Introduction - Data Science Guides

Welcome to PredictHQ’s Data Science documentation. This is your guide to getting started with PredictHQ’s intelligent event data for correlation and demand forecasting.

These articles are provided as a resource for Data Scientists to help get you up and running quickly.

We provide guides to using our API with common Data Science tools and libraries in Python. Articles include a link to a Jupyter Notebook that you can download and use. The guides include code samples and instructions on performing common tasks.

  • See our API documentation for more details on using PredictHQ’s API. You can also find more detailed documentation about each category in our Category Info guides.

  • See our Feature Engineering Guide for a guide to building ML features for your models and getting started with using events in your forecast

  • See our Demand Forecasting Guide for details on how to use intelligent event data in your demand forecasting model.

  • See our Live TV Events Notebooks for details on how Data Science teams and technical teams can use our Live TV events data.

  • See our Attended Events Notebooks for details on how Data Science teams and technical teams can use our Attended Events data.

  • See our Non-Attended Events Notebooks for details on how Data Science teams and technical teams can use our Public holidays, School holidays, and Observances data.

  • See our Academic Events Notebooks for details on how Data Science teams and technical teams can use our Academic Events category.

  • See our Frequently Asked Questions for more details on our event data, coverage, categories, ranking, and other topics.

Sign up to get data from the API

Sign up for a free developer trial and create an API Client and token in Control Center in order to use our API. Our notebooks come with free CSV data. Once you have a token update the notebook to use the token and you can pull back different data from our APIs.

Google Colab

We also provide our notebooks in Google Colab. Colab allows anybody to write and execute arbitrary python code through the browser and is especially well suited to machine learning, data analysis, and education.

The “Open in Colab” button now appears on top of notebooks that are available in Colab. By clicking on that button, the notebook opens immediately in Google Colab. It allows you to change and run the notebook code within the Colab environment without even needing to download the notebook.

Experiment with the notebooks and try changing the code to query different locations, date ranges, or any other code you want to change.

alt