fe.py 文件源码

def get_pattern(DB,tr,te,patterns):
    cols = ['p%d'%c for c,p in enumerate(patterns)]
    if tr is None:
        test = DB.data['test_variants_filter'] if te=='stage1' else DB.data['stage2_test_variants']
        if te=='stage1':
            train = DB.data['training_variants']
        else:
            train = pd.concat([DB.data['training_variants'],DB.data["test_variants_filter"]],axis=0)
        Data =[train,test]
    else:
        Data = [DB.data['training_variants']]

    for data in Data:
        for c,p in enumerate(patterns):
            data['p%d'%c] = data['Variation'].apply(lambda x: len(re.findall(p,str(x).lower())))

    if tr is None:
        return train[cols].values,test[cols].values
    else:
        X = data[cols].values
        return X[tr],X[te]