Optimus/code/examples/run_glue_data_integration.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.
""" Finetuning the library models for sequence classification on GLUE (Bert, XLM, XLNet, RoBERTa)."""

from __future__ import absolute_import, division, print_function

import argparse
import glob
import logging
import os
import random
import pdb

cwd = os.getcwd()
print(f"Current working dir is {cwd}")

import sys
sys.path.append('./')
pt_path = os.path.join( cwd, 'pytorch_transformers')
sys.path.append(pt_path)
print(f"Pytorch Transformer {pt_path}")


import numpy as np
import torch
from torch.utils.data import (DataLoader, RandomSampler, SequentialSampler,
                              TensorDataset)
from torch.utils.data.distributed import DistributedSampler
from tensorboardX import SummaryWriter
from tqdm import tqdm, trange

from pytorch_transformers import (WEIGHTS_NAME, BertConfig,
                                  BertForSequenceClassification, BertTokenizer,BertForSequenceClassificationLatentConnector,
                                  RobertaConfig,
                                  RobertaForSequenceClassification,
                                  RobertaTokenizer,
                                  XLMConfig, XLMForSequenceClassification,
                                  XLMTokenizer, XLNetConfig,
                                  XLNetForSequenceClassification,
                                  XLNetTokenizer)

from pytorch_transformers import AdamW, WarmupLinearSchedule

from utils_glue import (compute_metrics, convert_examples_to_features,
                        output_modes, processors)

logger = logging.getLogger(__name__)

ALL_MODELS = sum((tuple(conf.pretrained_config_archive_map.keys()) for conf in (BertConfig, XLNetConfig, XLMConfig, RobertaConfig)), ())

MODEL_CLASSES = {
    'bert': (BertConfig, BertForSequenceClassificationLatentConnector, BertTokenizer),
    'xlnet': (XLNetConfig, XLNetForSequenceClassification, XLNetTokenizer),
    'xlm': (XLMConfig, XLMForSequenceClassification, XLMTokenizer),
    'roberta': (RobertaConfig, RobertaForSequenceClassification, RobertaTokenizer),
}


def set_seed(args):
    random.seed(args.seed)
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    if args.n_gpu > 0:
        torch.cuda.manual_seed_all(args.seed)

def load_and_cache_examples(args, task, tokenizer, file_txt, evaluate=False):
    if args.local_rank not in [-1, 0] and not evaluate:
        torch.distributed.barrier()  # Make sure only the first process in distributed training process the dataset, and the others will use the cache

    processor = processors[task]()
    output_mode = output_modes[task]

    label_list = processor.get_labels()
    if task in ['mnli', 'mnli-mm'] and args.model_type in ['roberta']:
        # HACK(label indices are swapped in RoBERTa pretrained model)
        label_list[1], label_list[2] = label_list[2], label_list[1] 
    examples = processor.get_train_examples(args.data_dir, args.percentage_per_label, args.sample_per_label)
    
    # Chunyuan: convert examples into text lines here

    # write data in a file. 
    for item in examples:
        # pdb.set_trace()
        if item.text_b:
            line = item.text_a + " " + tokenizer.sep_token + " " + item.text_b + "\n"
        else:
            line = item.text_a + " \n"
        file_txt.write(line) 

    file_txt.close()


def main():
    parser = argparse.ArgumentParser()

    ## Required parameters 
    parser.add_argument("--data_dir", default=None, type=str, required=True,
                        help="The input data dir. Should contain the .tsv files (or other data files) for the task.")
    parser.add_argument("--output_dir", default=None, type=str, required=True,
                        help="The output directory where the model predictions and checkpoints will be written.")

    parser.add_argument('--gloabl_step_eval', type=int, default=661,
                        help="Evaluate the results at the given global step")
    parser.add_argument("--model_type", default=None, type=str, required=True,
                        help="Model type selected in the list: " + ", ".join(MODEL_CLASSES.keys()))
    parser.add_argument("--model_name_or_path", default=None, type=str, required=True,
                        help="Path to pre-trained model or shortcut name selected in the list: " + ", ".join(ALL_MODELS))

