从0开始机器学习--Day16--神经网络作业
题目：构建逻辑回归模型来辨认数字0-9代码如下：
import numpy as np
from scipy.io import loadmat
import scipy.optimize as opt
from sklearn.metrics import classification_report
# 定义函数sigmoid，方便后续假设函数以sigmoid（z）表示
def sigmoid(z):
return 1 / (1 + np.exp(-z))
# 定义代价函数
def computeCost (theta, X, y, l=1 ):
predictions = sigmoid(X @ theta)
first = y * np.log(predictions)
second = (1 - y) * np.log(1 - predictions)
reg = theta@theta*(l/(2*len(X))) #正则化项
return -np.sum(first + second)/len(X) +reg# 返回标量
def gradient(theta, X, y, l=1):
reg = theta * (l/len(X))
reg = np.insert(reg, 0, values=0, axis=0)
first = (X.T@(sigmoid(X@theta)-y))/len(X)
return first + reg
def one_vs_all(X, y, l=1, K = 10):
n = X.shape
theta = np.zeros((K, n)) #创建与X的列数相同长度的0数组
for i in range(1, K+1):
theta_i = np.zeros(n, )
res = opt.minimize(fun=computeCost,
x0=theta_i,
args=(X, y==i, l),
method='TNC',
jac=gradient)
theta = res.x
return theta
def predict(X, theta):
h = sigmoid(X@theta.T)
h_argmax = np.argmax(h, axis=1)
return h_argmax + 1
data = loadmat('ex3data1.mat')
raw_x = data['X']
raw_y = data['y']
X = np.insert(raw_x, 0, values=np.ones(raw_x.shape), axis=1)
y = raw_y.flatten()
print(y.shape)
theta_all = one_vs_all(X, y, l=1, K=10)
print(theta_all)
y_pred = predict(X, theta_all)
acc = np.mean(y_pred == y)
print(acc)
print(classification_report(y, y_pred))
输出：
(5000,)
[[-2.38017165e+000.00000000e+000.00000000e+00 ...1.30445260e-03
-7.38340466e-100.00000000e+00]
[-3.18105182e+000.00000000e+000.00000000e+00 ...4.45068628e-03
-5.07434671e-040.00000000e+00]
[-4.79899590e+000.00000000e+000.00000000e+00 ... -2.86819678e-05
-2.48325958e-070.00000000e+00]
...
[-7.98439304e+000.00000000e+000.00000000e+00 ... -8.94750803e-05
7.22839979e-060.00000000e+00]
[-4.57041525e+000.00000000e+000.00000000e+00 ... -1.33611163e-03
9.99192279e-050.00000000e+00]
[-5.40239782e+000.00000000e+000.00000000e+00 ... -1.16450568e-04
7.86669421e-060.00000000e+00]]
0.9446
precision recallf1-score support
1 0.95 0.99 0.97 500
2 0.95 0.92 0.93 500
3 0.95 0.91 0.93 500
4 0.95 0.95 0.95 500
5 0.92 0.92 0.92 500
6 0.97 0.98 0.97 500
7 0.95 0.95 0.95 500
8 0.93 0.92 0.92 500
9 0.92 0.92 0.92 500
10 0.97 0.99 0.98 500
accuracy 0.94 5000
macro avg 0.94 0.94 0.94 5000
weighted avg 0.94 0.94 0.94 5000 用神经网络前向传播计算正确率代码：
from scipy.io import loadmat
import numpy as np
from sklearn.metrics import classification_report
def sigmoid(z):
return 1 / (1 + np.exp(-z))
data = loadmat('ex3data1.mat')
raw_x = data['X']
raw_y = data['y']
X = np.insert(raw_x, 0, values=np.ones(raw_x.shape), axis=1)
y = raw_y.flatten()
print(y.shape)
theta = loadmat('ex3weights.mat')
theta1 = theta['Theta1']
theta2 = theta['Theta2']
a1 = X
z2 = X@theta1.T
a2 = sigmoid(z2)
a2 = np.insert(a2, 0, values=1, axis=1)
z3 = a2@theta2.T
a3 = sigmoid(z3)
y_pred = np.argmax(a3, axis=1) + 1
acc = np.mean(y_pred == y)
print(acc)
print(classification_report(y, y_pred))
输出：
(5000,)
0.9752
precision recallf1-score support
1 0.97 0.98 0.98 500
2 0.98 0.97 0.98 500
3 0.98 0.96 0.97 500
4 0.97 0.97 0.97 500
5 0.97 0.98 0.98 500
6 0.98 0.99 0.98 500
7 0.98 0.97 0.97 500
8 0.98 0.98 0.98 500
9 0.97 0.96 0.96 500
10 0.98 0.99 0.99 500
accuracy 0.98 5000
macro avg 0.98 0.98 0.98 5000
weighted avg 0.98 0.98 0.98 5000 总结：在构建多元分类的模型中，方法就是将其转化为二元分类，再做循环计算，如许每次只必要将本身看做为0或1即可，注意其每次循环时要取概率最高的那次才有意义。用神经网络时，其结果有点过于抱负了，怀疑是出现了过拟合现象。
视频订正参考：【作业讲解】编程作业3：神经网络（上）_哔哩哔哩_bilibili
免责声明：如果侵犯了您的权益，请联系站长，我们会及时删除侵权内容，谢谢合作！更多信息从访问主页：qidao123.com:ToB企服之家，中国第一个企服评测及商务社交产业平台。
页:
[1]