This repository contains the notebook of several mini-projects I did starting from my own personal interest. Topics range from very different domain.
Here is the list with a brief summary of the content for each mini-project (click on the link to jump straightaway into the rendered notebook):
In this notebook I use scikit-learn and Cost Complexity Pruning to build Classification Tree, which uses continuous and categorical data from the UCI ML Repository to predict whether or not a patient has hearth disease based on their sex, age, blood pressure and a variety of other metrics. Specifically, I use the Heart Disease Dataset
In this notebook I implement MC simulation in order to illustrate and get familiar with this method.
Here I try to answer to a simple question which propably we had to answer few times while doing online shopping for example on Amazon: would you rather buy the product with less reviews but higher rating stars, or a similar product with more reviews but lower rating stars? I analyse this issue by means of a Monte Carlo simulation varying sample size and distribution of ratings
I use Support Vector Machine to build and train a model using human cell records, and classify cells to whether the samples are benign (mild state) or malignant (evil state).
in the first part I implement a Monte Carlo simulation and in the second part a Bayesian analysis where based on prior understanding about how likely we are to have any of many 'true' distributions.
- Fractal 🎨
This notebook illustrates how to plot fractals in python. Specifically I plot the Barnsley fern using python, numpy and matplotlib.
This notebook is aimed at locating and plotting the location of the International Space Station.
Did elimination of copayment in Norway increase visits to the physician? This notebook implements the Difference in Difference method for causality.