    ## Other parameters
    parser.add_argument("--config_name", default="", type=str,
                        help="Pretrained config name or path if not the same as model_name")
    parser.add_argument("--tokenizer_name", default="", type=str,
                        help="Pretrained tokenizer name or path if not the same as model_name")
    parser.add_argument("--cache_dir", default="", type=str,
                        help="Where do you want to store the pre-trained models downloaded from s3")
    parser.add_argument("--max_seq_length", default=128, type=int,
                        help="The maximum total input sequence length after tokenization. Sequences longer "
                             "than this will be truncated, sequences shorter will be padded.")

    parser.add_argument("--do_train", action='store_true',
                        help="Whether to run training.")
    parser.add_argument("--do_lower_case", action='store_true',
                        help="Set this flag if you are using an uncased model.")
    parser.add_argument("--percentage_per_label", type=float, default=1.0,
                        help="Set this value (<1.0), if you are using a subset of training dataset.")
    parser.add_argument("--sample_per_label", type=int, default=-1,
                        help="Set this value, if you are using a subset of training dataset, and a fixed number of samples are specified.")                        
    parser.add_argument("--use_freeze", action='store_true',
                        help="Set this flag if you are not updating the model.")


    parser.add_argument('--logging_steps', type=int, default=50,
                        help="Log every X updates steps.")
    parser.add_argument('--save_steps', type=int, default=50,
                        help="Save checkpoint every X updates steps.")
    parser.add_argument("--eval_all_checkpoints", action='store_true',
                        help="Evaluate all checkpoints starting with the same prefix as model_name ending and ending with step number")
    parser.add_argument("--no_cuda", action='store_true',
                        help="Avoid using CUDA when available")
    parser.add_argument('--overwrite_output_dir', action='store_true',
                        help="Overwrite the content of the output directory")
    parser.add_argument('--overwrite_cache', action='store_true',
                        help="Overwrite the cached training and evaluation sets")
    parser.add_argument('--seed', type=int, default=42,
                        help="random seed for initialization")
    parser.add_argument("--use_philly", action='store_true',
                        help="Use Philly for computing.")

    parser.add_argument("--local_rank", type=int, default=-1,
                        help="For distributed training: local_rank")

    args = parser.parse_args()

    if os.path.exists(args.output_dir) and os.listdir(args.output_dir) and args.do_train and not args.overwrite_output_dir:
        raise ValueError("Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome.".format(args.output_dir))

    # Setup CUDA, GPU & distributed training
    if args.local_rank == -1 or args.no_cuda:
        device = torch.device("cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu")
        args.n_gpu = torch.cuda.device_count()
    else:  # Initializes the distributed backend which will take care of sychronizing nodes/GPUs
        torch.cuda.set_device(args.local_rank)
        device = torch.device("cuda", args.local_rank)
        torch.distributed.init_process_group(backend='nccl')
        args.n_gpu = 1
    args.device = device

    # Setup logging
    logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
                        datefmt = '%m/%d/%Y %H:%M:%S',
                        level = logging.INFO if args.local_rank in [-1, 0] else logging.WARN)

    # Set seed
    set_seed(args)


    ## Tokenizer 
    args.model_type = args.model_type.lower()
    config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type]
    tokenizer = tokenizer_class.from_pretrained(args.model_name_or_path, do_lower_case=args.do_lower_case)

    # Load pretrained model and tokenizer
    if args.local_rank not in [-1, 0]:
        torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab

    if not os.path.isdir(args.output_dir):
        os.mkdir(args.output_dir)

    logger.info("Parameters %s", args)

    # Prepare GLUE task
    TASK_NAME = ['CoLA', 'SST-2', 'MRPC', 'STS-B', 'QQP', 'MNLI', 'QNLI', 'RTE', 'WNLI']
    parent_path = args.data_dir

    for task_ in TASK_NAME:

        args.data_dir = os.path.join(parent_path, task_) 
        args.task_name = task_.lower()

        if args.task_name not in processors:
            raise ValueError("Task not found: %s" % (args.task_name))
        processor = processors[args.task_name]()
        args.output_mode = output_modes[args.task_name]

        args.output_file_name = os.path.join(args.output_dir, f"{args.task_name}.txt")
        logger.info("Dataset input file at %s", args.data_dir)
        logger.info("Dataset ouput file at %s", args.output_file_name)

        file_txt = open(args.output_file_name, "w") 

        load_and_cache_examples(args, args.task_name, tokenizer, file_txt, evaluate=False)

        



if __name__ == "__main__":
    main()