Restaurant Data Analytics

Project Overview

This repository contains code and datasets for analyzing restaurant data sourced from Google BigQuery. The aim is to provide insights into customer check-in behaviors, restaurant popularity, market analysis based on geographical and temporal data points, and so on.

Features

• Data extraction from Google BigQuery.
• Data preprocessing including data cleaning and data transformation.
• Analytical visualizations of check-in data across different cities and price ranges.
• Implementation of data aggregation and analysis using Python Pandas and visualization using Tableau.

Installation

To set up this project locally, follow these steps:

1. Clone the repository:

   git clone https://github.com/Eins51/RestaurantAnalytics.git
   

2. Navigate to the project directory:

   cd RestaurantAnalytics
   

3. Install required Python packages:

   pip install -r requirements.txt
   

Usage

1. Run the Jupyter Notebook for data preprocessing and analysis:

   jupyter notebook notebooks/restaurant_data_analysis.ipynb
   

2. Explore the Tableau dashboards for interactive visualizations:

   • Dashboard 1: Market Trends and Spending Insights
     • Analyze restaurant distribution, spending trends, and high-potential regions.
     • Video Demo
     • 
   • Dashboard 2: Peak and Off-Peak Customer Behavior
     • Understand peak dining hours, months, and consumer trends.
     • Video Demo
     • 

Data Preprocessing

• Data Acquisition: Data was sourced from public Google Cloud Storage buckets and loaded into Google BigQuery.
• Data Cleaning: Removed duplicates, handled missing values, and conducted feature engineering (e.g., geographic classification, temporal data enrichment).
• Data Transformation: Time data was binned for granular analysis, and datasets were simplified for focused analysis.

Dashboards

Dashboard 1: Market Trends and Spending Insights

• Key Metrics:

  • Total Restaurants: 8.5 million
  • Operational Restaurants: 6.8 million
  • Total Check-ins: 12 billion
  • Total Reviews: 4.5 billion
  • Average Rating: 4/5

• Visualizations:

  • Geographic distribution of restaurant activity.
  • Spending trends by state and city.
  • Seasonal consumer behavior insights.

• Insights:

  • High-potential regions include Pennsylvania, Florida, and Louisiana.
  • Seasonal trends show spending peaks in March, May, and July.

• Link: https://public.tableau.com/app/profile/yi.wang4922/viz/MarketTrendsandSpendingInsights/Overview

Dashboard 2: Peak and Off-Peak Customer Behavior

• Key Metrics:

  • Peak Months: March, May, July
  • Off-Peak Months: January, September, November
  • Peak Hours: 11 PM to 1 AM
  • Off-Peak Hours: 8 AM to 10 AM

• Visualizations:

  • Hourly and monthly check-in patterns.
  • Peak traffic periods by location.

• Insights:

  • Late-night dining trends in urban areas.
  • Inventory and staffing optimization based on peak/off-peak patterns.

• Link: https://public.tableau.com/app/profile/yi.wang4922/viz/RestaurantAnalysisofPeakandOff-PeakTrafficPeriods/TopandBottom

Acknowledgments

Special thanks to:

• The Google Cloud Platform team for providing the data.
• Tableau for powerful visualization tools.
• Contributors and collaborators who supported this project.