generate_model.py 文件源码

def generate_model(data, classes, args):

    # Define the parameters
    tuned_parameters = {'C': C_RANGE,
                        'class_weight': CLASS_WEIGHTS}

    # Define the classifier
    if args.kernel == 'rbf':
        clf = svm.SVC(cache_size=CACHE_SIZE)
        tuned_parameters['gamma'] = GAMMA_RANGE
    else:
        clf = svm.LinearSVC(dual=False)

    print_verbose("Classifier: %s" % str(clf), 5)
    print_verbose("Parameters: %s" % str(tuned_parameters), 5)

    # Generate the K-fold development
    skf = cross_validation.StratifiedKFold(classes, n_folds=K_FOLD, shuffle=True)
    print_verbose("KFold: %s" % str(skf), 5)

    # Generate the grid search
    if args.search == 'grid':
        gscv = grid_search.GridSearchCV(clf, tuned_parameters, cv=skf, scoring='f1',
                                        n_jobs=1, verbose=get_verbose_level())
    else:
        gscv = grid_search.RandomizedSearchCV(clf, tuned_parameters, cv=skf, scoring='f1',
                                              n_jobs=1, verbose=get_verbose_level(), n_iter=args.iter)

    # Search
    print_verbose("GridSearch: %s" % str(gscv), 5)
    gscv.fit(data, classes)

    # Print scores
    print_verbose("GridSearch scores:", 5)
    for params, mean_score, scores in gscv.grid_scores_:
        print_verbose("%0.6f (+/-%0.06f) for %r"
                      % (mean_score, scores.std() / 2, params), 5)

    # Print best score
    print_verbose("GridSearch best score:", 0)
    print_verbose("%0.6f for %r" % (gscv.best_score_, gscv.best_params_), 0)

    return gscv