- A homework assignment for UC Berkeley's Data Analytics Bootcamp
- Analysis studies data from a hypothetical ridesharing application (Pyber) using Pandas and MatPlotLib
- The following conclusions can be reached from the analysis:
- About two thirds of all rides and total fare value come from urban passengers
- The average rural rider's ride tends to cost a lot, but rural riders only make up a small portion of overall riders
- Even though rural and suburban rider fares make up almost 40% of total fares, rural and suburban drivers make up less than 20% of total drivers
- The "pyber.ipynb" Jupyter Notebook uses MatPlotLib to conduct a graphical analysis of the ride sharing application data
- The "city_data.csv" and "ride_data.csv" files in the "data" folder are the data files used in the Jupyter Notebook analysis
- All the PNG files in the "output" folder are the graphs created in the Jupyter Notebook
MatPlotLib is used to create the following graphs:
- One bubble plot showing the relationship between the following variables:
- Average Fare ($) Per City
- Total Number of Rides Per City
- Total Number of Drivers Per City
- City Type (Urban, Suburban, Rural)
- Three pie charts showing the following:
- % of Total Fares by City Type
- % of Total Rides by City Type
- % of Total Drivers by City Type