File tagging_data_lib.py
has 335 lines of code (exceeds 250 allowed). Consider refactoring. 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 _tokenize_example
has a Cognitive Complexity of 16 (exceeds 5 allowed). Consider refactoring. Open
def _tokenize_example(example, max_length, tokenizer, text_preprocessing=None):
"""Tokenizes words and breaks long example into short ones."""
# Needs additional [CLS] and [SEP] tokens.
max_length = max_length - 2
new_examples = []
- 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 _read_one_file
has a Cognitive Complexity of 12 (exceeds 5 allowed). Consider refactoring. Open
def _read_one_file(file_name, label_list):
"""Reads one file and returns a list of `InputExample` instances."""
lines = tf.io.gfile.GFile(file_name, "r").readlines()
examples = []
label_id_map = {label: i for i, label in enumerate(label_list)}
- 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 generate_tf_record_from_data_file
has 8 arguments (exceeds 4 allowed). Consider refactoring. Open
def generate_tf_record_from_data_file(processor, data_dir, tokenizer,
Function token_classification_meta_data
has 7 arguments (exceeds 4 allowed). Consider refactoring. Open
def token_classification_meta_data(train_data_size,
Function write_example_to_file
has 5 arguments (exceeds 4 allowed). Consider refactoring. Open
def write_example_to_file(examples,
Function get_train_examples
has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring. Open
def get_train_examples(self, data_dir):
examples = _read_one_file(
os.path.join(data_dir, "train-en.tsv"), self.get_labels())
if not self.only_use_en_train:
for language in self.supported_languages:
- 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 get_dev_examples
has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring. Open
def get_dev_examples(self, data_dir):
examples = _read_one_file(
os.path.join(data_dir, "dev-en.tsv"), self.get_labels())
if not self.only_use_en_dev:
for language in self.supported_languages:
- 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"