Sleep Health Analysis

Overview

This repository contains machine learning models and Python analysis scripts based on Sleep Health Lifestyle dataset. The goal of this project is to leverage advanced machine learning techniques to understand and predict various aspects of sleep quality and its impacts on health.

See etl-pipelines branch for the ETL workflow orchestration.

Features

• Data Collection: Scripts for collecting and preprocessing a dataset from Kaggle.
• Model Training: Scripts for training machine learning models on sleep data.
• Analysis: Tools for analyzing the results and extracting insights about sleep patterns and their health implications.
• Visualization: Plots to visualize sleep trends and model predictions.

Technologies Used

• Python
• Pandas, NumPy
• Matplotlib, Seaborn
• Scikit-learn

Index

• Data Cleansing: missing values and outliers
• Univariate Analysis Plots (pie, bars, density, count)
• Multivariate Analysis Plots (bars, scatter, lines, count, correlation heatmap)
• Principal Components Analysis (PCA)
• Standardization of Data and Applying PCA (scatter plots, heatmaps, 3D cube plot)
• Clusters (3D cube plots)
• Linear Progression Models