How to build models quickly without sacrificing code’s quality — Building machine learning models isn’t easy. Heavy datasets and tricky data formats. A ton of hyper-parameters, models, optimization algorithms. Not talking about generic programming adventures like debugging, handling exceptions, and logging. It is especially true for the R&D (Research and Development) style of work when models, approaches (and sometimes, even…

An opinionated approach to structure your try-except code — Exceptions mechanism is widely adopted among modern programming languages, and Python is not an exception. (Pun intended!) Though this topic could seem obvious, like wrap your code blocks with try-catch clauses, and that’s all, there are some minor but important details, and taking them into account should make your code…

Using the standard library to convert a function’s signature into a console arguments parser — When working on machine leanring projects, you need to write lots of ad-hoc code snippets: downloading and reading/unpacking the data, converting the data into a convenient format, building training pipelines, and many more. You probably reuse some of these scripts, but the rest of them you’ll throw away after a…

A parable about missed deadlines and over-engineering — Some time ago I attended to a coding interview for the position of Data Scientist at one start-up. I felt myself well-prepared and confident, practicing lots of programming puzzles, coding various Machine Learning techniques from scratch, and having several years of programming experience under the belt. What can go wrong? …

A small comparison of various ways to serialize a pandas data frame to the persistent storage — When working on data analytical projects, I usually use Jupyter notebooks and a great pandas library to process and move my data around. It is a very straightforward process for moderate-sized datasets which you can store as plain-text files without too much overhead. However, when the number of observations in…

Implementing a simple neural network training loop with Python, PyTorch, and TorchVision. — Several months ago I started exploring PyTorch — a fantastic and easy to use Deep Learning framework. In the previous post, I was describing how to implement a simple recommendation system using MovieLens dataset. This time I would like to focus on the topic essential to any Machine Learning pipeline…

Applying neural network to make a simple recommendation system for MovieLens ratings dataset — Recently I’ve started watching fast.ai lectures — a great online course on Deep Learning and its applications. In one of his lectures, the author discusses the building of a simple neural network based recommendation system with application to the MovieLens dataset. While the lecture is an excellent source of information…

Reducing dimensionality of the data with clustering — The “classical” machine learning algorithms usually expect training dataset in the format of two matrices — a matrix with samples and an array with targets. However, how to deal with datasets where observations don’t have a fixed length? Consider the following case. You have a dataset of files where each…

Modern deep learning architectures show quite good results in various fields of artificial intelligence. One of them is images classification. In this post, I am going to see if one could achieve an accurate classification of images by applying out-of-the-box ImageNet pre-trained deep models from Keras Python package. Note: The…