PERFORMANCE EVALUATION OF DIFFERENT MACHINE LEARNING

TECHNIQUES FOR PREDICTION OF CARDIOVASCULAR DISEASE

A PROJECT REPORT

submitted

in the partial fulfillment of the requirements for the award of the degree of

BACHELOR OF TECHNOLOGY

in

COMPUTER SCIENCE AND ENGINEERING

By
SATHWIKA KISTIPATI (19B81A05D7)
MASKU NELSON SHARON PREKSHA (19B81A05F0)
SATWIK YARABATI (19B81A05H8)

Under the guidance of

Mrs. G. Sandhya

Assistant Professor

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CVR COLLEGE OF ENGINEERING
(An Autonomous institution, NBA, NAAC Accredited and Affiliated to JNTUH, Hyderabad)
Vastunagar, Mangalpalli (V), Ibrahimpatnam (M),
Rangareddy (D), Telangana- 501 510

i
 ACKNOWLEDGEMENT

The satisfaction that accompanies the successful completion of any task would be incom-
plete without the mention of the people who made it possible and whose encouragement
and guidance has been a source of inspiration throughout the course of the project.

It is a great pleasure to convey our profound sense of gratitude to our principal Dr. K.
Ramamohan Reddy, Vice-Principal Prof. L. C. Siva Reddy, Dr. A. Vani Vathsala,
Head of CSE Department, CVR College of Engineering, for having been kind enough to
arrange necessary facilities for executing the project in the college.

We deem it a pleasure to acknowledge our sense of gratitude to our project guide Mrs. G.
Sandhya under whom we have carried out the project work. His incisive and objective
guidance and timely advice encouraged us with constant flow of energy to continue the
work.

We wish a deep sense of gratitude and heartful thanks to the management for providing
excellent lab facilities and tools. Finally, we thank all those whose guidance helped us in
this regard.

SATHWIKA KISTIPATI(19B81A05D7)
MASKU NELSON SHARON PREKSHA(19B81A05F0)
SATWIK YARABATI(19B81A05H8)

ii
 DECLARATION

We the undersigned solemnly declare that the project report titled ‘PERFORMANCE
EVALUATION OF DIFFERENT MACHINE LEARNING TECHNIQUES FOR PRE-
DICTION OF CARDIOVASCULAR DISEASE’ is based on our own work carried out
during the course of our study under the supervision of Mrs. G. Sandhya, CSE Dept.,
CVR College of Engineering.

We assert the statements made and conclusions are drawn are an outcome of our research
work. We further certify that

1. The work contained in the report is original and has been done by us under the general
supervision of our supervisor.

2. The work has not been submitted to any other Institution for any other degree/di-
ploma/certificate in this university or in the any other University of India or abroad.

3. We have followed the guidelines provided by the university in writing the report.

iii
 CERTIFICATE

This is to certify that the project entitled “Performance Evaluation Of Different Machine
Learning Techniques For Prediction Of Cardiovascular Disease ” being submitted by
Sathwika Kistipati (19B81A05D7), Masku Nelson Sharon Preksha (19B81A05F0), Satwik
Yarabati (19B81A05H8) in partial fulfillment for the award of Bachelor of Technology in
Com- puter Science and Engineering to the CVR College of Engineering , is a record of bona
fide work carried out by them under my guidance and supervision during the year 2020-2021.

The results embodied in this project work have not been submitted to any other University or
Institute for the award of any degree or diploma.

Signature of the project guide, Signature of the HOD,

Mrs. G. Sandhya Dr. A. Vani Vathsala
Assistant Professor Head of Department (CSE)
CSE Department CVR College of Engineering

iv
 Abstract

Machine Learning has vast applications in different domains and healthcare industry is one of
the most popular ones. Machine Learning can play an essential role in prediction of various
diseases. Such information, if predicted well in advance, can provide important intuitions to
doctors who can then adapt their diagnosis and dealing per patient basis. Heart related diseases
or Cardiovas- cular Diseases (CVDs) are the main reasons for a huge number of deaths in the
world over the last few decades and has emerged as the one of the most life-threatening
diseases, not only in India but also in other parts of the world. So, there is a need of a reliable,
accurate and feasible system to diagnose such diseases in time for proper treatment based on the
patients medical his- tory. So, This project aims at predicting the possibility of Heart Disease in
people using Machine Learning algorithms. In this project we perform the comparative analysis
of various classifiers and propose a best fit, precise and efficient model for heart disease
prediction in order to enhance medical care and reduce cost.

v
 TABLE OF CONTENTS

Table of Contents

Page No.

List of Tables Vi

List of Figures viii

Abbreviations Ix

1 Introduction 1

1.1 Motivation 2

1.2 Problem statement 3

1.3 Project Objectives 4

2 Literature Survey 5

2.1 Existing Work 5

2.2 Limitation of Existing Work 7

3 Software & Hardware specifications 8

3.1 Software Requirement Specification 8

3.1.1 Functional requirements 10

3.1.2 Non-Functional requirements 10

3.2 System Requirements 11

3.2.1 Hardware Requirements 11

3.2.2 Software Requirements 11

4 Proposed System Design 12

vi
 4.1 Proposed Methods 12

4.2 Use Case Diagram 17

4.3 Sequence Diagram 18

4.4 Activity Diagram 19

4.5 Class Diagram 20

4.6 Component Diagram 21

4.7 Deployment Diagram 22

4.8 Proposed System Architecture 22

4.9 Technology Description 23

5 Implementation & Testing 25

5.1 Data Preprocessing for ML in Python 27

5.2 Data Cleaning 29

5.3 Machine Learning Process 31

5.4 Modules 37

5.5 Website Implementation 40

5.6 Result & Discussion 42

6 Conclusion and Future Scope 44

6.1 Conclusion 44

6.2 Future Scope 45

7 References 46

Appendix : Source Code 47

vii
 List of Figures

4.1.1 Schematic of Logistic Regression 12

4.1.2 Naïve Bayes 13
4.1.3 KNN Classifier 14
4.1.4 Schematic of Random Forest 14
4.1.5 Schematic of SVM 15
4.2 Use Case Diagram 17
4.3 Sequence Diagram 18
4.4 Activity Diagram 19
4.5 Class Diagram 21
4.6 Component Diagram 21
4.7 Deployment Diagram 22
5.1 Data Preprocessing 26
5.1.1 Data Preprocessing Stages 27
5.2 Data Cleaning Steps 29
5.3.1 Machine Learning Process 31
5.3.2 Software Development Lifecycle 35
5.5.1 Screen shot of Home Page 40
5.5.2 Enter required details of registering page 40
5.5.3 Result Screen 41
5.6 Bar graph predictions of classifiers 42

