Machine Learning with scikit-learn Quick Start Guide

Graphical hyperparameter optimization

In order to optimize the inverse regularization strength, we will plot the accuracy scores for the training and testing sets, using the following code:

import matplotlib.pyplot as plt from sklearn.svm import LinearSVCtraining_scores = []testing_scores = []param_list = [0.0001, 0.001, 0.01, 0.1, 10, 100, 1000]# Evaluate the training and test classification errors for each value of the parameterfor param in param_list:        # Create SVM object and fit        svm = LinearSVC(C = param, random_state = 42)    svm.fit(X_train, y_train)        # Evaluate the accuracy scores and append to lists        training_scores.append(svm.score(X_train, y_train) )    testing_scores.append(svm.score(X_test, y_test) )    # Plot resultsplt.semilogx(param_list, ...