stateCovs = np.expand_dims(stateCovs,1) #model = GaussianHMM(len(states),covariance_type="full",n_iter=1); model = GaussianHMM(numStates,covariance_type="full", n_iter=1); ###insert my own params model.means_ = stateMeans; model.covars_ = stateCovs; ### make transmat if args.transition <= -100: transitionMatrix = (1-np.eye(numStates))*args.transition*np.log(10); model._log_transmat =transitionMatrix; else: transitionMatrix = np.add(np.eye(numStates)*(1-(numStates-1)*10**args.transition),(1-np.eye(numStates))*10**args.transition); model._set_transmat(transitionMatrix); if args.verbose>0: sys.stderr.write(np.array_str(model._log_transmat)+"\n"); #exit; meanNormal = meanAll; normalState = cnvsToStateIs[args.ploidy]; lastClass = {}; for chr in chrOrder: lastClass[chr] = np.tile(args.ploidy,allData[chr].shape[0]); for i in range(0,args.iterations): warned=False; if args.verbose>1: sys.stderr.write(" Iteration %i.\n"%(i)); viterbi = {}