def main(argv):
'''main method.'''
# Get random peptides that match structure patterns from PDB:
pdb_data, hammings = data.sample_seqs(int(argv[2]), argv[9:],
int(argv[3]), int(argv[4]))
print hammings
args = { # 'aa_props_filter': range(1, (2**holygrail.NUM_AA_PROPS)),
# 'input_noise': [i / 10.0 for i in range(0, 10)],
# 'hidden_noise': [i / 10.0 for i in range(0, 10)],
# 'num_hidden_layers': range(1, 4),
# 'num_nodes': range(100, 5000, 100),
'activ_func': ['relu', 'prelu', 'lgrelu'],
'learning_rate': [x / 10000.0 for x in range(1, 100)],
'momentum': [x / 10.0 for x in range(0, 10)],
'patience': range(1, 10),
'min_improvement': [i / 1000.0 for i in range(1, 100)],
# 'validate_every': range(1, 25),
# 'batch_size': range(10, 50, 10),
# 'hidden_dropout': [i * 0.1 for i in range(0, 10)],
# 'input_dropout': [i * 0.1 for i in range(0, 10)]
}
classifier = ClassifierGeneticAlgorithm(pop_size=int(argv[1]),
pdb_data=pdb_data,
split=float(argv[5]),
args=args,
retain=float(argv[6]),
random_select=float(argv[7]),
mutate=float(argv[8]),
verbose=True)
classifier.run()
def getData(numSamples, rgx, rgLbl, min_ham=3, trn=2, val=1, tst=1):
'''Retreives peptide string matching regular expression list and randomly
samples them
into training, validation and test sets.
:param numSamples: number of samples per category.
:param rgx: regular expression matching peptide secondary structures to
retrieve.
:param rgLbl: regex label, replacement labels used for column headers
:param min_ham: minimum hamming distance between any two peptides.
:param trn,val,tst: correspond to training:validation:test ratio
:returns: tupple, (train,valid,test), each element is a pandas DataFrame.
'''
sq, _ = hgd.sample_seqs(numSamples, rgx, min_hamming=min_ham)
dt = pd.DataFrame()
for key in sq.iterkeys():
tmp = pd.DataFrame(sq[key])
tmp['Class'] = key
dt = pd.concat([dt, tmp], ignore_index=True)
dt.columns = ['seq', 'struct', 'PepChainID', 'StartStop', 'Class']
dt[['PepID', 'ChainID']] = dt['PepChainID'].apply(pd.Series)
dt[['pStart', 'pStop']] = dt['StartStop'].apply(pd.Series)
dt.drop(['PepChainID', 'StartStop'], axis=1, inplace=True)
# humanise class names in Class column
for idx, key in enumerate(rgx):
dt.loc[dt.Class == key, 'Class'] = rgLbl[idx]
dt = dt.iloc[np.random.permutation(len(dt))]
dt.reset_index(drop=True, inplace=True)
tot = trn + val + tst
rows, _ = np.shape(dt)
k1 = int(rows * trn / tot)
k2 = int(rows * (trn + val) / tot)
trDat = dt.iloc[0:k1]
vlDat = dt.iloc[k1:k2]
tstDat = dt.iloc[k2:]
return trDat, vlDat, tstDat