viii
 List of Abbreviations

ML Machine Learning

UCI Unique Client Identifier

KNN K- Nearest Neighbors
WHO World Health Organization
IDE Entity Relationship
CSV Comma Separated Value files
DL Deep Learning
HD Heart Disease
HDPM Heart Disease Prediction Model
WEKA Waikato Environment for Knowledge Analysis

ix
1. INTRODUCTION

Predicting a disease which depends on several factors is indeed not an easy task. To predict
whether a heart is healthy or not involves studying the variation in several contributing factors.
The complexity and the ambiguity can be reduced to a greater extent by processing the data and
executing the algorithm in a proper way. Several techniques and methods have evolved in the
field of Machine Learning for handling the datasets that contribute to the development of
predic- tion and forecasting ML models. We employed the Cleveland dataset of UCI repository
for tech- nical and experimental analysis of the project. This dataset contains the heart data of
303 individ- uals which are classified into 14 columns, this part is discussed in the later sections
of the paper. Heart Disease is predicted based on the variation of these attributes with respect to
the normalcy. There are many cases and evidences that Machine Learning has proven to be very
efficient in tackling the real-world problems and generating optimal and efficient solutions. ML,
in today’s world is being deployed to develop numerous applications. The fascination of the
Machine Learn- ing and Artificial Intelligence for the people is very high and this leads to the
development of various optimal applications for various industries.

Our motivation to work on this project is to put in the efforts of studying the in-depth
applications of the Machine Learning models and learn the evolution of ML in the field of
healthcare. We propose an approach to generate the efficient output from the model by
comparing the attributes such as accuracy, sensitivity, precision of various algorithms. Many
papers and projects are pub- lished which were focused on improving accuracy and efficiency of
heart disease prediction. Our objective is to take the reference of such papers and develop our
own method of model as an application of the subject in graduate level. Here, we did a
comparative analysis of the Machine Learning models.

We employed Logistic Regression, Decision Tree, Naïve Baye’s Theorem, K-NN, Neural Net-
work, Support Vector Machine, Random Forest models and subjected them to the datasets for
analysis. Based on the comparison of the accuracy achieved by the models, the output is
generated from the model that has high accuracy. The programming language we employed for
the project is Python. Python has proven to be very efficient in developing such applications

1
with the help of

2
its vast number of libraries and functions. The code for the models is written on a file and the
application of python is used for developing the comparison analysis

1.1 MOTIVATION

In the last fifteen years, HDs become still endured the leading causes of death. (WHO,
2019). In United States, Millions of humans are having a HD every year so that the HD takes
placed the biggest killer of people in the world. According to analyzation of WHO, twelve
million people are death due to HD in worldwide. One person dies almost every 34 seconds
from HD. (Patel Jaymin, 2016) Diagnosis of HDs is an essential task and yet intricate task to
perform accu- rately and efficiently in the hospital and clinic. These things are motivated to
build a HDPS ap- plication using ML algorithms. This proposed system can reserve problem by
accurately predict- ing the presence of HD in the patient.

ML is an emerging technology of AI that solved the various type of classification problem by

producing accurate output. ML algorithms are applied to forecast the HD of the patient. This
proposed system can be deployed with algorithms by comparing their accurate result and trained
time. A HDPM cane be built by employing one of the algorithms and deploying this model into
a web application, by further extension of the project. The outcome of this project is to deliver
an application named HDPS that successfully and accurately predict the presence of HD of
patients. This system is useful to support the decision making of doctors and healthcare
members in hos- pitals using model in a web application. The outcome of this project is to
deliver an application named HDPS that successfully and accurately predict the presence of HD
of patients. This system is useful to support the decision making of doctors and healthcare
members in hospitals.

3
1.2 PROBLEM STATEMENT

With the consideration of WHO statistical facts, the most powerful causes of death glob-
ally are a HD. It seemed to the negligence of patients as well as doctors to increase a HD
patient. Some of the difficulties to execute the doctor’s decision and lack of application to
clearly diag- nosis of HD become the cause of human death. Regarding the above issues, we are
proposing a HDPS using set of 7 algorithms, that is one of best solutions to efficiently and
accurately predict the HD patients. The proposed system eliminates the various testing of HD
and supports the de- cision making of doctors. This system can accept a singleton query and
display the clear output of the presence of HD level. This system is useful for any hospital and
clinic to evaluate the patient getting HD. It is reduced the number of tests and provide an
efficient output of patient HD. It supports to make the decision of doctors that consulates with
their patients easily.

The proposed system will support the healthcare systems as well as health-related application to
expand their services with efficiently and accurately providing results. It mitigates the time to
checkup of doctors.

Our motivation to work on this project is to put in the efforts of studying the in-depth
applications of the Machine Learning models and learn the evolution of ML in the field of
healthcare. We propose an approach to generate the efficient output from the model by
comparing the attributes such as accuracy, sensitivity, precision of various algorithms. Many
papers and projects are pub- lished which were focused on improving accuracy and efficiency of
heart disease prediction. Our objective is to take the reference of such papers and develop our
own method of model as an application of the subject in graduate level. Here, we did a
comparative analysis of the Machine Learning models.

