Professional Documents
Culture Documents
1SJ18CS101 Subhash K V 7 33
1SJ18CS101 Subhash K V 7 33
Declaration i
Abstract ii
Acknowledgement iii
Contents iv
List of Figures vi
3 TASK PERFORMED 9
4 REFLECTION NOTES 12
4.1 Experience 12
4.2 Technical Outcomes 12
iv
4.2.1 System Requirement Specification
4.3 System Analysis and Design 13
4.3.1 Existing System
4.3.2 Disadvantages of the Existing System
4.3.3 Proposed System
4.3.4 Advantages of the Proposed System
4.4 System Architecture 14
4.4.1 Data Flow Diagram
4.4.2 UML Diagram
4.4.3 USE CASE Diagram
4.4.4 Class Diagram
4.4.5 Sequence Diagram
4.4.6 Activity Diagram
4.5 Implementation 16
4.5.1 Modules
4.6 Screen Shots 18
5 CONCLUSION 20
6 BIBLIOGRAPHY 21
7 APPENDIX 22
Appendix A: Abbreviations
v
LIST OF FIGURES
Screenshots
1 Importing Data 18
2 Cleaning Data 18
3 Training & Testing Data 18
4 Fitting Model 19
5 Accuracy 19
6 Report 19
7 Output in Bar Graph 20
8 Output in Scatter Plot 20
vi
CHAPTER - 1
COMPANY PROFILE
Witnessing the current times, we can come to this conclusion that online education is
everywhere. There are numerous options for online training. We being a responsible
entity realize that it has become significant for the careerists to know about the right place
that will help them achieve their dreams, to feel the exhilaration of victory!
Our CEO, V.V Subrahmanyam founded Verzeo, in 2018. He aims to train students to
make them industry-ready. He believes that to savour each aspirant of the country with
the taste of good mentorship, it’s necessary to bridge the gap between technology and
education.
We have come up with a variety of courses ranging from Kids Programs, Job-Guarantee
Programs, and Pro-Degree Programs packed with live projects and interactive
sessions. We also provide Banking & CA training, along with technical programs. Our
aim is to provide learning aids in a broad spectrum, so that students from various fields
can rely on our one-stop online learning solution, Verzeo.
With more than 900 employees on board, the CEO aims to hit the company’s valuation
of 500 crores by the end of 2022. We, the Verzeo family, work day-in and day-out to
achieve our CEO’s target of shaping the future of millions of young minds.
At Verzeo, learning is not limited to any specific domain; we provide our students with
immense networking opportunities with industry professionals to expand their horizons
of growth and development.
1
RESTAURANT REVIEW PREDICTION ANALYSIS Company Profile
1.1.1 Objectives
Their goal is to consistently deliver success to students by going the extra mile. To help
their students meet their technological skills and career opportunities, they offer the
right people, solutions, and services.
By leveraging leading technologies and industry best practices, they provide their
students with the most efficient and effective training.
The race for digital transformation is on. In this globally connected on-demand world
with rapid advancements in internet technologies, businesses worldwide are under
constant pressure to add innovative real-time capabilities to their applications to
respond to market opportunities.
Over the course of the last 3 years, Verzeo has managed to make tremendous leaps in the
eLearning sector and create a remarkable impact on the current Indian education
dynamic.Since its inception, we have grown to specialize in 50+ departments and distribute
our comprehensive courses and training programs in every part of the country.With our AI-
backed platform, 150,000+ trained students.
Our super energetic and massive team at KSI is our core strength, forming an excellent
blend of IT minds with a creative bent. Their goal is to keep improving and delivering the
skills that will help students have a successful career in the IT industry.
Taking advantage of our highly skilled and experienced trainers. We are primarily a
student-centered organization dedicated to exceeding students' expectations in terms of
meeting their needs. They successfully hosted a group of seasoned professionals.
Trainers who collaborate in order to provide their students with the knowledge they need
to advance in their careers. They take pride in being a sought-after Skill development after
delivering successful internships. They have successfully delivered value to our students
as well as colleges over the years. They truly believe that the success of their students is
their success, and they do not consider themselves to be a vendor for their program. We'd
like to hear some of their stories and learn how far they've gone to ensure the success of
our students, and they'll do everything they can to make that happen.
