File size: 5,754 Bytes
6fc683c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
import os
import re

import numpy as np

from transformers.utils import logging


logger = logging.get_logger(__name__)


PREFIX_CHECKPOINT_DIR = "checkpoint"
_re_checkpoint = re.compile(r"^" + PREFIX_CHECKPOINT_DIR + r"\-(\d+)$")


def get_last_checkpoint(folder):
    content = os.listdir(folder)
    checkpoints = [
        path
        for path in content
        if _re_checkpoint.search(path) is not None and os.path.isdir(os.path.join(folder, path))
    ]
    if len(checkpoints) == 0:
        return
    return os.path.join(folder, max(checkpoints, key=lambda x: int(_re_checkpoint.search(x).groups()[0])))


def re_score(pred_relations, gt_relations, mode="strict"):
    """Evaluate RE predictions

    Args:
        pred_relations (list) :  list of list of predicted relations (several relations in each sentence)
        gt_relations (list) :    list of list of ground truth relations

            rel = { "head": (start_idx (inclusive), end_idx (exclusive)),
                    "tail": (start_idx (inclusive), end_idx (exclusive)),
                    "head_type": ent_type,
                    "tail_type": ent_type,
                    "type": rel_type}

        vocab (Vocab) :         dataset vocabulary
        mode (str) :            in 'strict' or 'boundaries'"""

    assert mode in ["strict", "boundaries"]

    relation_types = [v for v in [0, 1] if not v == 0]
    scores = {rel: {"tp": 0, "fp": 0, "fn": 0} for rel in relation_types + ["ALL"]}

    # Count GT relations and Predicted relations
    n_sents = len(gt_relations)
    n_rels = sum([len([rel for rel in sent]) for sent in gt_relations])
    n_found = sum([len([rel for rel in sent]) for sent in pred_relations])

    # Count TP, FP and FN per type
    for pred_sent, gt_sent in zip(pred_relations, gt_relations):
        for rel_type in relation_types:
            # strict mode takes argument types into account
            if mode == "strict":
                pred_rels = {
                    (rel["head"], rel["head_type"], rel["tail"], rel["tail_type"])
                    for rel in pred_sent
                    if rel["type"] == rel_type
                }
                gt_rels = {
                    (rel["head"], rel["head_type"], rel["tail"], rel["tail_type"])
                    for rel in gt_sent
                    if rel["type"] == rel_type
                }

            # boundaries mode only takes argument spans into account
            elif mode == "boundaries":
                pred_rels = {(rel["head"], rel["tail"]) for rel in pred_sent if rel["type"] == rel_type}
                gt_rels = {(rel["head"], rel["tail"]) for rel in gt_sent if rel["type"] == rel_type}

            scores[rel_type]["tp"] += len(pred_rels & gt_rels)
            scores[rel_type]["fp"] += len(pred_rels - gt_rels)
            scores[rel_type]["fn"] += len(gt_rels - pred_rels)

    # Compute per entity Precision / Recall / F1
    for rel_type in scores.keys():
        if scores[rel_type]["tp"]:
            scores[rel_type]["p"] = scores[rel_type]["tp"] / (scores[rel_type]["fp"] + scores[rel_type]["tp"])
            scores[rel_type]["r"] = scores[rel_type]["tp"] / (scores[rel_type]["fn"] + scores[rel_type]["tp"])
        else:
            scores[rel_type]["p"], scores[rel_type]["r"] = 0, 0

        if not scores[rel_type]["p"] + scores[rel_type]["r"] == 0:
            scores[rel_type]["f1"] = (
                2 * scores[rel_type]["p"] * scores[rel_type]["r"] / (scores[rel_type]["p"] + scores[rel_type]["r"])
            )
        else:
            scores[rel_type]["f1"] = 0

    # Compute micro F1 Scores
    tp = sum([scores[rel_type]["tp"] for rel_type in relation_types])
    fp = sum([scores[rel_type]["fp"] for rel_type in relation_types])
    fn = sum([scores[rel_type]["fn"] for rel_type in relation_types])

    if tp:
        precision = tp / (tp + fp)
        recall = tp / (tp + fn)
        f1 = 2 * precision * recall / (precision + recall)

    else:
        precision, recall, f1 = 0, 0, 0

    scores["ALL"]["p"] = precision
    scores["ALL"]["r"] = recall
    scores["ALL"]["f1"] = f1
    scores["ALL"]["tp"] = tp
    scores["ALL"]["fp"] = fp
    scores["ALL"]["fn"] = fn

    # Compute Macro F1 Scores
    scores["ALL"]["Macro_f1"] = np.mean([scores[ent_type]["f1"] for ent_type in relation_types])
    scores["ALL"]["Macro_p"] = np.mean([scores[ent_type]["p"] for ent_type in relation_types])
    scores["ALL"]["Macro_r"] = np.mean([scores[ent_type]["r"] for ent_type in relation_types])

    logger.info(f"RE Evaluation in *** {mode.upper()} *** mode")

    logger.info(
        "processed {} sentences with {} relations; found: {} relations; correct: {}.".format(
            n_sents, n_rels, n_found, tp
        )
    )
    logger.info(
        "\tALL\t TP: {};\tFP: {};\tFN: {}".format(scores["ALL"]["tp"], scores["ALL"]["fp"], scores["ALL"]["fn"])
    )
    logger.info("\t\t(m avg): precision: {:.2f};\trecall: {:.2f};\tf1: {:.2f} (micro)".format(precision, recall, f1))
    logger.info(
        "\t\t(M avg): precision: {:.2f};\trecall: {:.2f};\tf1: {:.2f} (Macro)\n".format(
            scores["ALL"]["Macro_p"], scores["ALL"]["Macro_r"], scores["ALL"]["Macro_f1"]
        )
    )

    for rel_type in relation_types:
        logger.info(
            "\t{}: \tTP: {};\tFP: {};\tFN: {};\tprecision: {:.2f};\trecall: {:.2f};\tf1: {:.2f};\t{}".format(
                rel_type,
                scores[rel_type]["tp"],
                scores[rel_type]["fp"],
                scores[rel_type]["fn"],
                scores[rel_type]["p"],
                scores[rel_type]["r"],
                scores[rel_type]["f1"],
                scores[rel_type]["tp"] + scores[rel_type]["fp"],
            )
        )

    return scores