def generate_LR_important_features(self,
clf_LR,
feature_names,
results_file,
N=1000):
'''
:param clf_logistic_regression:
:param feature_names:
:param results_file:
:param N:
:return:
'''
results_file = results_file.replace(
'/classifications/', '/feature_selection/classifications/')
FileUtility.ensure_dir(results_file)
file_name = results_file + '_LR'
idxs = argsort(np.abs(clf_LR.coef_.tolist()[0]).tolist(),
rev=True)[0:N]
f = codecs.open(file_name, 'w')
f.write('\t'.join(['feature', 'score']) + '\n')
for idx in idxs:
f.write('\t'.join(
[feature_names[idx],
str(clf_LR.coef_.tolist()[0][idx])]) + '\n')
f.close()
def numpy2trainfiles(file, name, out='../data/s8_features/'):
'''
test_file='/mounts/data/proj/asgari/dissertation/datasets/deepbio/protein_general/ss/data/cb513+profile_split1.npy'
train_file='/mounts/data/proj/asgari/dissertation/datasets/deepbio/protein_general/ss/data/cullpdb+profile_6133_filtered.npy'
:param name:
:param out:
:return:
'''
db = np.load(file)
a = np.arange(0, 21)
b = np.arange(35, 56)
c = np.hstack((a, b))
db = np.reshape(db, (db.shape[0], int(db.shape[1] / 57), 57))
seq = [
'A', 'C', 'E', 'D', 'G', 'F', 'I', 'H', 'K', 'M', 'L', 'N', 'Q',
'P', 'S', 'R', 'T', 'W', 'V', 'Y', 'X', 'NoSeq'
]
label = ['L', 'B', 'E', 'G', 'I', 'H', 'S', 'T']
sequences = []
labels = []
possible_features = dict()
for i in range(0, db.shape[0]):
sequences.append(''.join([
seq[np.argmax(x)] if np.max(x) == 1 else ''
for x in db[i, :, 0:21]
]).lower())
labels.append(''.join([
label[np.argmax(y)] if np.max(y) == 1 else ''
for y in db[i, :, 22:30]
]).lower())
lengths = [len(x) for x in sequences]
sorted_idxs = argsort(lengths)
lengths.sort()
sequences = [sequences[i] for i in sorted_idxs]
labels = [labels[i] for i in sorted_idxs]
FileUtility.save_list(out + name, [
'\n'.join([
' '.join([elx, labels[idx][idy]])
for idy, elx in enumerate(list(seq))
] + ['']) for idx, seq in enumerate(sequences)
])
db_new = db[sorted_idxs, :, :]
label_encoding = [[([0] if np.max(row) == 1 else [1]) + row
for row in db_new[i, :, 22:30].tolist()]
for i in range(0, db.shape[0])]
np.save(out + name + '_mat_Y', label_encoding)
db_new = db_new[:, :, c]
np.save(out + name + '_mat_X', db_new)
FileUtility.save_list(out + name + '_length.txt',
[str(l) for l in lengths])
def labeling_file_reader(file):
with open(file, 'r') as f:
train = f.read().splitlines()
X, y = [], []
sent = []
sent_labels = []
for elem in train:
if elem == '':
X.append(sent)
y.append(sent_labels)
sent = []
sent_labels = []
else:
xx, yy = elem.split()
sent.append(xx)
sent_labels.append(yy)
lengths = LabelingData.sequence_lengths(file)
sorted_idxs = argsort(lengths)
lengths.sort()
X = [X[i] for i in sorted_idxs]
y = [y[i] for i in sorted_idxs]
return X, y, lengths