This project presents an exploratory data analysis (EDA) of a dataset containing Uber and Lyft ride information and pricing in Boston, MA. The goal was to uncover insights into ride characteristics, pricing trends, and the influence of factors like time, distance, and weather. Through this analysis, we aimed to understand patterns within the rideshare data, demonstrating a practical approach to extracting meaningful information from real-world datasets. Note: This Overview section was created with AI.
- 📓 Easy Access to Notebook: Open analysis.ipynb
This version represents my personal adaptation of a project originally developed in collaboration with Matteo Dall'Olmo. It features my own refinements and revised documentation for clarity and portfolio purposes.
The analysis followed a structured EDA process, which included:
-
Data Acquisition and Basic Understanding:
Loading the dataset and getting an initial feel for its structure and content. -
Data Wrangling:
Cleaning and preparing the data for analysis. -
Data Profiling:
Understanding the distribution and characteristics of individual variables. -
Hypothesis Development:
Formulating questions to investigate based on initial observations. -
Hypothesis Investigation:
Using data to test developed hypotheses. -
Results Summary:
Summarizing findings and answering the initial questions. -
Critical Review:
Reviewing the workflow and discussing ethical considerations.