chemotools 0.1.8__py3-none-any.whl → 0.1.10__py3-none-any.whl

chemotools/outliers/studentized_residuals.py

@@ -0,0 +1,197 @@
+from typing import Optional, Union
+import numpy as np
+
+from sklearn.cross_decomposition._pls import _PLS
+from sklearn.pipeline import Pipeline
+from sklearn.utils.validation import validate_data, check_is_fitted
+
+
+from ._base import _ModelResidualsBase, ModelTypes
+from .leverage import calculate_leverage
+
+
+class StudentizedResiduals(_ModelResidualsBase):
+    """
+    Calculate the Studentized Residuals on a _PLS model preditions.
+
+    Parameters
+    ----------
+    model : Union[ModelType, Pipeline]
+        A fitted _PLS model or Pipeline ending with such a model
+
+    Attributes
+    ----------
+    model_ : ModelType
+        The fitted model of type _BasePCA or _PLS
+
+    preprocessing_ : Optional[Pipeline]
+        Preprocessing steps before the model
+
+    References
+    ----------
+
+    """
+
+    def __init__(self, model: Union[_PLS, Pipeline], confidence=0.95) -> None:
+        super().__init__(model, confidence)
+
+    def fit(self, X: np.ndarray, y: Optional[np.ndarray]) -> "StudentizedResiduals":
+        """
+        Fit the model to the input data.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Input data
+
+        y : array-like of shape (n_samples,)
+            Target data
+        """
+        # Validate the input data
+        X = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
+
+        # Preprocess the data
+        if self.preprocessing_:
+            X = self.preprocessing_.transform(X)
+
+        # Calculate y residuals
+        y_residuals = y - self.model_.predict(X)
+        y_residuals = (
+            y_residuals.reshape(-1, 1) if len(y_residuals.shape) == 1 else y_residuals
+        )
+
+        # Calculate the studentized residuals
+        studentized_residuals = calculate_studentized_residuals(
+            self.model_, X, y_residuals
+        )
+
+        # Calculate the critical threshold
+        self.critical_value_ = self._calculate_critical_value(studentized_residuals)
+
+        return self
+
+    def predict(self, X: np.ndarray, y: Optional[np.ndarray]) -> np.ndarray:
+        """Calculate studentized residuals in the model predictions. and return a boolean array indicating outliers.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Input data
+
+        y : array-like of shape (n_samples,)
+            Target data
+
+        Returns
+        -------
+        ndarray of shape (n_samples,)
+            Studentized residuals of the predictions
+        """
+        # Check the estimator has been fitted
+        check_is_fitted(self, ["critical_value_"])
+
+        # Validate the input data
+        X = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
+
+        # Preprocess the data
+        if self.preprocessing_:
+            X = self.preprocessing_.transform(X)
+
+        # Calculate y residuals
+        y_residuals = y - self.model_.predict(X)
+        y_residuals = (
+            y_residuals.reshape(-1, 1) if len(y_residuals.shape) == 1 else y_residuals
+        )
+
+        # Calculate the studentized residuals
+        studentized_residuals = calculate_studentized_residuals(
+            self.model_, X, y_residuals
+        )
+        return np.where(studentized_residuals > self.critical_value_, -1, 1)
+
+    def predict_residuals(
+        self, X: np.ndarray, y: Optional[np.ndarray], validate: bool = True
+    ) -> np.ndarray:
+        """Calculate the studentized residuals of the model predictions.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Input data
+
+        y : array-like of shape (n_samples,)
+            Target values
+
+        Returns
+        -------
+        ndarray of shape (n_samples,)
+            Studentized residuals of the model predictions
+        """
+        # Check the estimator has been fitted
+        check_is_fitted(self, ["critical_value_"])
+
+        # Validate the input data
+        if validate:
+            X = validate_data(self, X, ensure_2d=True, dtype=np.float64)
+
+        # Apply preprocessing if available
+        if self.preprocessing_:
+            X = self.preprocessing_.transform(X)
+
+        # Calculate y residuals
+        y_residuals = y - self.model_.predict(X)
+        y_residuals = (
+            y_residuals.reshape(-1, 1) if len(y_residuals.shape) == 1 else y_residuals
+        )
+
+        return calculate_studentized_residuals(self.model_, X, y_residuals)
+
+    def _calculate_critical_value(self, X: Optional[np.ndarray]) -> float:
+        """Calculate the critical value for outlier detection.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples,)
+            Studentized residuals
+
+        Returns
+        -------
+        float
+            The calculated critical value for outlier detection
+        """
+
+        return np.percentile(X, self.confidence * 100) if X is not None else 0.0
+
+
+def calculate_studentized_residuals(
+    model: ModelTypes, X: np.ndarray, y_residuals: np.ndarray
+) -> np.ndarray:
+    """Calculate the studentized residuals of the model predictions.
+
+    Parameters
+    ----------
+    model : ModelTypes
+        A fitted model
+
+    X : array-like of shape (n_samples, n_features)
+        Input data
+
+    y : array-like of shape (n_samples,)
+        Target values
+
+    Returns
+    -------
+    ndarray of shape (n_samples,)
+        Studentized residuals of the model predictions
+    """
+
+    # Calculate the leverage of the samples
+    leverage = calculate_leverage(model, X)
+
+    # Calculate the standard deviation of the residuals
+    std = np.sqrt(np.sum(y_residuals**2, axis=0) / (X.shape[0] - model.n_components))
+
+    return (y_residuals / (std * np.sqrt(1 - leverage.reshape(-1, 1)))).flatten()

