January 25, 2026
US Bikeshare Data Analysis
This project analyzes bike share usage data from three major US cities: Chicago, New York City, and Washington. The interactive Python program allows users to explore various statistics about bike share usage patterns, including popular travel times, popular stations, trip durations, and user demographics.
Key Features:
- Interactive filtering by city, month (January-June), and day of week
- Statistical analysis of travel patterns and user behavior
- Raw data viewer to explore individual trip records
- AI-powered exploration mode using local LLM (Ollama) for natural language questions about the data
- Case-insensitive input validation and comprehensive error handling
AI Exploration Mode: After viewing the standard statistics, users can enter AI mode to ask natural language questions about the bike share data. The AI assistant has access to the complete dataset across all cities and time periods, enabling interactive exploration and cross-city comparisons.
The AI mode features dynamic SQL query generation - when users ask statistical questions, the AI can automatically generate and execute SQL queries against an in-memory database to provide accurate, data-driven answers. This enables users to ask any analytical question about the data without being limited to pre-computed statistics.
Required:
- Python 3.x
- pandas library:
pip install pandas - Bikeshare data CSV files (place in
data/folder)
Optional (for AI exploration mode):
- Ollama: Download from ollama.com/download
- llama3.2:3b model:
ollama pull llama3.2:3b - ollama Python package:
pip install ollama
Note: The AI exploration mode is optional. All core features (statistics, filtering, raw data viewing) work without Ollama installed.
bikeshare.py- Main Python script containing all analysis functions and AI integrationdata/chicago.csv- Chicago bike share data (not included in repository)data/new_york_city.csv- New York City bike share data (not included in repository)data/washington.csv- Washington bike share data (not included in repository)
- Bike share data provided by Motivate, a bike share system provider
- Project template and requirements from Udacity Programming for Data Science Nanodegree
- AI capabilities powered by Ollama with llama3.2:3b model