New York Transportation Statistical Insights

Andrei Ionut Dumitrache

22 | United Kingdom | Economics


New York Transportation Statistical Insights is a project that is meant to provide information to people that are looking to travel to New York or local citizens that are interested in how transportation in one of the world’s most crowded cities functions. In this project I used Python for Data Analysis and Modeling, along with its libraries that helped me create new data frames and display several points across the map (Folium, Matplotlib, Pandas, NumPy). These insights can be used to populate a Machine Learning model and get results that are relevant to the area of Smart Cities and Transportation. This analysis is addressing one of the biggest problems that big cities have: overcrowding. By analyzing the number of cars, the traffic incident detections, the subway turnstile usage, number of pedestrians passing by and weather conditions we can derive patterns in the way people from New York like to move around the city. This can result in recommendations based on the datasets which can be used to avoid going out on certain days or suggest better routes to get to the destination. These insights were derived using a cloud based Python 3.6 instance powered by IBM: Developer Skills Network – Cognitive Class ( for smaller datasets and IBM Cloud ( for bigger datasets. Tableau Public was also used for displaying bar charts. The data was first modeled (converting, creating new data frames for accuracy, removing columns/rows that were not populated) and then it was used in order to get insights, plot maps and bar charts.
I strongly believe that Statistics and Machine Learning can help us build better cities in the future and I think that we can achieve that goal by using computational power. I have created the project with this idea in mind, but I also wanted to make it friendly and easy to watch or use


Hi! My name is Andrei Ionut Dumitrache. I’m currently a second year student at the University of Essex in UK. I am studying BSc Economics and Politics and I’ve recently developed a passion for programming and Data Science. During my first year at university I used Stata for Quantitative Economics, and I think that has motivated me to study more about programming and how it can be used in statistics. This led me to choose mostly analytical modules to study in my second year and I also enrolled in an IBM Data Science course which I finished this summer. I hope that in the future I will be able to work as a Data Scientist or Machine Learning Scientist/Researcher because I’m interested in the fields of computational analysis, AI and neural networks. I am really passionate about computers and so I hope that I will get to work in an environment that requires analytical thinking and programming.


Subway Ridership Counts / New York, United States

Pedestrian Counts / Brooklyn Bridge, New York, New York, United States

Traffic Incident Detections / Long Island, New York, United States

Average Weekday Traffic Volume / New York State DOT Region 5

Hourly Traffic on Metropolitan Transportation Authority Bridges and Tunnels / New York Metropolitan Area, New York, United States