{chemotools-0.1.8.dist-info → chemotools-0.1.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: chemotools
-Version: 0.1.8
+Version: 0.1.10
 Summary: chemotools: A Python Package that Integrates Chemometrics and scikit-learn
 License: MIT
 Author: Pau Cabaneros

{chemotools-0.1.8.dist-info → chemotools-0.1.10.dist-info}/RECORD

@@ -1,8 +1,10 @@
 chemotools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chemotools/augmentation/__init__.py,sha256=_DiyO7M0xztix8Ea_esxe0xjEYHTneJVJZ52bu5WFpg,248
-chemotools/augmentation/_add_noise.py,sha256=4SQFiU9Snl0Dz5EfvRjimpndlNGdXxW2ya3YplHL2fg,3502
+chemotools/augmentation/__init__.py,sha256=ohlRHgRWTkvNpO3RikKtowzboqunQqx0WqtNccuWOHw,397
+chemotools/augmentation/_add_noise.py,sha256=fkTJfIYtZXezcjy6Vz8asIhpBoVp4oaIifppK9vZpM8,4362
 chemotools/augmentation/_baseline_shift.py,sha256=kIlYvmKS9pu9vh_-eZ7PSHPuH_58V9mgYbSJt6Gq3BA,3476
-chemotools/augmentation/_index_shift.py,sha256=w1maDHGLAKSiGAQ8c9yYHofs_PJnxeN0nB1RU-pINcE,6042
+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/_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
@@ -28,6 +30,14 @@ chemotools/derivative/_savitzky_golay.py,sha256=CuCrKoLmrB1YmJ4ihIykgkL3tO3frqkS
 chemotools/feature_selection/__init__.py,sha256=1_i28hIxijjwhMypTy1w2fLbzXXVkKD5IYzzY8ZSuHw,117
 chemotools/feature_selection/_index_selector.py,sha256=lNTP2b7P3doWl30KiAr3Xd2HOMxeUmj24MuqoXl4Voc,3556
 chemotools/feature_selection/_range_cut.py,sha256=lVVVC30ZsK2z9jsDGb_z6l8Ty2I89yM05_dIDbMP73Q,3564
+chemotools/outliers/__init__.py,sha256=wpdlyqU34n1Pb9kGCM4idhcok35WAakxEhzP0xeKaZw,272
+chemotools/outliers/_base.py,sha256=zx9z_Snkvq5YWBoRi_-kRr3a-Q7jTz1zVlrGWycUTb4,5232
+chemotools/outliers/_utils.py,sha256=SDrrDvgEVQyPuKdh0Rw0DD4a8LShbNAQLRwSLICtiYU,2720
+chemotools/outliers/dmodx.py,sha256=R9LaQpUJeDv4GJ0hroKOlFcFbsfQRtrHWD_EI3-TX7Y,4521
+chemotools/outliers/hotelling_t2.py,sha256=Ga1qmlurF_fps9igaTUGOrnUOctIJEYqoCdb468KhY4,5006
+chemotools/outliers/leverage.py,sha256=zgxG2F7ZCf5wRVJeezHSJ2gaUDTP2CvK38Rr-hR6niA,4215
+chemotools/outliers/q_residuals.py,sha256=6_h73A1YxHBcQtjAXOAp1Rb7egHJwj0DQ0MKdnj6aBQ,7647
+chemotools/outliers/studentized_residuals.py,sha256=rF0wObKQV5DCa8THkZcuwdu7u4mBk-dbOHth5tj5cqM,5830
 chemotools/scale/__init__.py,sha256=eztqcHg-TKE1Rr0N9ArfytHk8teuqVfi4SZi2DS96vc,175
 chemotools/scale/_min_max_scaler.py,sha256=YvqRkV2pXu-viQrpjzWcp9KmSSCYSoubSnrZHRLqgKQ,3011
 chemotools/scale/_norm_scaler.py,sha256=CHWSir2q-pL1hxzw_ZB45yi4mw-SkJ4YOa1CUL4nm2I,2568
@@ -43,7 +53,7 @@ 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-0.1.8.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-0.1.10.dist-info/LICENSE,sha256=qtyOy2wDQVX9hxp58h3T-6Lmfv-mSCHoSRkcLUdM9bg,1070
+chemotools-0.1.10.dist-info/METADATA,sha256=fRgOO8cS2JNtNWz_CEG0uKvncSHEJ8myfhm2IOz3y-4,5240
+chemotools-0.1.10.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
+chemotools-0.1.10.dist-info/RECORD,,

{chemotools-0.1.8.dist-info → chemotools-0.1.10.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.0.1
+Generator: poetry-core 2.1.1
 Root-Is-Purelib: true
 Tag: py3-none-any