Recommender Systems Python Packages

ranx

⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍

recbole

A unified, comprehensive and efficient recommendation library

tensorflow-ranking

Learning to Rank in TensorFlow

merlin-dataloader

The merlin dataloader lets you rapidly load tabular data for training deep leaning models with TensorFlow, PyTorch or JAX

irspack

Train, evaluate, and optimize implicit feedback-based recommender systems.

caserecommender

A recommender systems framework for Python

fuxictr

A configurable, tunable, and reproducible library for CTR prediction https://fuxictr.github.io

datarec-lib

A Python Library for Standardized and Reproducible Data Management in Recommender Systems

prelims

Front matter post-processor for static site generators

similaripy

High-performance KNN similarity functions in Python, optimized for sparse matrices

datarec

Standardized & reproducible data management for recommender systems.

rank-eval

⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍

recometrics

(Python, R, C++) Library-agnostic evaluation framework for implicit-feedback recommender systems

repsys-framework

Framework for developing and analyzing recommender systems.

ml-recsys-tools

Tools for development of recommendation systems in Python.

recsysk

Framework-agnostic recsys benchmarking harness — pinned benchmarks, pluggable algorithms, reproducible runs.

rs-metrics

Recommendation systems metrics

fneighcf

Python implementation of 'Factor in the neighbors: Scalable and accurate collaborative filtering'

ezsasrec

An easy and efficient tool to build sequential recommendation system utilizing SASRec

lightfm-pandas

LightFM convenience tools.

teamoflow

A TensorFlow 2.X-based matrix factorization framework, particularly for the purpose of query (user)-value (item) matching.

neurec

An open source neural recommender library

rankcal

Calibration and uncertainty quantification for ranking systems

xcolumns

Consistent Optimization of Label-wise Utilities in Multi-label classificatioN