Zomato Data Analysis Project
Overview
This project explores customer behavior and restaurant trends using Zomato restaurant data.
Through data cleaning, transformation, and visualization, the analysis uncovers insights into
restaurant types, customer preferences, ratings, and ordering modes. The goal is to help
platforms like Zomato better understand user patterns and optimize their offerings.
Dataset Description
The dataset contains information about 148 restaurants, including:
name: Restaurant name
online_order: Whether the restaurant accepts online orders
book_table: Whether table booking is available
rate: Customer rating (converted from string to float)
votes: Number of votes received
approx_cost(for two people): Estimated cost for two people
listed_in(type): Type/category of restaurant (e.g., Buffet, Cafes, Dining)
Technologies Used
Python
Pandas for data manipulation
NumPy for numerical operations
Matplotlib & Seaborn for data visualization
Jupyter Notebook for interactive analysis
Data Preprocessing
Imported necessary libraries (pandas, numpy, matplotlib, seaborn)
Loaded the dataset using pd.read_csv()
Converted the rate column from string format (e.g., "4.1/5") to float using a custom
function
Verified data integrity using .info() — no null values detected
Exploratory Data Analysis (EDA)
1. Restaurant Type Popularity
Visualization: Countplot of listed_in(type)
Insight: Majority of restaurants fall under the Dining category
2. Votes by Restaurant Type
Visualization: Line plot of total votes grouped by listed_in(type)
Insight: Dining restaurants received the highest number of votes, indicating popularity
3. Ratings Distribution
Visualization: Histogram of rate
Insight: Most restaurants received ratings between 3.5 and 4.0
4. Spending Behavior of Couples
Visualization: Countplot of approx_cost(for two people)
Insight: Majority of couples prefer restaurants with an average cost of ₹300
5. Ratings by Order Mode
Visualization: Boxplot comparing rate across online_order values
Insight: Restaurants accepting online orders tend to have higher ratings
6. Order Mode by Restaurant Type
Visualization: Heatmap of restaurant types vs. online order preference
Insight:
o Dining restaurants receive more offline orders
o Cafes receive more online orders
Key Takeaways
Dining restaurants dominate both in quantity and popularity
Online ordering correlates with higher customer ratings
Cost-effective options (₹300 range) are preferred by couples
Zomato can target Dining restaurants for offline offers and Cafes for online promotions
Project Structure
Zomato_Project/
│
├── Zomato_Project.ipynb # Jupyter notebook with full analysis
├── Zomato data.csv # Dataset used for analysis
├── Zomato_Project.pdf # Exported report (optional)
└── README.md # Project documentation
How to Run
1. Clone the repository
2. Open Zomato_Project.ipynb in Jupyter Notebook
3. Run cells sequentially to view analysis and visualizations
