nyc-taxi

Overview

This is the code for this video on Youtube by Siraj Raval.

Software and Libraries

Python 3
Scikit-learn: Python’s open source machine learning library
XGBoost: Python package for XGBoost model,

Datasets

The primary train dataset (train.csv) and test dataset (test.csv) is at the Kaggle competition website.

The weather dataset is at: weather_data_nyc_centralpark_2016.csv.

The datasets for the fastest routes from OSRM can be found here. The files are: fastest_routes_train_part_1.csv, fastest_routes_train_part_2.csv, and fastest_routes_test.csv

Visualization Image

The final visualization image for the project report is visualization.pdf (.png), and is best viewed zoomed in.

Credits