1.4Services Offered
Training / Internships form a very important part of students over all development that's
why AICTE and Universities have made it mandatory for every engineer and MCA to
undergo the same, we help students in achieving this goal by helping them acquire latest
systems the ability to automatically learn and improve from experience without being
Learn Data science and how to use scientific methods, processes, algorithms and systems
to extract knowledge and insights from structured and unstructured data as one of the
hottest professions in the market today, bundled with Microsoft MTA Certification
Learn Java one of the most popular programming languages used in the development of
Web and Mobile applications. It is designed for flexibility, allowing developers to write
code that would run on any machine, regardless of architecture or platform Bundled with
Learn the ethical way of how to do penetration testing and other testing methodologies
5. Internet of Things
Learn how to work with connected devices use sensors and raspberry PI3 and connect
these devices to cloud to identify patterns and extract meaning-full information out of it,
6. Business Analytics
Learn Business Analytics and how it enables companies to automate and optimize their
business processes in-fact Data-driven companies treat their data as a corporate asset and
leverage it for a competitive advantage as they are able to use the insights to find new
7. Digital Marketing
Learn Digital Marketing and how its used for promoting products or services online via
internet, companies are gaining higher profitability and return on investment by having
their Digital marketing strategies in place the program is bundled with Google
Certification
6
RESTAURANT REVIEW PREDICTION ANALYSIS About the Department
2.3 Testing
Testing was done according to the Corporate Standards. As each component was being built,
Unit testing was performed in order to check if the desired functionality is obtained. Each
component in turn is tested with multiple test cases to verify if it is properly working. These
unit tested components are integrated with the existing built components and then integration
testing is performed. Here again, multiple test cases are run to ensure the newly built
component runs in co-ordination with the existing components. Unit and Integration testing are
iteratively performed until the complete product is built. Once the complete product is built, it
is again tested against multiple test cases and all the functionalities.
The product could be working fine in the developer’s environment but might not necessarily
work well in all other environments that the users could be using. Hence, the product is also
tested under multiple environments (Various operating systems and devices). At every step, if
a flaw is observed, the component is rebuilt to fix the bugs. This way, testing is done
hierarchically and iteratively.
➢ Python Programming
➢ Machine Learning Algorithms
DATA SET
This section describes, in brief, the data that has been used for the research. Data from
restourant was used in this project, the major amount of data was extracted from public website
Kaggle (Kaggle.com), data regarding the review and linked was obtained from a leading
Restaurant in India. Data from restaurant sources was integrated together to form a staging
data-set. For predicting the review is either positive or negative which uses for the people to
say that the which restaurant is best in class and it also uses for restaurant to improve there
levelk of standarsds in their quality items either it may be the quality food , private space,
surrounding of the place, etc.
Below table shows the different types of reviews present in the data-set.
9
RESTAURANT REVIEW PREDICTION ANALYSIS Task Performed
Data related to the Restaurant review was collected in .csv format, the data related to review was
extracted using data extraction tool provided by (Mozenda (n.d.)) in .csv files. Data being from
public portal had multiple records which got mixing and irrelevant values; data cleaning was
performed in Microsoft Excel by collecting all the records to a record having unwanted and
missing values. Once the data-set was added to google colab Unwanted columns were left over
there, and extracted only wanted (correctly organized) and then divided them into two parts that
review and tlinked.1 and then the cleaned data was transformed to be suitable for the model. The
original data-set had only the review as a representation of language, to have a consistent metrics
for the language score that is either 0 or 1. Similarly, by undertaking the training and testing data
we created a prediction model using SVC machine learning algorithm.
Algorithms
➢ Linear Regression
Linear Regression is a machine learning algorithm based on supervised learning. It performs a
regression task. Regression models a target prediction value based on independent variables. It is
mostly used for finding out the relationship between variables and forecasting. Different
regression models differ based on – the kind of relationship between dependent and independent
variables they are considering, and the number of independent variables getting used.
