def cross_validation():
estimator = misvm.miSVM(kernel=kernel,
gamma=gamma,
C=C,
verbose=True,
max_iters=200)
mil.crossValidation(estimator, 5, path)
def main(): # read hard and easy
estimator = misvm.miSVM(kernel=kernel,
gamma=gamma,
C=C,
verbose=True,
max_iters=100)
#estimator = misvm.miPSVM(feature=kernel, gamma=gamma, C=C, verbose=True, max_iters=100, n_components=36*3, sparse=['P'])
mil.train(estimator=estimator, resultSuperDirPath=path)
def leave_one_out(n_jobs=8):
estimator = misvm.miSVM(kernel=kernel,
gamma=gamma,
C=C,
verbose=True,
max_iters=200)
mil.leaveOneOut(estimator=estimator,
resultSuperDirPath=path,
n_jobs=n_jobs,
trainAcc=True)
def leave_one_person_out(n_jobs=8, resultVis=False):
if resultVis:
resultvis = 'inst_preds'
else:
resultvis = None
estimator = misvm.miSVM(kernel=kernel,
gamma=gamma,
C=C,
verbose=True,
max_iters=200)
mil.leaveOnePersonOut(estimator=estimator,
resultSuperDirPath=path,
n_jobs=n_jobs,
trainAcc=True,
resultVis=resultvis)
def gridsearch(params_grid, cv=2):
estimator = misvm.miSVM(max_iters=250)
mil.gridSearch(estimator=estimator, params_grid=params_grid, cv=cv)
def main(argv=sys.argv):
pos_train_file, neg_train_file, method, model_file, scale_file, score_file, res_file = process_options(
argv)
######train feature extraction
feature_matrix = []
for line in pos_train_file:
feature_vector = []
sequence_infor = line.split(',')
header = sequence_infor[0]
bag = sequence_infor[1]
sequence = sequence_infor[3].strip()
feature_vector.append(header)
feature_vector.append(bag)
feature_vector.extend(
kmer(sequence) + ksnpf(sequence) + nucleic_shift(sequence))
#feature_vector.extend(ksnpf(sequence))
feature_vector.append('1')
feature_matrix.append(feature_vector)
pos_train_file.close()
for line in neg_train_file:
feature_vector = []
sequence_infor = line.split(',')
header = sequence_infor[0]
bag = sequence_infor[1]
sequence = sequence_infor[3].strip()
feature_vector.append(header)
feature_vector.append(bag)
feature_vector.extend(
kmer(sequence) + ksnpf(sequence) + nucleic_shift(sequence))
#feature_vector.extend(ksnpf(sequence))
feature_vector.append('-1')
feature_matrix.append(feature_vector)
feature_array = np.array([b[2:-1] for b in feature_matrix],
dtype=np.float32)
min_max_scaler = preprocessing.MinMaxScaler(copy=True,
feature_range=(-1, 1))
feature_scaled = min_max_scaler.fit_transform(feature_array)
feature_matrix_T = map(list, zip(*feature_matrix))
feature_scaled_T = map(list, zip(*feature_scaled))
k = 0
train_feature_matrix_T = []
train_feature_matrix_T.append(feature_matrix_T[0])
train_feature_matrix_T.append(feature_matrix_T[1])
for i in range(len(feature_scaled_T)):
train_feature_matrix_T.append(feature_scaled_T[k])
k = k + 1
train_feature_matrix_T.append(feature_matrix_T[-1])
train_feature_matrix = map(list, zip(*train_feature_matrix_T))
neg_train_file.close()
np.savetxt("train_features.txt",
train_feature_matrix,
fmt='%s',
delimiter=',')
######put samples into bags
train_file_path = './train_features.txt'
[
train_bag_targets, train_bag_samples, train_bag_instance_targets,
sample_info
] = file_to_features(train_file_path)
if method == 0:
svc = misvm.miSVM(kernel='quadratic', C=5.4, max_iters=10)
elif method == 1:
svc = misvm.MISVM(kernel='quadratic', C=5.4, max_iters=10)
svc.fit(train_bag_samples, train_bag_targets)
#joblib.dump(svc,'./svc.pkl')
joblib.dump(svc, model_file)
joblib.dump(min_max_scaler, scale_file)
bag_predictions, inst_predictions = svc.predict(train_bag_samples, 1)
#score_file=open('training_score.txt','w+')
score_file.write("name\tscore\n")
for i in range(0, len(sample_info)):
score_file.write(sample_info[i] + "\t" + str(inst_predictions[i]) +
"\n")
score_file.close()
#reserved_samples=open('reserved_samples.txt','w+')
res_file.write("name\n")
for j in range(0, len(inst_predictions)):
if inst_predictions[j] >= 0:
res_file.write(sample_info[j] + "\n")
res_file.close()
instance=True)
results_inst_df.set_value(bag_size, proportion, test_inst_accuracy)
valid_results_inst_df.set_value(bag_size, proportion, valid_inst_accuracy)
results_df.to_csv('RESULTS_bag_size_proportion_{}.csv'.format(name))
valid_results_df.to_csv('RESULTS_bag_size_proportion_{}_validation.csv'.format(name))
if instancePrediction:
results_inst_df.to_csv('RESULTS_bag_size_proportion_{}_instance.csv'.format(name))
valid_results_inst_df.to_csv('RESULTS_bag_size_proportion_{}_instance_validation.csv'.format(name))
if __name__ == '__main__':
model_name = sys.argv[1]
if model_name == 'miSVM':
from misvm import miSVM
model = miSVM(verbose=0, max_iters=500, restarts=3)
run_model(model, test_grid, svm_grid, model_name, negative_label=-1, instancePrediction=True)
elif model_name == 'MISVM':
from misvm import MISVM
model = MISVM(verbose=0, max_iters=500, restarts=3)
run_model(model, test_grid, svm_grid, model_name, negative_label=-1, instancePrediction=False)
elif model_name == 'SIL':
from misvm import SIL
model = SIL(verbose=0, max_iters=500, restarts=3)
run_model(model, test_grid, sil_grid, model_name, negative_label=-1, instancePrediction=True)
elif model_name == 'miNet':