手写数字识别

import matplotlib.pyplot as plt
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
import joblib
from collections import Counter


def show_digit(idx):
    # 加载数据
    data = pd.read_csv('data/手写数字识别.csv')
    if idx < 0 or idx > len(data) - 1:
        return
    x = data.iloc[:, 1:]
    y = data.iloc[:,0]
    print('当前数字的标签为:',y[idx])

    # data 修改为 ndarray 类型
    data_ = x.iloc[idx].values
    # 将数据形状修改为 28*28
    data_ = data_.reshape(28, 28)
    # 关闭坐标轴标签
    plt.axis('off')
    # 显示图像
    plt.imshow(data_)
    plt.show()


def train_model():

    # 1. 加载手写数字数据集
    data = pd.read_csv('data/手写数字识别.csv')
    x = data.iloc[:, 1:] / 255
    y = data.iloc[:, 0]

    # 2. 打印数据基本信息
    print('数据基本信息:', x.shape)
    print('类别数据比例:', Counter(y))

    # 3. 分割数据集
    split_data = train_test_split(x, y, test_size=0.2, stratify=y, random_state=0)
    x_train, x_test, y_train, y_test = split_data

    # 4. 模型训练
    estimator = KNeighborsClassifier(n_neighbors=3)
    estimator.fit(x_train, y_train)

    # 5. 模型评估
    acc = estimator.score(x_test, y_test)
    print('测试集准确率: %.2f' % acc)

    # 6. 模型保存
    joblib.dump(estimator, 'model/knn.pth')


def test_model():
    # 读取图片数据
    import matplotlib.pyplot as plt
    import joblib
    img = plt.imread('temp/demo.png')
    plt.imshow(img)
    # 加载模型
    knn = joblib.load('model/knn.pth')
    y_pred = knn.predict(img.reshape(1, -1))
    print('您绘制的数字是:', y_pred)


if __name__ == '__main__':
        # 显示部分数字
    show_digit(1)
    # 训练模型
    train_model()
    # 测试模型
    test_model()