➢ SVC
The Linear Support Vector Classifier (SVC) method applies a linear kernel function to
perform classification and it performs well with a large number of samples. If we compare it
with the SVC model, the Linear SVC has additional parameters such as penalty normalization
which applies 'L1' or 'L2' and loss function.
➢ Pipeline
• Another type of ML pipeline is the art of splitting up your machine learning workflows into
independent, reusable, modular parts that can then be pipelined together to create models.
This type of ML pipeline makes building models more efficient and simplified, cutting out
redundant work.
• This goes hand-in-hand with the recent push for microservices architectures, branching off
the main idea that by splitting your application into basic and siloed parts you can build
more powerful software over time. Operating systems like Linux and Unix are also founded
on this principle. Basic functions like ‘grep’ and ‘cat’ can create impressive functions when
they are pipelined together.
• Training Phase
As the final task, a main project was developed using machine learning models to predict the
chance of a student to be admitted to a master’s program. This will assist students to know in
advance if they have a chance to get accepted. This project predicts the admission of a student
based on different features including university rating, student’s undergraduate GPA, GRE
score, research experience and etc. This predicts that how much chances are there that the
student will get admission in his selected university or not. In this project I have used multiple
algorithms including linear regression, artificial neural network (ANN), random forest
regressor, decision tree regressor. In the end I have deployed this model on a Web Based GUI
to check student’s admission chances and these models are working fine.
4.1 Experience
As per our experience during the internship, Verzeo India follows a good work culture and it
has friendly employees, starting from the staff level to the management level. The trainers are
well versed in their fields and they treat everyone equally. There is no distinguishing between
fresher graduates and corporates and everyone is respected equally. There is a lot of teamwork
followed in every task, be it hard or easy and there is a very calm and friendly atmosphere
maintained at all times. There is a lot of scope for self-improvement due to the great
communication and support that can be found. Interns have been treated and taught well and
all our doubts and concerns regarding the training or the companies have been properly
answered. All in all, Knowledge Solutions India was a great place for a fresher to start career
and also for a corporate to boost his/her career. It has been a great experience to be an intern
in such a reputed organization.
HARDWARE REQUIREMENTS:
SOFTWARE REQUIREMENTS:
12
RESTAURANT REVIEW PREDICTION ANALYSIS Reflection
Used multiple machine learning models to create a system that would help the restaurant
owner to get review that is either positive or negative by predicting using the given review.
The secondly it helps the customers to get the best hotel near by his location by seeing the
review. Linear Regression is a machine learning algorithm based on supervised learning. It
performs a regression task. Regression models a target prediction value based on independent
variables.
Review system was developed by (Waters and Miikkulainen (2013)) to support the visitors to
get the best hotel . which are Categorical variables and for machine learning to model work we
should input numerical values to perform. hence use Label Encoding on these 2 Features that
encode Yes/No as 0/1. After Encoding split the Dataset to X and Y variables and again split to
Train and Test sets of 70% and 30%. Apply Standardisation on Dataset as we have different
scale ranges for different Features. Hence after applying Standard scaling it will bring all the
values to a common range which is easy for model to compute and makes computation fast..
Logistic regression and SVC were used to create the model, both models performed equally
well and the final system was developed using Logistic regression due to its simplicity. The
time required by the admission committee to review the Restaurant was reduced by 74% but
human intervention was required to make the final decision on status.
• Limitation of this system only relied on the restaurant makes the restaurant to go
down and it takes so much time as if they change their behaviour, quality,
surroundings etc.
• The existing system lagged the factor of the research work in the related field.
• To improve the accuracy we need to use more number of training data and also we
need to use high performing algorithms
13
The principal objective of the research is to help the restourants to get there level of standards
in a way that positive or negative reviews and also helps to who are aspiring to go visit the
restaurant. The Restaurant review Prediction system will help them to evaluate the chances of
success in improving the customers needs. It will help them in saving a huge amount of time
and money spent in the knowing each and every customers decisions. Also, it will help them to
limit the number of customers liking the restaurant and what the customers are expecting from
the restaurant and it also helps the customers by suggesting them the best Restaurants where
they have high chances of their needs.
