发生Python scipy.optimize.fmin_l_bfgs_b错误
发生Python scipy.optimize.fmin_l_bfgs_b错误
提问于 2015-10-28 08:38:56
我的代码是实现一个主动学习算法，使用L优化.我想优化四个参数：alpha、beta、w和gamma。
但是，当我运行下面的代码时，我得到了一个错误：
optimLogitLBFGS = sp.optimize.fmin_l_bfgs_b(func, x0 = x0, args = (X,Y,Z), fprime = func_grad)
File "C:\Python27\lib\site-packages\scipy\optimize\lbfgsb.py", line 188, in fmin_l_bfgs_b
**opts)
File "C:\Python27\lib\site-packages\scipy\optimize\lbfgsb.py", line 311, in _minimize_lbfgsb
isave, dsave)
_lbfgsb.error: failed in converting 7th argument ``g' of _lbfgsb.setulb to C/Fortran array
0-th dimension must be fixed to 22 but got 4我的代码是：
# -*- coding: utf-8 -*-
import numpy as np
import scipy as sp
import scipy.stats as sps
num_labeler = 3
num_instance = 5
X = np.array([[1,1,1,1],[2,2,2,2],[3,3,3,3],[4,4,4,4],[5,5,5,5]])
Z = np.array([1,0,1,0,1])
Y = np.array([[1,0,1],[0,1,0],[0,0,0],[1,1,1],[1,0,0]])
W = np.array([[1,1,1,1],[2,2,2,2],[3,3,3,3]])
gamma = np.array([1,1,1,1,1])
alpha = np.array([1,1,1,1])
beta = 1
para = np.array([1,1,1,1,1,1,1,1,1,2,2,2,2,3,3,3,3,1,1,1,1,1])
def get_params(para):
# extract parameters from 1D parameter vector
assert len(para) == 22
alpha = para[0:4]
beta = para[4]
W = para[5:17].reshape(3, 4)
gamma = para[17:]
return alpha, beta, gamma, W
def log_p_y_xz(yit,zi,sigmati): #log P(y_it|x_i,z_i)
return np.log(sps.norm(zi,sigmati).pdf(yit))#tested
def log_p_z_x(alpha,beta,xi): #log P(z_i=1|x_i)
return -np.log(1+np.exp(-np.dot(alpha,xi)-beta))#tested
def sigma_eta_ti(xi, w_t, gamma_t): # 1+exp(-w_t x_i -gamma_t)^-1
return 1/(1+np.exp(-np.dot(xi,w_t)-gamma_t)) #tested
def df_alpha(X,Y,Z,W,alpha,beta,gamma):#df/dalpha
return np.sum((2/(1+np.exp(-np.dot(alpha,X[i])-beta))-1)*np.exp(-np.dot(alpha,X[i])-beta)*X[i]/(1+np.exp(-np.dot(alpha,X[i])-beta))**2 for i in range (num_instance))
#tested
def df_beta(X,Y,Z,W,alpha,beta,gamma):#df/dbelta
return np.sum((2/(1+np.exp(-np.dot(alpha,X[i])-beta))-1)*np.exp(-np.dot(alpha,X[i])-beta)/(1+np.exp(-np.dot(alpha,X[i])-beta))**2 for i in range (num_instance))
def df_w(X,Y,Z,W,alpha,beta,gamma):#df/sigma * sigma/dw
return np.sum(np.sum((-3)*(Y[i][t]**2-(-np.log(1+np.exp(-np.dot(alpha,X[i])-beta)))*(2*Y[i][t]-1))*(1/(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t])))**4)*(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t])))*(1-(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t]))))*X[i]+(1/(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t])))**2)*(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t])))*(1-(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t]))))*X[i]for t in range(num_labeler)) for i in range (num_instance))
def df_gamma(X,Y,Z,W,alpha,beta,gamma):#df/sigma * sigma/dgamma
return np.sum(np.sum((-3)*(Y[i][t]**2-(-np.log(1+np.exp(-np.dot(alpha,X[i])-beta)))*(2*Y[i][t]-1))*(1/(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t])))**4)*(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t])))*(1-(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t]))))+(1/(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t])))**2)*(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t])))*(1-(1/(1+np.exp(-np.dot(X[i],W[t])-gamma[t]))))for t in range(num_labeler)) for i in range (num_instance))
def func(para, *args):
alpha, beta, gamma, W = get_params(para)
#args
X = args [0]
Y = args[1]
Z = args[2]
return np.sum(np.sum(log_p_y_xz(Y[i][t], Z[i], sigma_eta_ti(X[i],W[t],gamma[t]))+log_p_z_x(alpha, beta, X[i]) for t in range(num_labeler)) for i in range (num_instance))
#tested
def func_grad(para, *args):
alpha, beta, gamma, W = get_params(para)
#args
X = args [0]
Y = args[1]
Z = args[2]
#gradiants
d_f_a = df_alpha(X,Y,Z,W,alpha,beta,gamma)
d_f_b = df_beta(X,Y,Z,W,alpha,beta,gamma)
d_f_w = df_w(X,Y,Z,W,alpha,beta,gamma)
d_f_g = df_gamma(X,Y,Z,W,alpha,beta,gamma)
return np.array([d_f_a, d_f_b,d_f_w,d_f_g])
x0 = np.concatenate([np.ravel(alpha), np.ravel(beta), np.ravel(W), np.ravel(gamma)])
optimLogitLBFGS = sp.optimize.fmin_l_bfgs_b(func, x0 = x0, args = (X,Y,Z), fprime = func_grad) 我不知道问题出在哪里。也许是func_grad造成了这个问题？有人能看看吗？谢谢
Stack Overflow用户
回答已采纳
发布于 2015-10-28 09:09:22
您需要对连接的alpha, beta, w, gamma参数数组中的每个元素使用func的导数，因此func_grad应该返回一个与x0 (即22)长度相同的一维数组。相反，它返回嵌套在np.object数组中的两个数组和两个标量浮动的混乱：
In [1]: func_grad(x0, X, Y, Z)
Out[1]:
array([array([ 0.00681272, 0.00681272, 0.00681272, 0.00681272]),
0.006684719133999417,
array([-0.01351227, -0.01351227, -0.01351227, -0.01351227]),
-0.013639910534587798], dtype=object)部分问题是，np.array([d_f_a, d_f_b,d_f_w,d_f_g])没有将这些对象连接到一个一维数组中，因为有些是numpy数组，有些是Python。这个部分很容易通过使用np.hstack([d_f_a, d_f_b,d_f_w,d_f_g])来解决。
然而，这些对象的合并大小仍然只有10，而func_grad的输出需要一个22长的向量。您需要再看看您的df_*函数。特别地，W是一个(3, 4)数组，但是df_w只返回(4,)向量，gamma是(4,)向量，df_gamma只返回标量。
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/33386294
复制相关文章
相似问题
腾讯云开发者
