python数据分析——手写数字识别

import numpy as np
# bmp 图片后缀
import matplotlib.pyplot as plt
%matplotlib inline

from sklearn.neighbors import KNeighborsClassifier

img_arr = plt.imread(‘./data/3/3_100.bmp‘)
plt.imshow(img_arr)

#./data/3/3_100.bmp

feature = []
target = []
for i in range(0,10):
    for j in range(1,501):
        img_path = ‘./data/‘+str(i)+‘/‘+str(i)+‘_‘+str(j)+‘.bmp‘
        img_arr = plt.imread(img_path)
        feature.append(img_arr)
        target.append(i)

len(feature)

feature = np.array(feature)

feature.shape

# 特征数据必须保证是二维的
# feature是一个三维数组（执行将维操作）
feature = feature.reshape(5000,28*28)

feature.shape

target = np.array(target)

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

x_train = feature[:4950]
y_train = target[:4950]
x_test = feature[-50:]
y_test = target[-50:]

knn = KNeighborsClassifier(n_neighbors=30)
knn.fit(x_train,y_train)
knn.score(x_train,y_train)

print(‘预测分类:‘,knn.predict(x_test))
print(‘真实数据:‘,y_test)

from sklearn.externals import joblib

joblib.dump(knn,‘./digist.m‘)

knn = joblib.load(‘./digist.m‘)

#外部图片的识别
img_arr = plt.imread(‘./数字.jpg‘)
plt.imshow(img_arr)

five_arr = img_arr[90:155,80:135]

plt.imshow(five_arr)

five_arr.shape

#five数组是三维的，需要进行降维，舍弃第三个表示颜色的维度
five_arr = five_arr.mean(axis=2)

five_arr.shape

import scipy.ndimage as ndimage

five = ndimage.zoom(five_arr,zoom = (28/65,28/55))

five.shape

# 转换为（1,784）形式
knn.predict(five.reshape(1,784))