chemotools 0.1.7__py3-none-any.whl → 0.1.8__py3-none-any.whl

chemotools/augmentation/__init__.py

@@ -1,16 +1,12 @@
-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
+from ._add_noise import AddNoise
+from ._baseline_shift import BaselineShift
+from ._index_shift import IndexShift
+from ._spectrum_scale import SpectrumScale
 
 
 __all__ = [
+    "AddNoise",
     "BaselineShift",
-    "ExponentialNoise",
-    "NormalNoise",
     "IndexShift",
     "SpectrumScale",
-    "UniformNoise",
 ]

chemotools/augmentation/{normal_noise.py → _add_noise.py}

@@ -1,44 +1,26 @@
-from typing import Optional
+from typing import Literal, 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):
+class AddNoise(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):
+    def __init__(
+        self,
+        noise_distribution: Literal["gaussian", "poisson", "exponential"] = "gaussian",
+        scale: float = 0.0,
+        random_state: Optional[int] = None,
+    ):
+        self.noise_distribution = noise_distribution
         self.scale = scale
         self.random_state = random_state
 
-    def fit(self, X: np.ndarray, y=None) -> "NormalNoise":
+    def fit(self, X: np.ndarray, y=None) -> "AddNoise":
         """
         Fit the transformer to the input data.
 
@@ -110,9 +92,23 @@ class NormalNoise(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
 
         # Calculate the standard normal variate
         for i, x in enumerate(X_):
-            X_[i] = self._add_random_noise(x)
+            match self.noise_distribution:
+                case "gaussian":
+                    X_[i] = self._add_gaussian_noise(x)
+                case "poisson":
+                    X_[i] = self._add_poisson_noise(x)
+                case "exponential":
+                    X_[i] = self._add_exponential_noise(x)
+                case _:
+                    raise ValueError("Invalid noise distribution")
 
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
 
-    def _add_random_noise(self, x) -> np.ndarray:
+    def _add_gaussian_noise(self, x) -> np.ndarray:
         return x + self._rng.normal(0, self.scale, size=x.shape)
+
+    def _add_poisson_noise(self, x) -> np.ndarray:
+        return self._rng.poisson(x, size=x.shape) * self.scale
+
+    def _add_exponential_noise(self, x) -> np.ndarray:
+        return x + self._rng.exponential(self.scale, size=x.shape)

{chemotools-0.1.7.dist-info → chemotools-0.1.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: chemotools
-Version: 0.1.7
+Version: 0.1.8
 Summary: chemotools: A Python Package that Integrates Chemometrics and scikit-learn
 License: MIT
 Author: Pau Cabaneros

{chemotools-0.1.7.dist-info → chemotools-0.1.8.dist-info}/RECORD

@@ -1,11 +1,9 @@
 chemotools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chemotools/augmentation/__init__.py,sha256=xIUoWov_aluoW5L3zpVAahyPdkWA5erApW-duzdE_9A,385
-chemotools/augmentation/baseline_shift.py,sha256=kIlYvmKS9pu9vh_-eZ7PSHPuH_58V9mgYbSJt6Gq3BA,3476
-chemotools/augmentation/exponential_noise.py,sha256=fhZ4zQGGqmW-OiSu388th6IhgXrFj1xOguqKYAgj8Y4,3348
-chemotools/augmentation/index_shift.py,sha256=w1maDHGLAKSiGAQ8c9yYHofs_PJnxeN0nB1RU-pINcE,6042
-chemotools/augmentation/normal_noise.py,sha256=-se2Xv1pAWt9HY7H5yC4XlxRArPKZWGeTy2MdyN4lBE,3318
-chemotools/augmentation/spectrum_scale.py,sha256=hMsmzXpssbI7tGm_YnQn9wjbByso3CgVxd3Hs8kfLS8,3442
-chemotools/augmentation/uniform_noise.py,sha256=8a-AYzEDIkLckL6FK2i8mr_jXnQGcFaKXh_roGCICaQ,3456
+chemotools/augmentation/__init__.py,sha256=_DiyO7M0xztix8Ea_esxe0xjEYHTneJVJZ52bu5WFpg,248
+chemotools/augmentation/_add_noise.py,sha256=4SQFiU9Snl0Dz5EfvRjimpndlNGdXxW2ya3YplHL2fg,3502
+chemotools/augmentation/_baseline_shift.py,sha256=kIlYvmKS9pu9vh_-eZ7PSHPuH_58V9mgYbSJt6Gq3BA,3476
+chemotools/augmentation/_index_shift.py,sha256=w1maDHGLAKSiGAQ8c9yYHofs_PJnxeN0nB1RU-pINcE,6042
+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
 chemotools/baseline/_ar_pls.py,sha256=Cl0tN0DGQA8JpnbIge4cBqT7aGQ7yltppYEDI6tWqiM,4385
@@ -45,7 +43,7 @@ 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-0.1.7.dist-info/LICENSE,sha256=qtyOy2wDQVX9hxp58h3T-6Lmfv-mSCHoSRkcLUdM9bg,1070
-chemotools-0.1.7.dist-info/METADATA,sha256=cLjx8z4fGKdTHdIyDZ1VGd6WgXX-WlXtw9OwqaYm0Fo,5239
-chemotools-0.1.7.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
-chemotools-0.1.7.dist-info/RECORD,,
+chemotools-0.1.8.dist-info/LICENSE,sha256=qtyOy2wDQVX9hxp58h3T-6Lmfv-mSCHoSRkcLUdM9bg,1070
+chemotools-0.1.8.dist-info/METADATA,sha256=gK71zOTZyaFxCqjxXGGKfQi4TvN43AXhBIaWdMWVJh4,5239
+chemotools-0.1.8.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
+chemotools-0.1.8.dist-info/RECORD,,

chemotools/augmentation/exponential_noise.py

@@ -1,117 +0,0 @@
-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/uniform_noise.py

@@ -1,124 +0,0 @@
-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 UniformNoise(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
-    """
-    Add uniform noise to the input data.
-
-    Parameters
-    ----------
-    min : float, default=0.0
-        The lower bound of the uniform distribution.
-
-    max : float, default=0.0
-        The upper bound of the uniform distribution.
-
-    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, min: float = 0.0, max: float = 0.0, random_state: Optional[int] = None
-    ):
-        self.min = min
-        self.max = max
-        self.random_state = random_state
-
-    def fit(self, X: np.ndarray, y=None) -> "UniformNoise":
-        """
-        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 : UniformNoise
-            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 uniform 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 uniform 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.uniform(self.min, self.max, size=x.shape)