passantadel Goto Github PK

auto-encoder

Implementation of an autoencoder using TensorFlow and Keras for image reconstruction. The script focuses on encoding and decoding images, along with the addition of noise for robustness training.

credit-card-fraud-detection

exploratory-of-spotify-streaming-data

This project focuses on analyzing the streaming data of various artists on spotify.

extracting-and-visualizing-stock-data

This project aims to analyze the historical stock price and revenue data of Tesla and GameStop using web scraping

hr-analysis-case-study

This project is focused on building and evaluating several classification models to predict employee promotions. It involves data preprocessing, exploratory data analysis, and the implementation of various machine learning algorithms.

image_colorization

This project demonstrates image colorization using an autoencoder architecture in TensorFlow and Keras. The code takes grayscale images as input and produces corresponding colorized images. The architecture includes downsampling and upsampling layers to capture and reconstruct color information.

iris-analysis

Iris dataset analysis (Classification) using multiple models

mlops

passantadel

principal-component-analysis-pca-

This script demonstrates how to perform image compression using Principal Component Analysis (PCA) in Python. It uses the scikit-learn library for PCA and OpenCV for image processing.

rumor-detection

In this project, I developed a machine learning model to detect rumors on Twitter. The model is based on a Random Forest classifier and was trained on a dataset of tweets. The key steps involved data preprocessing, feature extraction, and model training. The final model achieved impressive performance metrics.

simple-linear-regression-model

Simple linear regression model with salary dataset

spotify-analysis

titanic-survival-prediction

This repository contains a Python script for predicting survival on the Titanic using a Random Forest Classifier. The script utilizes the pandas and scikit-learn libraries for data manipulation and machine learning.

vehicle_attributes_identification-

This project focuses on the identification of five essential attributes of any vehicle: type, color, damage status, speed, and license plate number. Leveraging the power of computer vision and machine learning, we have implemented YOLOv8 to achieve accurate and real-time attribute recognition.