Once a machine learning model performs acceptably well on validation data, we’ll likely wish to see how it does on real-world data. Streamlit makes it easy to publish models to collect and act on user input.

Categorical data consists of variables that can take on a limited set of values(“levels”). Common examples include gender, grades and star-ratings. Let’s discuss some of the techniques for extracting insights from it.

In database lingo, partitioning refers to the splitting of a table into smaller physical units. It helps speed up queries by reducing the amount of data to sift through, and enabling action on chunks rather than individual rows.

It’s always fascinating watching a well orchestrated production line at work (How It’s Made). Raw materials go in, magic happens, and something wonderful comes out the other end. Such elegant efficiency can, and does exist in machine learning too.

With the recent surge in floods and droughts, and the constantly shifting weather patterns witnessed throughout the country; it’s easy to conclude that climate change is at work here. But, does historical data back this assertion?

A probability distribution is “the mathematical function that gives the probabilities(likelihood) of occurrence of different possible outcomes for an experiment” - Wikipedia

More often than not, a rather hefty amount of work is required to transform and/or aggregate raw data into a form that can be fed into graphical software to yield elaborate visualisations. This, however, doesn’t always have to be the case.