Bike-Sharing Demand Analysis

This is done by Yunjing Yao, Zihan Liu and Sianna Fang

This repository contains code to analyze bike-sharing demand across multiple cities, with a focus on understanding the impact of weather conditions, time of day, and city-specific trends.

Installation

To get started with this project, follow these steps:

1. Clone the repository: git clone https://github.com/GuoZheXinDeGuang/CSCI-381-Final-Project.git and cd CSCI-381-Final-Project

2. Install the required dependencies: Python 3.x Pandas NumPy Matplotlib Seaborn Jupyter Notebook

Usage

1. Load the Jupyter Notebook:

   • Open the Final_Group_Project.ipynb file in Jupyter Notebook or Jupyter Lab.
   • Run the cells in sequence to execute the analysis.

2. Run the analysis:

   • The notebook includes steps for data loading, preprocessing, exploratory data analysis (EDA), weather impact analysis, and visualization of results.

Key Features

1. Data Preprocessing: Cleans and prepares the dataset, handling missing values and extracting key features like the hour of the day.

2. Exploratory Data Analysis (EDA): Visualizes data to uncover trends and patterns in bike rental behavior across different times and conditions.

3. Weather Impact Analysis: Analyzes the relationship between weather conditions (e.g., temperature) and bike rental demand.

4. City-Specific Insights: Examines rental patterns unique to each city, providing targeted recommendations for optimization.

5. Machine Learning Analysis: Develops and evaluates predictive models to forecast bike rental demand, utilizing features like weather, time, and location.