We employed Logistic Regression, Decision Tree, Naïve Baye’s Theorem, K-NN, Neural Net-
work, Support Vector Machine, Random Forest models and subjected them to the datasets for
analysis. Based on the comparison of the accuracy achieved by the models, the output is
generated from the model that has high accuracy. The programming language we employed for
the project is Python. Python has proven to be very efficient in developing such applications
with the help of its vast number of libraries and functions. The code for the models is written on
4
a file and the application of python is used for developing the comparison analysis.

5
1.3 PROJECT OBJECTIVE

To design and implement Machine Learning based algorithm using techniques such as
Regression and Classification, for predicting the heart disease of patients using the given
attributes.

To make a study on comparison of the accuracy of algorithms deployed.

The proposed work makes an attempt to detect these heart diseases at early stage to avoid dan-
gerous consequences.

6
 2. LITERATURE SURVEY

2.1 EXISTING WORK

Title: Heart disease prediction using machine learning techniques

Author Names: Rairikar, A., Kulkarni, V., Sabale, V., Kale, H., & Lamgunde,

Description: In this work, three data mining classification algorithms like Random Forest, Deci-
sion Tree and Naïve Bayes are addressed and used to develop a prediction system in order to
analyse and predict the possibility of heart disease. The main objective of this significant
research work is to identify the best classification algorithm suitable for providing maximum
accuracy when classification of normal and abnormal person is carried out. Thus prevention of
the loss of lives at an earlier stage is possible. The experimental setup has been made for the
evaluation of the performance of algorithms with the help of heart disease benchmark dataset
retrieved from UCI machine learning repository. It is found that Random Forest algorithm
performs best with 81% precision when compared to other algorithms for heart disease
prediction.

Title: "Predictions in heart disease using techniques of machine learning."

Author Names: Gandhi, Monika, and Shailendra Narayan Singh

Description: This paper proposes a HDPS based on three different data mining techniques. The
various data mining methods used are Naive Bayes, Decision tree (J48), Random Forest and
WEKA API. The system can predict the likelihood of patients getting a heart disease by using
medical profiles such as age, sex, blood pressure, cholesterol and blood sugar. Also, the perfor-
mance will be compared by calculation of confusion matrix. This can help to calculate accuracy,
precision, and recall. The overall system provides high performance and better accuracy.

7
Title: Prediction and Analysis the occurrence of Heart Disease using data mining techniques.

Author Names: Chala Beyene

Description: Proposed a methodology to foretell the occurrence of HD to

overcome the problem of diagnosis of HD. It improved the existence methodology by choosing

Naïve Bayes, J48, and SVM for predicting the occurrence of HD for early automatic diagnosis

in short time in order to support the qualities of services and reduce costs to save the life of

individuals. This methodology uses various attributes of HD in order to identify whether a

patient has HD or not. The comparison of analysis in the dataset is used WEKA software.

Title: Diabetes disease prediction using machine learning

Author Name: Shetty, Deeraj, Kishor Rit, Sohail Shaikh, and Nikita Patil

Description: The goal of the data mining methodology is to think data from a data set and
change it into a reasonable structure for further use. Our examination concentrates on this part
of Medical conclusion learning design through the gathered data of diabetes and to create smart
therapeutic choice emotionally supportive network to help the physicians. The primary target of
this exami- nation is to assemble Intelligent Diabetes Disease Prediction System that gives
analysis of diabe- tes malady utilizing diabetes patient's database. In this system, we propose the
use of algorithms like Bayesian and KNN (K-Nearest Neighbor) to apply on diabetes patient's
database and analyze them by taking various attributes of diabetes for prediction of diabetes
disease.

8
2.2 LIMITATIONS OF EXISTING WORK

The system also needs to be accurate and efficient in the prediction of heart disease. Various
machine learning algorithms were used for disease prediction; some of them are SVM, Naïve
Bayes etc. But the results state that there may be some improvements to be done on terms of
accuracy and the prediction rate and the false positive rate. Medical Misdiagnosis is a serious
risk in the healthcare industry. If this persists, it might instill fear amongst the patients. Some
other techniques can replace previously applied techniques such as SVM and Naïve Bayes.
Also, the study states that the dataset also can be improved by using some methods over it. To
improve the quality of the input to the proposed system. Using KNN, we have certain weakness
such as they suffer from high dimensionality and overfitting. Naive Bayes assumes that all
features are inde- pendent, which rarely happens in real life. Most of these studies are theoretical
analysis at the macro level and lack quantitative investigation.

9
3. SOFTWARE & HARDWARE SPECIFICATIONS

3.1 SOFTWARE REQUIREMENT SPECIFICATION

What is SRS?

Software Requirements Specification (SRS) is the starting point of the software

developing activity. As system grew more complex it became evident that the goal of the entire
system cannot be easily comprehended. Hence the need for the requirement phase arose. The
software project is initiated by the client needs. The SRS is the means of translating the ideas of
the minds of clients (the input) into a formal document (the output of the requirement phase).

The SRS phase consists of two basic activities:

Problem/Requirement Analysis:

The process is order and more nebulous of the two, deals with understand the problem,
the goal and constraints.

Requirement Specification:

Here, the focus is on specifying what has been found giving analysis such as
representation, Specification languages and tools, and checking the specifications are addressed
during this activity.

The requirement phase terminates with the production of the validate SRS docu-
ment. Producing the SRS document is the basic of this phase.

Role of SRS:

The purpose of the SRS is to reduce the communication gap between the clients and the develop-
ers. SRS is the medium though which the client and user needs are accurately specified.

It forms the basis of software development. A good SRS should satisfy all the
parties involved in the system.
1
Purpose:

The purpose of this document is to describe all external requirements for the E-
learning System. It also describes the interfaces for the system.

 Scope:
This document is the only one that describes the requirements of the system. It is
meant for the use by the developers, and will also by the basis for validating the final deliver
system. Any changes made to the requirements in the future will have to go through a formal
change approval process. The developer is responsible for asking for clarifications, where
necessary, and will not make any alternations without the permission of the client.

