baseline(self, x) -> np.ndarray:
+        adding_factor = self._rng.uniform(low=0, high=self.scale)
+        return np.add(x, adding_factor)

chemotools/augmentation/exponential_noise.py

@@ -0,0 +1,117 @@
+from typing import Optional
+
+import numpy as np
+from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
+from sklearn.utils.validation import check_is_fitted, validate_data
+
+
+class ExponentialNoise(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
+    """
+    Add exponential noise to the input data.
+
+    Parameters
+    ----------
+    scale: float, default=0.0
+        The scale of the noise to add to the input data.
+
+    random_state : int, default=None
+        The random state to use for the random number generator.
+
+    Attributes
+    ----------
+    n_features_in_ : int
+        The number of features in the input data.
+
+    _is_fitted : bool
+        Whether the transformer has been fitted to data.
+
+    Methods
+    -------
+    fit(X, y=None)
+        Fit the transformer to the input data.
+
+    transform(X, y=0, copy=True)
+        Transform the input data by adding random noise.
+    """
+
+    def __init__(self, scale: float = 0.0, random_state: Optional[int] = None):
+        self.scale = scale
+        self.random_state = random_state
+
+    def fit(self, X: np.ndarray, y=None) -> "ExponentialNoise":
+        """
+        Fit the transformer to the input data.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to fit the transformer to.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        self : ExponentialNoise
+            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
+        )
+        # Set the number of features
+        self.n_features_in_ = X.shape[1]
+
+        # Set the fitted attribute to True
+        self._is_fitted = True
+
+        # Instantiate the random number generator
+        self._rng = np.random.default_rng(self.random_state)
+
+        return self
+
+    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
+        """
+        Transform the input data by adding random exponential noise.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to transform.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        X_ : np.ndarray of shape (n_samples, n_features)
+            The transformed data.
+        """
+        # Check that the estimator is fitted
+        check_is_fitted(self, "_is_fitted")
+
+        # Check that X is a 2D array and has only finite values
+        X_ = validate_data(
+            self,
+            X,
+            y="no_validation",
+            ensure_2d=True,
+            copy=True,
+            reset=False,
+            dtype=np.float64,
+        )
+
+        # Check that the number of features is the same as the fitted data
+        if X_.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"Expected {self.n_features_in_} features but got {X_.shape[1]}"
+            )
+
+        # Calculate the standard exponential variate
+        for i, x in enumerate(X_):
+            X_[i] = self._add_random_noise(x)
+
+        return X_.reshape(-1, 1) if X_.ndim == 1 else X_
+
+    def _add_random_noise(self, x) -> np.ndarray:
+        return x + self._rng.exponential(self.scale, size=x.shape)

chemotools/augmentation/index_shift.py

@@ -0,0 +1,120 @@
+from typing import Optional
+
+import numpy as np
+from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
+from sklearn.utils.validation import check_is_fitted, validate_data
+
+
+class IndexShift(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
+    """
+    Shift the spectrum a given number of indices between - shift and + shift drawn
+    from a discrete uniform distribution.
+
+    Parameters
+    ----------
+    shift : float, default=0.0
+        Shifts the data by a random integer between -shift and shift.
+
+    random_state : int, default=None
+        The random state to use for the random number generator.
+
+    Attributes
+    ----------
+    n_features_in_ : int
+        The number of features in the input data.
+
+    _is_fitted : bool
+        Whether the transformer has been fitted to data.
+
+    Methods
+    -------
+    fit(X, y=None)
+        Fit the transformer to the input data.
+
+    transform(X, y=0, copy=True)
+        Transform the input data by shifting the spectrum.
+    """
+
+    def __init__(self, shift: int = 0, random_state: Optional[int] = None):
+        self.shift = shift
+        self.random_state = random_state
+
+    def fit(self, X: np.ndarray, y=None) -> "IndexShift":
+        """
+        Fit the transformer to the input data.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to fit the transformer to.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        self : IndexShift
+            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
+        )
+
+        # Set the number of features
+        self.n_features_in_ = X.shape[1]
+
+        # Set the fitted attribute to True
+        self._is_fitted = True
+
+        # Instantiate the random number generator
+        self._rng = np.random.default_rng(self.random_state)
+
+        return self
+
+    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
+        """
+        Transform the input data by shifting the spectrum.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to transform.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        X_ : np.ndarray of shape (n_samples, n_features)
+            The transformed data.
+        """
+        # Check that the estimator is fitted
+        check_is_fitted(self, "_is_fitted")
+
+        # Check that X is a 2D array and has only finite values
+        X_ = validate_data(
+            self,
+            X,
+            y="no_validation",
+            ensure_2d=True,
+            copy=True,
+            reset=False,
+            dtype=np.float64,
+        )
+
+        # Check that the number of features is the same as the fitted data
+        if X_.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"Expected {self.n_features_in_} features but got {X_.shape[1]}"
+            )
+
+        # Calculate the standard normal variate
+        for i, x in enumerate(X_):
+            X_[i] = self._shift_spectrum(x)
+
+        return X_.reshape(-1, 1) if X_.ndim == 1 else X_
+
+    def _shift_spectrum(self, x) -> np.ndarray:
+        shift_amount = self._rng.integers(-self.shift, self.shift, endpoint=True)
+        return np.roll(x, shift_amount)

