API Client

This module provides a set of functions for performing relevance-based predictions using the Cambridge Sports Analytics (CSA) API. The relevance engine offers flexible prediction models that support single prediction tasks, multi-y prediction tasks (multiple dependent variables), and multi-theta prediction tasks (multiple sets of circumstances).

Key Features

• Single Task Prediction: Supports predictions with one dependent variable and one set of circumstances.

• Multi-y Task Prediction: Allows for predictions with multiple dependent variables and a single set of circumstances.

• Multi-theta Task Prediction: Enables predictions with one dependent variable and multiple sets of circumstances.

• Relevance-Based Grid Prediction: Generates optimal predictions by evaluating various thresholds and variable combinations.

• MaxFit Prediction: Finds the best fit model based on adjusted relevance.

Important

Multi-y and multi-theta tasks cannot be executed simultaneously. Please structure your inputs accordingly or loop through multiple calls to handle these cases separately.

Usage

The main functions in this module include:

• predict_grid: For generating the relevance-based optimal grid prediction as a composite predictions across various combinations of variables and maxfit thresholds.

• predict_maxfit: For finding the best fit model based on relevance.

• predict: For general relevance-based predictions.

Each function takes inputs in the form of NumPy arrays for y, X, and theta, and utilizes option classes (PredictionOptions, MaxFitOptions, GridOptions) to configure the prediction task.

See api_client.py in the package for more details.