 Overview:
The SRS begins the translation process that converts the software Requirements into
the language the developers will use. The SRS draws on the Use Cases from the user
Requirement Document and analyses the situations from a number of perspectives to discover
and eliminate inconsistencies, ambiguities and omissions before development progresses
significantly under mistaken assumptions.

Requirements:

The minimum requirements of the project are listed below:

 Examine the tools and methodologies required to gain an overview of the system
require- ments for the proposed database.
 Examine suitable database management systems that can be used to implement the pro-
posed database.
 Evaluate appropriate website authoring and web graphic creation tools that can be used
to develop web based forms for the proposed database

 Produce and apply suitable criteria for evaluating the solution

Requirement Analysis:

Taking into account the comparative analysis stated in the previous section we could start speci-
fying the requirements that our website should achieve. As a basis, an article on all the different
1
requirements for software development was taken into account during this process. We divide
the requirements in 2 types: functional and nonfunctional requirements.

3.1.1 Functional requirements

Functional requirement should include function performed by a specific screen outline work-
flows performed by the system and other business or compliance requirement the system must
meet.
The functional specification describes what the system must do, how the system does it is de-
scribed in the design specification.

Functional Requirements:

1) Loading Dataset
2) Data cleaning
3) Data Transformation
4) Data Visualization
5) Choosing Algorithm
6) Train Dataset
7) Validate Dataset
8) Record Accuracy
9) Create Model
10) Predict Outcome

3.1.2 Nonfunctional requirement

Describe user-visible aspects of the system that are not directly related with the functional
behav- ior of the system. Non-Functional requirements include quantitative constraints, such as
response time (i.e. how fast the system reacts to user commands.) or accuracy (.e. how precise
are the systems numerical answers.).

 Portability
 Reliability
1
  Usability
 Time Constraints
 Error messages
 Actions which cannot be undone should ask for confirmation
 Responsive design should be implemented
 Space Constraints
 Performance
 Standards
 Ethics
 Interoperability
 Security
 Privacy
 Scalability

3.2 SYSTEM REQUIREMENTS

3.2.1 Hardware Requirements:

 Processor : Intel i3 and above

 RAM : 4GB and Higher
 Hard Disk : 500GB: Minimum

3.2.2 Software Requirements:

 Programming Language / Platform : Python

 IDE : pycharm/jupyter
 Web application framework : Python flask

1
 4. PROPOSED SYSTEM DESIGN

The objective of this research is to design a robust machine learning algorithm to predict heart
disease. The prediction of heart disease is performed using Ensemble of machine learning algo-
rithms. This is to boost the accuracy achieved by individual machine learning algorithms.
Methods: Heart Disease Prediction System is developed where the user can input the patient de-
tails and the prediction for the particular patient is made using the model developed. The model
will predict the output to be either normal or risky. Regression Trees (CART), Support Vector
Machines (SVM), K-Nearest Neighbors (KNN) and Naïve Bayes classifier are used as base
learn- ers. These algorithms are combined using random forest as the Meta classifier.

4.1 PROPOSED METHODS

 Logistic Regression:
Regression means to predict the value using the input data. Regression models are used
to predict a continuous value. It is mostly used to find the relationship between the
variables and forecasting (functional dependency). Regression models differ based on
the kind of relationship between dependent and independent variables. Logistic
Regression is a tech- nique to establish CATEGORICAL classification of data. Figure
4.4 represents the sche- matic of the Logistic Regression Model. The equation is
generally stated as:
E(y) = P(y=1/ x1, x2,.................xp)

1
Figure 4.1.1: Schematic of Logistic Regression

1
 Naïve Baye’s Theorem:
Naïve Bayes classifier is a supervised algorithm. It is a simple classification technique
using Bayes theorem. It assumes strong (Naive) independence among attributes. Bayes
theorem is a mathematical concept to get the probability. The predictors are neither
related to each other nor have correlation to one another. All the attributes independently
con- tribute to the probability to maximize it. Naïve Bayes is a simple, easy to
implement, and efficient classification algorithm that handles non-linear, complicated
data. However, there is a loss of accuracy as it is based on assumption and class
conditional independence. The equation is represented as follows.

Figure 4.1.2: Naïve Bayes

 K- Nearest Neighbors :
The K- Nearest Neighbors algorithm is a supervised classification algorithm method. It
classifies objects dependent on nearest neighbor. It is a type of instance-based learning.
KNN usually works by just trying to see to which class is the new feature near to and it
just puts it to the class closest to that point. K-NN algorithm is simple to carry out
without creating a model or making other assumptions. This algorithm is versatile and is
used for classification, regression, and search. Even though K-NN is the simplest
algorithm, noisy and irrelevant features affect its accuracy. Figure depicts the schematic
representation of K-NN algorithm:

1
 Figure 4.1.3: KNN Classifier

 Random Forest:
It is a popular machine leaning algorithm that belongs to the supervised ML technique. It
is based on the concept of ensemble learning, which is a process of combining multiple
classifiers to solve a complex problem and to improve the performance of the model.
Ran- dom forest is a classifier that contains a number of decision trees on various
subsets of the given dataset and takes the average to improve the predictive accuracy of
that dataset. The figure depicts the flow of Random Forest classifier.

Figure 4.1.4: Schematic of Random Forest

1
 Support Vector Machine:
The goal of the SVM algorithm is to create the best line or decision boundary that can
segregate n-dimensional space into classes so that we can easily put the new data point
in the correct category in future. This best decision boundary is called a hyperplane.
SVM chooses the extreme points that help in creating the hyperplane. These extreme
cases are called as support vectors. Figure depicts the general representation of SVM.

Figure 4.1.5: Schematic of SVM

 XGBoosting:
XGBoost which stands for Extreme Gradient Boosting, is a scalable, distributed
gradient- boosted decision tree (GBDT) machine learning library. It provides parallel
tree boosting and is the leading machine learning library for regression, classification,
and ranking prob- lems.
It’s vital to an understanding of XGBoost to first grasp the machine learning concepts
and algorithms that XGBoost builds upon: supervised machine learning, decision trees,
en- semble learning, and gradient [Link] machine learning uses algorithms
to train a model to find patterns in a dataset with labels and features and then uses the
trained model to predict the labels on a new dataset’s features.

