Organize some grid-based traffic flow datasets, mainly New York City bicycle and taxi data
Develop ML models predict taxi trip duration in NYC. Ranked : Top 6% | RMSLE : 0.377 (Kaggle) | #DS
In this project using New York dataset we will predict the fare price of next trip. The dataset can be downloaded from https://www.kaggle.com/kentonnlp/2014-new-york-city-taxi-trips The dataset contains 2 Crore records and 8 features along with GPS coordinates of pickup and dropoff
🗽🚕 Performance of data analysis in taxi trips in NYC and creation of a Random Forest Regressor in order to predict the duration of taxi trips.
End-to-end NYC taxi mobility analytics using public TLC data, Python EDA, SQL, and Streamlit dashboards.
Analysis of human behaviour in NYC using taxi data
Code for fetching, sampling, and analysis of NYC taxi data from TLC and Uber for 2009-2018
Examine relationship between NYC weather and taxi data from 2016
Machine learning project for NYC Yellow Taxi fare prediction. Complete data pipeline with DuckDB/Polars ETL, exploratory analysis of 34M trips, feature engineering, and ML model preparation. Achieves 0.954 correlation between distance and fare through comprehensive 2023 dataset analysis.
Kubernetes-native data platform for NYC Taxi analytics — Lakehouse architecture with Iceberg, Spark, Airflow, Nessie(catalog), Rustfs(S3 compatible object storage), Trino, Superset.
Neural network that predicts NYC taxi fares. CAP4770 final project.
Final project of Course Applied Data Science @nyu CUSP
Visualization dashboard of NYC green taxi data using plotly-dash
AI-driven taxi fleet repositioning on 263 NYC zones — demand forecasting, multi-agent simulation, offline RL & reproducible OPE | NDCG@3 0.9565 | +39/day lift | 402 tests
Cloud-ready NYC Taxi data engineering pipeline using Airflow, MinIO, DuckDB, and CSV analytics exports.
To associate your repository with the nyc-taxi topic, visit your repo's landing page and select "manage topics."