def run(self, argv):
assert(self.data is not None)
param_grid = {}
results = []
sum_acc = 0
self.start_logging([self.kernel_type,
str(int(self.randomize_data)), argv[0]])
i = 0
while i < self.n_runs:
sys.stdout.write('%i ' % i)
sys.stdout.flush()
if self.limit_sets:
new_sets = make_d.merge_multiclasses(self.data, self.set1, self.set2)
sets = make_d.make_set(new_sets, training_fraction=0.75)
else:
sets = make_d.make_set(self.data, training_fraction=0.75)
train_y, train_x, test_y, test_x = sets
if self.randomize_data:
random.shuffle(train_y)
random.shuffle(test_y)
pass
print [len(x) for x in sets]
train_x = [make_d.encode(x, make_d.encode_dic) for x in train_x]
def run(self, argv):
assert(self.data is not None)
encode_dic = {'A': [0], 'C': [1], 'G': [2], 'U': [3]}
recog_rates = []
self.start_logging(['RFOREST',
str(int(self.randomize_data)), argv[0]])
i = 0
while i < self.n_runs:
sys.stdout.write('%i ' % i)
sys.stdout.flush()
if self.limit_sets:
new_sets = make_d.merge_multiclasses(self.data,
self.set1, self.set2)
sets = make_d.make_set(new_sets, training_fraction=1.0)
else:
sets = make_d.make_set(self.data, training_fraction=1.0)
train_y, train_x, test_y, test_x = sets
if self.randomize_data:
random.shuffle(train_y)
random.shuffle(test_y)
pass
print [len(x) for x in sets]
train_x = [make_d.encode(x, encode_dic) for x in train_x]
def main(argv):
global C_RANGE
global GAMMA_RANGE
global SET1
global SET2
i = 0
param_grid = {}
results = []
sum_acc = 0
init(argv[1:])
print SET1, SET2
fn = argv[0]
dataset = make_d.read_data(open(fn))
dataset = make_d.assign_classes(dataset)
data = make_d.prepare_data(dataset)
print data.keys(), [len(v) for v in data.values()]
param = svm.svm_parameter('-b 1')
if KERNEL_TYPE == 'LINEAR':
param.kernel_type = svm.LINEAR
GAMMA_RANGE = 1, 0, -2
else:
param.kernel_type = svm.RBF
cvfunc = svmfun.leave_one_out
n_cv = None
limit_sets = not SET1 is None and not SET2 is None
outfile = os.path.basename(fn)
outfile = outfile.replace('.fasta', '')
outfile = outfile.replace('.fas', '')
if limit_sets:
outfile = ''.join(map(str, map(int, SET1))) + 'vs'
outfile += ''.join(map(str, map(int, SET2)))
log_name = '%s-%s-%i-%s.csv' % (TIMESTAMP,
KERNEL_TYPE,
int(RANDOMIZE_DATA),
outfile)
logfile = open(log_name, 'w')
while i < N_RUNS:
sys.stdout.write('%i ' % i)
sys.stdout.flush()
if limit_sets:
new_sets = make_d.merge_multiclasses(data, SET1, SET2)
sets = make_d.make_set(new_sets, training_fraction=0.75)
else:
sets = make_d.make_set(data, training_fraction=0.75)
train_y, train_x, test_y, test_x = sets
if RANDOMIZE_DATA:
random.shuffle(train_y)
random.shuffle(test_y)
pass
print [len(x) for x in sets]
