Skip to content

Featrix User Guide

Welcome to the Featrix user guide. This guide covers everything you need to know to use Featrix effectively.

Quick Start

from featrixsphere.api import FeatrixSphere

featrix = FeatrixSphere()

# Train a Foundational Model
fm = featrix.create_foundational_model(data_file="your_data.csv")
fm.wait_for_training()

# Create a predictor
predictor = fm.create_binary_classifier(target_column="your_target")
predictor.wait_for_training()

# Make predictions
result = predictor.predict({"column1": "value1", "column2": 123})
print(result.predicted_class, result.confidence)

Guide Contents

# Guide What You'll Learn
01 Training Foundational Models Data requirements, sources, configuration, webhooks
02 Training Predictors Classifiers, regressors, custom thresholds, model cards
03 Running Predictions Single and batch predictions, interpreting results
04 Safety and Quality Verification, quality metrics, data integrity
05 Model Cards, Publishing, Monitoring Lifecycle management, production deployment
06 Training Movies Visualizing embedding space evolution during training
07 Metadata Columns Storing data that travels with records but isn't trained on
08 Jupyter Notebooks Visualization APIs for notebooks
09 When to Use Featrix Best fit scenarios, performance expectations
10 Troubleshooting & FAQ Common issues, automatic interventions, FAQ

Installation

pip install featrixsphere

Getting Help