• Visualize Uber's ridership growth in NYC in 2014 and 2018.
• Visualize pickup coordinates in a real-time map.
• Characterize the demand based on the identified data from the dataset.
• Estimate the predicted fare using the extracted features from the dataset using two ML Models.
• Compare UBER and LYFT on the basis of the number of service cars available and the number of customers in each service.

REQUIREMENTS: The code is written in a Jupyter Notebook with a Python 3.9 kernel and in addition, it requires the following packages:

• Pandas
• Matplotlib
• Seaborn
• Scikit-Learn
• Numpy
• Google Apps API

SNIPPETS FROM THE NOTEBOOK:

PICKUP LOCATIONS of UBER CUSTOMERS

Heat Map of UBER RIDES