1
 Decision Tree:
Decision tree algorithm falls under the category of supervised learning. They can be
used to solve both regression and classification problems.
Decision tree uses the tree representation to solve the problem in which each leaf node
corresponds to a class label and attributes are represented on the internal node of the
tree. We can represent any Boolean function on discrete attributes using the decision tree

UML DIAGRAMS

UML stands for Unified Modeling Language. UML is a standardized general-purpose mod-
eling language in the field of object-oriented software engineering. The standard is
managed, and was created by, the Object Management Group.
The goal is for UML to become a common language for creating models of object oriented
computer software.

1
4.2 USE CASE DIAGRAM:

A use case diagram in the Unified Modeling Language (UML) is a type of behavioral diagram
defined by and created from a Use-case analysis. The main purpose of a use case diagram is to
show what system functions are performed for which actor. Roles of the actors in the system
can be depicted.

Figure 4.2: Use Case Diagram

2
4.3 SEQUENCE DIAGRAM:

Sequence Diagrams Represent the objects participating the interaction horizontally and time ver-
tically.

Figure 4.3: Sequence Diagram

2
4.4 ACTIVITY DIAGRAM:

Activity diagrams are graphical representations of Workflows of stepwise activities and actions
with support for choice, iteration and concurrency. In the Unified Modeling Language, activity
diagrams can be used to describe the business and operational step-by-step workflows of com-
ponents in a system. An activity diagram shows the overall flow of control.

Figure 4.4: Activity Diagram

2
4.5 CLASS DIAGRAM:

In software engineering, a class diagram in the Unified Modeling Language (UML) is a type of
static structure diagram that describes the structure of a system by showing the system's
classes, their attributes, operations (or methods), and the relationships among the classes. It
explains which class contains information.

Figure 4.5: Class Diagram

4.6 COMPONENT DIAGRAM:

Component diagrams are used to model the physical aspects of a system. Physical aspects are
the elements such as executables, libraries, files, documents, etc. which reside in a node.

Component diagrams are used to visualize the organization and relationships among
components in a system.

It does not describe the functionality of the system but it describes the components used to make
those functionalities.

2
Component diagrams can also be described as a static implementation view of a system. Static
implementation represents the organization of the components at a particular moment.

A single component diagram cannot represent the entire system but a collection of diagrams is
used to represent the whole.

The purpose of the component diagram can be summarized as −

 Visualize the components of a system.

 Construct executables by using forward and reverse engineering.

 Describe the organization and relationships of the components.

Figure 4.6: Component Diagram

2
4.7 DEPLOYMENT DIAGRAM

There may be more steps involved, depending on what specific requirements you have, but
below are some of the main steps:

Figure 4.7: Deployment Diagram

4.8 PROPOSED SYSTEM ARCHITECTURE:

The proposed system is built around conventional three-tier architecture. The three-tier
architecture for web development allows programmers to separate various aspects of the
solution design into modules and work on them separately. That is, a developer who is best at
one part of development, say UI development need not worry about the implementation levels
so much. It also allows for easy maintenance and future enhancements. The three-tiers of the
solution include:

 The Layout:

This tier is at the uppermost layer and is closely bound to the user, i.e., the users of the
system interact with it through this tier.

2
  The business-tier:

This tier is responsible for implementing all the business rules of the organization. It
operates on the data provided by the users through the web-tier and the data stored in the
underlying data-tier. So in a way this tier works on data from the web-tier and the data-tier
in order to perform task for the users in agreement with the business rules of the
organization.

 The data-tier:

This tier contains the persist able data that is required by the business tier to operate on. Data
plays a very important role in the functioning of any organization. Thus, persisting of such
data is very important. The data tier performs the job of persisting the data.

4.9 TECHNOLOGY DESCRIPTION

About python:

The Python programming language is an Open Source, cross-platform, high level, dynamic, in-
terpreted language.

The Python 'philosophy' emphasizes readability, clarity and simplicity, whilst maximizing the
power and expressiveness available to the programmer. The ultimate compliment to a Python
programmer is not that his code is clever, but that it is elegant. For these reasons Python is an
excellent 'first language', while still being a powerful tool in the hands of the seasoned and
cynical programmer.

Python is a very flexible language. It is widely used for many different purposes. Typical uses
include :

 Web application programming with frameworks like Zope, Django and Turbogears
 System administration tasks via simple scripts
 Desktop applications using GUI toolkits like Tkinter or wxPython (and recently
Windows Forms and IronPython)
 Creating windows applications, using the Pywin32 extension for full windows integration
and possibly Py2exe to create standalone programs
23
  Scientific research using packages like Scipy and Matplotlib.

jupyter notebook:

The Jupyter Notebook is an open-source web application that allows you to create and share
doc- uments that contain live code, equations, visualizations and narrative text. Uses include:
data cleaning and transformation, numerical simulation, statistical modeling, data visualization,
ma- chine learning, and much more.

jupyter Notebooks are a powerful way to write and iterate on your Python code for data analysis.
Rather than writing and re-writing an entire program, you can write lines of code and run them
one at a time. Then, if you need to make a change, you can go back and make your edit and
rerun the program again, all in the same window.

Jupyter Notebook is built off of IPython, an interactive way of running Python code in the
termi- nal using the REPL model (Read-Eval-Print-Loop). The IPython Kernel runs the
computations and communicates with the Jupyter Notebook front-end interface. It also allows
Jupyter Notebook to support multiple languages. Jupyter Notebooks extend IPython through
additional features, like storing your code and output and allowing you to keep markdown notes.

