def featspacelen(self) :
""" Vary the feature space and the sequence length """
self.tasklist = []
featspace = self.kwdargs['featspace']
seqspace = 20
seqlen = self.kwdargs['seqlen']
dims = [(seqspace,featspace)]*seqlen
# Repeat for all the tasks described
for taskid in range(self.ntimes) :
hmm = HMM()
self._set_params_generic(hmm,seqlen,dims)
cmrf = CMRF(hmm)
feats = self._gen_feats_generic(seqlen,featspace)
task = Task('sim'+STUDY+'_'+self.name+'_'+\
str(seqlen)+'_'+str(featspace)+'_'+str(taskid),cmrf,feats)
# Run Brute force to enumerate the frontier
if self.kwdargs['run_brute'] :
with benchmark(task.name+'brute') as t:
seq,energies = self.bruteforce(cmrf,feats)
task.all_seq = seq
task.all_seq_energy = energies
task.brute_time = t.elapsed
# Now run the toy simulation`
with benchmark(task.name+'pareto') as t :
task.frontier,task.frontier_energy = \
pareto_frontier(cmrf,feats)
if self.plot_all :
task.plot_frontier(frontier_only=True)
task.pareto_time = t.elapsed
self.tasklist.append(task)
def ziftied(self) :
""" Set up the toy simulation """
self.tasklist = []
feats = self.kwdargs['feats']
weights = self.kwdargs['weights']
hmm = HMM()
self._set_params_ziftied(hmm)
#1/0
cmrf = CMRF(hmm)
for taskid in range(self.ntimes) :
task = Task('bio'+str(STUDY)+'_'+self.name+'_'+str(taskid),cmrf,\
feats)
# Run Brute force to enumerate the frontier
# with benchmark(task.name+'brute') as t:
# seq,energies = self.bruteforce(cmrf,feats)
# task.all_seq = seq
# task.all_seq_energy = energies
# task.brute_time = t.elapsed
# Sample the frontier
with benchmark(task.name+'sample') as t:
seq,energies = self.sample(cmrf,feats)
task.sample_seq = seq
task.sample_seq_energy = energies
task.sample_time = t.elapsed
# Now run the toy simulation`
with benchmark(task.name+'pareto') as t :
task.frontier,task.frontier_energy = \
pareto_frontier(cmrf,feats)
if self.plot_all :
task.plot_frontier(frontier_only = True,plot_samples=True)
task.pareto_time = t.elapsed
self.tasklist.append(task)
def toy(self) :
""" Set up the toy simulation """
self.tasklist = []
feats = self.get_feats_standard()
hmm = HMM()
self._set_params_toy(hmm)
cmrf = CMRF(hmm)
for taskid in range(self.ntimes) :
task = Task('sim'+STUDY+'_'+self.name+'_'+str(taskid),cmrf,\
feats)
# Run Brute force to enumerate the frontier
with benchmark(task.name+'brute') as t:
seq,energies = self.bruteforce(cmrf,feats)
task.all_seq = seq
task.all_seq_energy = energies
task.brute_time = t.elapsed
# Now run the toy simulation`
with benchmark(task.name+'pareto') as t :
task.frontier,task.frontier_energy = \
pareto_frontier(cmrf,feats)
if self.plot_all :
task.plot_frontier()
task.pareto_time = t.elapsed
self.tasklist.append(task)
def randfeatsuntied(self) :
""" Run many iterations of toy with random probs """
self.tasklist = []
feats = self.get_feats_standard()
# Repeat for all the tasks described
for taskid in range(self.ntimes) :
hmm = HMM()
self._set_params_randprobsuntied(hmm)
cmrf = CMRF(hmm)
feats = self._gen_feats_random()
task = Task('sim'+STUDY+'_'+self.name+'_'+str(taskid),cmrf,\
feats)
# Run Brute force to enumerate the frontier
with benchmark(task.name+'brute') as t:
seq,energies = self.bruteforce(cmrf,feats)
task.all_seq = seq
task.all_seq_energy = energies
task.brute_time = t.elapsed
# Now run the toy simulation`
with benchmark(task.name+'pareto') as t :
task.frontier,task.frontier_energy = \
pareto_frontier(cmrf,feats)
if self.plot_all :
task.plot_frontier()
task.pareto_time = t.elapsed
self.tasklist.append(task)
def toy(self):
""" Set up the toy simulation """
self.tasklist = []
feats = self.get_feats_standard()
hmm = HMM()
self._set_params_toy(hmm)
cmrf = CMRF(hmm)
for taskid in range(self.ntimes):
task = Task('sim'+STUDY+'_'+self.name+'_'+str(taskid),cmrf,\
feats)
# Run Brute force to enumerate the frontier
with benchmark(task.name + 'brute') as t:
seq, energies = self.bruteforce(cmrf, feats)
task.all_seq = seq
task.all_seq_energy = energies
task.brute_time = t.elapsed
