differential-privacy-library VS spaCy

Differential privacy. Basically i wanted to create a randomly generated database file, akin to medical records, create a Private Aggregation of Teacher Ensembles algorithms based on 20-60% of its content and then use this teacher model on the other 80-40% of database which was just a plaintext, not that that matters. The problem is, I've barely got ideas on how it all works, and the one example I've found used Cryptonumeric's library called cn.protect. And that went like I've already described. I've fallen back on practical part of the paper and found another way of getting any practical usage as the assignment requires and now am trying to use https://github.com/IBM/differential-privacy-library and the example on 30s guide to instead make the practical part about choosing epsilon ( a measure of how much information you can give away as a result of one query on the database to a third malicious party) by tracking associated accuracy of result dataset compared to original. I hope I'll manage to edit the code to accept my text file after parsing it through into ndarray from txt, separating the last column to use as a target and going from there.

IBM's Diffprivlib is a well-documented implementation of differential privacy in Python. Source code and getting started documentation is available on the IBM differential-privacy-library Github repository.

Hi Community, In this article, I will demonstrate below steps to create your own chatbot by using spaCy (spaCy is an open-source software library for advanced natural language processing, written in the programming languages Python and Cython):

SpaCy: An open-source library providing tools for advanced NLP tasks like tokenization, entity recognition, and part-of-speech tagging.

spaCy https://spacy.io/

In this article, I'm going to walk through a sentiment analysis project from start to finish, using open-source Amazon product reviews. However, using the same approach, you can easily implement mass sentiment analysis on your own products. We'll explore an approach to sentiment analysis with one of the most popular Python NLP packages: spaCy.

Spacy [0] is a state-of-art / easy-to-use NLP library from the pre-LLM era. This post is the Spacy founder's thoughts on how to integrate LLMs with the kind of problems that "traditional" NLP is used for right now. It's an advertisement for Prodigy [1], their paid tool for using LLMs to assist data labeling. That said, I think I largely agree with the premise, and it's worth reading the entire post.

The steps described in "LLM pragmatism" are basically what I see my data science friends doing — it's hard to justify the cost (money and latency) in using LLMs directly for all tasks, and even if you want to you'll need a baseline model to compare against, so why not use LLMs for dataset creation or augmentation in order to train a classic supervised model?

[0] https://spacy.io/

[1] https://prodi.gy/

spaCy

I chose spacy. Although it's not state of the art, it's very well established and stable.