nirantk / nlp_quickbook Goto Github PK

NLP in Python with Deep Learning

Home Page: https://nirantk.com/NLP_Quickbook

License: MIT License

Jupyter Notebook 98.68% Python 1.22% HTML 0.10%

natural-language-processing spacy-nlp spacy natural-language tutorial-code text-classification nlp spell-correction practitioners language-processing

nlp_quickbook's Introduction

Natural Language Processing Notebooks

Available as a Book: NLP in Python - Quickstart Guide

Written for Practicing Engineers

This work builds on the outstanding work which exists on Natural Language Processing. These range from classics like Jurafsky's Speech and Language Processing to rather modern work in The Deep Learning Book by Ian Goodfellow et al.

While they are great as introductory textbooks for college students - this is intended for practitioners to quickly read, skim, select what is useful and then proceed. There are several notebooks divided into 7 logical themes.

Each section builds on ideas and code from previous notebooks, but you can fill in the gaps mentally and jump directly to what interests you.

Chapter 01

Introduction To Text Processing, with Text Classification

Perfect for Getting Started! We learn better with code-first approaches

Chapter 02

Text Cleaning notebook, code-first approaches with supporting explanation. Covers some simple ideas like:
- Stop words removal
- Lemmatization
Spell Correction covers almost everything that you will ever need to get started with spell correction, similar words problems and so on

Chapter 03

Leveraging Linguistics is an important toolkit in any practitioners toolkit. Using spaCy and textacy we look at two interesting challenges and how to tackle them:

Redacting names
- Named Entity Recognition
Question and Answer Generation
- Part of Speech Tagging
- Dependency Parsing

Chapter 04

Text Representations is about converting text to numerical representations aka vectors

Covers popular celebrities: word2vec, fasttext and doc2vec - document similarity using the same
Programmer's Guide to gensim

Chapter 05

Modern Methods for Text Classification is simple, exploratory and talks about:

Simple Classifiers and How to Optimize Them from scikit-learn
How to combine and ensemble them for increased performance
Builds intuition for ensembling - so that you can write your own ensembling techniques

Chapter 06

Deep Learning for NLP is less about fancy data modeling, and more engineering for Deep Learning

From scratch code tutorial with Text Classification as an example
Using PyTorch and torchtext
Write our own data loaders, pre-processing, training loop and other utilities

Chapter 07

Building your own Chatbot from scratch in 30 minutes. We use this to explore unsupervised learning and put together several of the ideas we have already seen.

simpler, direct problem formulation instead of complicated chatbot tutorials commonly seen
intents, responses and templates in chat bot parlance
hacking word based similarity engine to work with little to no training samples

nlp_quickbook's People

Contributors

Stargazers

Watchers

Forkers

sunilseegi newenglandml pratyut kingcv gautamojha1997 prashant118 mcohen01 arunbadhai jeremy-demlow theainerd mithundeshmukh8 vganesh46 deleserna prhldk nakarumanchi thedeveloperr adityamansana swordkeeper ashish265 deepak-0016 pfbalan codedcclxxvii anandara khushboo0012 chandansinha shiva170 pragyagautam nazaranalytics rahul-38-26-0111-0003 subhash-pal ysrsnmz meganytech vitvicky a515151 olibart bluce allensmile chaoyue729 colorfulbutterfly jiangbin713 erguvanix lzjtt2017 legendtianjin nirupam1sharma ignertic raogopal5 nlp-paper avi0gaur vermank9 zoid-anurag payalbhatia vickeytomer007 siddhartha-addictive sujit-deokar brian8903 arvindnaidu1991 ziqi418 sougata09 sahilcodery greensnabl fengyinyang skycreeper2000 jrdeco560 amit2014 stasyanko nikhil-k-singh naveenvayilapalli hitman56 avipartho pnajit shulya403 sandupal arbi11 abhayshivamtiwari sachi-gkp sanoojps dsaichand3 navpreet-ml chinmay26 coding-geeks explore-artificial-intelligence slbinilkumar jonggan-kim pecaso phillette roymachinelearning shmilyface afghani-iitkgp dainny1 tokonex nitishast mukkuway jjediny coiokwmnoster amaresh0612 parrondo dragomirradev agawlowicz jyoshnaekasi javeriatabassum

nlp_quickbook's Issues

anaconda-client version might be outdated

On running pip install -r requirements.txt in the virtual environment, this shows up

Collecting anaconda-client==1.6.14 (from -r requirements.txt (line 1))
  ERROR: Could not find a version that satisfies the requirement anaconda-client==1.6.14 (from -r requirements.txt (line 1)) (from versions: 1.1.1, 1.2.2)
ERROR: No matching distribution found for anaconda-client==1.6.14 (from -r requirements.txt (line 1))

Did some digging around and found that there are two versions supported now - 1.2.2 and 1.1.1 (https://pypi.org/project/anaconda-client/#history). I changed it to 1.2.2 and it worked fine.

nlp = spacy.load('en'), error appeared

for nlp = spacy.load('en') when I run on jupyter i faced following error.

OSError Traceback (most recent call last)
in ()
1 #python -m spacy download en as Administrator
----> 2 nlp = spacy.load('en')

C:\Users\Public\Anaconda3\lib\site-packages\spacy_init_.py in load(name, **overrides)
13 if depr_path not in (True, False, None):
14 deprecation_warning(Warnings.W001.format(path=depr_path))
---> 15 return util.load_model(name, **overrides)
16
17

C:\Users\Public\Anaconda3\lib\site-packages\spacy\util.py in load_model(name, **overrides)
117 elif hasattr(name, 'exists'): # Path or Path-like to model data
118 return load_model_from_path(name, **overrides)
--> 119 raise IOError(Errors.E050.format(name=name))
120
121

OSError: [E050] Can't find model 'en'. It doesn't seem to be a shortcut link, a Python package or a valid path to a data directory.

To which you suggested to apply "python -m spacy download en as Administrator" . I was given following error
(base) C:\Users\Public>python -m spacy download en as Administrator
Collecting as
Could not find a version that satisfies the requirement as (from versions: )
No matching distribution found for as

(base) C:\Users\Public>python
Python 3.6.5 |Anaconda, Inc.| (default, Mar 29 2018, 13:32:41) [MSC v.1900 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.

-m spacy download en as Administrator
File "", line 1
-m spacy download en as Administrator
^
SyntaxError: invalid syntax
exit()

Do review and advice