A few weeks ago, I and fellow Zindi ambassadors from East Africa organized the first East African virtual machine learning hackathon called AI4D Swahili News Classification Challenge. The virtual hackathon was a private hackathon open to participants from East Africa Countries (Tanzania, Kenya, Malawi, Uganda, and Rwanda).
If you don’t know Zindi, it is Africa’s largest data science competition platform, solving complex challenges using artificial intelligence (AI) and machine learning (ML). …
I remember the first time I created a simple machine learning model. It was a model that could predict your salary according to your years of experience. And after making it, I was curious about how I could deploy it into production.
If you have been learning machine learning, you might have seen this challenge in online tutorials or books. You can find the source code here if you are interested.
It was really difficult for me to figure out where I could deploy my model. …
Most trained machine learning models are saved as pickle files. This file type is the standard way of serializing and de-serializing objects in Python.
In order to make predictions, you need to load the saved trained model and then perform predictions from the inputs provided.
m2cgen (Model 2 Code Generator) is a simple Python library that converts a trained machine learning…
Happy new year to you, 2021 is here and you did it 💪. 2020 is now behind us, and even though 2020 has been a tough and strange year for many people around the world, there’s still a lot to celebrate. In 2020, I learned that all we need is the love & support of our loved ones, family members, and friends.
“In the face of adversity, we have a choice. We can be bitter, or we can be better. Those words are my North Star.”- Caryn Sullivan
This will be my first article for 2021, and I will talk…
Last week I organized a Tourism Machine Learning Hackathon called Tanzania Tourism Prediction Challenge hosted & supported by Zindi Africa and Tanzania Pycon Community during the Second Pycon conference here in Tanzania.
If you don’t know Zindi Africa, in short, Zindi Africa is Africa’s largest data science competition platform, solving complex challenges using artificial intelligence (AI) and machine learning (ML). The platform allows data scientists across the African continent to compete to solve challenges that focus on transport, health, social impacts, agriculture, African languages, electricity, or economics, to name a few.
Did you know that 90% of machine learning models never actually make it into production?
This means that the topic of machine learning deployment is rarely discussed when people learn machine learning. As a result, many AI practitioners know how to create useful ML models, but they find it difficult to deploy them into production.
Needless to say, machine learning deployment is one of the more important skills you should have if you’re going to work with ML models.
The topic of Machine Learning Model Deployment is not new nowadays, but many AI practitioners especially beginners find it difficult to deploy their models into production. In this article, we are going to learn how to call our model API from the Algorithmia platform to the Laravel application and make predictions.
This is the third and final part of the series focus on alternative hyperparameters optimization techniques you need to know. In the first part, we looked at the most commonly used methods (GridsearchCV and randomizedSearchCV) and the first alternative method called Hyperopt (click here to read the first part). In the second part we looked at another alternative hyperparameter optimization technique called scikit-optimize (click here to read the second part).
Now let’s learn the third alternative hyperparameter optimization technique.
Optuna is another open-source python framework for hyperparameter optimization that uses Bayesian method to automate search space of hyperparameters. The framework…
This is the second part of the series focus on alternative hyperparameters optimization techniques you need to know. In the first part, we looked at the most commonly used methods (GridsearchCV and randomizedSearchCV) and the first alternative method called Hyperopt. If this is your first time, I highly advise you to read the first part here.
Now let's learn the second alternative hyperparameter optimization technique.
Scikit-optimize is another open-source python library for hyperparameter optimization that implements several methods for sequential model-based optimization. The library is very easy to use and provides a general toolkit for Bayesian optimization that can be…
When working on a machine learning project, you need to follow a series of steps until you reach your goal, one of the steps you have to execute is hyperparameter optimization on your selected model. This task always comes after the model selection process (select the best model that is performing well than other models).
Before I define hyperparameter optimization you need to understand what is a hyperparameter. In short description, hyperparameters are different parameter values that are used to control the learning process and have a significant effect on the performance of machine learning models. Example of hyperparameters in…