building_feature_engineering_pipelines\numeric_prediction_using_pipelines

helpers.py

import numpy as np
import sklearn.base
from sklearn import metrics


class transform_predict(sklearn.base.BaseEstimator, sklearn.base.TransformerMixin):

    def __init__(self, clf: sklearn.base.BaseEstimator):
        self.clf = clf

    def fit(self, *args, **kwargs):
        self.clf.fit(*args, **kwargs)

        return self

    def transform(self, X: np.ndarray, **transform_params):
        pred = self.clf.predict(X)

        return pred.reshape(-1, 1) if len(pred.shape) == 1 else pred


class transform_predict_proba(sklearn.base.BaseEstimator, sklearn.base.TransformerMixin):

    def __init__(self, clf: sklearn.base.ClassifierMixin, drop: bool = True):
        self.clf = clf
        self.drop = drop

    def fit(self, *args, **kwargs):
        self.clf.fit(*args, **kwargs)

        return self

    def transform(self, X: np.ndarray, **transform_params):
        pred = self.clf.predict_proba(X)

        return pred[:, 1:] if self.drop else pred
        
        
def get_regression_metrics(y_true, y_pred):
    print('mean_squared_error', np.round(metrics.mean_squared_error(y_true, y_pred), 4))
    print('explained_variance_score', np.round(metrics.explained_variance_score(y_true, y_pred), 4))
    print('mean_absolute_error', np.round(metrics.mean_absolute_error(y_true, y_pred), 4))
    print('mean_squared_error', np.round(metrics.mean_squared_error(y_true, y_pred), 4))
    print('median_absolute_error', np.round(metrics.median_absolute_error(y_true, y_pred), 4))
    print('r2_score', np.round(metrics.r2_score(y_true, y_pred), 4))

numeric_prediction_using_pipelines.ipynb