LiutongZhou

How to document a project

How to update the docs and publish to the Home Page?

Prerequisites

One-time installation of dependencies

python3 -m pip install -U jupyter-book ghp-import

LiutongZhou

Large-Scale Distributed Data and Model Parallel Training

Data Streaming

FastFile Mode

sagemaker.inputs.TrainingInput(S3_INPUT_FOLDER, input_mode='FastFile') 

LiutongZhou

"""BitMask"""

class BitMask:
    __slots__ = ("size", "mask")
    
    def __init__(self, size: int = 16):
        """Create a bit mask to store (size) 0/1 status"""
        self.size = size
        self.mask = 1 << size
        

LiutongZhou

"""MinHeap and MaxHeap (Optimized Implementation)"""
from abc import ABC, abstractmethod
from collections import Counter, UserList
from functools import singledispatchmethod
from heapq import (
    _heapify_max,
    _heappop_max,
    _heapreplace_max,
    _siftdown,
    _siftdown_max,

LiutongZhou

"""UnionFind (Disjoint Sets)"""

from typing import Optional, Iterable, Hashable, Any


class UnionFind:
    def __init__(
        self, initial_disjoint_items: Optional[Iterable[Hashable]] = None
    ):
        """Initialize a UnionFind of disjoint sets"""

LiutongZhou

""" Time-and-Space-Efficient Sampling Methods"""
from typing import Iterable
from random import random, randint, seed
from math import exp, log, floor
from itertools import islice

__author__ = "Liutong Zhou"


def take(iterable, n: int) -> list:

LiutongZhou

Setup Cloud9 on EC2 and remote Jupyter

Create an EC2 instance on AWS

• Launch: t3.2xlarge ($0.33/h) / m8g.4xlarge ($0.718) / g6.4xlarge ($1.32/h) / p3.2xlarge ($3.02/h)
• Image: Deep Learning AMI (Ubuntu 22.04)
• Configure Security Group:
  • open custom TCP and port 9999
  • open HTTPS, HTTP to anywhere
• Attach an Elastic IP to the instance

ssh into EC2 from MobaXterm and run

LiutongZhou

#  Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
#  SPDX-License-Identifier: LicenseRef-.amazon.com.-AmznSL-1.0
#  Licensed under the Amazon Software License  http://aws.amazon.com/asl/

"""S3 Client

A helper class which wraps boto3's s3 service
"""

__author__ = "Liutong Zhou"

LiutongZhou

import functools
from typing import Any, Mapping


def singleton(cls):
    '''a class decorator that wraps class definition so that only one class instance can exist'''
    existing_instances = dict() 
    @functools.wraps(cls)
    def singleton_class(*args, **kwargs): 
        if cls not in existing_instances:

LiutongZhou

# Add to ~/.bash_aliases
alias port_forward='nohup ssh -N -f -L localhost:8889:localhost:8889 username:password@remote_server_ip'
alias remote_notebook_start='nohup ssh -f username:password@remote_server_ip "cd rne; conda activate env_name; jupyter notebook --no-browser --port=8889"; port_forward'
alias remote_notebook_stop='ssh username:password@remote_server_ip "pkill -u username jupyter"'
# Add this to crontab -e
@reboot cd /home/{username}; source ./.bashrc;  ./miniconda3/envs/{env_name}/bin/jupyter-lab >> ./cronrun.log 2>&1