id: 1
unit: def train()
file: src/datatuner/lm/train.py
start line: 0
end line: 0
size: 350 LOC
McCabe index: 64
number of parameters: 0

id: 2
unit: def run()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 286 LOC
McCabe index: 54
number of parameters: 0

id: 3
unit: def main()
file: src/datatuner/classification/run_classifier.py
start line: 0
end line: 0
size: 265 LOC
McCabe index: 55
number of parameters: 1

id: 4
unit: def score()
file: paper/experiments/mturk/prepare_mturk.py
start line: 0
end line: 0
size: 166 LOC
McCabe index: 37
number of parameters: 4

id: 5
unit: def train()
file: src/datatuner/classification/run_classifier.py
start line: 0
end line: 0
size: 115 LOC
McCabe index: 48
number of parameters: 4

id: 6
unit: def prepare()
file: paper/experiments/mturk/prepare_mturk.py
start line: 0
end line: 0
size: 107 LOC
McCabe index: 37
number of parameters: 5

id: 7
unit: def get_data_loaders()
file: src/datatuner/lm/data_loader.py
start line: 0
end line: 0
size: 80 LOC
McCabe index: 25
number of parameters: 3

id: 8
unit: def evaluate()
file: src/datatuner/classification/run_classifier.py
start line: 0
end line: 0
size: 80 LOC
McCabe index: 23
number of parameters: 4

id: 9
unit: def parse()
file: paper/experiments/webnlg/preprocess.py
start line: 0
end line: 0
size: 77 LOC
McCabe index: 14
number of parameters: 4

id: 10
unit: def get_dataset_from_file()
file: src/datatuner/lm/data_loader.py
start line: 0
end line: 0
size: 70 LOC
McCabe index: 27
number of parameters: 5

id: 11
unit: def load_and_cache_examples()
file: src/datatuner/classification/run_classifier.py
start line: 0
end line: 0
size: 60 LOC
McCabe index: 32
number of parameters: 4

id: 12
unit: def clean_beam()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 59 LOC
McCabe index: 25
number of parameters: 4

id: 13
unit: def setup()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 56 LOC
McCabe index: 13
number of parameters: 1

id: 14
unit: def tokenize()
file: src/datatuner/lm/custom_tokenizer.py
start line: 0
end line: 0
size: 54 LOC
McCabe index: 20
number of parameters: 3

id: 15
unit: def bleu()
file: src/datatuner/lm/metrics.py
start line: 0
end line: 0
size: 42 LOC
McCabe index: 16
number of parameters: 6

id: 16
unit: def step()
file: src/datatuner/lm/novograd.py
start line: 0
end line: 0
size: 42 LOC
McCabe index: 14
number of parameters: 2

id: 17
unit: def preprocess()
file: paper/experiments/viggo/preprocess.py
start line: 0
end line: 0
size: 40 LOC
McCabe index: 8
number of parameters: 3

id: 18
unit: def preprocess()
file: paper/experiments/ldc/preprocess.py
start line: 0
end line: 0
size: 39 LOC
McCabe index: 8
number of parameters: 5

id: 19
unit: def get_e2e_metrics()
file: src/datatuner/lm/metrics.py
start line: 0
end line: 0
size: 38 LOC
McCabe index: 9
number of parameters: 2

id: 20
unit: def get_distractors()
file: src/datatuner/classification/distractors.py
start line: 0
end line: 0
size: 38 LOC
McCabe index: 13
number of parameters: 7

id: 21
unit: def write_classification_data()
file: src/datatuner/classification/distractors.py
start line: 0
end line: 0
size: 31 LOC
McCabe index: 5
number of parameters: 3

id: 22
unit: def parse_mr()
file: paper/experiments/viggo/preprocess.py
start line: 0
end line: 0
size: 31 LOC
McCabe index: 8
number of parameters: 1

id: 23
unit: def custom_gpt2_with_smoothing()
file: src/datatuner/lm/custom_gpt2.py
start line: 0
end line: 0
size: 26 LOC
McCabe index: 2
number of parameters: 1

id: 24
unit: def top_filtering()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 25 LOC
McCabe index: 8
number of parameters: 8

