Brown-Datathon-2017

TripAdvisor Challenge: predict whether or not a user will make a purchase based on information about them, such as the date, browsing time, page views, etc. Given a million-example data set to perform data analysis.

Getting started

Requirements and instructions for setting up dependencies.

Prerequisites

• Python 3

Libraries (can be installed using pip):

• numpy

• scikit-learn (version 0.18)

• pandas

Environment setup

Create the following directory structure:

project
└───Brown-Datathon-2017
│   │   data_clean.py
│   │   ml_model.py
│   │   .gitignore
│   |   README.md
|
└───TripAdvisorChallenge
|   |   datathon_tadata.csv

Running the code

Enter the Brown-Datathon-2017 directory (which is this one) through the terminal, and enter these commands:

python3 data_clean.py
python3 ml_model.py

This may take a minute or two to run but should terminate relatively quickly.