amenalahassa/women_poverty_insight

International Women's Day Challenge on Zindi: zindi.africa ## About International Women's Day Challenge on Zindi This repo contains the code for the International Women's Day Challenge on Zindi. The challenge is to build a predictive model that accurately estimates the % of households per ward that are female-headed and living below a particular income threshold by using data points that can be collected through other means without an intensive household survey like the census. I first tried to build a model using the data provided in the challenge. And also do some data analysis to understand the data better. My main intention was to build a model using Tensorflow Decision Forest. But I also tried to build a model using Yggdrasil Decision Forest and Deep Neural Network. ### Technologies Used - Python - Pandas - Numpy - Matplotlib - Seaborn - Scikit-learn - Tensorflow DF - YDF (Yggdrasil Decision Forest) ### Data The data is provided by Zindi. I can't share the data here. But you can download the data from the Zindi website. ### Notebooks - analysis.ipynb: Data analysis of the provided data and some visualizations. - tfdf_model.ipynb: Model building using Tensorflow Decision Forest. - ydf_model.ipynb: Model building using Yggdrasil Decision Forest. - dnn_model.ipynb: Model building using Deep Neural Network.