print('{}: w = {}'.format(i, w.T[0, :]))
for j in range(n):
for sign in [-1, 1]:
w_test = w.copy()
w_test[j, 0] += eps * sign
test_error = rss(X, y, w_test)
if test_error < min_error:
min_error = test_error
w = w_test
all_ws[i, :] = w.T
return all_ws
if '__main__' == __name__:
X, y = load_data('abalone.txt')
X, y = standarize(X), standarize(y)
epsilon = 0.005
niter = 1000
all_ws = stagewise_regression(X, y, eps=epsilon, niter=niter)
w = all_ws[-1, :]
y_prime = X * w.T
# 计算相关系数
corrcoef = get_corrcoef(np.array(y.reshape(1, -1)),
np.array(y_prime.reshape(1, -1)))
print('Correlation coefficient: {}'.format(corrcoef))
# 绘制逐步线性回归回归系数变化轨迹
def lasso_traj(X, y, ntest=30):
''' 获取回归系数轨迹矩阵
'''
_, n = X.shape
ws = np.zeros((ntest, n))
for i in range(ntest):
print(u'lasso_traj【30次】ntest:', i)
w = lasso_regression(X, y, lambd=exp(i - 10))
ws[i, :] = w.T
#print('lambda = e^({}), w = {}'.format(i-10, w.T[0, :]))
return ws
if '__main__' == __name__:
# 对于单因变量
X, y = load_data('NYHXB.txt')
#对于多因变量
X, y = standarize(X), standarize(y)
ntest = 30
#绘制轨迹
ws = lasso_traj(X, y, ntest)
#ws = lasso_traj(XX, yy, ntest)
print(u'回归系数轨迹ws:', ws, np.shape(ws))
fig = plt.figure()
ax = fig.add_subplot(111)
lambdas = [i - 0 for i in range(ntest)]
plt.title(u'NYHXB')
plt.xlabel('Iteration')
plt.ylabel('w')
ax.plot(lambdas, ws)
plt.show()
# 获取此点相应的回归系数
xWx = X.T * W * X
if np.linalg.det(xWx) == 0:
print('xWx is a singular matrix')
return
w = xWx.I * X.T * W * Y
return w
if '__main__' == __name__:
k = 0.03
X, Y = load_data('ex0.txt')
y_prime = []
for x in X.tolist():
w = lwlr(x, X, Y, k).reshape(1, -1).tolist()[0]
y_prime.append(np.dot(x, w))
corrcoef = get_corrcoef(np.array(Y.reshape(1, -1)), np.array(y_prime))
print('Correlation coefficient: {}'.format(corrcoef))
fig = plt.figure()
ax = fig.add_subplot(111)
# 绘制数据点
x = X[:, 1].reshape(1, -1).tolist()[0]
y = Y.reshape(1, -1).tolist()[0]
return w
def lasso_traj(X, y, ntest=30):
''' 获取回归系数轨迹矩阵
'''
_, n = X.shape
ws = np.zeros((ntest, n))
for i in range(ntest):
w = lasso_regression(X, y, lambd=exp(i-10))
ws[i, :] = w.T
print('lambda = e^({}), w = {}'.format(i-10, w.T[0, :]))
return ws
if '__main__' == __name__:
X, y = load_data('abalone.txt')
X, y = standarize(X), standarize(y)
# w = lasso_regression(X, y, lambd=10)
#
# y_prime = X*w
# # 计算相关系数
# corrcoef = get_corrcoef(np.array(y.reshape(1, -1)),
# np.array(y_prime.reshape(1, -1)))
# print('Correlation coefficient: {}'.format(corrcoef))
ntest = 30
# 绘制轨迹
ws = lasso_traj(X, y, ntest)
fig = plt.figure()
W[i, i] = exp((np.linalg.norm(x - xi))/(-2*k**2))
# 获取此点相应的回归系数
xWx = X.T*W*X
if np.linalg.det(xWx) == 0:
print('xWx is a singular matrix')
return
w = xWx.I*X.T*W*Y
return w
if '__main__' == __name__:
k = 0.03
X, Y = load_data('ex0.txt')
y_prime = []
for x in X.tolist():
w = lwlr(x, X, Y, k).reshape(1, -1).tolist()[0]
y_prime.append(np.dot(x, w))
corrcoef = get_corrcoef(np.array(Y.reshape(1, -1)), np.array(y_prime))
print('Correlation coefficient: {}'.format(corrcoef))
fig = plt.figure()
ax = fig.add_subplot(111)
# 绘制数据点
x = X[:, 1].reshape(1, -1).tolist()[0]
y = Y.reshape(1, -1).tolist()[0]
def lasso_traj(X, y, ntest=30):
''' 获取回归系数轨迹矩阵
'''
_, n = X.shape
ws = np.zeros((ntest, n))
for i in range(ntest):
w = lasso_regression(X, y, lambd=exp(i-10))
ws[i, :] = w.T
#print('lambda = e^({}), w = {}'.format(i-10, w.T[0, :]))
return ws
if '__main__' == __name__:
# 对于单因变量
X, y = load_data('bingji_28.txt')
#对于多因变量
#XX, yy = load_data00('MXPC.txt')
#print'xx:',xx
X, y = standarize(X), standarize(y)
#XX, yy = standarize(XX), standarize(yy)
#w = lasso_regression(X, y, lambd=10)
#y_prime = X*w
#计算相关系数
#corrcoef = get_corrcoef(np.array(y.reshape(1, -1)),
#np.array(y_prime.reshape(1, -1)))
#print('Correlation coefficient: {}'.format(corrcoef))
ntest = 30
#绘制轨迹