On Tuesday, January 5, 2016 at 3:26:15 PM UTC-5, Robert wrote: > Hi, > > I run below code, which is downloaded from link: > > http://stackoverflow.com/questions/15513792/expectation-maximization-coin-toss-examples?rq=1 > > > > //////////// > # represent the experiments > head_counts = np.array([5,9,8,4,7]) > tail_counts = 10-head_counts > experiments = zip(head_counts,tail_counts) > > # initialise the pA(heads) and pB(heads) > pA_heads = np.zeros(100); pA_heads[0] = 0.60 > pB_heads = np.zeros(100); pB_heads[0] = 0.50 > > # E-M begins! > delta = 0.001 > j = 0 # iteration counter > improvement = float('inf') > while (improvement>delta): > expectation_A = np.zeros((5,2), dtype=float) > expectation_B = np.zeros((5,2), dtype=float) > for i in range(0,len(experiments)): > e = experiments[i] # i'th experiment > ll_A = get_mn_log_likelihood(e,np.array([pA_heads[j],1-pA_heads[j]])) > # loglikelihood of e given coin A > ll_B = get_mn_log_likelihood(e,np.array([pB_heads[j],1-pB_heads[j]])) > # loglikelihood of e given coin B > > weightA = math.exp(ll_A) / ( math.exp(ll_A) + math.exp(ll_B) ) # > corresponding weight of A proportional to likelihood of A > weightB = math.exp(ll_B) / ( math.exp(ll_A) + math.exp(ll_B) ) # > corresponding weight of B proportional to likelihood of B > > > expectation_A[i] = np.dot(weightA, e) > expectation_B[i] = np.dot(weightB, e) > > print "sum(expectation_A)[0]", sum(expectation_A)[0] > pA_heads[j+1] = sum(expectation_A)[0] / sum(sum(expectation_A)); > pB_heads[j+1] = sum(expectation_B)[0] / sum(sum(expectation_B)); > ////////// > The print message is: > sum(expectation_A)[0] 21.2974818963 > sum(expectation_A)[0] 19.2093824201 > sum(expectation_A)[0] 19.4102767983 > sum(expectation_A)[0] 19.7538328728 > sum(expectation_A)[0] 19.9753285438 > sum(expectation_A)[0] 20.0879016403 > sum(expectation_A)[0] 20.139820175 > sum(expectation_A)[0] 20.1628374165 > > > > When I check below in detail in interactive mode (Canopy Python shell), > > sum(expectation_A)[0] > > it has error: > ///////////// > sum(expectation_A)[0] > --------------------------------------------------------------------------- > IndexError Traceback (most recent call last) > <ipython-input-145-d6f33dff0343> in <module>() > ----> 1 sum(expectation_A)[0] > > IndexError: invalid index to scalar variable. > ////////////// > > I can see expectation_A content with: > > In[146]:expectation_A > Out[146]: > array([[ 0.52278641, 0.52278641], > [ 8.55858656, 0.95095406], > [ 6.75024946, 1.68756237], > [ 0.1260128 , 0.1890192 ], > [ 4.20520218, 1.80222951]]) > > It looks like > sum(expectation_A)[0] > > can run in .py file, while it cannot be run in python shell. > Is it true? > > Thanks,
I just wonder that the cmd line function sum may be different from the .py file used. One is numpy package, the other is a general one. Then, how can I further make it clear for this guess? Thanks, -- https://mail.python.org/mailman/listinfo/python-list
