OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Qrec

QRec is a Python framework for implementing and evaluating recommender-system models, including models that use social recommendation data. It provides configuration-based model runs and evaluation options such as test sets, automatic train/test partitioning, and cross-validation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Qrec — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use QRec when a Python-based workflow for configuring recommendation models and evaluating them against defined data splits suits the experiment.

Who it is for

  • Researchers prototyping or comparing recommender-system models.
  • Developers implementing recommendation algorithms through QRec's interfaces.

Documented uses

  • Configure a recommendation model against ratings data.
  • Use social data with models that support social recommendation.
  • Evaluate models with a specified test set, an automatic data split, or cross-validation.
  • Run prediction for a specified list of users without evaluation.
Before you choose

Requirements & limits

  • The README specifies Python 3.7.4 and TensorFlow 1.14 or later as supported requirements, and lists pinned package versions.
  • Ratings and social-data files require column mappings; rows may be separated by spaces, tabs, or commas.
  • The documented model-run path uses a model-specific configuration file and main.py; snippet.py is an alternative code-based route.
  • The repository describes Windows, Linux, and macOS support.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Configure and run a recommendation model

Run a QRec recommendation model using its documented configuration-file workflow.

Before you start

  • Python 3.7.4 and TensorFlow 1.14 or later are identified as supported requirements.
  • Install the README-listed dependencies, including gensim 4.1.2, joblib 1.1.0, NumPy 1.20.3, SciPy 1.6.2, and TensorFlow 1.14.0.
  • Prepare ratings data, and social data if needed by the selected model; rows may be space-, tab-, or comma-separated.

Steps

  1. Open the configuration file for the selected model in the config directory.

  2. Set the ratings file path and, when applicable, the social-data path and their column mappings.

  3. Set the model name and choose an evaluation setup, such as a test-set path, automatic partition ratio, or cross-validation fold count.

  4. Run main.py.

Expected outcome

The documented workflow runs the selected recommendation model with the configured data and evaluation setup.

Guide limitations

  • The README's listed dependency versions include TensorFlow 1.14.0; it does not establish compatibility with other dependency combinations.
  • The README does not provide a complete dataset preparation example in the included usage instructions.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
Coder-Yu/QRec · Official homepage title · retained in its source language
How we review sourcesSuggest a correction

Related options

SELFRec — The QRec README points to SELFRec for PyTorch implementations of some models; QRec is described as TensorFlow-based.