2
 5. IMPLEMENTATION AND TESTING:

We proposed as an alternative to the user-based neighborhood approach. We first consider the

dimensions of the input and output of the neural network. In order to maximize the amount of
training data we can feed to the network, we consider a training example to be a user profile (i.e.
a row from the user-item matrix R) with one rating withheld. The loss of the network on that
training example must be computed with respect to the single withheld rating. The consequence
of this is that each individual rating in the training set corresponds to a training example, rather
than each user. As we are interested in what is essentially a regression, we choose to use root
mean squared error (RMSE) with respect to known ratings as our loss function. Compared to the
mean absolute error, root mean squared error more heavily penalizes predictions which are
further off. We reason that this is good in the context of recommender system because
predicting a high rating for an item the user did not enjoy significantly impacts the quality of the
recommendations. On the other hand, smaller errors in prediction likely result in
recommendations that are still use- ful—perhaps the regression is not exactly correct, but at
least the highest predicted rating are likely to be relevant to the user.

Data Processing is a task of converting data from a given form to a much more usable and
desired form i.e. making it more meaningful and informative. Using Machine Learning
algorithms, math- ematical modeling and statistical knowledge, this entire process can be
automated. The output of this complete process can be in any desired form like graphs, videos,
charts, tables, images and many more, depending on the task we are performing and the
requirements of the machine. This might seem to be simple but when it comes to really big
organizations like Twitter, Facebook, Administrative bodies like Paliament, UNESCO and
health sector organizations, this entire pro- cess needs to be performed in a very structured
manner.

2
 Figure 5.1: Data Preprocessing

Collection:
The most crucial step when starting with ML is to have data of good quality and accuracy. Data
can be collected from any authenticated source like [Link], Kaggle or UCI dataset reposi-
tory.
A huge amount of capital, time and resources are consumed in collecting data. Organizations or
researchers have to decide what kind of data they need to execute their tasks or research.
Preparation:
The collected data can be in a raw form which can’t be directly fed to the machine. So, this is a
process of collecting datasets from different sources, analyzing these datasets and then
construct- ing a new dataset for further processing and exploration. This preparation can be
performed either manually or from the automatic approach. Data can also be prepared in

2
numeric forms also which

2
would fasten the model’s learning.
Input:
Now the prepared data can be in the form that may not be machine-readable, so to convert this
data to readable form, some conversion algorithms are needed. For this task to be executed, high
computation and accuracy is needed.
Processing:
This is the stage where algorithms and ML techniques are required to perform the instructions
provided over a large volume of data with accuracy and optimal computation.
Output:
In this stage, results are procured by the machine in a meaningful manner which can be inferred
easily by the user. Output can be in the form of reports, graphs, videos, etc
Storage:
This is the final step in which the obtained output and the data model data and all the useful
information are saved for the future use.

5.1 DATA PREPROCESSING FOR ML IN PYTHON

• Pre-processing refers to the transformations applied to our data before feeding it to the algorithm.

• Data Preprocessing is a technique that is used to convert the raw data into a clean data set. In
other words, whenever the data is gathered from different sources it is collected in raw format
which is not feasible for the analysis.

Figure 5.1.1: Data Preprocessing Stages

2
Need of Data Preprocessing

• For achieving better results from the applied model in Machine Learning projects the format of
the data has to be in a proper manner. Some specified Machine Learning model needs
information in a specified format, for example, Random Forest algorithm does not support null
values, there- fore to execute random forest algorithm null values have to be managed from the
original raw data set.

• Another aspect is that data set should be formatted in such a way that more than one Machine
Learning and Deep Learning algorithms are executed in one data set, and best out of them is
chosen.

Rescale Data

 When our data is comprised of attributes with varying scales, many machine
learn- ing algorithms can benefit from rescaling the attributes to all have the
same scale.
 We can rescale your data using scikit-learn using the MinMaxScaler class.

Binarize Data (Make Binary)

 We can transform our data using a binary threshold. All values above the
threshold are marked 1 and all equal to or below are marked as 0.
 We can create new binary attributes in Python using scikit-learn with the
Binarizer class.

Standardize Data

 Standardization is a useful technique to transform attributes with a Gaussian distribu-

tion and differing means and standard deviations to a standard Gaussian distribution
with a mean of 0 and a standard deviation of 1.
 We can standardize data using scikit-learn with the StandardScaler class.

2
5.2 DATA CLEANING

Data cleaning is one of the important parts of machine learning. It plays a significant part in
building a model. Data Cleaning is one of those things that everyone does but no one really talks
about. Professional data scientists usually spend a very large portion of their time on this step.

Because of the belief that, “Better data beats fancier algorithms”.

If we have a well-cleaned dataset, we can get desired results even with a very simple algorithm,
which can prove very beneficial at times.

Obviously, different types of data will require different types of cleaning.

Steps involved in Data Cleaning

Figure 5.2: Data Cleaning Steps

[Link] of unwanted observations

This includes deleting duplicate/ redundant or irrelevant values from your dataset. Duplicate ob-
servations most frequently arise during data collection and irrelevant observations are those that
don’t actually fit the specific problem that you’re trying to solve.

3
  Redundant observations alter the efficiency by a great extent as the data repeats and may
add towards the correct side or towards the incorrect side, thereby producing unfaithful
results.
 Irrelevant observations are any type of data that is of no use to us and can be removed
directly.
2. Fixing Structural errors

The errors that arise during measurement transfer of data or other similar situations are called
structural errors. Structural errors include typos in the name of features, same attribute with dif-
ferent name, mislabeled classes, i.e. separate classes that should really be the same or
inconsistent capitalization.

3. Managing Unwanted outliers

Outliers can cause problems with certain types of models. For example, linear regression models
are less robust to outliers than decision tree models. Generally, we should not remove outliers
until we have a legitimate reason to remove them. Sometimes, removing them improves perfor-
mance, sometimes not. So, one must have a good reason to remove the outlier, such as
suspicious measurements that are unlikely to be the part of real data.

4. Handling missing data

Missing data is a deceptively tricky issue in machine learning. We cannot just ignore or remove
the missing observation. They must be handled carefully as they can be an indication of
something important. The two most common ways to deal with missing data are:

[Link] observations with missing values.

[Link] the missing values from past observations.

