Machine Learning M.Sc. Course Project

Dataset: "New York City Taxi Fare Prediction" (Kaggle).

More can be found here

Contributors

Nick Nikitas

Filippos Markolefas

Myron Sampsakis

Notebook Structure

~/Machine_Learning_Project.ipynb
│
└── Connection With Kaggle
│
└── Load Dataset
│
└── Preprocessng
   | Feature Extraction
   | Clean Data
       | General
       | Geospatial Data   
│
└── Exploratory Data Analysis
   | General Analysis
   | Feature Interaction
   | Plots
│
└── Machine Learning
   | Split Data Into Train, Test set
   | Functions
   | Algorithms
       | Linear Regression
       | Random Forest
       | Epsilon-Support Vector Regression
       | XGBoost
       | Voting Regressor
       | Bagging Regressor
       | Histogram-based Gradient Boosting Regression Tree
       | Neural Network
   | Results

(The files JFK2.txt, LaGuardia2.txt, Manhattan.txt, Newark2.txt contain the coordinates for the NYC airports and Manhattan)

Licence

Copyright © 2020 Nick Nikitas, Filippos Markolefas, Myron Sampsakis