基于机器学习的临床决策支持-ANN

DrugAI

发布于 2021-01-28 17:48:19

3230

发布于 2021-01-28 17:48:19

文章被收录于专栏：DrugAI

声明：本文示例来自于GitHub用户vkasojhaa的项目，一切权利归其所有，此处仅是自己学习分享。

实现了基于机器学习的乳腺癌的恶性和良性预测，比较了不同机器学习算法之间的性能。主要目的是评估在每种算法的准确性和效率方面对数据进行分类的正确性。

loss

# 损失值：预估值与实际值之间的均方差

optimizer

# 优化器

trainer = optimizer.minimize(loss)

# 训练：最小化损失函数

基于机器学习(ANN)的乳腺癌预测

代码示例

#导入依赖库
#!/usr/bin/python3

from __future__ import print_function
import keras 
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
from IPython.display import clear_output
from keras.utils import plot_model

#载入数据并进行数据预处理
data = pd.read_csv("data.csv")
data.head()
data.drop('id',axis=1,inplace=True)
data.drop('Unnamed: 32',axis=1,inplace=True)
data['diagnosis'] = data['diagnosis'].map({'M':1,'B':0})
data.head()

print("Row, Col", data.shape)# (row,col)

(data['diagnosis'][:398]==1).sum(),(data['diagnosis'][:398]==0).sum()

(data['diagnosis'][398:]==1).sum(),(data['diagnosis'][398:]==0).sum()

mat=data.as_matrix()
mat.shape
mat

模型训练：

#Using 2 Sigmoid Layers and RMSprop optimizer
model2 = Sequential()
model2.add(Dense(500, activation='sigmoid', use_bias=True, input_shape=(30,)))
model2.add(Dense(1, activation='sigmoid'))
keras.optimizers.RMSprop(lr=0.01, rho=0.9, epsilon=None, decay=0.0)
model2.compile(optimizer='rmsprop',loss='binary_crossentropy', metrics=['accuracy'])

history01 = model2.fit(mat[:,1:],mat[:,0], validation_split=0.3,shuffle=False,epochs=3000, batch_size=128,verbose=0)

score = model2.evaluate(mat[:398,1:],mat[:398,0], verbose=0, batch_size=128)
print('Train loss:', score[0])
print('Train accuracy:', score[1])

Train loss: 0.00821199454791287
Train accuracy: 1.0

score = model2.evaluate(mat[398:,1:],mat[398:,0], verbose=0, batch_size=128)
print('Validation loss:', score[0])
print('Validation accuracy:', score[1])

Validation loss: 0.1262894694568121
Validation accuracy: 0.9473684154755888

plt.plot(history01.history['acc'], label='acc')
plt.plot(history01.history['val_acc'], label='val_acc')
plt.legend()
plt.show()
plt.plot(history01.history['loss'], label='loss')
plt.plot(history01.history['val_loss'], label='val_loss')
plt.legend()
plt.show()
count=0
for i in history01.history['acc']:
    if i>0.99:
        count+=1
print(count)

#Using 3 Sigmoid Layers and RMSprop optimizer
model3 = Sequential()
model3.add(Dense(500, activation='sigmoid', use_bias=True, input_shape=(30,)))
model3.add(Dense(500, activation='sigmoid', use_bias=True))
model3.add(Dense(1, activation='sigmoid'))
keras.optimizers.RMSprop(lr=0.01, rho=0.9, epsilon=None, decay=0.0)
model3.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['accuracy'])

history0 = model3.fit(mat[:,1:],mat[:,0], validation_split=0.3,shuffle=False,epochs=3000, batch_size=128, verbose=0)

score2 = model3.evaluate(mat[:398,1:],mat[:398,0], verbose=0, batch_size=128)
print('Train loss:', score2[0])
print('Train accuracy:', score2[1])

Train loss: 0.011901359889894986
Train accuracy: 0.992462311557789

score2 = model3.evaluate(mat[398:,1:],mat[398:,0], verbose=0, batch_size=128)
print('Validation loss:', score2[0])
print('Validation accuracy:', score2[1])

Validation loss: 0.0804629116945448
Validation accuracy: 0.9707602311296073

plt.plot(history0.history['acc'], label='acc')
plt.plot(history0.history['val_acc'], label='val_acc')
plt.legend()
plt.show()
plt.plot(history0.history['loss'], label='loss')
plt.plot(history0.history['val_loss'], label='val_loss')
plt.legend()
plt.show()
count=0
for i in history0.history['acc']:
    if i>0.99:
        count+=1
print(count)

#Using 3 Sigmoid Layers and RMSprop optimizer
model3 = Sequential()
model3.add(Dense(500, activation='sigmoid', use_bias=True, input_shape=(30,)))
model3.add(Dense(500, activation='sigmoid', use_bias=True))
model3.add(Dense(1, activation='sigmoid'))
keras.optimizers.RMSprop(lr=0.01, rho=0.9, epsilon=None, decay=0.0)
model3.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['accuracy'])

history0 = model3.fit(mat[:,1:],mat[:,0], validation_split=0.3,shuffle=False,epochs=3000, batch_size=128, verbose=0)

score2 = model3.evaluate(mat[:398,1:],mat[:398,0], verbose=0, batch_size=128)
print('Train loss:', score2[0])
print('Train accuracy:', score2[1])

Validation loss: 0.0804629116945448
Validation accuracy: 0.9707602311296073

plt.plot(history0.history['acc'], label='acc')
plt.plot(history0.history['val_acc'], label='val_acc')
plt.legend()
plt.show()
plt.plot(history0.history['loss'], label='loss')
plt.plot(history0.history['val_loss'], label='val_loss')
plt.legend()
plt.show()
count=0
for i in history0.history['acc']:
    if i>0.99:
        count+=1
print(count)

#Using 4 Sigmoid Layers and RMSprop optimizer
model4 = Sequential()
model4.add(Dense(500, activation='sigmoid', use_bias=True, input_shape=(30,)))
model4.add(Dense(500, activation='sigmoid', use_bias=True))
model4.add(Dense(500, activation='sigmoid', use_bias=True))
model4.add(Dense(1, activation='sigmoid'))
keras.optimizers.RMSprop(lr=0.01, rho=0.9, epsilon=None, decay=0.0)
model4.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])

history1 = model4.fit(mat[:,1:],mat[:,0], validation_split=0.3,shuffle=False,epochs=3000, batch_size=128, verbose=0)

#model.evaluate(mat[:,1:],mat[:,0], batch_size=None, verbose=1, sample_weight=None, steps=None)
score = model4.evaluate(mat[:398,1:],mat[:398,0], verbose=0, batch_size=128)
print('Train loss:', score[0])
print('Train accuracy:', score[1])

Train loss: 0.1454299822000403
Train accuracy: 0.9346733668341709

score = model4.evaluate(mat[398:,1:],mat[398:,0], verbose=0, batch_size=128)
print('Validation loss:', score[0])
print('Validation accuracy:', score[1])

Validation loss: 0.33671002412400053
Validation accuracy: 0.8830409339296887

plt.plot(history1.history['acc'], label='acc')
plt.plot(history1.history['val_acc'], label='val_acc')
plt.legend()
plt.show()
plt.plot(history1.history['loss'], label='loss')
plt.plot(history1.history['val_loss'], label='val_loss')
plt.legend()
plt.show()
count=0
for i in history1.history['acc']:
    if i>0.99:
        count+=1
print(count)