if __name__ == "__main__":
n = 1000
models_path = "/Users/heydar/Stuff/tmp/gprt/models_ntrain_%d.pk" % (n)
with open(models_path, "r") as ff:
models = pickle.load(ff)[0]
ff.close()
print len(models)
raw_input()
peptides = data_tools.read_data()
# duplicated_message = data_tools.checked_duplicated(peptides)
# print duplicated_message
bench = ml_tools.rt_benchmark(peptides, "elude", "gp", 100, 5)
fmat = []
mmat = []
dmat = []
for i in range(bench.parts.nfolds):
print i
model = bench.train_model(i)
f, m, d = bench.test_sorted(i, model)
fmat.append(f)
mmat.append(m)
dmat.append(d)
fmat = np.matrix(fmat)
def load_data( self ):
path = self.params.save_tmp % ( self.params.data_root, self.params.models_tag, self.n )
self.peptides = data_tools.read_data( self.params.data_path )
self.benchmark = ml_tools.rt_benchmark(self.peptides, 'elude', 'gp', self.n, self.params.nparts, self.params.train_ratio )
self.models, self.kernels = ml_tools.load_rt_models( path )
#!/usr/bin/python
import numpy as np
import data_tools
import ml_tools
import pickle as pk
from common import parameters
if __name__ == "__main__":
params = parameters()
peptides = data_tools.read_data( params.data_path )
for n in params.ntrain :
print n
benchmark = ml_tools.rt_benchmark( peptides, 'elude', 'gp', n , params.nparts, params.train_ratio )
models = ml_tools.single_train_gp( benchmark )
save_path = params.save_tmp % ( params.data_root, params.models_tag, n )
with open( save_path, 'w' ) as ff :
pk.dump( [ models ], ff )
ff.close()
models = None
