Personal Blog -

GitHub Innovation Graph data

This is a similar analysis to my previous which looked into GitHub use in Africa. I used GitHub Innovation Graph data to see how GitHub public repositories activity is…

Github Use in Africa using Maps

Analyzing developer activity through contributions, repositories, and pushes from the GitHub Innovation Graph data can reveal valuable insights into technological engagement…

Analyzing Kenya’s Fiscal Trends from 2000 to 2023

Exploring Kenya’s fiscal journey since 2000 unveils a narrative of growing revenues shadowed by even greater expenditures, signaling an enduring budget deficit financed…

Welcome To My Blog

news

Okay I’m excited to finally sit down and work on my blog!. I hope to continually add interesting.

Shap Calculation R

A mini example of calculating shap values in R. I used an open source data set from Kaggle. See more about Wiscosin breast cancer data set. I use IML package from R I prefer…

MNIST Digits Recognition

library(tidyverse)
library(data.table)
library(keras)
library(caret)
library(DT)
library(caretEnsemble)
library(tictoc)

train_data <- fread("data/train.csv")
set.seed(100)…

Predicting loan defaults

code

analysis

library(tidyverse)
library(data.table)
library(caret)
library(ggthemes)
library(lubridate)
library(DT)

Predict whether the cancer is benign or malignant

In this tutorial I’m going to predict whether a breast cancer tumor is benign or malignant. Using Wiscosin breast cancer data set available on Kaggle. The 30 predictors are…

Association analysis

code

analysis

Maybe you have heard of a grocery store that carried out analysis and found out that men who buy diapers between 5pm to 7pm were more likely to buy beer. The grocery store…