erinconeill/kenya-survey

# kenya-survey ## Description This repository contains Python and Jupyter Notebook scripts for analyzing data from the Kenya Relief Survey. The survey aims to gather information about various aspects of life and health in different communities in Kenya. The analysis includes preprocessing the data, exploring key metrics, identifying trends, and conducting statistical tests to derive insights. ### Preprocessing - The data is read from an Excel file (`Kenya Relief Survey.xlsx`). - Various preprocessing steps are applied, including handling missing values, standardizing data, and converting categorical variables. ### Exploratory Data Analysis (EDA) - Baseline statistics are computed, including gender distribution, average age, number of unique communities, etc. - Analysis of responses from leadership and non-leadership roles, focusing on key changes and requests for the community. - Categorization and analysis of disease-related responses. - Exploration of the relationship between days unable to work and distance to health centers. ### Statistical Analysis - T-test to determine the significance of differences in days unable to work between communities with and without NGOs. ### Results The analysis provides insights into various aspects of health, community needs, and the impact of NGOs on community health. Key findings include the prevalence of certain diseases, community requests for improvements, and the correlation between health center distance and days unable to work. ### Conclusion This analysis offers valuable insights that can inform healthcare interventions, resource allocation, and policy decisions in the surveyed communities. Further research and targeted interventions may be needed to address specific health challenges and meet community needs effectively. ## Dependencies - csv - pandas - seaborn - matplotlib - numpy - collections - re - nltk - scikit-learn - scipy