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)
hmm.length = 12
hmm.dims = [(2, 3)] * hmm.length # (latent,emit) dimspace
hmm.emit = [[[0.6, 0.2, 0.2], [0.2, 0.6, 0.2]]] * hmm.length
hmm.trans = [[[0.7, 0.3], [0.3, 0.7]]] * hmm.length
hmm.seqmap = [{"a": 0, "b": 1}] * hmm.length
hmm.seqmap2 = [{0: "a", 1: "b"}] * hmm.length
hmm.featmap = [{"H": 0, "B": 1, "L": 2}] * hmm.length
hmm.initprob = [0.5, 0.5]
hmm.trained = True
if __name__ == "__main__":
hmm = HMM()
# 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()
def set_params_hmm_exp1(hmm):
""" Sets the params of a hmm for sim experiment 1"""
hmm.length = 12
hmm.dims = [(2, 3)] * hmm.length # (latent,emit) dimspace
hmm.emit = [[[0.6, 0.2, 0.2], [0.2, 0.6, 0.2]]] * hmm.length
hmm.trans = [[[0.7, 0.3], [0.3, 0.7]]] * hmm.length
hmm.seqmap = [{'a': 0, 'b': 1}] * hmm.length
hmm.seqmap2 = [{0: 'a', 1: 'b'}] * hmm.length
hmm.featmap = [{'H': 0, 'B': 1, 'L': 2}] * hmm.length
hmm.initprob = [0.5, 0.5]
hmm.trained = True
if __name__ == '__main__':
hmm = HMM()
# Set the params of the h,,
set_params_hmm_exp1(hmm)
cmrf = CMRF(hmm)
seq1 = 'a' * 12
feat1 = 'HHHHLLLLHHHH'
seq2 = 'b' * 12
feat2 = 'BBBBLLLLBBBB'
# Find the pareto frontier
frontier, frontier_energy = pareto_frontier(cmrf, [feat1, feat2])
from pprint import pprint
pprint("Frontier is ")
pprint(frontier)
pprint("Frontier Energies are")
pprint(frontier_energy)
hmm.trans.append([])
for j, aa1 in enumerate(hmm.alphabet):
hmm.trans[-1].append([])
for k, aa2 in enumerate(hmm.alphabet):
val = (counts2[i].get(aa1 + aa2, 0) + self.smoothfac) / (
counts[i].get(aa1, 0) +
self.smoothfac * len(hmm.alphabet))
hmm.trans[-1][-1].append(val)
return hmm
if __name__ == '__main__':
b = BoostedHMM()
hmm1, hmm2 = b.hmm1, b.hmm2
# Set the params of the hmm
cmrf1 = CMRF(hmm1)
cmrf2 = CMRF(hmm2)
feat = 'HHHHHHHHHHHH'
# Plot the entire sequence space
ll_list1, ll_list2 = [], []
for seq in product('ab', repeat=12):
ll_list1.append(cmrf1.score(seq, feat))
ll_list2.append(cmrf2.score(seq, feat))
ll_list3, ll_list4 = [], []
for seq in b.kseqlist:
ll_list3.append(cmrf1.score(seq, feat))
ll_list4.append(cmrf2.score(seq, feat))
pl.figure()
pl.plot(ll_list1, ll_list2, 'b*')
hmm.length = 12
hmm.dims = [(2, 3)] * hmm.length # (latent,emit) dimspace
hmm.emit = [[gen_random_dist(3), gen_random_dist(3)]] * hmm.length
hmm.trans = [[gen_random_dist(2), gen_random_dist(2)]] * hmm.length
hmm.seqmap = [{'a': 0, 'b': 1}] * hmm.length
hmm.seqmap2 = [{0: 'a', 1: 'b'}] * hmm.length
hmm.featmap = [{'H': 0, 'B': 1, 'L': 2}] * hmm.length
hmm.initprob = [0.5, 0.5]
hmm.trained = True
if __name__ == '__main__':
hmm = HMM()
# Set the params of the h,,
set_params_hmm_exp1(hmm)
cmrf = CMRF(hmm)
seq1 = 'a' * 12
feat1 = 'HHHHLLLLHHHH'
seq2 = 'b' * 12
feat2 = 'BBBBLLLLBBBB'
### 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))
hmm.trans = []
for i in range(len(seqlist[0])-1) :
hmm.trans.append([])
for j,aa1 in enumerate(hmm.alphabet) :
hmm.trans[-1].append([])
for k,aa2 in enumerate(hmm.alphabet) :
val = (counts2[i].get(aa1+aa2,0)+self.smoothfac) / (counts[i].get(aa1,0)+self.smoothfac*len(hmm.alphabet))
hmm.trans[-1][-1].append(val)
return hmm
if __name__ == '__main__' :
b = BoostedHMM()
hmm1,hmm2 = b.hmm1,b.hmm2
# Set the params of the hmm
cmrf1 = CMRF(hmm1)
cmrf2 = CMRF(hmm2)
feat = 'HHHHHHHHHHHH'
# Plot the entire sequence space
ll_list1,ll_list2 = [],[]
for seq in product('ab',repeat=12):
ll_list1.append(cmrf1.score(seq,feat))
ll_list2.append(cmrf2.score(seq,feat))
ll_list3,ll_list4 = [],[]
for seq in b.kseqlist:
ll_list3.append(cmrf1.score(seq,feat))
ll_list4.append(cmrf2.score(seq,feat))
pl.figure()