Skip to content

aman-thapa/Radix-Edu

Repository files navigation

Internship Work

This repo contains all of mine assignments and learnings during my Internship period at Radix Educational Trust.


Accident Risk Index

The rise in vehicles on the road will also lead to multiple challenges and the road will be more vulnerable to accidents. Increased accident rates also lead to more insurance claims and payouts rise for insurance companies.

In order to preemptively plan for the losses, the insurance firms leverage accident data to understand the risk across the geographical units e.g. Postal code/district, etc. You have to predict the “Accident_Risk_Index” against the postcodes. Accident_Risk_Index (mean casualties at a postcode) = sum(Number_of_causalities)/count(Accident_ID).

Solution: Code


Detection of Parkinson's Disease

This dataset was collected from UC Irvine Machine Learning Repository and comprises a range of biomedical voice measurements from 31 people, 23 with Parkinson's disease (PD). Each column in the table is a particular voice measure, and each row corresponds to one of 195 voice recordings from these individuals ("name" column). The main aim of the data is to discriminate healthy people from those with PD, according to the "status" column which is set to 0 for fit and 1 for PD, i.e. this is a binary classification problem. The test should have at maximum a False Negative Rate of 0.1%, that is the test sensitivity should be high, at least 0.9% as it is more important to identify patients with the disease correctly.

Solution: Code


Forest Fires Prediction

Using the following 4 Methods:

  • Support Vector Regression
  • Decision Trees
  • Random Forest
  • 3-layer dense Neural Network

I tried to show the relative performance of each method to predict forest fires from the dataset available at the UCI Machine Learning Repository.