cpssd / lucas Goto Github PK
View Code? Open in Web Editor NEWThe repository for the LUCAS/Lucify project
License: MIT License
The repository for the LUCAS/Lucify project
License: MIT License
In this order, a linear progression of learning can be gained to get a good foundational understanding of the most important ML technologies and concepts so we can progress into Deep Learning
Set up dependencies, etc
Using our new features, optimized algorithms, and cleaned/processed data, run a number of experiments in Jupyter notebooks to derive a well generalizing model for our API
This will involve taking the review content from JSON, throwing it at the LUCAS API, and appending the results back into the original JSON
Defined basic /classify endpoint, that takes a review and returns the class and class probabilities.
After Perceptron, begin the foray into neural network architectures and understand the foundation
Use BOW features, Naive Bayes, Regression, maybe SVM
Create the maximum generalizing Amazon review model based on current data and features
Until API integration is acheived, this will be from dummy data.
https://blog.openai.com/content/images/2017/04/sentiment-prediction.png
By use of feature/word embeddings, feature importance selection, reviewer-centric features, etc.
This will involve turning a product page's link into a blob of JSON corresponding to the reviews for that product
Update:
Niall and Stefan have contributed to this issue by highlighting some libraries and visualizations that can be performed on Keras and Tensorflow models and the like. Thus far, no effort on the frontend to implement neural visualizations.
Tensorflow serving can't be used for simple scikit learn models so flask will be used for this sprint
To start working towards our MVP of being able to provide a product page
Table or graph of most / least important word? word cloud? 3d generator?
Needed for more insight into how decision making is made, ie. ranking most important classifying features
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.