def discover(args):
datafile = args.datafile
outputfile = args.output
paramsfile = args.params
sample_req = args.sample
sample_flag = False #used to check whether sample_req exists
print 'Loading data file...'
dataloader = DataManager(datafile)
params = dataloader.getParams(paramsfile)
dataloader.skipHeadline()
sample = dataloader.getNextSample()
targets_list = dataloader.getTargetsList()
output = file(outputfile, 'w')
output.write(
'SAMPLE_ID\tCNV\tFULL_INTERVAL\tINDEX\tINTERVAL\tREAD_DEPTH\n')
while sample:
if sample_req == '' or (sample_req != ''
and sample['sample_id'] == sample_req):
sample_flag = True
#target_index is used to split observations sequence
target_index_begin = 0
target_index_end = 0
temp = 1
for targets in targets_list:
print 'Running HMM for sample[' + sample['sample_id'] + ']: ',
print 'chr' + targets[0]._chr + ' [' + str(temp) + '\\' + str(
len(targets_list)) + ']'
temp += 1
target_index_end = target_index_begin + len(targets)
modelParams = ModelParams(params, targets)
#the 'observations' of sample is splitted
model = Model(
modelParams, sample['observations']
[target_index_begin:target_index_end])
pathlist = model.forwardBackward_Viterbi()
dataloader.outputCNV(
output, sample['sample_id'], targets, pathlist,
sample['observations']
[target_index_begin:target_index_end])
target_index_begin = target_index_end
sample = dataloader.getNextSample()
output.close()
dataloader.closeFile()
if not sample_flag:
print 'Could not find the sample_id specified.'
trans_prob = {
'rainy': {
'rainy': 0.7,
'sunny': 0.3
},
'sunny': {
'rainy': 0.4,
'sunny': 0.6
}
}
emit_prob = {
'rainy': {
'walk': 0.1,
'shop': 0.4,
'clean': 0.5
},
'sunny': {
'walk': 0.6,
'shop': 0.3,
'clean': 0.1
}
}
sequence = ['walk', 'shop', 'clean', 'clean', 'walk', 'walk', 'walk', 'clean']
model = Model(states, symbols, start_prob, trans_prob, emit_prob)
print model.evaluate(sequence)
print model.decode(sequence)
params = dataloader.getParams(paramsfile)
dataloader.skipHeadline()
sample = dataloader.getNextSample()
targets_list = dataloader.getTargetsList()
output = file(outputfile, 'w')
while sample:
#target_index is used to split observations sequence
target_index_begin = 0
target_index_end = 0
temp = 1
for targets in targets_list:
print 'Running HMM for sample[' + sample['sample_id'] + ']: ',
print 'chr' + targets[0]._chr + ' [' + str(temp) + '\\' + str(
len(targets_list)) + ']'
temp += 1
target_index_end = target_index_begin + len(targets)
modelParams = ModelParams(params, targets)
#the 'observations' of sample is splitted
model = Model(
modelParams,
sample['observations'][target_index_begin:target_index_end])
pathlist = model.forwardBackward_Viterbi()
dataloader.outputCNV(
output, sample['sample_id'], targets, pathlist,
sample['observations'][target_index_begin:target_index_end])
target_index_begin = target_index_end
sample = dataloader.getNextSample()
output.close()
conf_prob, trans_prob = pro._tran_conf_prob(train, test_wordcount, word_count,
hidden_states)
'''
test = [["中华人民共和国今天成立了中国人民从此站起来了"],
["江泽民的三个代表是中国在社会主义改革过程中的智慧结晶"],
["人民日报称改革开发的伟大旗帜要坚定不移动的走下去"],
["日理万机的周总理"],
["国务院今天颁发了关于农业的改革方向前进步伐"],
["机器学习及其翻译激起了人们极其浓厚的兴趣"],
["中共中央书记"]]
observations = pro._str2words(test)
'''
observations = test
phi = {'B': 0.5, 'E': 0, 'M': 0, 'S': 0.5}
model = Model(S, observation, phi, trans_prob, conf_prob)
o_hstate = []
for obser in observations:
'''
Notice,if a setence is too long,when we use viterbi algorithm it may result in the beta = 0
There are two solution,one is split the setence into serval sub_setence,another is use log function for the viterbi
here we select the first method
'''
length = len(obser)
index, sub_obser, state = 0, [], []
while index < length:
sub_obser.append(obser[index])
if obser[index] == '。' or obser[index] == '，':
sub_state = model.decode(sub_obser)
sub_obser = []
#The prob of observation in condition of a hidden state
conf_prob = {
'rainy': {
'walk': 0.1,
'shop': 0.3,
'clean': 0.6
},
'sunny': {
'walk': 0.4,
'shop': 0.5,
'clean': 0.1
},
'cloudy': {
'walk': 0.6,
'shop': 0.25,
'clean': 0.15
}
}
observations = [
'walk', 'shop', 'clean', 'clean', 'walk', 'walk', 'walk', 'clean'
]
#The iter_num is the iteration number in the EM algorithm
iter_num = 50
model = Model(states, observation, phi, trans_prob, conf_prob, iter_num)
print model.evaluate(observations)
print model.decode(observations)
