All Projects → uclnlp → Stat Nlp Book

uclnlp / Stat Nlp Book

Interactive Lecture Notes, Slides and Exercises for Statistical NLP

Projects that are alternatives of or similar to Stat Nlp Book

Deepnlp Models Pytorch
Pytorch implementations of various Deep NLP models in cs-224n(Stanford Univ)
Stars: ✭ 2,760 (+1050%)
Mutual labels:  jupyter-notebook
R C3d
code for R-C3D
Stars: ✭ 238 (-0.83%)
Mutual labels:  jupyter-notebook
Skills
个人的技能树仓库,主要包含个人机器学习以及深度学习的笔记
Stars: ✭ 240 (+0%)
Mutual labels:  jupyter-notebook
Learndatascience
Open Content for self-directed learning in data science
Stars: ✭ 2,688 (+1020%)
Mutual labels:  jupyter-notebook
Learningdl
三个月教你从零入门深度学习Tensorflow版配套代码
Stars: ✭ 238 (-0.83%)
Mutual labels:  jupyter-notebook
Ida ipython
An IDA Pro Plugin for embedding an IPython Kernel
Stars: ✭ 238 (-0.83%)
Mutual labels:  jupyter-notebook
Jsanimation
[DEPRECATED] An IPython notebook-compatible Javascript/HTML viewer for matplotlib animations
Stars: ✭ 237 (-1.25%)
Mutual labels:  jupyter-notebook
Malaya
Natural Language Toolkit for bahasa Malaysia, https://malaya.readthedocs.io/
Stars: ✭ 239 (-0.42%)
Mutual labels:  jupyter-notebook
Deeplung
WACV18 paper "DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification"
Stars: ✭ 238 (-0.83%)
Mutual labels:  jupyter-notebook
Iclr2021 Openreviewdata
Crawl & visualize ICLR papers and reviews.
Stars: ✭ 238 (-0.83%)
Mutual labels:  jupyter-notebook
Pytorch Bert Crf Ner
KoBERT와 CRF로 만든 한국어 개체명인식기 (BERT+CRF based Named Entity Recognition model for Korean)
Stars: ✭ 236 (-1.67%)
Mutual labels:  jupyter-notebook
Bayesian Neural Network Mnist
Bayesian neural network using Pyro and PyTorch on MNIST dataset
Stars: ✭ 238 (-0.83%)
Mutual labels:  jupyter-notebook
Kaggle airbus ship detection
Kaggle airbus ship detection challenge 21st solution
Stars: ✭ 238 (-0.83%)
Mutual labels:  jupyter-notebook
Covid Chestxray Dataset
We are building an open database of COVID-19 cases with chest X-ray or CT images.
Stars: ✭ 2,759 (+1049.58%)
Mutual labels:  jupyter-notebook
Datascience
Data Science in Julia course for JuliaAcademy.com, taught by Huda Nassar
Stars: ✭ 239 (-0.42%)
Mutual labels:  jupyter-notebook
Blog
for code created as part of http://studywolf.wordpress.com
Stars: ✭ 236 (-1.67%)
Mutual labels:  jupyter-notebook
End2end All Conv
Deep Learning to Improve Breast Cancer Detection on Screening Mammography
Stars: ✭ 236 (-1.67%)
Mutual labels:  jupyter-notebook
Text Classification
Machine Learning and NLP: Text Classification using python, scikit-learn and NLTK
Stars: ✭ 239 (-0.42%)
Mutual labels:  jupyter-notebook
Deepreplay
Deep Replay - Generate visualizations as in my "Hyper-parameters in Action!" series!
Stars: ✭ 240 (+0%)
Mutual labels:  jupyter-notebook
Aravec
AraVec is a pre-trained distributed word representation (word embedding) open source project which aims to provide the Arabic NLP research community with free to use and powerful word embedding models.
Stars: ✭ 239 (-0.42%)
Mutual labels:  jupyter-notebook

The Stat-NLP-Book Project

Render Book Statically

The easiest option for reading the book is via the static nbviewer. While this does not allow you to change and execute code, it also doesn't require you to install software locally and only needs a browser.

Docker installation

We assume you have a command line interface (CLI) in your OS (bash, zsh, cygwin, git-bash, power-shell etc.). We assume this CLI sets the variable $(pwd) to the current directory. If it doesn't replace all mentions of $(pwd) with the current directory you are in.