id: 25
unit: def get_semantic_stats()
file: src/datatuner/classification/classify_generated.py
start line: 0
end line: 0
size: 25 LOC
McCabe index: 9
number of parameters: 4

id: 26
unit: def calculate_stats()
file: paper/experiments/mturk/text_stats.py
start line: 0
end line: 0
size: 24 LOC
McCabe index: 4
number of parameters: 1

id: 27
unit: def add()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 22 LOC
McCabe index: 3
number of parameters: 8

id: 28
unit: def is_middle_token()
file: src/datatuner/lm/utils.py
start line: 0
end line: 0
size: 21 LOC
McCabe index: 10
number of parameters: 3

id: 29
unit: def aggregate_metrics()
file: src/datatuner/lm/metrics.py
start line: 0
end line: 0
size: 20 LOC
McCabe index: 5
number of parameters: 5

id: 30
unit: def swap_pronouns()
file: src/datatuner/classification/distractors.py
start line: 0
end line: 0
size: 20 LOC
McCabe index: 7
number of parameters: 1

id: 31
unit: def add_repetition()
file: src/datatuner/classification/distractors.py
start line: 0
end line: 0
size: 20 LOC
McCabe index: 5
number of parameters: 4

id: 32
unit: def compute_metrics_from_run()
file: src/datatuner/lm/metrics.py
start line: 0
end line: 0
size: 19 LOC
McCabe index: 6
number of parameters: 5

id: 33
unit: def compute_stat_sig()
file: paper/experiments/mturk/prepare_mturk.py
start line: 0
end line: 0
size: 19 LOC
McCabe index: 8
number of parameters: 2

id: 34
unit: def create_input()
file: src/datatuner/lm/reranker.py
start line: 0
end line: 0
size: 17 LOC
McCabe index: 3
number of parameters: 3

id: 35
unit: def score()
file: src/datatuner/lm/reranker.py
start line: 0
end line: 0
size: 17 LOC
McCabe index: 4
number of parameters: 3

id: 36
unit: def get_nearby_text()
file: paper/experiments/webnlg/preprocess.py
start line: 0
end line: 0
size: 17 LOC
McCabe index: 5
number of parameters: 2

id: 37
unit: def read_special_tokens()
file: src/datatuner/lm/model_loader.py
start line: 0
end line: 0
size: 16 LOC
McCabe index: 12
number of parameters: 3

id: 38
unit: def sample_sequence()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 16 LOC
McCabe index: 1
number of parameters: 0

id: 39
unit: def get_run_info()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 16 LOC
McCabe index: 3
number of parameters: 2

id: 40
unit: def split_list()
file: src/datatuner/lm/process_json.py
start line: 0
end line: 0
size: 15 LOC
McCabe index: 6
number of parameters: 2

id: 41
unit: def swap_entities()
file: src/datatuner/classification/distractors.py
start line: 0
end line: 0
size: 15 LOC
McCabe index: 4
number of parameters: 3

id: 42
unit: def add_phrase_omission()
file: src/datatuner/classification/distractors.py
start line: 0
end line: 0
size: 15 LOC
McCabe index: 7
number of parameters: 2

id: 43
unit: def __init__()
file: src/datatuner/lm/reranker.py
start line: 0
end line: 0
size: 14 LOC
McCabe index: 1
number of parameters: 4

id: 44
unit: def get_dataset()
file: src/datatuner/lm/data_loader.py
start line: 0
end line: 0
size: 14 LOC
McCabe index: 7
number of parameters: 8

id: 45
unit: def custom_deep_copy()
file: src/datatuner/lm/utils.py
start line: 0
end line: 0
size: 14 LOC
McCabe index: 3
number of parameters: 1

id: 46
unit: def _create_examples()
file: src/datatuner/classification/consistency_processor.py
start line: 0
end line: 0
size: 14 LOC
McCabe index: 4
number of parameters: 3

id: 47
unit: def evaluate()
file: src/datatuner/classification/consistency_classifier.py
start line: 0
end line: 0
size: 14 LOC
McCabe index: 3
number of parameters: 3

