Using Featuretools to Predict Missed Appointments
In this tutorial, we show how Featuretools can be used to predict whether or not a patient will show up to a scheduled appointment using a dataset from Kaggle. We make all of the features from the most popular kernel on kaggle, and make some other interesting features automatically.
The Tutorial notebook from this repository exists on Kaggle. If you would prefer to work in that environment, you can fork the existing kernel to use as a starting point.
- We generate interesting aggregations by age and location automatically.
- We use a secondary time index to generate features from the no-show column without leaking invalid information.
Running the tutorial
If you would like to work on Kaggle, the Tutorial notebook has been uploaded as a kernel. You can fork that notebook to use as a starting point. If you prefer to work locally:
Clone the repo
git clone https://github.com/Featuretools/predict-appointment-noshow.git
Install the requirements
pip install -r requirements.txt
You will also need to install graphviz for this demo. Please install graphviz according to the instructions in the Featuretools Documentation
Download the data
You can download the data from Kaggle or create a kernel and use Featuretools there. After downloading, save the CSV to a directory called
datain the root of this repository.
Run the Tutorial using Jupyter
Featuretools is an open source project created by Feature Labs. To see the other open source projects we're working on visit Feature Labs Open Source. If building impactful data science pipelines is important to you or your business, please get in touch.
Any questions can be directed to email@example.com