PLSR_.py

from Packages import *
from Class_Mod.Miscellaneous import * 
from Class_Mod.Regression_metrics import metrics


class PinardPlsr:
    def __init__(self, x_train, y_train, x_test, y_test):
        self.x_train = x_train
        self.x_test = x_test 
        self.y_train = y_train
        self.y_test = y_test

        # create model module with PINARD
        # Declare preprocessing pipeline
        svgolay = [   ('_sg1',pp.SavitzkyGolay()),
                    ('_sg2',pp.SavitzkyGolay())  # nested pipeline to perform the Savitzky-Golay method twice for 2nd order preprocessing
                    ]
        preprocessing = [   ('id', pp.IdentityTransformer()), # Identity transformer, no change to the data
                            ('savgol', pp.SavitzkyGolay()), # Savitzky-Golay smoothing filter
                            ('derivate', pp.Derivate()), # Calculate the first derivative of the data
                            ('SVG', FeatureUnion(svgolay))
                            # Pipeline([('_sg1',pp.SavitzkyGolay()),('_sg2',pp.SavitzkyGolay())])  # nested pipeline to perform the Savitzky-Golay method twice for 2nd order preprocessing
                            ]
        # Declare complete pipeline
        pipeline = Pipeline([
            ('scaler', MinMaxScaler()), # scaling the data
            ('preprocessing', FeatureUnion(preprocessing)), # preprocessing
            ('PLS',  PLSRegression())])
        # Estimator including y values scaling
        estimator = TransformedTargetRegressor(regressor = pipeline, transformer = MinMaxScaler())
        # Training
        self.trained = estimator.fit(self.x_train, self.y_train)


        # fit scores
        # Predictions on test set
        self.yc = pd.DataFrame(self.trained.predict(self.x_train)) # make predictions on test data and assign to Y_preds variable
        self.ycv = pd.DataFrame(cross_val_predict(self.trained, self.x_train, self.y_train, cv = 3)) # make predictions on test data and assign to Y_preds variable
        self.yt = pd.DataFrame(self.trained.predict(self.x_test)) # make predictions on test data and assign to Y_preds variable

        ################################################################################################################
        

        ################################################################################################################

    @property
    def model_(self):
        return self.trained
    
    @property
    def metrics_(self):
        metc = metrics(self.y_train, self.yc)
        metc = metc.evaluate_

        metcv = metrics(self.y_train, self.ycv)
        metcv = metcv.evaluate_

        mett = metrics( self.y_test, self.yt)
        mett = mett.evaluate_
        
        met = pd.concat([metc, metcv, mett], axis = 0)
        met.index = ['calib','cv','test']
        return met

    @property
    def pred_data_(self):
        
        return self.yc, self.ycv, self.yt