0
我很困惑爲什麼我得到錯誤ValueError: setting an array element with a sequence.當我試圖最小化的函數顯式返回並接受一個向量。使用scipy優化2次迭代後的ValueError儘管顯式返回1d數組
這裏是我的實現，這是多項Logistic迴歸從http://czep.net/stat/mlelr.pdf
from __future__ import division
import os
import re
import numpy as np
import pandas as pd
from collections import defaultdict, Counter, OrderedDict
cont_data = pd.read_csv('data.csv', sep=' ')
cont_data['age'] = [np.mean(map(int, x.split('_'))) for x in cont_data['age']]
d = cont_data.drop('age', axis=1)
# vector n contains the number of members in each group
n = d.sum(axis=1)
K = 1 # we are using 0 based indexing
J = 2
# matrix y is the input data with the baseline class dropped
y = d.drop('none', axis=1)
# design matrix
X = np.array([[age ** k for k in xrange(K + 2)] for age in cont_data.age])
# calculate pi following equations 24 and 25
def calculate_pi_i_j(i, j, b):
try:
return np.exp(np.sum([X[i][k] * b[k][j] for k in xrange(K)]))
except Exception, e:
assert False, (e, i, j, k, b)
def calc_prob(i, j, b):
num = calculate_pi_i_j(i, j, b)
denom = 1 + np.sum([calculate_pi_i_j(i, j, b) for j in xrange(J - 1)])
return num/denom
def calculate_pi(b):
# calculate pi for the first 2 columns
pi = np.array([[calc_prob(i, j, b) for j in xrange(J - 1)] for i in xrange(len(n))])
# calculate pi for the last column where J=J
pi_j = np.array([1/(1 + np.sum([calculate_pi_i_j(i, j, b) for j in xrange(J - 1)])) for i in xrange(len(n))])
return np.hstack([pi, pi_j.reshape(len(n), 1)])
# equation to optimize
def eqn_32(b):
# b comes in as a vector
b = b.reshape(3, 2)
pi = calculate_pi(b)
r = [] # will hold the result of the gradient calculation for each member of beta
try:
for k in xrange(b.shape[0]):
for j in xrange(b.shape[1]):
r.append(np.sum([(y.iloc[i][j] * X[i][k]) * (n.iloc[i] * pi[i][j] * X[i][k]) for i in xrange(len(n))]))
except Exception, e:
assert False, (e, k, j, b)
print r
return np.array(r)
from scipy.optimize import *
# starting values for coefficients
b = np.zeros(6)
#minimize(eqn_32, x0=b, method='Nelder-Mead')
fmin_bfgs(eqn_32, x0=b)
適應那裏data.csv包含：
age ster other none
15_19 3 61 232
20_24 80 137 400
25_29 216 131 301
30_34 268 76 203
35_39 197 50 188
40_44 150 24 164
45_49 91 10 183
正如你所看到的，b最初的6陣列，並且返回值r是一個6成員列表，然後將其轉換爲數組。當我使用調試打印語句運行代碼時可以看到這一點：
[249525.5, 130873.5, 270069249.5, 100471089.0, 342109256925.5, 94938609711.0]
[249525.50185910985, 130873.49902491644, 270069251.5121727, 100471088.25143206, 342109259474.41266, 94938609003.652222]
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-8-edd793c643e2> in <module>()
67 b = np.zeros(6)
68 #minimize(eqn_32, x0=b, method='Nelder-Mead')
---> 69 fmin_bfgs(eqn_32, x0=b)
/Users/ifiddes/anaconda/lib/python2.7/site-packages/scipy/optimize/optimize.pyc in fmin_bfgs(f, x0, fprime, args, gtol, norm, epsilon, maxiter, full_output, disp, retall, callback)
791 'return_all': retall}
792
--> 793 res = _minimize_bfgs(f, x0, args, fprime, callback=callback, **opts)
794
795 if full_output:
/Users/ifiddes/anaconda/lib/python2.7/site-packages/scipy/optimize/optimize.pyc in _minimize_bfgs(fun, x0, args, jac, callback, gtol, norm, eps, maxiter, disp, return_all, **unknown_options)
845 else:
846 grad_calls, myfprime = wrap_function(fprime, args)
--> 847 gfk = myfprime(x0)
848 k = 0
849 N = len(x0)
/Users/ifiddes/anaconda/lib/python2.7/site-packages/scipy/optimize/optimize.pyc in function_wrapper(*wrapper_args)
287 def function_wrapper(*wrapper_args):
288 ncalls[0] += 1
--> 289 return function(*(wrapper_args + args))
290
291 return ncalls, function_wrapper
/Users/ifiddes/anaconda/lib/python2.7/site-packages/scipy/optimize/optimize.pyc in approx_fprime(xk, f, epsilon, *args)
620
621 """
--> 622 return _approx_fprime_helper(xk, f, epsilon, args=args)
623
624
/Users/ifiddes/anaconda/lib/python2.7/site-packages/scipy/optimize/optimize.pyc in _approx_fprime_helper(xk, f, epsilon, args, f0)
560 ei[k] = 1.0
561 d = epsilon * ei
--> 562 grad[k] = (f(*((xk + d,) + args)) - f0)/d[k]
563 ei[k] = 0.0
564 return grad
ValueError: setting an array element with a sequence.
爲什麼在2次迭代後失敗？