plex-recommender

Description: Get movie/tv recommendations based on your current PleX library. It will go through each item in the list, pull the number of recommendations you request, tally them, and then print out an ordered list of the most recommended items based on your inputs.

Notes: In order for it to work you will need a TMDB API key, which is free.

The script uses no external libraries, and is built for Python 3. There is little in the way for error checking bad user input.

Creating .json: I recommend using Tautulli to create the main .json for ingestion, the script is built around this specific export format. To do that, go to the library you want to export, choose 'Export Metadata' and set the following different from default:

Data File Format: JSON
Custom Metadata Fields: guids.id
Media Info Export Level: Level 0 - None / Custom

From there, all you have to do is run the script and select the previously created .json.

Example usage and output:

python .\recommender.py

(R)ecommended - From "recommended" list on media page.
(S)imilar - From similar keywords and genres.
Select recommendation type (R/S):
        s
Enter media type (Movie/TV):
        m
Enter number of recommendations (range 1-20):
        10
Enter TMDB API key:
        xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Enter full path to Tautulli metadata output .json with guids.id field:
        ".\Library - Movies - All [1].json"


Extracting TMDB IDs from list of media at:
        .\Library - Movies - All [1].json...

Getting 10 TMDB recommendations for each of the 1166 IDs...
        Progress: |██████████████████████████████| 100.00% Complete

1 titles with no recommendations:
        Zombie Cop (1991)

Total recommendations:
        7947

Top 10 recommendations:
        Movie - Death Race (2008)
        TMDB - https://www.themoviedb.org/movie/10483
        IMDB - https://www.imdb.com/title/tt0452608/
        Recommended - 125 times

<snip>

Plex-recommender - Get movie recommendations based on your current PleX library

Related tags

Overview

plex-recommender

Owner

6002project-rl - An implemention of offline RL on recommender system

Elliot is a comprehensive recommendation framework that analyzes the recommendation problem from the researcher's perspective.

Reinforcement Knowledge Graph Reasoning for Explainable Recommendation

RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendation

Graph Neural Networks for Recommender Systems

This library intends to be a reference for recommendation engines in Python

Cross Domain Recommendation via Bi-directional Transfer Graph Collaborative Filtering Networks

Deep recommender models using PyTorch.

A library of Recommender Systems

A tensorflow implementation of the RecoGCN model in a CIKM'19 paper, titled with "Relation-Aware Graph Convolutional Networks for Agent-Initiated Social E-Commerce Recommendation".

Cross-Domain Recommendation via Preference Propagation GraphNet.

Use Jupyter Notebooks to demonstrate how to build a Recommender with Apache Spark & Elasticsearch

The source code for "Global Context Enhanced Graph Neural Network for Session-based Recommendation".

Fast Python Collaborative Filtering for Implicit Feedback Datasets

E-Commerce recommender demo with real-time data and a graph database

A framework for large scale recommendation algorithms.

EXEMPLO DE SISTEMA ESPECIALISTA PARA RECOMENDAR SERIADOS EM PYTHON

Code for ICML2019 Paper "Compositional Invariance Constraints for Graph Embeddings"

Collaborative variational bandwidth auto-encoder (VBAE) for recommender systems.

RecList is an open source library providing behavioral, "black-box" testing for recommender systems.