def all_chem_adjust(self, mz_heat, cp_heat, output):
"""Does vector compression, ignoring biological activity. Uses all baskets from a run, not
just those that are within a biological cutoff range.
"""
new_cp = cp.cp(None)
for feat in cp_heat.features():
new_cp[str(feat)] = cp.feature(str(feat))
runcount = 0
n = 0
av_dist = 0
widgets = ['VectorMove: ', Percentage(), ' ', Bar(marker=RotatingMarker()), ' ',\
ETA(), ' ', FileTransferSpeed()]
pbar = ProgressBar(widgets=widgets, maxval=len(cp_heat.fingerprints())).start()
largest_scaler = None
#This is a dictionary of run (as string) - [run_vector, add_vector] pairs
add_vectors = dict()
for run in cp_heat.fingerprints():
output.write("\t" + str(run) + "\n")
runcount += 1
pbar.update(runcount)
labels = run.keys()
#This is the original vector fingerprint in log scale
run_vec = numpy.log(run.values(), dtype=float)
print run_vec
#This is going to be a list of vectors, one from each basket, in log scale
bask_vectors = []
#This is the number of vectors, one for each connection, with multiple connections per basket
vector_num = 0
for bask in mz_heat.grab_basks(str(run)):
#If there's only one run, then the vector has nothing to connect to
if len(bask.keys()) <= 1:
continue
#This is the average value of the scaler, for use in line plots later
av_scaler = 0.0
for connect_run in bask.keys():
cprun = connect_run.replace("_", "")
#Don't connect the query run to itself, that's not useful
if cprun == str(run):
continue
#If the run isn't in the cp_heatmap, just continue; that means it also wasn't used for creating synthetic fingerprints
if cprun not in cp_heat.map:
continue
#Get the vector difference between the target and the source, but it's in log scale. Also, make sure label values are
# in the same order between the vectors. Remember log scale!
vec_dif = numpy.log(numpy.array([cp_heat[cprun][val] for val in labels]) - run_vec)
scaler = self.bask_prob(bask, cp_heat[cprun]) + self.bask_prob(bask, run)
print scaler
if scaler >= largest_scaler:
largest_scaler = scaler
av_scaler = numpy.logaddexp(av_scaler, scaler)
bask_vectors.append(vec_dif + scaler)
print "bask_ind", vec_dif+scaler
vector_num += 1
if not vector_num == 0:
output.write("\t\t\t{}; {}\n".format(str(bask), numpy.exp(av_scaler) / vector_num))
#This is the sum of the basket vectors, still in log scale
print "all", bask_vectors
add_vector = logsumexp(bask_vectors, axis=0)
print "summed", add_vector
if not vector_num == 0:
add_vector -= numpy.log(vector_num)
print "averaged", add_vector
print 'large', largest_scaler
return
# if not largest_scaler == 0:
# add_vector /= 2 * largest_scaler
add_vectors[str(run)] = [run_vec, add_vector]
for run, (run_vec, add_vector) in add_vectors.items():
add_vector = numpy.exp(add_vector - (numpy.log(2) + largest_scaler))
run_vec = numpy.exp(run_vec) + add_vector
new_cp[str(run)] = cp.fingerprint(str(run))
for param, value in zip(labels, run_vec):
new_cp[param][str(run)] = new_cp[str(run)][param] = value
output.write("\t\tRun Movement: {}\n".format(numpy.sqrt(add_vector.dot(add_vector))))
av_dist += numpy.sqrt(add_vector.dot(add_vector))
n += 1
pbar.finish()
output.write("Average Movement: " + str(av_dist / n) + "\n")
return new_cp
def chem_adjust(self, mz_heat, cp_heat, output):
new_cp = cp.cp(None)
for feat in cp_heat.features():
new_cp[str(feat)] = cp.feature(str(feat))
runcount = 0
n = 0
av_dist = 0
widgets = ['VectorMove: ', Percentage(), ' ', Bar(marker=RotatingMarker()), ' ',\
ETA(), ' ', FileTransferSpeed()]
pbar = ProgressBar(widgets=widgets, maxval=len(cp_heat.fingerprints())).start()
for run in cp_heat.fingerprints():
output.write("\t" + str(run) + "\n")
runcount += 1
pbar.update(runcount)
all_basks = [bask for bask in mz_heat.grab_basks(str(run))]
inruns = set([inrun + "_" for inrun in cp_heat.cluster(str(run), max_tolerance=0.5, min_tolerance=0.65)])
# antiruns = set([antirun + "_" for antirun in cp_heat.anticluster(str(run), pmax=-0.2, fraction=1)])
basks = []
for bask in all_basks:
bruns = set(bask.keys())
# if len(bruns & antiruns) > 0:
# continue
if len(bruns & inruns) < 2:
continue
basks.append(bask)
labels = run.keys()
run_vec = numpy.array(run.values(), dtype=float)
add_vector = numpy.zeros(len(labels))
vector_num = 0
largest_scaler = 0.0
for bask in basks:
av_scaler = 0.0
for connect_run in bask.keys():
cprun = connect_run.replace("_", "")
if cprun == str(run):
continue
if cprun not in cp_heat.map:
continue
vec_dif = numpy.array([cp_heat[cprun][val] for val in labels]) - run_vec
scaler = self.bask_prob(bask, cp_heat[cprun]) * self.bask_prob(bask, run)
if scaler >= largest_scaler:
largest_scaler = scaler
av_scaler += scaler
add_vector += vec_dif * scaler
vector_num += 1
if not vector_num == 0:
av_scaler /= vector_num
output.write("\t\t\t{}; {}\n".format(str(bask), av_scaler))
if not vector_num == 0:
add_vector /= vector_num
if not largest_scaler == 0:
add_vector /= 2 * largest_scaler
run_vec += add_vector
new_cp[str(run)] = cp.fingerprint(str(run))
for param, value in zip(labels, run_vec):
new_cp[param][str(run)] = new_cp[str(run)][param] = value
output.write("\t\tRun Movement: {}\n".format(numpy.sqrt(add_vector.dot(add_vector))))
av_dist += numpy.sqrt(add_vector.dot(add_vector))
n += 1
pbar.finish()
output.write("Average Movement: " + str(av_dist / n) + "\n")
return new_cp