id: 48
unit: def __init__()
file: src/datatuner/lm/novograd.py
start line: 0
end line: 0
size: 13 LOC
McCabe index: 5
number of parameters: 5

id: 49
unit: def forward()
file: src/datatuner/lm/cross_entropy.py
start line: 0
end line: 0
size: 13 LOC
McCabe index: 2
number of parameters: 4

id: 50
unit: def count_words()
file: paper/experiments/mturk/text_stats.py
start line: 0
end line: 0
size: 13 LOC
McCabe index: 5
number of parameters: 2

id: 51
unit: def get_model_directory()
file: src/datatuner/lm/model_loader.py
start line: 0
end line: 0
size: 12 LOC
McCabe index: 3
number of parameters: 1

id: 52
unit: def process_one_item()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 12 LOC
McCabe index: 1
number of parameters: 0

id: 53
unit: def generate()
file: src/datatuner/classification/classify_generated.py
start line: 0
end line: 0
size: 12 LOC
McCabe index: 1
number of parameters: 0

id: 54
unit: def get_stats()
file: src/datatuner/classification/classify_generated.py
start line: 0
end line: 0
size: 12 LOC
McCabe index: 5
number of parameters: 2

id: 55
unit: def bracket_contents()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 12 LOC
McCabe index: 9
number of parameters: 4

id: 56
unit: def generate_from_json()
file: src/datatuner/lm/special_token_generator.py
start line: 0
end line: 0
size: 11 LOC
McCabe index: 3
number of parameters: 3

id: 57
unit: def generate_from_jsonl()
file: src/datatuner/lm/special_token_generator.py
start line: 0
end line: 0
size: 11 LOC
McCabe index: 4
number of parameters: 4

id: 58
unit: def fix_text_in_dir()
file: src/datatuner/lm/utils.py
start line: 0
end line: 0
size: 11 LOC
McCabe index: 7
number of parameters: 1

id: 59
unit: def load_pretrained()
file: src/datatuner/lm/model_loader.py
start line: 0
end line: 0
size: 11 LOC
McCabe index: 1
number of parameters: 0

id: 60
unit: def add_negation_errors()
file: src/datatuner/classification/distractors.py
start line: 0
end line: 0
size: 11 LOC
McCabe index: 3
number of parameters: 2

id: 61
unit: def process_tripleset()
file: paper/experiments/webnlg/preprocess.py
start line: 0
end line: 0
size: 11 LOC
McCabe index: 1
number of parameters: 1

id: 62
unit: def dedup_consecutive_data()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 10 LOC
McCabe index: 3
number of parameters: 2

id: 63
unit: def run_parser()
file: paper/experiments/webnlg/preprocess.py
start line: 0
end line: 0
size: 10 LOC
McCabe index: 3
number of parameters: 2

id: 64
unit: def combine()
file: src/datatuner/lm/process_json.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 2
number of parameters: 2

id: 65
unit: def remove_unsupported_tokens()
file: src/datatuner/lm/reranker.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 2
number of parameters: 2

id: 66
unit: def build_input_from_segments()
file: src/datatuner/lm/data_loader.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 1
number of parameters: 0

id: 67
unit: def onehot()
file: src/datatuner/lm/cross_entropy.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 3
number of parameters: 3

id: 68
unit: def cross_entropy()
file: src/datatuner/lm/cross_entropy.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 1
number of parameters: 0

id: 69
unit: def binary_cross_entropy()
file: src/datatuner/lm/cross_entropy.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 4
number of parameters: 6

id: 70
unit: def forward()
file: src/datatuner/lm/cross_entropy.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 1
number of parameters: 3

id: 71
unit: def _read_tsv()
file: src/datatuner/classification/consistency_processor.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 4
number of parameters: 3

id: 72
unit: def rerank_and_eval()
file: src/datatuner/classification/classify_generated.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 1
number of parameters: 0

id: 73
unit: def cut_entities()
file: src/datatuner/classification/distractors.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 3
number of parameters: 3

id: 74
unit: def add_omission()
file: src/datatuner/classification/distractors.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 4
number of parameters: 2

id: 75
unit: def flatten()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 9 LOC
McCabe index: 4
number of parameters: 3

