shubhamagarwal92

#!/usr/bin/env bash

export CURRENT_DIR=${PWD}
export PARENT_DIR="$(dirname "$CURRENT_DIR")"
echo "File is in: " $CURRENT_DIR

# https://stackoverflow.com/questions/192319/how-do-i-know-the-script-file-name-in-a-bash-script
export FileNameWithExt=${0##*/}
export FILE_NAME=${FileNameWithExt%.*}

shubhamagarwal92

# Yield successive n-sized
# chunks from l.
def divide_chunks(l, n):

    # looping till length l
    for i in range(0, len(l), n):
        yield l[i:i + n]


test_list = list(range(100))

shubhamagarwal92

def save_h5_data(file_path, data_split="train", **data_dump):

    hf = h5py.File(file_path, 'w')
    hf.attrs['split'] = data_split

    for key in data_dump:
        hf.create_dataset(key, data=data_dump[key])

    hf.close()

shubhamagarwal92

# Also refer https://stackoverflow.com/a/1176225
import sys
class Foobar:
    pass
  
def str_to_class(str):
    return getattr(sys.modules[__name__], str)

str_to_class("Foobar")

shubhamagarwal92

import torch
import logging
from pytorch_transformers import BertModel, BertTokenizer
from pytorch_transformers import *
from typing import List

CLS_TOKEN = "[CLS]"
SEP_TOKEN = "[SEP]"

logger = logging.getLogger(__name__)

shubhamagarwal92

# Refer https://fizzylogic.nl/2017/11/06/edit-jupyter-notebooks-over-ssh/

# On server
jupyter notebook --no-browser --port=8080

# On local machine
ssh -N -L 8080:localhost:8080 <remote_user>@<remote_host>

shubhamagarwal92

import argparse

def parse_args():
    ....
    return args

args = parse_args()
config = vars(args)

for arg in vars(config):

shubhamagarwal92

git submodule deinit <path_to_submodule>
git rm <path_to_submodule>
git commit-m "Removed submodule "
rm -rf .git/modules/<path_to_submodule>

shubhamagarwal92

today="$(date '+%Y-%m-%d')"
yesterday="$(date -d yesterday '+%Y-%m-%d')"

echo $today
echo $yesterday

shubhamagarwal92

# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
.idea/
.DS_Store/
# C extensions
*.so

# Distribution / packaging