official/nlp/data/pretrain_dataloader.py
File pretrain_dataloader.py
has 451 lines of code (exceeds 250 allowed). Consider refactoring. Open
Open
# Copyright 2024 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
Function _parse
has a Cognitive Complexity of 13 (exceeds 5 allowed). Consider refactoring. Open
Open
def _parse(self, record: Mapping[str, tf.Tensor]):
"""Parses raw tensors into a dict of tensors to be consumed by the model."""
x = {}
inputs = record['input_word_ids']
- Read upRead up
Cognitive Complexity
Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.
A method's cognitive complexity is based on a few simple rules:
- Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
- Code is considered more complex for each "break in the linear flow of the code"
- Code is considered more complex when "flow breaking structures are nested"
Further reading
Function _word_span_mask
has 28 lines of code (exceeds 25 allowed). Consider refactoring. Open
Open
def _word_span_mask(self, inputs: tf.Tensor, boundary: tf.Tensor):
"""Sample whole word spans as prediction targets."""
min_num_words = self._params.min_num_words
max_num_words = self._params.max_num_words
Function _token_span_mask
has 27 lines of code (exceeds 25 allowed). Consider refactoring. Open
Open
def _token_span_mask(self, inputs: tf.Tensor) -> tf.Tensor:
"""Samples token spans as prediction targets."""
min_num_tokens = self._params.min_num_tokens
max_num_tokens = self._params.max_num_tokens
Function _online_sample_mask
has a Cognitive Complexity of 8 (exceeds 5 allowed). Consider refactoring. Open
Open
def _online_sample_mask(self, inputs: tf.Tensor,
boundary: tf.Tensor) -> tf.Tensor:
"""Samples target positions for predictions.
Descriptions of each strategy:
- Read upRead up
Cognitive Complexity
Cognitive Complexity is a measure of how difficult a unit of code is to intuitively understand. Unlike Cyclomatic Complexity, which determines how difficult your code will be to test, Cognitive Complexity tells you how difficult your code will be to read and comprehend.
A method's cognitive complexity is based on a few simple rules:
- Code is not considered more complex when it uses shorthand that the language provides for collapsing multiple statements into one
- Code is considered more complex for each "break in the linear flow of the code"
- Code is considered more complex when "flow breaking structures are nested"