id: 76
unit: def pad_dataset()
file: src/datatuner/lm/data_loader.py
start line: 0
end line: 0
size: 8 LOC
McCabe index: 6
number of parameters: 2

id: 77
unit: def camel_case_split()
file: paper/experiments/webnlg/webnlg_utils.py
start line: 0
end line: 0
size: 8 LOC
McCabe index: 5
number of parameters: 1

id: 78
unit: def dedup_consecutive_data()
file: paper/experiments/mturk/prepare_mturk.py
start line: 0
end line: 0
size: 8 LOC
McCabe index: 4
number of parameters: 2

id: 79
unit: def split()
file: src/datatuner/lm/process_json.py
start line: 0
end line: 0
size: 7 LOC
McCabe index: 2
number of parameters: 3

id: 80
unit: def compute_metric()
file: src/datatuner/lm/metrics.py
start line: 0
end line: 0
size: 7 LOC
McCabe index: 1
number of parameters: 5

id: 81
unit: def rerank()
file: src/datatuner/lm/reranker.py
start line: 0
end line: 0
size: 7 LOC
McCabe index: 3
number of parameters: 3

id: 82
unit: def should_ignore_in_score()
file: src/datatuner/lm/utils.py
start line: 0
end line: 0
size: 7 LOC
McCabe index: 4
number of parameters: 6

id: 83
unit: def almostmatch()
file: src/datatuner/lm/metrics.py
start line: 0
end line: 0
size: 6 LOC
McCabe index: 3
number of parameters: 4

id: 84
unit: def launch()
file: src/datatuner/lm/launch_tokenizer.py
start line: 0
end line: 0
size: 6 LOC
McCabe index: 2
number of parameters: 2

id: 85
unit: def average_distributed_scalar()
file: src/datatuner/lm/utils.py
start line: 0
end line: 0
size: 6 LOC
McCabe index: 2
number of parameters: 2

id: 86
unit: def should_stop_further_beam_exploration()
file: src/datatuner/lm/utils.py
start line: 0
end line: 0
size: 6 LOC
McCabe index: 3
number of parameters: 6

id: 87
unit: def __init__()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 6 LOC
McCabe index: 1
number of parameters: 3

id: 88
unit: def get_cons_rep()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 6 LOC
McCabe index: 1
number of parameters: 3

id: 89
unit: def set_seed()
file: src/datatuner/classification/run_classifier.py
start line: 0
end line: 0
size: 6 LOC
McCabe index: 2
number of parameters: 1

id: 90
unit: def cleanup()
file: paper/experiments/webnlg/webnlg_utils.py
start line: 0
end line: 0
size: 6 LOC
McCabe index: 2
number of parameters: 1

id: 91
unit: def generate_from_item()
file: src/datatuner/lm/special_token_generator.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 4
number of parameters: 3

id: 92
unit: def match()
file: src/datatuner/lm/metrics.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 3
number of parameters: 4

id: 93
unit: def get_inputs()
file: src/datatuner/lm/data_loader.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 1
number of parameters: 4

id: 94
unit: def load_pretrained_tokenizer()
file: src/datatuner/lm/model_loader.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 2
number of parameters: 2

id: 95
unit: def load_training_args()
file: src/datatuner/lm/model_loader.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 1
number of parameters: 1

id: 96
unit: def get_finished_models()
file: src/datatuner/ops/mlflow.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 2
number of parameters: 1

id: 97
unit: def get_data_fields()
file: src/datatuner/classification/consistency_classifier.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 2
number of parameters: 0

id: 98
unit: def __init__()
file: src/datatuner/classification/consistency_classifier.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 1
number of parameters: 2

id: 99
unit: def ewm_mean()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 2
number of parameters: 2

id: 100
unit: def newest_file()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 1
number of parameters: 2

id: 101
unit: def read_lines_from_file()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 3
number of parameters: 1

id: 102
unit: def get_entities()
file: paper/experiments/ldc/preprocess.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 6
number of parameters: 1

id: 103
unit: def run()
file: paper/experiments/webnlg/preprocess.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 1
number of parameters: 0

