机器学习之手写数字识别-小数据集

1.手写数字数据集

• from sklearn.datasets import load_digits
• digits = load_digits()

 

from sklearn.datasets import load_digits
digits = load_digits()

　　

2.图片数据预处理

• x：归一化MinMaxScaler()
• y：独热编码OneHotEncoder()或to_categorical
• 训练集测试集划分
• 张量结构

 

import numpy as np
from sklearn.datasets import load_digits
from  sklearn.preprocessing import MinMaxScaler,OneHotEncoder

digits = load_digits()
#数据处理
X_data = digits.data.astype(np.float32)
Y_data = digits.target.astype(np.float32).reshape(-1,1)#将Y_ data变为一列
scale =MinMaxScaler()#归一化
X_data = scale.fit_transform(X_data)
print('MinMaxScaler_trans_X_data:')
print(X_data)

Y = OneHotEncoder().fit_transform(Y_data).todense()#one-hot处理
print('one-hot_Y:')
print(Y)

# 转换为图片的格式
X = X_data.reshape(-1,8,8,1)

from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,Y,test_size=0.2,random_state=0,stratify=Y)
print(X_train.shape,X_test.shape,y_train.shape,y_test.shape)

　　

 

归一化

 

 

one-hot处理

 

 图片格式

 

 划分测试集与训练集

 

 

 

3.设计卷积神经网络结构

 

 

4.模型训练

#导入相关包
from tensorflow.keras.models import Sequential
from  tensorflow.keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D
#建立模型
model = Sequential()
ks = (3, 3)
# 第一层卷积
# 第一层输入数据的shape要指定外，其他层的数据的shape框架会自动推导
model.add(Conv2D(filters=16, kernel_size=ks, padding='same', input_shape=X_train.shape[1:],
                 activation='relu'))
# 池化层
model.add(MaxPool2D(pool_size=(2, 2)))
# 防止过拟合
model.add(Dropout(0.25))
# 第二层卷积
model.add(Conv2D(filters=32, kernel_size=ks, padding='same', activation='relu'))
# 池化层
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# 第三层卷积
model.add(Conv2D(filters=64, kernel_size=ks, padding='same', activation='relu'))
# 第四层卷积
model.add(Conv2D(filters=128, kernel_size=ks, padding='same', activation='relu'))
# 池化层
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())# 平坦层
model.add(Dense(128, activation='relu'))# 全连接层
model.add(Dropout(0.25))
model.add(Dense(10, activation='softmax'))# 激活函数softmax
model.summary()

model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
train_history = model.fit(x=X_train,y=y_train,validation_split=0.2,batch_size=300,epochs=10,verbose=2)
score = model.evaluate(X_test, y_test)
print(score)

训练运行结果如下：

 

 

 

5.模型评价

• model.evaluate()
• 交叉表与交叉矩阵
• pandas.crosstab
• seaborn.heatmap

import seaborn as sns
import pandas as pd

results = model.evaluate(X_test, y_test)
print('评估结果：', results)
# 预测值
y_pred = model.predict_classes(X_test)
print('预测值：', y_pred[:10])
# 交叉表与交叉矩阵
y_test1 = np.argmax(y_test, axis=1).reshape(-1)
y_true = np.array(y_test1)[0]
# 交叉表查看预测数据与原数据对比
c=pd.crosstab(y_true, y_pred, rownames=['true'], colnames=['predict'])
# 交叉矩阵
y_test1 = y_test1.tolist()[0]
a = pd.crosstab(np.array(y_test1), y_pred, rownames=['Lables'], colnames=['Predict'])
df = pd.DataFrame(a)#转换成属dataframe
sns.heatmap(df, annot=True, cmap="RdGy", linewidths=0.2, linecolor='G')
plt.show()

交叉表预测数据与原数据

预测数据与原数据热力图如下

 具体代码如下：

# -*- coding:utf-8 -*-
# 班级：17软件工程一班
# 开发人员：爱飞的大白鲨
# 开发时间：2020/6/8 10:20
# 文件名称：手写数据集及预处理.py
import numpy as np
from sklearn.datasets import load_digits
from  sklearn.preprocessing import MinMaxScaler,OneHotEncoder

digits = load_digits()
#数据处理
X_data = digits.data.astype(np.float32)
Y_data = digits.target.astype(np.float32).reshape(-1,1)#将Y_ data变为一列
scale =MinMaxScaler()#归一化
X_data = scale.fit_transform(X_data)
print('MinMaxScaler_trans_X_data:')
print(X_data)

Y = OneHotEncoder().fit_transform(Y_data).todense()#one-hot处理
print('one-hot_Y:')
print(Y)

# 转换为图片的格式
X = X_data.reshape(-1,8,8,1)

from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,Y,test_size=0.2,random_state=0,stratify=Y)
print(X_train.shape,X_test.shape,y_train.shape,y_test.shape)


#导入相关包
from tensorflow.keras.models import Sequential
from  tensorflow.keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D
#建立模型
model = Sequential()
ks = (3, 3)
# 第一层卷积
# 第一层输入数据的shape要指定外，其他层的数据的shape框架会自动推导
model.add(Conv2D(filters=16, kernel_size=ks, padding='same', input_shape=X_train.shape[1:],
                 activation='relu'))
# 池化层
model.add(MaxPool2D(pool_size=(2, 2)))
# 防止过拟合
model.add(Dropout(0.25))
# 第二层卷积
model.add(Conv2D(filters=32, kernel_size=ks, padding='same', activation='relu'))
# 池化层
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
# 第三层卷积
model.add(Conv2D(filters=64, kernel_size=ks, padding='same', activation='relu'))
# 第四层卷积
model.add(Conv2D(filters=128, kernel_size=ks, padding='same', activation='relu'))
# 池化层
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())# 平坦层
model.add(Dense(128, activation='relu'))# 全连接层
model.add(Dropout(0.25))
model.add(Dense(10, activation='softmax'))# 激活函数softmax
model.summary()

model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
train_history = model.fit(x=X_train,y=y_train,validation_split=0.2,batch_size=300,epochs=10,verbose=2)
score = model.evaluate(X_test, y_test)
print(score)


train_history.history

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['FangSong'] # 指定字体
def show_train_history(train_history, train, validation):
    plt.plot(train_history.history[train])
    plt.plot(train_history.history[validation])
    plt.ylabel('train')
    plt.xlabel('epoch')
    plt.legend(['train', 'validation'], loc='upper left')
    plt.show()


p = plt.figure(figsize=(15, 15))
a1 = p.add_subplot(2, 1, 1)
show_train_history(train_history, 'accuracy', 'val_accuracy')
plt.title("准确率")
a2 = p.add_subplot(2, 1, 2)
show_train_history(train_history, 'loss', 'val_loss')
plt.title("损失率")
plt.show()


import seaborn as sns
import pandas as pd

results = model.evaluate(X_test, y_test)
print('评估结果：', results)
# 预测值
y_pred = model.predict_classes(X_test)
print('预测值：', y_pred[:10])
# 交叉表与交叉矩阵
y_test1 = np.argmax(y_test, axis=1).reshape(-1)
y_true = np.array(y_test1)[0]
# 交叉表查看预测数据与原数据对比
c=pd.crosstab(y_true, y_pred, rownames=['true'], colnames=['predict'])
# 交叉矩阵
y_test1 = y_test1.tolist()[0]
a = pd.crosstab(np.array(y_test1), y_pred, rownames=['Lables'], colnames=['Predict'])
df = pd.DataFrame(a)#转换成属dataframe
sns.heatmap(df, annot=True, cmap="RdGy", linewidths=0.2, linecolor='G')
plt.show()