When we are training a machine learning model, we have some choices to make, from which model to use, how to prepare our data set, how to handle outliers, and so on.
One of the choices is the hyperparameters, those are the parameters that control the learning process but can’t be derived by the training itself. Some examples are:
Some of the questions that come along are…
In this post I’m going to discuss how to make real-time predictions with incoming stream data from Apache Kafka, the solution we are going to implement looks like this:
Hyperparameter tuning is an important part of the machine learning pipeline—most common implementations use a grid search (random or not) to choose between a set of combinations.
In this article, we’ll use evolutionary algorithms with the python package sklearn-genetic-opt to find the set of parameters that optimizes our defined cross-validation metric. This package has some functionalities that can make this process easier:
Learn how to find the optimal number of positions needed to manage incoming traffic.
Finding the right number of positions to use in a queue system, has been a study case for a long time now, it has applications in several fields and industries, for example finding the optimal number of call centers agents, deciding the number of bankers in a support station, network traffic analysis and so on.
There are several methods to analyze this problem, in this article, we are going to take a look at how to solve it using Erlang C with python’s Pyworkforce package.
In this post, we are going through the main aspect of MLflow, an open-source platform to manage the life cycle of machine learning models.
MLOps is a methodology for enabling collaboration across data scientists, it helps to gain control over different models versions, multiple experiments within the same problem, and models management and deployment. There are several both open source and commercial solutions to approach this problem, we are going to take a look at MLflow.
According to the MLflow’s site:
In this post, you will learn how to:
* Train and save a machine learning model using Sckit-learn
* Create an API that can take incoming predictions requests
* Get your API running using Docker
* Test your API performance with Locust
Machine learning is definitely one of the hottest topics in data science, there is a lot of resources about how to train your model, from data cleaning, feature selection, and how to choose between a lot of candidates and fine-tune them.
At this point, everything must be working great on your computer, but when it comes to deploying…