Welcome to my Data Science Projects repository! This repository contains a curated collection of my data science projects, each designed to showcase my skills and expertise in various aspects of data science. From data analysis and machine learning to data visualization, each project demonstrates different techniques and methodologies that are essential in the field of data science.
This project aims to predict the survival of passengers on the Titanic using machine learning techniques. The dataset contains various features such as passenger age, gender, ticket class, and more. The goal is to build a model that can accurately predict whether a passenger survived the tragic sinking of the Titanic.
The ensemble approach combining XGBoost and Random Forest classifiers achieved an accuracy score of 89%, demonstrating the effectiveness of using multiple models to enhance predictive performance.
This project aims to predict house prices in Delhi using various machine learning techniques. The dataset includes features such as the number of bathroom, location, square footage, and more. The goal is to build a model that can accurately predict house prices based on these features.
The ensemble approach combining Gradient Boosting Regressor, XGBoost Regressor, and Random Forest Regressor achieved an accuracy score of 90%, demonstrating the effectiveness of using multiple models to enhance predictive performance.
This project aims to predict medical insurance prices using various machine learning techniques. The dataset includes features such as age, sex, BMI, number of children, smoking status, and region. The goal is to build a model that can accurately predict the price of medical insurance based on these features.
The Random Forest Regressor achieved an accuracy score of 95%, demonstrating its effectiveness in predicting medical insurance prices with high accuracy.
This project aims to predict the likelihood of heart stroke using various machine learning techniques. The dataset includes features such as age, gender, hypertension, heart disease, ever married, work type, residence type, average glucose level, BMI, and smoking status. The goal is to build a model that can accurately predict the risk of a heart stroke based on these features.
Additionally, the SMOTE (Synthetic Minority Over-sampling Technique) was used to address class imbalance in the dataset, enhancing the model's ability to predict strokes accurately.
The Random Forest Classifier, combined with SMOTE for balancing the dataset, achieved an accuracy score of 99%, demonstrating its high effectiveness in predicting heart stroke risk.
This project aims to predict an individual's weight using various machine learning techniques. The dataset includes features such as height, age, gender, and other relevant factors. The goal is to build a model that can accurately predict weight based on these features.
The ensemble approach combining XGBoost and LightGBM classifiers achieved an accuracy score of 91%, demonstrating the effectiveness of using multiple models to enhance predictive performance.