A.I, Data and Software Engineering

Categorydata science

Advanced python part 2

python icon

In part 1, we introduced advanced string, bytes manipulation in Python. This article covers some advanced python knowledge with built-in functions and other useful tools for sequence iteration, data transformation. Useful built-in functions Use any() to return true if any of the sequence values are trueUse all() to return true only if all values are trueQuickly find the minimum/maximum value in a...

Advanced python: Styling, Boolean, String and bytes

python icon

Let get some more advanced python techniques, tools, libraries. Python coding style It is quite common for beginner to skip the coding style and conventions in any programming language. But when you have a chance to revisit your code or others’ code, you will soon recognise how important of following coding conventions. To learn more, you can visit PEP 8 — Style guide for Python code...

Continue training big models on less powerful devices

It would not be a surprise that you may not have a powerful expensive machine to train a complicate model. You may experience the problem of not enough memory during training in some epoch. This article demonstrates a simple workaround for this. The problem Training deep learning models requires a lot of computing power. For most laptop and desktop today, you can still train the models but it can...

Create bipartite graph from a rating matrix

bipartite graph from movie lens

As deep learning on graphs is trending recently, this article will quickly demonstrate how to use networkx to turn rating matrices, such as MovieLens dataset, into graph data. The rating data We use rating data from the movie lens. The rating data is loaded into rdata which is a Pandas DataFrame. This article demonstrates how to preprocess movie lens data. After processing, the rdata should look...

MLP for implicit binary collaborative filtering

multi-layer perception

In this post, we demonstrate Keras implementation of the implicit collaborative filtering. We also introduce some techniques to improve the performance of the current model, including weight initialization, dynamic learning rate, early stopping callback etc. The implicit data For demonstration purposes, we use the dataset generated from negative samples using the technique mentioned in this post...

A.I, Data and Software Engineering

PetaMinds focuses on developing the coolest topics in data science, A.I, and programming, and make them so digestible for everyone to learn and create amazing applications in a short time.

Pin It on Pinterest