id: 104
unit: def sample()
file: paper/experiments/mturk/prepare_mturk.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 1
number of parameters: 2

id: 105
unit: def add_closest_score()
file: paper/experiments/mturk/prepare_mturk.py
start line: 0
end line: 0
size: 5 LOC
McCabe index: 3
number of parameters: 3

id: 106
unit: def __setstate__()
file: src/datatuner/lm/novograd.py
start line: 0
end line: 0
size: 4 LOC
McCabe index: 2
number of parameters: 2

id: 107
unit: def load_test_data()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 4 LOC
McCabe index: 1
number of parameters: 2

id: 108
unit: def _is_long()
file: src/datatuner/lm/cross_entropy.py
start line: 0
end line: 0
size: 4 LOC
McCabe index: 3
number of parameters: 1

id: 109
unit: def get_labels()
file: src/datatuner/classification/consistency_processor.py
start line: 0
end line: 0
size: 4 LOC
McCabe index: 3
number of parameters: 2

id: 110
unit: def write_args_to_file()
file: src/datatuner/classification/run_classifier.py
start line: 0
end line: 0
size: 4 LOC
McCabe index: 1
number of parameters: 2

id: 111
unit: def uniquify_in_order()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 4 LOC
McCabe index: 4
number of parameters: 1

id: 112
unit: def __init__()
file: paper/experiments/webnlg/preprocess.py
start line: 0
end line: 0
size: 4 LOC
McCabe index: 1
number of parameters: 4

id: 113
unit: def round_dict()
file: src/datatuner/lm/metrics.py
start line: 0
end line: 0
size: 3 LOC
McCabe index: 2
number of parameters: 1

id: 114
unit: def group_by_field()
file: src/datatuner/lm/metrics.py
start line: 0
end line: 0
size: 3 LOC
McCabe index: 1
number of parameters: 2

id: 115
unit: def load_task_config()
file: src/datatuner/lm/utils.py
start line: 0
end line: 0
size: 3 LOC
McCabe index: 1
number of parameters: 1

id: 116
unit: def get_artifact()
file: src/datatuner/ops/mlflow.py
start line: 0
end line: 0
size: 3 LOC
McCabe index: 1
number of parameters: 2

id: 117
unit: def __init__()
file: src/datatuner/classification/consistency_processor.py
start line: 0
end line: 0
size: 3 LOC
McCabe index: 1
number of parameters: 2

id: 118
unit: def geo_mean()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 3 LOC
McCabe index: 1
number of parameters: 1

id: 119
unit: def get_custom_tags()
file: src/datatuner/lm/special_token_generator.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 1

id: 120
unit: def get_str_diff()
file: src/datatuner/lm/metrics.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 4
number of parameters: 2

id: 121
unit: def is_added_token()
file: src/datatuner/lm/utils.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 2

id: 122
unit: def __iter__()
file: src/datatuner/lm/evaluate.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 1

id: 123
unit: def clean_mrl()
file: src/datatuner/lm/converters.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 1

id: 124
unit: def __init__()
file: src/datatuner/lm/cross_entropy.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 0

id: 125
unit: def binary_cross_entropy_with_logits()
file: src/datatuner/lm/cross_entropy.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 6

id: 126
unit: def __init__()
file: src/datatuner/lm/cross_entropy.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 0

id: 127
unit: def __init__()
file: src/datatuner/lm/cross_entropy.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 0

id: 128
unit: def get_train_examples()
file: src/datatuner/classification/consistency_processor.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 2

id: 129
unit: def get_dev_examples()
file: src/datatuner/classification/consistency_processor.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 2

id: 130
unit: def get_test_examples()
file: src/datatuner/classification/consistency_processor.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 2

id: 131
unit: def str_part_matches_array()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 2
number of parameters: 2

id: 132
unit: def str_start_matches_array()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 2
number of parameters: 2

id: 133
unit: def arr_part_matches_string()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 2
number of parameters: 2

id: 134
unit: def get_curr_time()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 1
number of parameters: 0

id: 135
unit: def is_empty_or_absent_dir()
file: src/datatuner/utils.py
start line: 0
end line: 0
size: 2 LOC
McCabe index: 2
number of parameters: 1