air-quality-and-covid-19-data-insight

This project aims to investigate the relationship between long-term average exposure to low air quality and the risk of COVID-19 hospitalization in the United States.

analysis-of-labour-condition-applications-of-h1b-visas

This Project contains the tableau file and data for an interactive visualization of H1B LCA (Labor Condition Application) applications made in the United States, built using Tableau. The visualization shows the distribution of H1B LCA applications by state, occupation, wage level, and more, and allows users to filter/ drill down on various options

aws-etl--weather-analysis

classification-of-violent-crime-prediction-in-global-communities

This project is focused on analyzing communities and crime. Specifically, we are utilizing machine learning techniques to classify violent and non-violent crime rates. The aim is to provide insights into the factors contributing to these crime rates and explore potential solutions for reducing crime in these communities.

climate-prediction-model-for-temperature-forecasting

This project aims to predict Celsius temperatures using machine learning techniques. It utilizes a dataset containing historical temperature records, including the year, month, day, and the corresponding Celsius temperature for Joliet, IL.

clustering-and-validation-techniques

In this project, the objective is to implement different clustering methods to synthetic and real-world data and validate using external and internal validation techniques

coronary-heart-disorder-prediction-system

In this project, we will predict whether or not a person has coronary heart disease based on their health care factors.

credit-card-risk-forecasting-with-machine-learning

This project's main aim is to predict credit card delinquency for the upcoming month, and it uses a dataset from the UCI Machine Learning Repository, the focus was to assess predictive power and computational efficiency. The models' performances provided insights that could aid financial institutions in mitigating risks & making financial decision

credit-risk-assessment---mlops

Credit Risk Assessment project! This repository showcases a complete journey of predicting credit risk using machine learning and MLOps principles. You'll find everything from data preprocessing and feature engineering to building, training, and deploying the model.

data-analysis-projects

This repository includes the Data Analytics projects I completed while learning and practicing the subject.

data-science-cheat-sheets

A collection of Data Science cheat sheets.

data-science-cheatsheets

A collection of Data Science cheat sheets.

datasciencecoursera

datasharing

The Leek group guide to data sharing

divvy-analytics-for-bikes-trips

This project is to use Tableau to visualize the usage patterns of Divvy bikes in Chicago. By analyzing the trip data provided, we can gain insights into when, where, and how bikes are being used. This information can be useful for Divvy and the City of Chicago in planning future bike infrastructure and promoting sustainable transportation options.

eda-time_series

This project involves time series forecasting through EDA and uses ARIMA and SARIMA models. The goal is to analyze and understand data trends, then make accurate forecasts.

emotion-recognition-system---mlops

The Emotion Recognition System project is a end-to-end MLOps solution aimed at deploying a speech emotion recognition system on Google Cloud Platform (GCP). The project makes use of different GCP services such as Cloud Composer, Vertex AI, Artifacts Registry, and Model Registry to streamline the workflow from data generation to model deployment

feature-selection-techniques

This GitHub repository teaches feature selection and feature engineering techniques with practical examples and tutorials, making it a valuable resource for data scientists and machine learning engineers.

go-health---marketing-analysis-on-health-insurance-

investment-tourism-database-management-system

This project designed the A&S Consultancy Group database, which can be used in industries such as investment and travel portfolios. This database can help the firm and its clients make better decisions by providing analytical and visualization insights.

large-language-model-llm-

machine-learning---home-appliances-energy-prediction

This repository is a comprehensive resource for a machine learning project that predicts the energy consumption of home appliances. The repository includes the dataset used for training the predictive models, which includes a range of features related to home appliances and their usage pattern

machinelearning-ops

This is the Machine Learning Project Lifecycle repository! This project aims to guide you through the various steps involved in a machine learning project, covering aspects from inception to deployment.

ml-ops

Machine Learning In Production (MLOps)

mlops---airflow-docker

mlops---elk

In this Github Respository, I will guide you through setting up the ELK (Elasticsearch, Logstash, Kibana) stack for log management and visualization while simultaneously training a Linear Regression (LR) model. This integration enables efficient monitoring and analysis of log data generated during model training.

mlproject

pipeline_machine_learning

predicting-crime-patterns-in-world-wide-comunities

This project predicts crime rates in communities using regression analysis and dimensional reduction. The model is trained on historical crime data and can be used to predict future crime rates. The repository also includes code for data cleaning, preprocessing, and modeling.

predictive-healthcare-analytics-using-ml

This is a web application that aims to help with the diagnosis of various diseases such as breast cancer, chronic kidney disease, coronary heart disease, liver disease, and diabetes mellitus by analyzing different parameters. The application employs machine learning models on the backend, which is a technique of integrating several ML models