ZOMATO
ANALYSIS AND RATING PREDICTION
Detailed Project Review
SATYAM SHRMA
PROJECT DETAIL
Project title Zomato Rating Prediction
Technology Machine learning Technology
Domain E-commerce
Project Difficulty level Intermediate
Programming language used Python
Tools Used Jupyter Notebook, Vscode, FASTApi
OBJECTIVE
The main goal of this project is to perform extensive Exploratory Data
Analysis(EDA) on the Zomato Dataset and build an appropriate Machine
Learning Model that will help various Zomato Restaurants to predict their
respective Ratings based on certain features.
PROBLEM STATEMENT
The underlying problem here is it has become difficult for non-established
restaurants to compete with already established restaurants. You are
required to predict the rating for their better future.
A data is formed by taking 12,000 restaurants, serving dishes from all over
the world. The data include Location of the restaurant, Theme based
restaurant or not and many more things.
ARCHITECTURE
Missing
Handling
Value Cleaning
Dataset Imputations
REAL
WORLD
FAST API
Insights (EDA)
Low Level Design Document
REPORTING HighLevel Design Document
Architecture Document
Wireframe Document
Detailed Project Review
DATASET INFORMATION
URL Contains the URL of the restaurant in the zomato website
Address Contains the address of the restaurant in Bengaluru
Name Contains the name of the restaurant
Online order whether online ordering is available in the restaurant or not.
book table Table book option available or not
location Contains the neighborhood in which the restaurant is located.
rest type The type of restaurant
KEY PERFORMACE
1. P e r c e n t a g e o f P e o p l e b o o k t a b l e o n l i n e o r o f f l i n e .
2. L o c a t i o n o f r e s t a u r a n t s .
3. N e i g h b o r h o o d i n w h i c h t h e r e s t a u r a n t s i s l i s t e d .
4. R e s t a u r a n t s a c c e p t s o n l i n e o r d e r s o r n o t .
5. M o s t l i k e d d i s h o f t h e r e s t a u r a n t s .
6. C u i s i n e o f t h e r e s p e c t i v e r e s t a u r a n t s .
CONCLUSION
From the analysis, 'Onesta', 'Empire Restaurant' & 'KFC' are the most famous restaurants in bangalore.
Most Restaurants offer options for online order and delivery.
Most restaurants don't offer table booking.
From the analysis, most of the ratings are within 3.5 and 4.5.
From the analysis. we can see that most of the restaurants located in 'Koramangala 5th Block', 'BTM' & 'Indiranagar'.Then least
restaurants are located 'KR Puram', 'Kanakapura', 'Magadi Road'.
'Casual Dining', 'Quick Bites', 'Cafe', 'Dessert Parlor' are the most common types of [Link] 'Food Court', 'Casual Dining',
'Dhaba' are the least common.
From the analysis, pasta & Pizza most famous food in bangalore restaurants.
From the analysis, we can see that North Indian Cuisines are most famous in bangalore restaurants.
Two main service types are Delivery and Dine-out.
From the analysis, we can see that 'Onesta', 'Truffles' & 'Empire Restaurant' are highly voted restaurants.
For the modeling part, i used LinearRegression, DecisionTree Regressor, RandomForest Regressor , Supprotvector Regressor &
ExtraTree Regressor. From all these models ExtraTree Regressor perform well compared to the other [Link] i selected
ExtraTree Regressor for model creation.
QNA
Q1) What's the source of data? Q4) What techniques were you using for
The Dataset were taken from kaggle Website. data?
[Link]
Removing unwanted attributes.
Visualizing relation of independent varibales
Q2) What was the type of data? with each other and output variables.
The data was the combination of numerical and Categorical Removing outliers
values. Clearning data and imputing if null values are
present.
Converting Categorical data into Numerical data.
Q3) What's the complete flow you followed in this
project?
Q5) What were the libraries that you used
Refer Slide 5th for better understanding.
in Python?
I used pandas, NumPy, Matplotlib, Seaborn and
Geopy libraries in Pyhon.