Ada Kibet

Scraping twitter handles of the most popular Kenyan twitter users from various websites, scraping their most recent tweets using tweepy then classifying the tweets into 4 major categories (economic, social, health and culture) through Jaccard similarities and finally observing the tweets count relationship in the 4 groups using K-means clustering.

Change point analysis to quantify the impact of the Kenyan government policy interventions to slow the spread of COVID-19.

Change point analysis is done through the calculation of spreading and recovery rate parameters of Covid-19 at each intervention. The model used performs bayesian inferencing for central epidemiological parameters of an SIR model using MCMC sampling to compute the posterior distribution of the parameters and to sample from it for forecasting.

A regression task whose main aim is to come up with an end to end product that delivers Sales prediction across multiple stores of some Pharmaceutical company. The performance of 4 regression models are explored: Linear Regression, XGBoost, Random Forest and GradBoost. Random Forest regressor emerges the best performer with a Mean Square Error of 0.01876. Streamlit is used for model deployment.