Gain Insights from Your URLs in Python — Motivation Have you ever tried to extract features and insights from URLs, but found it difficult to do so? Wouldn’t it be nice if you can extract features and create a nice network graph for your URLs like below?

And How to Create One in One Line of Code — Motivation It is important to structure your data science project based on a certain standard so that your teammates can easily maintain and modify your project. But what kind of standard should you follow? …

Make Sure Your Data Matches Your Expectation — Motivation In a data science project, it is not only important to test your functions, but it is also important to test your data to make sure they work as you expected. In the previous article, I showed how to use Great Expectations to validate your data. Great Expectations: Always Know What to Expect From Your Data Ensure Your Data Works as Expected Using Pythontowardsdatascience.com

A Comprehensive Introduction to Collaborating Filtering in Python — Motivation Imagine you have a database of movie ratings from different users. There are some movies in the system that your users haven’t watched. How do recommend new and relevant movies to your users using this data? One straightforward approach is to guess the rating of user 1…

Optimize Your SQL Code with Python and DuckDB — Motivation As a data scientist, you might be familiar with both Pandas and SQL. However, there might be some queries, transformations that you feel comfortable doing in SQL instead of Python. Wouldn’t it be nice if you can query a pandas DataFrame using SQL… …while also speeding up your code when…

Keep Your Data, Models, Experiments, and Code in One Place — Motivation As a data scientist, you might want to version your code, model, data, parameters, and metrics so that you can reproduce a certain experiment. GitHub is a great platform for version control your code, but it is not ideal to version your data, model, and metrics for two reasons: GitHub…

Containerize and Deploy Your ML Model in Python — Motivation You have just built a machine learning model to predict which group a customer belongs to. The model seems to do a good job in segmenting your customers. …

Make Sure Your NLP Model Works as Expected — Motivation Your NLP model doesn’t throw any errors when being tested on new data. Does it mean it can be used for production? Not necessary. ML systems can run to completion without throwing any errors but can still produce incorrect outputs. Thus, it is important to test the behaviors of your…