File size: 6,642 Bytes
e9057bf | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 | # coding=utf-8
# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION. 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
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from sklearn.metrics import mean_squared_error,r2_score
try:
from scipy.stats import pearsonr, spearmanr
import numpy as np
from sklearn.metrics import matthews_corrcoef, precision_score, recall_score, f1_score, roc_auc_score, average_precision_score
_has_sklearn = True
except (AttributeError, ImportError):
_has_sklearn = False
def is_sklearn_available():
return _has_sklearn
if _has_sklearn:
def simple_accuracy(preds, labels):
return (preds == labels).mean()
def acc_and_f1(preds, labels):
acc = simple_accuracy(preds, labels)
f1 = f1_score(y_true=labels, y_pred=preds)
return {
"acc": acc,
"f1": f1,
"acc_and_f1": (acc + f1) / 2,
}
def acc_f1_mcc(preds, labels):
acc = simple_accuracy(preds, labels)
f1 = f1_score(y_true=labels, y_pred=preds)
mcc = matthews_corrcoef(labels, preds)
return {
"acc": acc,
"f1": f1,
"mcc": mcc
}
def acc_f1_mcc_auc_aupr_pre_rec(preds, labels, probs):
acc = simple_accuracy(preds, labels)
precision = precision_score(y_true=labels, y_pred=preds)
recall = recall_score(y_true=labels, y_pred=preds)
f1 = f1_score(y_true=labels, y_pred=preds)
mcc = matthews_corrcoef(labels, preds)
auc = roc_auc_score(labels, probs)
aupr = average_precision_score(labels, probs)
return {
"acc": acc,
"f1": f1,
"mcc": mcc,
"auc": auc,
"aupr": aupr,
"precision": precision,
"recall": recall,
}
def acc_f1_mcc_auc_aupr_pre_rec_5cls(preds, labels, probs):
# 计算准确率
acc = simple_accuracy(labels, preds)
# 计算精确率、召回率、F1-score
precision = precision_score(y_true=labels, y_pred=preds, average='macro')
recall = recall_score(y_true=labels, y_pred=preds, average='macro')
f1 = f1_score(y_true=labels, y_pred=preds, average='macro')
# 计算MCC
mcc = matthews_corrcoef(labels, preds)
# 计算AUC和AUPR
# 对于多分类，需要使用one-vs-rest策略
auc = roc_auc_score(labels, probs, multi_class='ovr')
aupr = average_precision_score(labels, probs, average='macro')
return {
"acc": acc,
"f1": f1,
"mcc": mcc,
"auc": auc,
"aupr": aupr,
"precision": precision,
"recall": recall,
}
def acc_f1_mcc_auc_pre_rec(preds, labels, probs):
acc = simple_accuracy(preds, labels)
precision = precision_score(y_true=labels, y_pred=preds, average="macro")
recall = recall_score(y_true=labels, y_pred=preds, average="macro")
f1 = f1_score(y_true=labels, y_pred=preds, average="macro")
mcc = matthews_corrcoef(labels, preds)
auc = roc_auc_score(labels, probs, average="macro", multi_class="ovo")
return {
"acc": acc,
"f1": f1,
"mcc": mcc,
"auc": auc,
"precision": precision,
"recall": recall,
}
def pearson_and_spearman(preds, labels):
pearson_corr = pearsonr(preds, labels)[0]
spearman_corr = spearmanr(preds, labels)[0]
rmse_score = np.sqrt(mean_squared_error(labels, preds))
return {
"pearson": pearson_corr,
"spearmanr": spearman_corr,
"corr": (pearson_corr + spearman_corr) / 2,
"rmse":rmse_score,
"r2": r2_score(labels, preds),
}
def rmse(preds, labels):
rmse_score = np.sqrt(mean_squared_error(labels, preds))
return {"rmse":rmse_score}
def glue_compute_metrics(task_name, preds, labels, probs=None):
assert len(preds) == len(labels)
if task_name == "cola":
return {"mcc": matthews_corrcoef(labels, preds)}
elif task_name == "sst-2":
return {"acc": simple_accuracy(preds, labels)}
elif task_name in ["dna690", "dnapair"]:
return acc_f1_mcc_auc_aupr_pre_rec(preds, labels, probs)
elif task_name == "dnaprom":
return acc_f1_mcc_auc_pre_rec(preds, labels, probs)
# return {"acc": simple_accuracy(preds, labels)}
elif task_name == "dnasplice":
return acc_f1_mcc_auc_pre_rec(preds, labels, probs)
elif task_name == "mrpc":
return acc_and_f1(preds, labels)
elif task_name == "sts-b":
return pearson_and_spearman(preds, labels)
elif task_name == "qqp":
return acc_and_f1(preds, labels)
elif task_name == "mnli":
return {"acc": simple_accuracy(preds, labels)}
elif task_name == "mnli-mm":
return {"acc": simple_accuracy(preds, labels)}
elif task_name == "qnli":
return {"acc": simple_accuracy(preds, labels)}
elif task_name == "rte":
return {"acc": simple_accuracy(preds, labels)}
elif task_name == "wnli":
return {"acc": simple_accuracy(preds, labels)}
elif task_name == "hans":
return {"acc": simple_accuracy(preds, labels)}
elif task_name == "genepred":
return pearson_and_spearman(preds, labels)
elif task_name == "cre5clas":
return acc_f1_mcc_auc_aupr_pre_rec_5cls(preds, labels, probs)
elif task_name == "cre4clas":
return acc_f1_mcc_auc_aupr_pre_rec_5cls(preds, labels, probs)
else:
raise KeyError(task_name)
def xnli_compute_metrics(task_name, preds, labels):
assert len(preds) == len(labels)
if task_name == "xnli":
return {"acc": simple_accuracy(preds, labels)}
else:
raise KeyError(task_name)
|