chapter_4.py 文件源码

def plot_feature_importances(columns, X_train, y_train):
    feat_labels = columns[1:]

    forest = RandomForestClassifier(n_estimators=10000, random_state=0)

    forest.fit(X_train, y_train)
    importances = forest.feature_importances_

    indices = np.argsort(importances)[::-1]

    for f in range(X_train.shape[1]):
        print("%2d) %-*s %f" % (
            f+1,
            30,
            feat_labels[indices[f]],
            importances[indices[f]],
        ))
    print()

    plt.title('Feature Importances')
    plt.bar(
        range(X_train.shape[1]),
        importances[indices],
        color='lightblue',
        align='center',
    )
    plt.xticks(range(X_train.shape[1]), feat_labels[indices], rotation=90)
    plt.xlim([-1, X_train.shape[1]])
    plt.show()

    feature_selector = SelectFromModel(forest, threshold=0.15, prefit=True)
    X_selected = feature_selector.transform(X_train)
    print(X_selected.shape)