从零使用SVM（支持向量积）进行模糊数字分类

数据集

下载数据点击这里！！！
这里下载这俩即可

分别读入训练数据和测试数据

 # 加载训练集数据以及测试集数据
    print('Load Training File Start...')
    # data = pd.read_csv('optdigits.tra', header=None)
    # x, y = data[list(range(64))], data[64]
    # x, y = x.values, y.values
    data = np.loadtxt('optdigits.tra', dtype=np.float, delimiter=',')
    x, y = np.split(data, (-1,), axis=1)
    images = x.reshape(-1, 8, 8)
    print('images.shape = ', images.shape)
    y = y.ravel().astype(np.int)

    print('Load Test Data Start...')
    data = np.loadtxt('optdigits.tes', dtype=np.float, delimiter=',')
    x_test, y_test = np.split(data, (-1,), axis=1)
    print(y_test.shape)
    images_test = x_test.reshape(-1, 8, 8)
    y_test = y_test.ravel().astype(np.int)
    print('Load Data OK...')

绘制部分训练集图像

 # 画出部分训练集图像
    matplotlib.rcParams['font.sans-serif'] = ['SimHei']
    matplotlib.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(15, 9), facecolor='w')
    for index, image in enumerate(images[:16]):
        plt.subplot(4, 8, index + 1)
        plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
        plt.title('训练图片: %i' % y[index])
    for index, image in enumerate(images_test[:16]):
        plt.subplot(4, 8, index + 17)
        plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
        # save_image(image.copy(), index)
        plt.title('测试图片: %i' % y_test[index])
    plt.tight_layout()
    plt.show()

如下图

建模训练并预测

 #  建模训练并做预测
    model = svm.SVC(C=1, kernel='rbf', gamma=0.001)
    print('Start Learning...')
    t0 = time()
    model.fit(x, y)
    t1 = time()
    t = t1 - t0
    print('训练+CV耗时：%d分钟%.3f秒' % (int(t / 60), t - 60 * int(t / 60)))
    # print '最优参数：\t', model.best_params_
    # clf.fit(x, y)
    print('Learning is OK...')
    print('训练集准确率：', accuracy_score(y, model.predict(x)))
    y_hat = model.predict(x_test)
    print('测试集准确率：', accuracy_score(y_test, model.predict(x_test)))
    print(y_hat)
    print(y_test)

输出

寻找预测错误的数据

# 寻找预测错误数据
    err_images = images_test[y_test != y_hat]
    err_y_hat = y_hat[y_test != y_hat]
    err_y = y_test[y_test != y_hat]
    print(err_y_hat)
    print(err_y)

绘制部分预测错误的数据与预测值

# 画出部分预测错误数据
    plt.figure(figsize=(10, 8), facecolor='w')
    for index, image in enumerate(err_images):
        if index >= 12:
            break
        plt.subplot(3, 4, index + 1)
        plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
        plt.title('错分为：%i，真实值：%i' % (err_y_hat[index], err_y[index]))
    plt.tight_layout()
    plt.show()

如下图

全部代码

if __name__ == "__main__":
    # 加载训练集数据以及测试集数据
    print('Load Training File Start...')
    # data = pd.read_csv('optdigits.tra', header=None)
    # x, y = data[list(range(64))], data[64]
    # x, y = x.values, y.values
    data = np.loadtxt('optdigits.tra', dtype=np.float, delimiter=',')
    x, y = np.split(data, (-1,), axis=1)
    images = x.reshape(-1, 8, 8)
    print('images.shape = ', images.shape)
    y = y.ravel().astype(np.int)

    print('Load Test Data Start...')
    data = np.loadtxt('optdigits.tes', dtype=np.float, delimiter=',')
    x_test, y_test = np.split(data, (-1,), axis=1)
    print(y_test.shape)
    images_test = x_test.reshape(-1, 8, 8)
    y_test = y_test.ravel().astype(np.int)
    print('Load Data OK...')

    # x, x_test, y, y_test = train_test_split(x, y, test_size=0.4, random_state=1)
    # images = x.reshape(-1, 8, 8)
    # images_test = x_test.reshape(-1, 8, 8)
    # 画出部分训练集图像
    matplotlib.rcParams['font.sans-serif'] = ['SimHei']
    matplotlib.rcParams['axes.unicode_minus'] = False
    plt.figure(figsize=(15, 9), facecolor='w')
    for index, image in enumerate(images[:16]):
        plt.subplot(4, 8, index + 1)
        plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
        plt.title('训练图片: %i' % y[index])
    for index, image in enumerate(images_test[:16]):
        plt.subplot(4, 8, index + 17)
        plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
        # save_image(image.copy(), index)
        plt.title('测试图片: %i' % y_test[index])
    plt.tight_layout()
    plt.show()

    # params = {'C':np.logspace(0, 3, 7), 'gamma':np.logspace(-5, 0, 11)}
    # model = GridSearchCV(svm.SVC(kernel='rbf'), param_grid=params, cv=3)
    #  建模训练并做预测
    model = svm.SVC(C=1, kernel='rbf', gamma=0.001)
    print('Start Learning...')
    t0 = time()
    model.fit(x, y)
    t1 = time()
    t = t1 - t0
    print('训练+CV耗时：%d分钟%.3f秒' % (int(t / 60), t - 60 * int(t / 60)))
    # print '最优参数：\t', model.best_params_
    # clf.fit(x, y)
    print('Learning is OK...')
    print('训练集准确率：', accuracy_score(y, model.predict(x)))
    y_hat = model.predict(x_test)
    print('测试集准确率：', accuracy_score(y_test, model.predict(x_test)))
    print(y_hat)
    print(y_test)
    # 寻找预测错误数据
    err_images = images_test[y_test != y_hat]
    err_y_hat = y_hat[y_test != y_hat]
    err_y = y_test[y_test != y_hat]
    print(err_y_hat)
    print(err_y)
    # 画出部分预测错误数据
    plt.figure(figsize=(10, 8), facecolor='w')
    for index, image in enumerate(err_images):
        if index >= 12:
            break
        plt.subplot(3, 4, index + 1)
        plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
        plt.title('错分为：%i，真实值：%i' % (err_y_hat[index], err_y[index]))
    plt.tight_layout()
    plt.show()