Skip to main content

John Snow Labs NLU provides state of the art algorithms for NLP&NLU with hundreds of pretrained models in 60+ languages. It enables swift and simple development and research with its powerful Pythonic and Keras inspired API. It is powerd by John Snow Labs powerful Spark NLP library.

Project description

NLU: The Power of Spark NLP, the Simplicity of Python

John Snow Labs' NLU is a Python library for applying state-of-the-art text mining, directly on any dataframe, with a single line of code. As a facade of the award-winning Spark NLP library, it comes with hundreds of pretrained models in tens of languages - all production-grade, scalable, and trainable.

Project's Website

Take a look at our official Spark NLU page: https://nlu.johnsnowlabs.com/ for user documentation and examples

NLU in action

Getting Started with NLU

To get your hands on the power of NLU, you just need to install it via pip and ensure Java 8 is installed and properly configured. Checkout Quickstart for more infos

pip install nlu

Loading and predict with any model in 1 line python

import nlu 
nlu.load('sentiment').predict('I love NLU! <3') 

Loading and predict with multiple models in 1 line

Get 6 different embeddings in 1 line and use them for downstream data science tasks!

nlu.load('bert elmo albert xlnet glove use').predict('I love NLU! <3') 

What kind of models does NLU provide?

NLU provides everything a data scientist might want to wish for in one line of code!

  • The 100+ of the latest NLP word embeddings ( BERT, ELMO, ALBERT, XLNET, GLOVE, BIOBERT, ELECTRA, COVIDBERT) and different variations of them
  • The 45+ of the latest NLP sentence embeddings ( BERT, ELECTRA, USE) and different variations of them
  • 50 + Classifiers
  • Generation of Sentence, Chunk and Document from these embeddings
  • Language Classification of 20 languages
  • 36 pretrained NER models
  • 34 Part of Speech (POS) models
  • 34 Lemmatizer models
  • Emotion (joy, fear, suprise, sadness)
  • Labeled and Unlabeled Dependency parsing
  • Spell Checking
  • Stopword removers for 41 languages
  • Classifiers for 12 different problems
  • 244 unique NLU components
  • 176 unique NLP models and algorithms
  • 68 unique NLP pipelines consisting of composed NLP models

Classifiers trained on many different different datasets

Choose the right tool for the right task! Whether you analyze movies or twitter, NLU has the right model for you!

  • 50 Class Questions Classifier
  • Spam Classifier
  • Fake News Classifier
  • Emotion Classifier
  • Cyberbullying Classifier
  • Sarcasm Classifier
  • Toxic Classifer
  • E2E Classifier
  • Sentiment classifier pretrained on IMDB movie reviews
  • Sentiment classifier pretrained on twitter
  • NER pretrained on ONTO notes
  • NER trainer on CONLL
  • Language classifier for 20 languages on the wiki 20 lang dataset.

Data Pre-Processing and Text Cleaning

Working with text data can sometimes be quite a dirty Job. NLU helps you keep your hands clean by providing lots of components that take away data engineering intensive tasks.

  • Datetime Matcher
  • Pattern Matcher
  • Chunk Matcher
  • Phrases Matcher
  • Stopword Cleaners
  • Pattern Cleaners
  • Slang Cleaner
  • Tokenization

Where can I see NLUs entire offer?

Checkout the NLU Namespace for everything that NLU has to offer!

Supported Data Types

  • Pandas DataFrame and Series
  • Spark DataFrames
  • Modin with Ray backend
  • Modin with Dask backend
  • Numpy arrays
  • Strings and lists of strings

Checkout the following notebooks for examples on how to work with NLU.

NLU Demos on Datasets

NLU component examples

The following are Collab examples which showcase each NLU component and some applications.

Need help?

Simple NLU Demos

Project details


Release history Release notifications | RSS feed

This version

0.2

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nlu-0.2.tar.gz (60.1 kB view hashes)

Uploaded Source

Built Distribution

nlu-0.2-py3-none-any.whl (116.5 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page