Hi, I'm Happiness Ndanu!
I’m a proficient data analyst skilled in R and Python with a passion for transforming data into clear insights and business value. Currently expanding into data science, I’m building expertise in machine learning and predictive modeling through hands-on projects. This portfolio showcases both my proven analytics skills and my journey into advanced data science.
Sleep Disorder & Lifestyle Analysis
Developed a machine learning model to predict sleep disorders by analyzing lifestyle and physiological data, including age, gender, occupation, sleep quality, stress levels, and . The project involved Exploratory Data Analysis (EDA),data preprocessing, feature engineering, and the application of classification algorithms such as Logistic Regression. This work demonstrates the application of machine learning in healthcare analytics, offering insights for early detection and intervention strategies.
Social Media & Entertainment DashBoard
Developed an interactive R Shiny dashboard to analyze social media fatigue, integrating EDA techniques to explore user demographics and usage patterns. The application allows users to input age, gender, and daily social media usage time to predict fatigue levels, visualized through dynamic plots. This tool provides insights into user behavior, aiding in understanding the impact of social media consumption on well-being.
Superstore Sale Analysis
Conducted a comprehensive analysis of Superstore sales data spanning multiple years to uncover key performance indicators and trends. Utilized R for data cleaning, transformation, and visualization, employing libraries such as ggplot2. The analysis revealed insights into sales distribution across regions, product categories, and customer segments, identifying areas of high performance and opportunities for improvement. This project demonstrates the application of data analysis techniques to drive business decision-making and strategy.
Tuberculosis Cases Analysis
Developed an interactive R Shiny dashboard to monitor and analyze tuberculosis (TB) cases across Kenya. The application visualizes key metrics such as case notifications, treatment outcomes, and demographic distributions, enabling stakeholders to identify trends and areas requiring intervention. Utilized shinydashboard for UI layout, plotly for interactive visualizations, and dplyr for data manipulation, ensuring a user-friendly interface for public health officials and administrators.
Crime Data Analysis
Conducted an in-depth analysis of crime data to identify patterns and trends over a six-month period. Utilized R for data wrangling, visualization, and statistical analysis, employing libraries such as dplyr, ggplot2, and lubridate. The analysis focused on crime types, time of occurrence, and geographic distribution, providing insights into areas with higher crime rates and temporal patterns. This project demonstrates the application of data analysis techniques to inform public safety strategies and resource allocation.
HealthCare Workers Vaccination Analysis
Developed an interactive R Shiny dashboard to monitor and analyze COVID-19 vaccination rates among healthcare workers. The application provides real-time visualizations of vaccination coverage, stratified by demographics and healthcare settings, enabling stakeholders to identify gaps and target interventions effectively. Utilized shinydashboard for UI layout, plotly for interactive visualizations, and dplyr for data manipulation, ensuring a user-friendly interface for public health officials and administrators.
Mental Health Cases Analysis
Developed an interactive R Shiny dashboard to explore and visualize mental health data, focusing on key indicators such as prevalence rates, treatment access, and demographic disparities. The application allows users to interact with dynamic visualizations, including bar charts, line graphs, and choropleth maps, to gain insights into mental health trends and disparities.
Weather Prediction Model
Developed a machine learning model to predict weather patterns in Nairobi, Kenya, utilizing historical meteorological data. The project involved data preprocessing, feature engineering, and the application of regression algorithms to forecast variables such as temperature, humidity, and precipitation. The model provides insights into seasonal variations and can assist in planning for agriculture, tourism, and disaster management in the region.