utils.py

# 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.

"""
This module contains some utility functions.
"""

import json
import logging
import os
import random
import sys
from typing import List, Dict

import numpy as np
import torch


def init_logging(log_file, stdout=False):
    formatter = logging.Formatter('%(asctime)s [%(levelname)s] %(module)s: %(message)s',
                                  datefmt='%m/%d/%Y %H:%M:%S')

    print('Making log output file: %s' % log_file)
    print(log_file[: log_file.rfind(os.sep)])
    if not os.path.exists(log_file[: log_file.rfind(os.sep)]):
        os.makedirs(log_file[: log_file.rfind(os.sep)])

    fh = logging.FileHandler(log_file)
    fh.setFormatter(formatter)
    fh.setLevel(logging.INFO)

    logger = logging.getLogger()
    logger.addHandler(fh)
    logger.setLevel(logging.INFO)

    if stdout:
        ch = logging.StreamHandler(sys.stdout)
        ch.setFormatter(formatter)
        ch.setLevel(logging.INFO)
        logger.addHandler(ch)

    return logger


def set_seed(seed: int) -> None:
    """Set RNG seeds for python's `random` module, numpy and torch"""
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    if torch.cuda.is_available():
        torch.cuda.manual_seed_all(seed)


def save_jsonl(entries: List[Dict], path: str):
    with open(path, 'w', encoding='utf8') as fh:
        for entry in entries:
            fh.write(f'{json.dumps(entry)}\n')


def read_jsonl(path: str) -> List[Dict]:
    pairs = []
    with open(path, 'r', encoding='utf8') as fh:
        for line in fh:
            pairs.append(json.loads(line))
    return pairs