手写数字识别——SVM和XGBOOST

下面是训练集和测试集的部分图像

SVM模型代码（进行了调参）：

#!/usr/bin/python
# -*- coding:utf-8 -*-

import numpy as np
import pandas as pd
from sklearn import svm
import matplotlib.colors
import matplotlib.pyplot as plt
from PIL import Image
from sklearn.metrics import accuracy_score
import os
from sklearn.model_selection import GridSearchCV
from time import time


def show_accuracy(a, b, tip):
    acc = a.ravel() == b.ravel()
    print(tip + '正确率：%.2f%%' % (100 * np.mean(acc)))


def save_image(im, i):
    im *= (256 / 17)
    im = 255 - im
    a = im.astype(np.uint8)
    output_path = './HandWritten'
    if not os.path.exists(output_path):
        os.mkdir(output_path)
    Image.fromarray(a).resize(size=(100, 100)).save(output_path + ('\\%d.png' % i))


if __name__ == "__main__":
    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  # 转换为numpy形式，返回DataFrame的Numpy表示。
    images = x.reshape(-1, 8, 8)  # 不知道多少行，反正每一行是一个8*8的矩阵，对应着图片
    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) # axis=1 按行方向拆分数据，也就是水平方向
    print(y_test.shape)
    images_