After properly completing the Data Cleaning steps, we’ll have a robust dataset that avoids many
of the most common pitfalls. This step should not be rushed as it proves very beneficial in the
further process.

3
5.3 MACHINE LEARNING PROCESS

Figure 5.3.1: Machine learning Process

Machine Learning algorithm is trained using a training data set to create a model. When new
input data is introduced to the ML algorithm, it makes a prediction on the basis of the model.
The prediction is evaluated for accuracy and if the accuracy is acceptable, the Machine Learning
algorithm is deployed. If the accuracy is not acceptable, the Machine Learning algorithm is
trained again and again with an augmented training data set.

The Machine Learning process involves building a Predictive model that can be used to find a
solution for a Problem Statement. To understand the Machine Learning process let’s assume
that you have been given a problem that needs to be solved by using Machine Learning.

The below steps are followed in a Machine Learning process:

Step 1: Define the objective of the Problem Statement

Step 2: Data Gathering

Step 3: Data Preparation

Step 4: Exploratory Data Analysis

Step 5: Building a Machine Learning Model

Step 6: Model Evaluation & Optimization

Step 7: Predictions

3
Input Design and Output Design

Input Design

The input design is the link between the information system and the user. It comprises the
devel- oping specification and procedures for data preparation and those steps are necessary to
put trans- action data in to a usable form for processing can be achieved by inspecting the
computer to read data from a written or printed document or it can occur by having people
keying the data directly into the system. The design of input focuses on controlling the amount
of input required, control- ling the errors, avoiding delay, avoiding extra steps and keeping the
process simple. The input is designed in such a way so that it provides security and ease of use
with retaining the privacy. Input Design considered the following things:

 What data should be given as input?

 How the data should be arranged or coded?
 The dialog to guide the operating personnel in providing input.
 Methods for preparing input validations and steps to follow when error occur.

Objectives

1. Input Design is the process of converting a user-oriented description of the input into a com-
puter-based system. This design is important to avoid errors in the data input process and show
the correct direction to the management for getting correct information from the computerized
system.

2. It is achieved by creating user-friendly screens for the data entry to handle large volume of
data. The goal of designing input is to make data entry easier and to be free from errors. The
data entry screen is designed in such a way that all the data manipulates can be performed. It
also provides record viewing facilities.

3. When the data is entered it will check for its validity. Data can be entered with the help of
screens. Appropriate messages are provided as when needed so that the user will not be in maize
of instant. Thus the objective of input design is to create an input layout that is easy to follow

3
Output Design

A quality output is one, which meets the requirements of the end user and presents the
information clearly. In any system results of processing are communicated to the users and to
other system through outputs. In output design it is determined how the information is to be
displaced for im- mediate need and also the hard copy output. It is the most important and direct
source information to the user. Efficient and intelligent output design improves the system’s
relationship to help user decision-making.

1. Designing computer output should proceed in an organized, well thought out manner; the
right output must be developed while ensuring that each output element is designed so that
people will find the system can use easily and effectively. When analysis design computer
output, they should Identify the specific output that is needed to meet the requirements.

2. Select methods for presenting information.

3. Create document, report, or other formats that contain information produced by the system.

The output form of an information system should accomplish one or more of the following ob-
jectives.

 Convey information about past activities, current status or projections of the

 Future.
 Signal important events, opportunities, problems, or warnings.
 Trigger an action.
 Confirm an action.
System Study

Feasibility Study

The feasibility of the project is analyzed in this phase and business proposal is put
forth with a very general plan for the project and some cost estimates. During system
analysis the feasibility study of the proposed system is to be carried out. This is to ensure
that the proposed system is not a burden to the company. For feasibility analysis, some
understanding of the major requirements for the system is essential.

3
Three key considerations involved in the feasibility analysis are

 ECONOMICAL FEASIBILITY
 TECHNICAL FEASIBILITY
 SOCIAL FEASIBILITY

Economical Feasibility

This study is carried out to check the economic impact that the system will have on the organi-
zation. The amount of fund that the company can pour into the research and development of the
system is limited. The expenditures must be justified. Thus the developed system as well within
the budget and this was achieved because most of the technologies used are freely available.
Only the customized products had to be purchased.

Technical Feasibilty
This study is carried out to check the technical feasibility, that is, the technical
requirements of the system. Any system developed must not have a high demand on the
available technical resources. This will lead to high demands on the available technical
resources. This will lead to high demands being placed on the client. The developed system
must have a modest re- quirement, as only minimal or null changes are required for
implementing this system.

Social Feasibility

The aspect of study is to check the level of acceptance of the system by the user. This
includes the process of training the user to use the system efficiently. The user must not feel
threatened by the system, instead must accept it as a necessity. The level of acceptance by the
users solely depends on the methods that are employed to educate the user about the system and
to make him familiar with it. His level of confidence must be raised so that he is also able to
make some constructive criticism, which is welcomed, as he is the final user of the system

3
Software Development Life Cycle:

The Systems Development Life Cycle (SDLC), or Software Development Life Cycle in systems
engineering, information systems and software engineering, is the process of creating or altering
systems, and the models and methodologies use to develop these systems.

Figure 5.3.2 Software Development Lifecycle

Requirement Analysis and Design

Analysis gathers the requirements for the system. This stage includes a detailed study of the
busi- ness needs of the organization. Options for changing the business process may be
considered. Design focuses on high level design like, what programs are needed and how are
they going to interact, low-level design (how the individual programs are going to work),
interface design (what are the interfaces going to look like) and data design (what data will be
required). During these phases, the software's overall structure is defined. Analysis and Design
are very crucial in the whole development cycle. Any glitch in the design phase could be very
expensive to solve in the later stage of the software development. Much care is taken during this
phase. The logical system of the product is developed in this phase.

Implementation

In this phase the designs are translated into code. Computer programs are written using a
conven- tional programming language or an application generator. Programming tools like
Compilers, In-

3
terpreters, and Debuggers are used to generate the code. Different high level programming lan-
guages like PYTHON 3.6, Anaconda Cloud are used for coding. With respect to the type of ap-
plication, the right programming language is chosen.

