10，knn手写数字识别

# 导包
import numpy as np
import matplotlib.pyplot as plt
from sklearn.neighbors import KNeighborsClassifier

# 获取数据
feature = []
target = []
for i in range(10):
    for j in range(1,501):
        img_arr = plt.imread('F:/data/%d/%d_%d.bmp'%(i,i,j))
        feature.append(img_arr)
        target.append(i)

feature = np.array(feature)
target = np.array(target)
print(feature.shape,target.shape)

# 测试结果
index = np.random.randint(0,5000,size=1)[0]
print('该索引对应的目标值',target[index])
digit = feature[index]
plt.figure(figsize=(2,2))
plt.imshow(digit,cmap='gray')

# 打乱数据顺序
np.random.seed(3) #按照同一标准打乱
np.random.shuffle(feature)

np.random.seed(3)
np.random.shuffle(target)

# 分别获取训练，测试数据
x_train = feature[:4950]
y_train = target[:4950]
x_test = feature[-50:]
y_test = target[-50:]
x_train.shape   #(4950, 28, 28)

# 特征数据必须保证是二维
x_train = x_train.reshape(4950,784)
#像素点一共784个，倒着数为-1
x_test = x_test.reshape(50,-1)

# 建立knn对象
knn = KNeighborsClassifier(n_neighbors=15)
knn.fit(x_train,y_train)
knn.score(x_train,y_train)

# 比对结果
y_ = knn.predict(x_test)
print('真实:',y_test)
print('预测:',y_)

#模型保存
from sklearn.externals import joblib
joblib.dump(knn,'./knn.m')

knn = joblib.load('./knn.m')
# 让模型进行外部模型的识别操作
img_arr = plt.imread('F:/数字.jpg')
plt.imshow(img_arr)

five_img = img_arr[95:150,85:130]
plt.imshow(five_img)
five_img.shape
# 对目标照片进行降维
five_img = five_img.mean(axis=2)

# 将照片的像素压缩成和样本同样的像素，即28*28
import scipy.ndimage as ndimage
five_img.shape
five = ndimage.zoom(five_img,zoom=(28/55,28/45))

five.shape
knn.predict(five.reshape(1,784))
最终获得结果