Arcaici

Marco Venturi's repositories

Distibuted_SVM

Distributed version of Support Vector Machine Model

Language:Python1 10

The repo contains a Hadoop cluster configuration and a client-server app. The goal is to predict smartphone's price range using a machine learning model generated over Apache Spark, and visualize charts about smarphone statistics using data originated by Apache Hive.

Language:HTML1 20

kubernetes_prometheus_configuration

This repo contain a single node kubernetes cluster configuration with the use of prometheus telemetry sistem for monitoring cluster-health, pods and services with cutom metrics set up for ExpressJS server.

Language:JavaScript1 10

Cats_Dogs_Breeds_Image_Classification

This project aims to implement a custom CNN as well as well-known CNN techniques for image classification of cat and dog breeds.

Language:Python020

datasciencecoursera

Language:HTML010

datasharing

The Leek group guide to data sharing

000

ExData_Base_Plotting_System

Plotting Assignment 1 for Exploratory Data Analysis Datascience Specialization

000

ITADATAhack2023

This repository documents the participation of our team of data scientist students from the University of Perugia in the ITADATAhack 2023, a national event dedicated to innovation in the field of data!

Language:Jupyter Notebook000

MLCoffebreak-Deployed-Kubernetes

CoffeBreak is a Flask-based web application that predicts the type of caffeine drink based on user input. It uses a trained machine learning model to make predictions and stores the input data in a Cassandra database

Language:Python010

Opera-Graph-Visualization

This repo use data from graph drawing contest (2022) and JavaScript libraries, with purpose to search patterns through data visualizing them with graphs algorithms

Language:HTML010

TobaccoControlMonitor_WHO

This repository presents a study on tobacco product consumption around the world, utilizing R for exploratory data analysis and statistical tests. The dataset is collected and sourced from the World Health Organization.

Language:R010

whatcooking

My First Machine Learning Project. What's Cooking is a dataset available on Kaggle and provided by yummly. The Dataset include a train.json file containing 39774 recipes with 20 different cuisine types that results in a unbalanced dataset. The challenge is to find a model that predict cuisine types using the ingredients as features.