Jailsonrs / Poneglyph

Poneglyph is an optimized distributed advanced analytics as a service framework designed to be highly efficient, flexible and scalable. It implements machine learning algorithms such as UMAP and Gaussian Mixture Models to yield insights and shed light to business, industry and scinentific questions.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool



Poneglyph is an optimized distributed advanced analytics as a service framework designed to be highly efficient, flexible and scalable. It implements machine learning algorithms such as UMAP and Gaussian Mixture Models to yield insights and shed light on business, industry and scientific questions.

Features

Application Structure:

Directory Structure

.
├── app
│   ├── data
│   │   ├── raw
│   │   │   └── dados_municipais.csv
│   │   └── transformed
│   │       ├── clustered_dataset
│   │       ├── dados_limpos.csv
│   │       └── UMAP_embeddings.csv
│   ├── index.html
│   ├── rsconnect
│   │   └── shinyapps.io
│   │       └── jailson-rodrigues
│   │           └── Cluster-test.dcf
│   ├── server.R
│   ├── src
│   │   └── R
│   │       ├── libs.R
│   │       ├── modules
│   │       │   ├── inputs.R
│   │       │   └── outputs.R
│   │       ├── multiClassSummary.R
│   │       └── MyGgthemes.R
│   ├── ui.R
│   └── www
│       ├── alert.js
│       └── style.css
├── appscreen.png
├── data
│   ├── raw
│   │   └── dados_municipais.csv
│   └── transformed
│       ├── clustered_dataset
│       ├── dados_limpos.csv
│       └── UMAP_embeddings.csv
├── README.md
├── src
│   ├── clustering.py
│   ├── Dockerfile
│   ├── ranking.py
│   └── sankey.R
└── UMAP-GMM.ipynb



Screenshots

About

Poneglyph is an optimized distributed advanced analytics as a service framework designed to be highly efficient, flexible and scalable. It implements machine learning algorithms such as UMAP and Gaussian Mixture Models to yield insights and shed light to business, industry and scinentific questions.


Languages

Language:Jupyter Notebook 91.5%Language:R 2.8%Language:HTML 2.3%Language:CSS 1.8%Language:Python 1.3%Language:Dockerfile 0.1%Language:JavaScript 0.1%