run_SAG_mnli.py

# 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.

# Code is originally from https://github.com/nlpyang/pytorch-transformers/blob/master/examples/run_glue.py
# Adapted to the SAG task by Ulrike Pado, HFT Stuttgart: Run a fine-tuned model on given input data to predict short-answer grades.




from __future__ import absolute_import, division, print_function

import argparse
import os
import random
import sys

import numpy as np
import torch
from torch.utils.data import DataLoader, SequentialSampler, TensorDataset

from sklearn.metrics import f1_score, accuracy_score
from sklearn.metrics import classification_report

from transformers import (
    BertConfig,
    BertForSequenceClassification,
    BertTokenizer,
)

from transformers import glue_compute_metrics as compute_metrics
from transformers import (
    glue_convert_examples_to_features as convert_examples_to_features,
)
from transformers.data.processors.utils import (
    DataProcessor,
    InputExample,
)

#logger = logging.getLogger(__name__)

MODEL_CLASSES = {
    "bert": (BertConfig, BertForSequenceClassification, BertTokenizer),
}


def set_seed():
    random.seed(42)
    np.random.seed(42)
    torch.manual_seed(42)


def evaluate(args, model, tokenizer, prefix=""):
    # Loop to handle MNLI double evaluation (matched, mis-matched)
    # and SemEval evaluation (unseen questions, unseen answers, unseen domains)
    eval_task_names = ("sag",
                       )