• Information about the prediction analysis is clear to enter all the required information
to predict the review is either positive or negative.
• The user interface code will interact with the Linear Regression, KNN, SVC to
provide the users with the required result.
• User reviews may redirect consumers to more qualitative restaurants which leads lower
quality restaurants to close or to improve quality in response to changes in consumer demand.
The machine learning models are trained with the given dataset. The machine learning models
used in this project are linear regression, linear simple vector classifier(svc), random forest
regressor, decision tree regressor. Once the models are trained, the model are entered to predict
the chances of getting positive or negative review.
13
13
Implementation
4.2.1Modules
2. Data Visualization
MODULES DESCRIPTION
Data Visualization: Using data visualization, I summarized the data with graphs, pictures and
maps, so that the human mind has an easier time processing and understanding the given data.
Data visualization plays a significant role in the representation of both small and large data sets,
but it is especially useful when we have large data sets, in which it is impossible to see all of our
data, let alone process and understand it manually.
Training and Testing: In this project, datasets are split into two subsets. The first subset is known
as the training data - it's a portion of our actual dataset that is fed into the machine learning model
to discover and learn patterns. In this way, it trains our model. The other subset is known as the
testing data.
Train and Evaluate Linear Support Vector Classifier (SVC): The Linear Support Vector
Classifier (SVC) method applies a linear kernel function to perform classification and it performs
well with a large number of samples. If we compare it with the SVC model, the Linear SVC has
additional parameters such as penalty normalization which applies 'L1' or 'L2' and loss function
13
13
4.4 Screenshots
1. Importing data
2. Cleaning data.
13
5. Accuracy
6. Report.
13
13
CHAPTER – 4
CONCLUSION
This project helps to get the people satisfaction about existing restaurants of different areas in a city
and analyses them to predict reviewing of the restaurant. This makes it an important aspect to be
considered, before making a dining decision. Such analysis is essential part of planning before
establishing a venture like that of a restaurant.
Lot of researches have been made on factors which affect sales and market in restaurant industry.
Various dine-scape factors have been analysed to improve customer satisfaction levels. If the data for
other citirs is also collected, such predictions could be made for accurate.
13
BIBLIOGRAPHY
• Shina, Sharma, S. & Singha ,A. (2018). A study of tree based machine learning Machine
Learning Techniques for Restaurant review. 2018 4th International Conference on Computing
Communication and Automation (ICCCA) DOI:/10.1109/CCAA.2018.8777649
• Neha Joshi. A Study on Customer Preference and Satisfaction towards Restaurant in Dehradun
City. Global Journal of Management and Business Research(2012) Link:
https://pdfs.semanticscholar.org/fef5/88622c39ef76dd773fcad8bb5d 233420a270.pdf
• Bidisha Das Baksi, Harrsha P, Medha, Mohinishree Asthana, Dr. Anitha C.(2018) Restaurant
Market Analysis. International Research Journal of Engineering and Technology (IRJET) Link:
https://www.irjet.net/archives/V5/i5/IRJET-V5I5489.pdf
13
APPENDIX
Appendix A: Abbreviation
AI: Artificial intelligence (AI) refers to the simulation of human intelligence in machines that
are programmed to think like humans and mimic their actions. The term may also be applied to
any machine that exhibits traits associated with a human mind such as learning and problem-
solving.
ML: Machine learning (ML) is a type of artificial intelligence (AI) that allows software
applications to become more accurate at predicting outcomes without being explicitly
programmed to do so. Machine learning algorithms use historical data as input to predict new
output values.
KNN: The k-nearest neighbors (KNN) algorithm is a simple, supervised machine learning
algorithm that can be used to solve both classification and regression problems. It's easy to
implement and understand, but has a major drawback of becoming significantly slows as the size
of that data in use grows.
Pipeline: pipeline is a means of automating the machine learning workflow by enabling data to be
transformed and correlated into a model that can then be analyzed to achieve outputs. This type of
ML pipeline makes the process of inputting data into the ML model fully automated.
13