Forecast NYC taxi activity with deep learning. We compare the performances of models based on MLPs, RNNs, LSTMs, GNNs, and ARIMAX. Additionally, our code provides users with an easy-to-use pipeline for producing custom time series datasets of taxi activity from publicly available NYC TLC data.

Python scripts to download, process, and analyze the New York City Taxi and Limousine Commission (TLC) Trip Record Data dataset

New York Taxi Trip Duration

This is a full-stack application built using the MERN stack and Vite for the frontend. The application displays information about For Hire Vehicles (FHV) in New York City using the Open Data API.

Import public NYC taxi and for-hire vehicle (Uber, Lyft) trip data into a PostgreSQL or ClickHouse database

Taxi Trip Duration Prediction Using the NYC Dataset

A summative coursework for CSC8101 Engineering for AI

Linear regression-Assignment on different datasets

определить характеристики и с их помощью спрогнозировать длительность поездки такси

TLC Trip Record Data Collector

Using Java to consume data from Google Cloud new york taxi tycoon topic, and send it to an on Premises Kafka topic.

This project aims to predict the Taxi-trip duration within NYC based on several factors as predictors. Various combinations of relevant features are explored as iterations. After analysing the dataset, important and necessary features are selected. Several regression models are implemented & evaluated based on R2 & RMSE, & predictions visualised

This repository houses complete data science projects.

Spatial Hotspot Analysis on Geo-Spatial Data using Apache Spark and Scala

Exploratory Data Analysis of Parking Violations in New York City from July 2020 to June 2021. The analysis explores the distribution of violations by state, top vehicle makes, and peak violation months and days, and provides recommendations for NYC.

NYC Taxi Fare Prediction with 7 models (Linear Regression, Random Forest, XGBoost, LightGBM, CatBoost, KNN, and Decision Tree) The models used range from simple linear regression to more complex ensemble methods such as boosting algorithms. The aim was to improve prediction accuracy and handle categorical features efficiently.

NYC Taxi Fare Prediction with 7 models (Linear Regression, Random Forest, XGBoost, LightGBM, CatBoost, KNN, and Decision Tree) The models used range from simple linear regression to more complex ensemble methods such as boosting algorithms. The aim was to improve prediction accuracy and handle categorical features efficiently.

This script downloads the NYC taxi trips dataset from the Taxi & Limousine Commission's website. The datasets are publicly available and the script acts as an easy way of retrieving the data.

NYC Taxi Fare Prediction with XGBoost and LightGBM.