Ratings and Reviews 0 Ratings

Total
ease
features
design
support

This software has no reviews. Be the first to write a review.

Write a Review

Ratings and Reviews 0 Ratings

Total
ease
features
design
support

This software has no reviews. Be the first to write a review.

Write a Review

Alternatives to Consider

  • Epicor Connected Process Control Reviews & Ratings
    4 Ratings
    Company Website
  • SMS Storetraffic Reviews & Ratings
    111 Ratings
    Company Website
  • Building Logistics Reviews & Ratings
    192 Ratings
    Company Website
  • PackageX OCR Scanning Reviews & Ratings
    46 Ratings
    Company Website
  • CompUp Reviews & Ratings
    66 Ratings
    Company Website
  • SAP S/4HANA Cloud Public Edition Reviews & Ratings
    3,438 Ratings
    Company Website
  • dbt Reviews & Ratings
    212 Ratings
    Company Website
  • Stigg Reviews & Ratings
    25 Ratings
    Company Website
  • Teradata VantageCloud Reviews & Ratings
    992 Ratings
    Company Website
  • STACK Reviews & Ratings
    1,400 Ratings
    Company Website

What is MPCPy?

MPCPy is a Python-based library specifically created to facilitate the testing and implementation of occupant-integrated model predictive control (MPC) in building systems. This innovative tool focuses on utilizing data-driven, simplified physical or statistical models to predict the performance of buildings and improve control methodologies. It consists of four key modules that offer object classes for tasks such as data importation, engagement with either real or simulated systems, estimation and validation of data-driven models, and optimization of control inputs. While MPCPy acts as a comprehensive integration platform, it relies on a variety of free, open-source third-party software for executing models, conducting simulations, implementing parameter estimation techniques, and optimizing solvers. This includes Python libraries for scripting and data manipulation, as well as specialized software solutions designed for specific functions. Importantly, the tasks involving modeling and optimization of physical systems are currently based on the requirements of the Modelica language, which significantly enhances the package's flexibility and capabilities. Overall, MPCPy empowers users to harness sophisticated modeling methods within a dynamic and cooperative environment, ultimately fostering improved building system performance. Furthermore, it opens up opportunities for researchers and practitioners alike to experiment with cutting-edge control strategies tailored to real-world scenarios.

What is MLBox?

MLBox is a sophisticated Python library tailored for Automated Machine Learning, providing a multitude of features such as swift data ingestion, effective distributed preprocessing, thorough data cleansing, strong feature selection, and precise leak detection. It stands out with its capability for hyper-parameter optimization in complex, high-dimensional environments and incorporates state-of-the-art predictive models for both classification and regression, including techniques like Deep Learning, Stacking, and LightGBM, along with tools for interpreting model predictions. The main MLBox package is organized into three distinct sub-packages: preprocessing, optimization, and prediction, each designed to fulfill specific functions: the preprocessing module is dedicated to data ingestion and preparation, the optimization module experiments with and refines various learners, and the prediction module is responsible for making predictions on test datasets. This structured approach guarantees a smooth workflow for machine learning professionals, enhancing their productivity. In essence, MLBox streamlines the machine learning journey, rendering it both user-friendly and efficient for those seeking to leverage its capabilities.

Media

Media

Integrations Supported

Python
GitHub
Ubuntu

Integrations Supported

Python
GitHub
Ubuntu

API Availability

Has API

API Availability

Has API

Pricing Information

Free
Free Trial Offered?
Free Version

Pricing Information

Pricing not provided.
Free Trial Offered?
Free Version

Supported Platforms

SaaS
Android
iPhone
iPad
Windows
Mac
On-Prem
Chromebook
Linux

Supported Platforms

SaaS
Android
iPhone
iPad
Windows
Mac
On-Prem
Chromebook
Linux

Customer Service / Support

Standard Support
24 Hour Support
Web-Based Support

Customer Service / Support

Standard Support
24 Hour Support
Web-Based Support

Training Options

Documentation Hub
Webinars
Online Training
On-Site Training

Training Options

Documentation Hub
Webinars
Online Training
On-Site Training

Company Facts

Organization Name

MPCPy

Company Location

United States

Company Website

github.com/lbl-srg/MPCPy

Company Facts

Organization Name

Axel ARONIO DE ROMBLAY

Date Founded

2017

Company Website

mlbox.readthedocs.io/en/latest/

Categories and Features

Machine Learning

Deep Learning
ML Algorithm Library
Model Training
Natural Language Processing (NLP)
Predictive Modeling
Statistical / Mathematical Tools
Templates
Visualization

Popular Alternatives

Cybernetica CENIT Reviews & Ratings

Cybernetica CENIT

Cybernetica

Popular Alternatives

MyDataModels TADA Reviews & Ratings

MyDataModels TADA

MyDataModels
Neural Designer Reviews & Ratings

Neural Designer

Artelnics
COLUMBO Reviews & Ratings

COLUMBO

PiControl Solutions
INCA MPC Reviews & Ratings

INCA MPC

Inca Tools