prmc

A Cost-based metric for Predictive Maintenance

https://github.com/hunkbenny/prmc

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (4.6%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

A Cost-based metric for Predictive Maintenance

Basic Info
  • Host: GitHub
  • Owner: HunkBenny
  • License: other
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 19.2 MB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 3 years ago · Last pushed 11 months ago
Metadata Files
Readme License Citation

README.md

PRMC

Repository tree:

   LSTMPRMC.ipynb
   README.md
   XGBOOSTPRMC.ipynb

data gold test.csv train.csv validation.csv

emp init.py

losses prmc keras.py xgboost.py

metrics maintenance.py ranking.py

models init.py

   prmc
           keras.py

packages hypopt modelselection.py version.py _init__.py

preprocessing keras.py

packages:

This folder contains code from the hypopt-package that was used during the hyper parameter search.
Hypopt GitHub: https://github.com/cgnorthcutt/hypopt

notebooks:

The notebooks 'LSTMPRMC.ipynb' and 'XGBOOSTPRMC.ipynb' contain code on training a model with the PRMC as objective. In both notebooks, after the "ANALYSIS" cell, an analysis is done with use of the PRMC-metric.

instance-based PRMC for XGBoost was loosely based on:

https://github.com/bram-janssens/B2Boost

Owner

  • Login: HunkBenny
  • Kind: user
  • Company: BSS-BV

Student Business Engineering: Data Analytics @ University of Ghent! 2.5 years of experience in PHP & Python. Data Science & Web Development.

GitHub Events

Total
  • Delete event: 1
  • Push event: 3
  • Pull request event: 2
Last Year
  • Delete event: 1
  • Push event: 3
  • Pull request event: 2