parse_features.py 文件源码

def build_vectors(keyword="",data_label="",lower_limit=None,upper_limit=None,folder_path="dataset"):
    # training
    training_vector,labels,maxlen_training = create_dataset(dataset_path = folder_path+"/train",keyword=keyword,lower_limit=lower_limit,upper_limit=upper_limit)

    # validation
    evaluation_training_vector,evaluation_labels,maxlen_evaluation = create_dataset(dataset_path = "{0}/test".format(folder_path),keyword=keyword,lower_limit=lower_limit,upper_limit=upper_limit)

    # # X_training
    training_vector = sequence.pad_sequences(training_vector, maxlen=np.max([maxlen_training,maxlen_evaluation]),dtype='float32')
    pickle.dump(training_vector,open("pickled_vectors/{1}{0}_training_vector.pickle".format(keyword,data_label),"wb"))
    #
    # # y
    #
    pickle.dump(labels,open("pickled_vectors/{1}{0}_label.pickle".format(keyword,data_label),"wb"))
    #
    #
    # # evaluation
    evaluation_training_vector = sequence.pad_sequences(evaluation_training_vector, maxlen=np.max([maxlen_training,maxlen_evaluation]),dtype='float32')
    pickle.dump(evaluation_training_vector,open("pickled_vectors/{1}{0}_evaluation_training_vector.pickle".format(keyword,data_label),"wb"))
    #
    # # evaluation
    pickle.dump(evaluation_labels,open("pickled_vectors/{1}{0}_evaluation_label.pickle".format(keyword,data_label),"wb"))
    with(open("maxlen_{0}".format(keyword),"w")) as _f:
        _f.write(str(np.max([maxlen_training,maxlen_evaluation])))