This repository contains an Exploratory Data Analysis (EDA) on the Zomato dataset, which contains information about restaurants, their ratings, and customer reviews in India. The dataset was obtained from Kaggle and contains data from various cities in India.
As the demand for restaurant food in Bengaluru continues to increase, it has become increasingly difficult for new establishments to compete with established ones. This project aims to explore the factors that affect the establishment of different types of restaurants in Bengaluru, and to provide insights on the popular cuisines and locations for restaurant-goers in the city.
Using the Zomato dataset, we will analyze various factors such as the location, theme, and approximate price of food, as well as the demographics of different localities, to determine which types of cuisines are most popular in certain areas of the city. By understanding these trends, we can help new restaurants better cater to the needs and preferences of their target audience, and ultimately enhance their chances of success in the competitive restaurant industry.
Through this project, we hope to provide valuable insights for restaurant owners and investors, as well as for foodies who are seeking the best dining experiences in Bengaluru. This analysis can be used to inform business decisions, marketing strategies, and menu offerings, and can ultimately contribute to the growth and diversity of the restaurant industry in the city.
This notebook will walk you through a thorough data analysis of the Kaggle dataset for Zomato Bengalore Restaurants. The purpose of this project is to provide decision-makers the ability to make choices while considering data regarding eateries in Bengalore. Hence, we can:
-
Get an intuitive understanding of the data.
-
Record an exploratory data analysis.
-
Employ graphical modules (such as Matplotlib,Seaborn and Plotly) to provide answers to inquiries.
-
Loading the dataset : Load the data and import the libraries
-
Data Cleaning & preprocessing :
- Deleting redundant columns.
- Renaming the columns.
- Dropping duplicates.
- Cleaning individual columns.
- Remove the NaN values from the dataset.
- Exploratory Data Analysis & Visualization :
- Is Online delivery service available?
- Is Table Booking service available?
- Is there any difference b/w rate of restaurants accepting and not accepting online orders?
- Dfference b/w rate of restaurants providing table booking service and not providing table booking service
- Rating distribution
- What are the top 10 location based on restaurant count?
- Location wise rating.
- Top 10 location based on votes count.
- Top 10 location based on Average cost.
- Which are the most common restaurant type in Banglore?
- Average of rating based of different restaurant type.
- What are the different type of services restaurant provide?
- Relation between types of services and their rating
- Cost distribution
- Cost vs rating
- Which are the most popular cuisines of bangalore?
- Which are the top restaurant chains in Bangalore?
- Which are the most popular casual dining restaurant chains?
- Most popular Quick bites restaurant chains
- Most popular cafe of banglore
- Finding the best restaurants - cheapest,highly rated and reliable(large number of votes)
- https://www.kaggle.com/code/shahules/zomato-complete-eda-and-lstm-model
- https://www.kaggle.com/code/chirag9073/zomato-restaurants-analysis-and-prediction
- https://www.kaggle.com/code/parthsharma5795/finding-the-best-restaurants-in-bangalore
That's all, folks!
We finally concluded our task here and we can be quite happy of what we've done. With this implementation, it was possible to provide helpful information to Zomato users for selecting the best restaurant for ordering (specially the new ones) and for the new establishments for getting in the restaurant business(they can take decision and build strategy).
Regression analysis is also coming in the next part
Thank you for being with me till the end and , if you liked , please upvote this kernel and leave a comment below.
continue..