utils.py 文件源码

def _preprocess(self, input_file, tensor_file):
        if input_file.endswith(".bz2"): file_reference = BZ2File(input_file, "r")
        elif input_file.endswith(".txt"): file_reference = io.open(input_file, "r")
        raw_data = file_reference.read()
        file_reference.close()
        data = raw_data.encode(encoding=self.encoding)
        # Convert the entirety of the data file from characters to indices via the vocab dictionary.
        # How? map(function, iterable) returns a list of the output of the function
        # executed on each member of the iterable. E.g.:
        # [14, 2, 9, 2, 0, 6, 7, 0, ...]
        # np.array converts the list into a numpy array.
        self.tensor = np.array(map(self.vocab.get, data))
        # Compress and save the numpy tensor array to data.npz.
        np.savez_compressed(tensor_file, tensor_data=self.tensor)