Drug Consumption and Misuse Analysis

Repository for Drug Consumption and Misuse analysis carried out for the "Mathematics in Machine Learning" of my Master's Degree.

Introduction

The problem of evaluating an individual’s risk of drug consumption and misuse is highly important. An online survey methodology was employed to collect data includ- ing Big Five personality traits (NEO-FFI-R), impulsivity (BIS-11), sensation seeking (ImpSS), and demographic information. The data set [1] contained information on the consumption of 18 central nervous system psychoactive drugs. Correlation analysis demonstrated the existence of groups of drugs with strongly correlated consumption patterns. Among these different kind of drugs, one was selected on which we carried out the analysis. A number of classification methods were employed (decision tree, random forest, k-nearest neighbors, logistic regression and support vector machine). The best results achieved over 75% in accuracy.

Requirements

The necessary requirements are specified in requirements.txt. To run the following program on your own machine:

1. Clone this repository
2. Install dependencies

   pip3 install -r requirements.txt

3. Explore code in notebook
4. Read the report or look at the presentation