chemotools/augmentation/normal_noise.py

@@ -0,0 +1,118 @@
+from typing import Optional
+
+import numpy as np
+from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
+from sklearn.utils.validation import check_is_fitted, validate_data
+
+
+class NormalNoise(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
+    """
+    Add normal noise to the input data.
+
+    Parameters
+    ----------
+    scale : float, default=0.0
+        The scale of the noise to add to the input data.
+
+    random_state : int, default=None
+        The random state to use for the random number generator.
+
+    Attributes
+    ----------
+    n_features_in_ : int
+        The number of features in the input data.
+
+    _is_fitted : bool
+        Whether the transformer has been fitted to data.
+
+    Methods
+    -------
+    fit(X, y=None)
+        Fit the transformer to the input data.
+
+    transform(X, y=0, copy=True)
+        Transform the input data by adding random noise.
+    """
+
+    def __init__(self, scale: float = 0.0, random_state: Optional[int] = None):
+        self.scale = scale
+        self.random_state = random_state
+
+    def fit(self, X: np.ndarray, y=None) -> "NormalNoise":
+        """
+        Fit the transformer to the input data.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to fit the transformer to.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        self : NormalNoise
+            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
+        )
+
+        # Set the number of features
+        self.n_features_in_ = X.shape[1]
+
+        # Set the fitted attribute to True
+        self._is_fitted = True
+
+        # Instantiate the random number generator
+        self._rng = np.random.default_rng(self.random_state)
+
+        return self
+
+    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
+        """
+        Transform the input data by adding random normal noise.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to transform.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        X_ : np.ndarray of shape (n_samples, n_features)
+            The transformed data.
+        """
+        # Check that the estimator is fitted
+        check_is_fitted(self, "_is_fitted")
+
+        # Check that X is a 2D array and has only finite values
+        X_ = validate_data(
+            self,
+            X,
+            y="no_validation",
+            ensure_2d=True,
+            copy=True,
+            reset=False,
+            dtype=np.float64,
+        )
+
+        # Check that the number of features is the same as the fitted data
+        if X_.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"Expected {self.n_features_in_} features but got {X_.shape[1]}"
+            )
+
+        # Calculate the standard normal variate
+        for i, x in enumerate(X_):
+            X_[i] = self._add_random_noise(x)
+
+        return X_.reshape(-1, 1) if X_.ndim == 1 else X_
+
+    def _add_random_noise(self, x) -> np.ndarray:
+        return x + self._rng.normal(0, self.scale, size=x.shape)

chemotools/augmentation/spectrum_scale.py

@@ -0,0 +1,120 @@
+from typing import Optional
+
+import numpy as np
+from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
+from sklearn.utils.validation import check_is_fitted, validate_data
+
+
+class SpectrumScale(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
+    """
+    Scales the data by a value drawn from the uniform distribution centered
+    around 1.0.
+
+    Parameters
+    ----------
+    scale : float, default=0.0
+        Range of the uniform distribution to draw the scaling factor from.
+
+    random_state : int, default=None
+        The random state to use for the random number generator.
+
+    Attributes
+    ----------
+    n_features_in_ : int
+        The number of features in the input data.
+
+    _is_fitted : bool
+        Whether the transformer has been fitted to data.
+
+    Methods
+    -------
+    fit(X, y=None)
+        Fit the transformer to the input data.
+
+    transform(X, y=0, copy=True)
+        Transform the input data by scaling the spectrum.
+    """
+
+    def __init__(self, scale: float = 0.0, random_state: Optional[int] = None):
+        self.scale = scale
+        self.random_state = random_state
+
+    def fit(self, X: np.ndarray, y=None) -> "SpectrumScale":
+        """
+        Fit the transformer to the input data.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to fit the transformer to.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        self : SpectrumScale
+            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
+        )
+
+        # Set the number of features
+        self.n_features_in_ = X.shape[1]
+
+        # Set the fitted attribute to True
+        self._is_fitted = True
+
+        # Instantiate the random number generator
+        self._rng = np.random.default_rng(self.random_state)
+
+        return self
+
+    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
+        """
+        Transform the input data by scaling the spectrum.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to transform.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        X_ : np.ndarray of shape (n_samples, n_features)
+            The transformed data.
+        """
+        # Check that the estimator is fitted
+        check_is_fitted(self, "_is_fitted")
+
+        # Check that X is a 2D array and has only finite values
+        X_ = validate_data(
+            self,
+            X,
+            y="no_validation",
+            ensure_2d=True,
+            copy=True,
+            reset=False,
+            dtype=np.float64,
+        )
+
+        # Check that the number of features is the same as the fitted data
+        if X_.shape[1] != self.n_features_in_:
+            raise ValueError(
+                f"Expected {self.n_features_in_} features but got {X_.shape[1]}"
+            )
+
+        # Calculate the scaled spectrum
+        for i, x in enumerate(X_):
+            X_[i] = self._scale_spectrum(x)
+
+        return X_.reshape(-1, 1) if X_.ndim == 1 else X_
+
+    def _scale_spectrum(self, x) -> np.ndarray:
+        scaling_factor = self._rng.uniform(low=1 - self.scale, high=1 + self.scale)
+        return np.multiply(x, scaling_factor)