When using Windows PowerShell all instances of "$(pwd)" should be replaced with ${PWD}.

Install Docker

Go to the docker webpage and follow the instruction for your platform.

Download Stat-NLP-Book Image

Next you can download the stat-nlp-book docker image like so:

docker pull riedelcastro/stat-nlp-book

Get Stat-NLP-Book Repository

You can use the git installation in the docker container to get the repository:

docker run -v "$(pwd)":/home/jovyan/work riedelcastro/stat-nlp-book git clone https://github.com/uclmr/stat-nlp-book.git  

Note: this will create a new stat-nlp-book directory in your current directory.

Change into Stat-NLP-Book directory

We assume from here on that you are in the top level stat-nlp-book directory:

cd stat-nlp-book

Note: you need to be in the stat-nlp-book directory every time you want to run/update the book.

Run Notebook

docker run -it --rm -p 8888:8888 -v "$(pwd)":/home/jovyan/work riedelcastro/stat-nlp-book 

You are now ready to visit the overview page of the installed book.

Usage

Once installed you can always run your notebook server by first changing into your local stat-nlp-book directory, and then executing:

docker run -it --rm -p 8888:8888 -v "$(pwd)":/home/jovyan/work riedelcastro/stat-nlp-book 

This is assuming that your docker daemon is running and that you are in the stat-nlp-book directory. How to run the docker daemon depends on your system.

Update the notebook

We frequently make changes to the book. To get these changes you should first make sure to clean your local changes to avoid merge conflicts. That is, you might have made changes (by changing the code or simply running it) to the files that we changed. In these cases git will complain when you do the update. To overcome this you can undo all your changes by executing:

docker run -v "$(pwd)":/home/jovyan/work riedelcastro/stat-nlp-book git checkout -- .

If you want to keep your changes create copies of the changed files. Jupyter has a "Make a copy" option in the "File" menu for this. You can also create a clone of this repository to keep your own changes and merge our changes in a more controlled manner.

To get the actual updates then run

docker run -v "$(pwd)":/home/jovyan/work riedelcastro/stat-nlp-book git pull

Access Content

The repository contains a lot of material, some of which may not be ready for consumption yet. This is why you should always access content through the top-level overview page (local-link).

virtualenv installation [BETA]

Install virtualenv

Follow the instructions here In short:

pip3 install virtualenv

git clone the stat-nlp-book repository

git clone https://github.com/uclmr/stat-nlp-book.git

Create virtual environment

Enter the cloned stat-nlp-book directory:

cd stat-nlp-book

and create the virtual environment:

virtualenv -p python3 venv

Enter the virtual environment

source venv/bin/activate

Install dependencies

pip3 install --upgrade pip
pip3 install -r requirements.txt
pip3 install git+git://github.com/robjstan/tikzmagic.git
jupyter-nbextension install rise --py --sys-prefix
jupyter-nbextension enable rise --py --sys-prefix    

Run the notebook

jupyter notebook

Installation on the UCL CS cluster

Install virtualenv

When installing virtualenv (full instructions here here) on the CS cluster you will likely have to install it with the --user flag. In short:

pip3 install --user virtualenv

At this point virtualenv may not yet directly be found. You can solve this by finding its location via

pip3 show virtualenv

then appending the LOCATION shown (a directory name) to your $PATH variable using

export PATH=$PATH:LOCATION

and giving permission to execute via

chmod u=rwx LOCATION/virtualenv.py

You should then be able to run virtualenv.py. You can check this by running

virtualenv.py --version

git clone the stat-nlp-book repository

Now we're ready to clone the notebook:

git clone https://github.com/uclmr/stat-nlp-book.git

Create virtual environment

Enter the cloned stat-nlp-book directory via

cd stat-nlp-book

and create the virtual environment:

virtualenv.py -p python3 venv

Enter the virtual environment

source venv/bin/activate

Install dependencies

pip3 install --upgrade pip
pip3 install -r requirements.txt
pip3 install git+git://github.com/robjstan/tikzmagic.git
jupyter-nbextension install rise --py --sys-prefix
jupyter-nbextension enable rise --py --sys-prefix

Run the notebook

jupyter notebook

Access in local browser

With the notebook running on the UCL CS cluster, you can also access it locally via first setting up an SSH tunnel

# run this on your local machine
ssh -N -f -L localhost:8157:localhost:8888 [email protected]_cluster

and accessing it through your local browser by entering

localhost:8157

into the browser address bar.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].