Uber Data Analysis

This repository contains a Jupyter Notebook that performs exploratory data analysis (EDA) on an Uber rides dataset. The notebook explores trip volume, distance, top pickup/dropoff locations, user insights, and basic data quality checks.

Files

• UberDataAnalysis.ipynb: Main analysis notebook.
• UberDataset.csv: Primary dataset for the exploratory analysis.
• UberDataset.xlsx: Alternative format used for specific predictive analysis tasks.

Dataset

• Expected filename: UberDataset.csv (placed in the same folder as the notebook).
• The notebook uses kagglehub.dataset_download("bhanupratapbiswas/uber-data-analysis") to download the data if kagglehub is available. If you do not wish to use kagglehub, download the dataset manually from the source and place UberDataset.csv alongside the notebook.

Prerequisites

• Python 3.8 or newer
• Jupyter (Notebook or JupyterLab)
• Required Python packages:
  • pandas
  • numpy
  • matplotlib
  • seaborn
  • kagglehub (optional — only for automated data download)

Install dependencies with pip:

pip install pandas numpy matplotlib seaborn
# Optional: only if you plan to use kagglehub in the notebook
pip install kagglehub

How to Run

1. Ensure UberDataset.csv is in the same folder as UberDataAnalysis.ipynb, or update the file_path variable in the notebook to point to your dataset location.

2. Start Jupyter and open the notebook:

jupyter notebook UberDataAnalysis.ipynb

3. Run the notebook cells in order. The notebook performs:
   • Data loading and structure inspection (df.info())
   • Missing value and duplicate checks
   • Box plots for numeric columns to identify outliers
   • Date/time conversions for START_DATE and END_DATE
   • Volume analysis (daily, hourly, and day-of-week trends)
   • Visualization of top pickup and dropoff locations
   • Trip distance metrics for the MILES column
   • Customer/user insights based on trip purpose and categories

Notes & Tips

• Automatic Download: If you don't have kagglehub, comment out the download lines in the first cell and set the path variable to the local folder containing UberDataset.csv.

• Column Names: The notebook expects columns named START_DATE, END_DATE, and MILES. If your specific version of the dataset uses different naming (e.g., lowercase or underscores), update the preprocessing section of the notebook accordingly.

• Visualization: Ensure that variables such as pickup_col, dropoff_col, and daily_rides are correctly mapped to your dataframe columns before running the plotting cells.

License & Attribution

• Dataset Source: bhanupratapbiswas/uber-data-analysis (Kaggle).
• Please check the original dataset page for specific license and attribution requirements.

Contact

For changes or questions, please update the notebook or open an issue if using version control.