Use Lambda, API Gateway, and AWS to make your models cheap and easy for others to use at scale

Photo by Riccardo Bertolo


If you’re not scraping data, how are you going to remain competitive?


Eight lines of Python to memoize ANY Dynamic Programming problem. Only one if you’re feeling snarky

Don’t you want to be a cool Dynamic Programming Wizard like him? Photo by Nikolay Ivanov from Pexels


Getting Started

Pipelines can be hard to navigate here’s some code that works in general.

Photo by Quinten de Graaf on Unsplash



from datasets import list_datasets, load_dataset, list_metrics
from sklearn.pipeline import FeatureUnion, Pipeline
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn import svm

As an NLP engineer, I’m going to be out of a job soon 😅

Photo by C. Cagnin from Pexels


How to train a chatbot to sound like anyone with a phone, including your deceased relatives.

Photo by Manea Catalin from Pexels


Label Smarter Not More.

Photo by RUN 4 FFWPU from Pexels


There is a dearth of good psychotherapy data. Let’s work on that.

Photo by Polina Zimmerman from Pexels


Figuring out what words are predictive for your problem is easy!

Photo Credit: Kendrick Mills


It’s only ~100 lines of code but the tweets are infinite.

The Author’s rendition of a Twitter bot


  1. Walk through setting up a Twitter bot from scratch
  2. Train one of the most cutting edge language models to generate text for us
  3. Use the Twitter API to make your bot tweet!

Nicolas Bertagnolli

Sr. Machine Learning Engineer interested in NLP. Let’s connect on LinkedIn!

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store