Deopen_regression.py 文件源码

def data_split(inputfile,reads_count):
    data = hkl.load(inputfile)
    reads_count= hkl.load(reads_count)
    X = data['mat']
    X_kspec = data['kmer']
    reads_count = np.array(reads_count)
    y = np.mean(reads_count, axis = 1)
    y = np.log(y+1e-3)
    rs = ShuffleSplit(len(y), n_iter=1,random_state = 1)
    X_kspec = X_kspec.reshape((X_kspec.shape[0],1024,4))
    X = np.concatenate((X,X_kspec), axis = 1)
    X = X[:,np.newaxis]
    X = X.transpose((0,1,3,2))
    for train_idx, test_idx in rs:
        X_train = X[train_idx,:]
        y_train = y[train_idx]
        X_test = X[test_idx,:]
        y_test = y[test_idx]
    X_train = X_train.astype('float32')
    y_train = y_train.astype('float32')
    X_test = X_test.astype('float32')
    y_test = y_test.astype('float32')
    print 'Data prepration done!'
    return [X_train, y_train, X_test, y_test]


#define the network architecture