def load_dataset(organism):
from ml_data import SequenceNucsData, SimpleHistData
global max_features
global maxlen
print('Load organism: {}'.format(organism))
npath, ppath = './fasta/{}_neg.fa'.format(
organism), './fasta/{}_pos.fa'.format(organism)
print(npath, ppath)
ini = 59
k = 1
max_features = 4**k
samples = SequenceNucsData(npath, ppath, k=k)
samples2 = SimpleHistData(npath, ppath, k=3, upto=True)
X, y = samples.getX(), samples.getY()
X = np.hstack((X, samples2.getX()))
# X = X.reshape(-1, 38, 79, 1).astype('float32')
np.random.seed(int(time.time()))
mask = np.array(np.random.randint(2, size=X.shape[1]) + 1, dtype=bool)
# mask = np.array(np.zeros(X.shape[1]) , dtype=bool)
# mask[59]=1
# mask[60]=1
# mask[61]=1
# mask[49]=1
# mask[50]=1
# mask[51]=1
# mask[24]=1
# mask[25]=1
# mask[26]=1
mask[ini] = 1
print(mask)
X = X[:, mask]
X = X.astype('int32')
# ini = 199
# X = X[:, (ini-30):(ini+11)]
y = y.astype('int32')
print('Input Shapes\nX: {} | y: {}'.format(X.shape, y.shape))
maxlen = X.shape[1]
return X, y
#npath = "fasta/Bacillus_non_prom.fa" #ppath = "fasta/Bacillus_prom.fa" #npath = "fasta/Arabidopsis_non_prom_big.fa" #ppath = "fasta/Arabidopsis_non_tata.fa" npath = "fasta/Ecoli_non_prom.fa" ppath = "fasta/Ecoli_prom.fa" #mldata = SequenceNucsData(npath, ppath, k=3) mldata = SequenceDinucProperties(npath, ppath) mldata2 = SimpleHistData(npath, ppath, k=4, upto=True) X = mldata.getX() X2 = mldata2.getX() Y = mldata.getY() print X.shape print Y.shape posIndex = numpy.where(Y[:] == 1)[0] negIndex = numpy.where(Y[:] == 0)[0] diff = len(negIndex) - len(posIndex) diff = len(negIndex) - diff print 'DIFF', diff toremove = numpy.arange(len(negIndex)) numpy.random.shuffle(toremove) toremove = toremove[:diff]
factor=0.1,
patience=5,
verbose=0,
mode='auto',
epsilon=0.001,
cooldown=0,
min_lr=0)
npath = "fasta/Bacillus_non_prom.fa"
ppath = "fasta/Bacillus_prom.fa"
#mldata = SequenceNucsData(npath, ppath, k=3)
mldata = SimpleHistData(npath, ppath, k=4)
mldata2 = SequenceNucsData(npath, ppath, k=3)
mldata3 = DinucAutoCovarData(npath, ppath)
X = mldata.getX()
Y = mldata.getY()
X2 = mldata2.getX()
X3 = mldata3.getX()
kf = StratifiedKFold(n_splits=10, shuffle=True, random_state=1234)
kf.get_n_splits(X, Y)
cvscores = []
for train_index, test_index in kf.split(X, Y):
X_train = X[train_index, :]
X_train2 = X2[train_index, :]
#X_train2 = X_train2[:,:,numpy.newaxis]
X_train3 = X3[train_index, :]