# Now run the toy simulation`
with benchmark(task.name + 'pareto') as t:
task.frontier,task.frontier_energy = \
pareto_frontier(cmrf,feats)
if self.plot_all:
task.plot_frontier()
task.pareto_time = t.elapsed
self.tasklist.append(task)
def featspacelen(self):
""" Vary the feature space and the sequence length """
self.tasklist = []
featspace = self.kwdargs['featspace']
seqspace = 20
seqlen = self.kwdargs['seqlen']
dims = [(seqspace, featspace)] * seqlen
# Repeat for all the tasks described
for taskid in range(self.ntimes):
hmm = HMM()
self._set_params_generic(hmm, seqlen, dims)
cmrf = CMRF(hmm)
feats = self._gen_feats_generic(seqlen, featspace)
task = Task('sim'+STUDY+'_'+self.name+'_'+\
str(seqlen)+'_'+str(featspace)+'_'+str(taskid),cmrf,feats)
# Run Brute force to enumerate the frontier
if self.kwdargs['run_brute']:
with benchmark(task.name + 'brute') as t:
seq, energies = self.bruteforce(cmrf, feats)
task.all_seq = seq
task.all_seq_energy = energies
task.brute_time = t.elapsed
# Now run the toy simulation`
with benchmark(task.name + 'pareto') as t:
task.frontier,task.frontier_energy = \
pareto_frontier(cmrf,feats)
if self.plot_all:
task.plot_frontier(frontier_only=True)
task.pareto_time = t.elapsed
self.tasklist.append(task)
def randfeatsuntied(self):
""" Run many iterations of toy with random probs """
self.tasklist = []
feats = self.get_feats_standard()
# Repeat for all the tasks described
for taskid in range(self.ntimes):
hmm = HMM()
self._set_params_randprobsuntied(hmm)
cmrf = CMRF(hmm)
feats = self._gen_feats_random()
task = Task('sim'+STUDY+'_'+self.name+'_'+str(taskid),cmrf,\
feats)
# Run Brute force to enumerate the frontier
with benchmark(task.name + 'brute') as t:
seq, energies = self.bruteforce(cmrf, feats)
task.all_seq = seq
task.all_seq_energy = energies
task.brute_time = t.elapsed
# Now run the toy simulation`
with benchmark(task.name + 'pareto') as t:
task.frontier,task.frontier_energy = \
pareto_frontier(cmrf,feats)
if self.plot_all:
task.plot_frontier()
task.pareto_time = t.elapsed
self.tasklist.append(task)
# Set the params of the h,,
set_params_hmm_exp1(hmm)
cmrf = CMRF(hmm)
seq1 = "a" * 12
feat1 = "HHHHLLLLHHHH"
seq2 = "b" * 12
feat2 = "BBBBLLLLBBBB"
# Plot the entire sequence space
ll_list1, ll_list2 = [], []
for seq in product("ab", repeat=12):
ll_list1.append(cmrf.score(seq, feat1))
ll_list2.append(cmrf.score(seq, feat2))
# Find the pareto frontier
frontier, frontier_energy = pareto_frontier(cmrf, [feat1, feat2])
pl.figure()
pl.plot(ll_list1, ll_list2, "b*")
pl.plot(*zip(*sorted(frontier_energy)), color="magenta", marker="*", linestyle="dashed")
ctr = dict(zip(set(frontier_energy), [0] * len(set(frontier_energy))))
for i, e in enumerate(frontier_energy):
ctr[e] += 1
if i == 0:
pl.text(e[0] + 0.5, e[1] - 0.4, str(i), fontsize=10)
pl.text(e[0] - 3, e[1] + 0.8, frontier[i], fontsize=9)
else:
pl.text(e[0] + 0.5, e[1] - 0.4, str(i), fontsize=10)
pl.text(e[0] - 3, e[1] - 1.5, frontier[i], fontsize=9)
pl.xlabel("Energy:" + feat1)
### DEBUG
import pickle
cmrf = pickle.load(open('cmrf.pkl'))
# Plot the entire sequence space
ll_list1, ll_list2 = [], []
seq_list = ["".join(s) for s in product('ab', repeat=12)]
for seq in seq_list:
ll_list1.append(cmrf.score(seq, feat1))
ll_list2.append(cmrf.score(seq, feat2))
min_feat1id = ll_list1.index(min(ll_list1))
min_feat2id = ll_list2.index(min(ll_list2))
# Find the pareto frontier
frontier, frontier_energy = pareto_frontier(cmrf, [feat1, feat2])
# Plot only the frontier
pl.figure()
pl.plot(*zip(*sorted(frontier_energy)),color='magenta',marker='*',\
linestyle='dashed')
ctr = dict(zip(set(frontier_energy), [0] * len(set(frontier_energy))))
for i, e in enumerate(frontier_energy):
ctr[e] += 1
pl.text(e[0], e[1] + 0.1 * ctr[e], str(i), fontsize=10)
pl.text(e[0] + 0.1, e[1] + 0.1 * ctr[e], frontier[i], fontsize=9)
pl.xlabel('Energy:' + feat1)
pl.ylabel('Energy:' + feat2)
pl.title('Energy Plot')
xmin, xmax = pl.xlim()
ymin, ymax = pl.ylim()