A big city receives thousands of daily calls to its emergency services, reporting everything from illegal parking to life-threatening emergencies. In this liveProject, you’ll take on the role of a data scientist called in to advise on how the city can better allocate resources for these safety events. Your challenge is to create a machine learning model that can predict when and where different emergencies will occur. To do this, you’ll analyze data to identify trends, build and enhance a predictive model, and make your model explainable with model interpretability tools. You’ll also perform checks to ensure that the model won’t lead to bias or discrimination, and tweak your model so it can account for major lockdown events such as a pandemic.
This project is designed for learning purposes and is not a complete, production-ready application or solution.
This liveProject is for data scientists and data engineers, and software engineers looking to break into machine learning. To begin this liveProject, you will need to be familiar with:
- Intermediate Python
- Basics of pandas
- Basics of scikit-learn
- Basics of Jupyter notebook
- Basics of data science
- Basics of data visualization
you will learn
In this liveProject, you’ll learn to train and analyze machine learning models using common Python data science libraries. The skills you learn will be easy to transfer to other data science projects and workflows.
- Cleaning, filtering, and preprocessing data
- Analyzing and visualizing location-based and time dependent data
- Interactive data visualization with Jupyter Notebook and ipywidgets
- Model selection and hyper-parameter tuning
- Creating Python packages for data science projects
- Evaluating risks of bias and discrimination in production models
- Adjusting for unforeseen events