🚲 Exploratory Data Analysis - Seoul Bike Rental

This project analyzes the Seoul Bike Rental dataset to explore factors influencing bike rentals. The goal is to uncover meaningful patterns and relationships between bike rental counts and variables such as weather, time, and holidays.

📁 Dataset

• Source: Seoul public bike sharing system UC Irvine
• Duration: Hourly data from December 2017
• Key Features:
  • Rented Bike Count
  • Temperature, Humidity, Wind Speed, Rainfall, Snowfall, Solar Radiation
  • Hour, Date, Holiday, Season, Functioning Day

🔍 Objectives

• Explore when and why people rent public bikes.
• Understand how weather and time affect bike demand.
• Generate insights using descriptive statistics and visualizations.
• Apply feature engineering to enrich the dataset.

📊 Key Analyses

• Univariate Analysis: Distribution of Rented Bike Count, Temperature, etc.
• Bivariate Analysis: Correlations between Rented Bike Count and weather variables.
• Multivariate Analysis: Heatmap of relationships across all numerical variables.
• Time-of-Day Feature Engineering: New feature categorizing hour into logical periods (e.g., Morning Rush, Evening Rush).

📈 Visualizations

• Scatter plots and box plots to observe rental trends.
• Correlation heatmap to reveal strongest predictors.
• Hourly and daily rental patterns.

🧠 Insights

• Rentals peak during Evening Rush and Night, likely due to leisure and commuting flexibility.
• Temperature and solar radiation are positively correlated with rentals.
• Humidity, rainfall, and wind speed reduce bike usage.

🛠 Tools Used

• Python
• Pandas
• Seaborn & Matplotlib
• Jupyter Notebook

📌 How to Run

1. Clone the repo or open the notebook.
2. Install required libraries:

   pip install pandas seaborn matplotlib