Testing

In this phase the system is tested. Normally programs are written as a series of individual
modules, this subject to separate and detailed test. The system is then tested as a whole. The
separate mod- ules are brought together and tested as a complete system. The system is tested to
ensure that interfaces between modules work (integration testing), the system works on the
intended platform and with the expected volume of data (volume testing) and that the system
does what the user requires (acceptance/beta testing).

Maintenance

Inevitably the system will need maintenance. Software will definitely undergo change once it is
delivered to the customer. There are many reasons for the change. Change could happen
because of some unexpected input values into the system. In addition, the changes in the system
could directly affect the software operations. The software should be developed to
accommodate changes that could happen during the post implementation period.

System Design

System design is transition from a user oriented document to programmers or data base
personnel. The design is a solution, how to approach to the creation of a new system. This is
composed of several steps. It provides the understanding and procedural details necessary for
implementing the system recommended in the feasibility study. Designing goes through logical
and physical stages of development, logical design reviews the present physical system, prepare
input and output specification, details of implementation plan and prepare a logical design
walkthrough.

The database tables are designed by analyzing functions involved in the system and format of
the fields is also designed. The fields in the database tables should define their role in the
3
system. The unnecessary fields should be avoided because it affects the storage areas of the
system. Then in

3
the input and output screen design, the design should be made user friendly. The menu should
be precise and compact.

Software Design

In designing the software following principles are followed:

1. Modularity and partitioning: software is designed such that, each system should consists of
hierarchy of modules and serve to partition into separate function.

2. Coupling: modules should have little dependence on other modules of a system.

3. Cohesion: modules should carry out in a single processing function.

4. Shared use: avoid duplication by allowing a single module be called by other that need the
function it provide

5.4 MODULES:

Data Source:

As I mentioned before the main data sets were collected from the Kaggle machine learning
repos- itory which is open data resource for the data mining and for the predictive analytics
purposes. The acquired data source was a CSV file

Data cleaning

The data in the CSV files need to be checked whether it has any missing values, as the data
source have missing values every attribute have checked using the filters and null values are
removed which helps to increase the accuracy level.

Technology Implementation:

The Real estate data is processed with the help of Python programming and Jupyter IDE and the
numerical data is normalized using the script so the data will equally distributed and variables
cannot dominate each other. It helps to bring the values of the attribute on a common scale.

3
Implementation of Random Forest:

Random Forest, data is been split into test and train 75 percent data is used for the test data and
remaining for the train data since I am using the Random forest. The prices have been predicted
and its shown in the graph. Here the average output of several trees has been taken in order to
provide more accuracy

Evaluation:

The idea of a regression is to predict a real value which means number in regression model we
can compute the several values

Visualization:

Here the test data and the predicted price are loaded into the tableau and it's clear that there is a
linear trend between the actual and predicted values so the random forest model performs well
and the accuracy percentage is more when we compared with the others.

Libraries:

1. numpy: To work with arrays

2. pandas: To work with csv files and dataframes

3. matplotlib: To create charts using pyplot, define parameters using rcParams and color them
with [Link]

4. warnings: To ignore all warnings which might be showing up in the notebook due to
past/fu- ture depreciation of a feature

5. train_test_split: To split the dataset into training and testing data

6. StandardScaler: To scale all the features, so that the Machine Learning model better adapts
to the dataset

7. Sklearn: It features various classification, regression and clustering algorithms including

sup- port vector machines, random forests, gradient boosting, k-means and DBSCAN, and
is de- signed to interoperate with the Python numerical and scientific libraries NumPy and
4
SciPy.

4
SAMPLE CODE:

corr = [Link]()
[Link](figsize = (15,15))
[Link](corr, annot = True)
corr()
sns.set_style('whitegrid')
[Link](x = 'target', data = data)
dataset = [Link]()
[Link]()
X = [Link](['target'], axis = 1)
y = dataset['target']
[Link]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 42)
model = RandomForestClassifier(n_estimators=20)
[Link](X_train, y_train)
pred = [Link](X_test)
pred[:10]
confusion_matrix(y_test, pred)
print(f"Accuracy of model is {round(accuracy_score(y_test, pred)*100, 2)}%")
claasifier=RandomForestClassifier(n_jobs=-1, n_estimators=400,bootstrap= False,crite-
rion='gini',max_depth=5,max_features=3,min_samples_leaf= 7)
[Link](X_train, y_train)
confusion_matrix(y_test, [Link](X_test))
print(f"Accuracy is {round(accuracy_score(y_test, [Link](X_test))*100,2)}%")
[Link](classifier, open('[Link]', 'wb'))

4
5.5 WEBSITE IMPLEMENTATION:

Figure 5.5.1 Screen shot of Home Page

Figure 5.5.2 Enter required details of registering page

4
Figure 5.5.3 Result Screen

4
5.6 RESULT & DISCUSSION

The aim of this project is to know whether the patient has heart disease or not. The records in
the datasets are divided into training set and test sets. After preprocessing the data, data mining
clas- sification technique namely Random Forest were applied. This section shows the results of
those classification model done using Python Programming. The results are generated for both
training datasets and test data sets.

Figure 5.6: Bar graph predictions of classifiers

Results: The predictions of classifier are combined using random forest algorithm. The accuracy
is lifted from 85.53% to 87.64% which is an impressive improvement on accuracy.

4
Test cases

Tested Test name Inputs Expected out- Actual Out- status

put put
1 Load Dataset Csv file Read dataset Load dataset success
2 Split dataset Train80% and Divide the Split train success
test20% training set and and Test
Testing set
Train Model Train dataset, Train with best Train with success
random value, accuracy best accu-
predicted class racy
4 Validate No .of Epochs Validate the Model Gen- success
Model Model with best erated
fit
5 Predict accu- Accuracy Plot expected Plot ex- success
racy and Er- accuracy and pected pre-
ror Rate predicted accu- dicted accu-
racy racy
6 Test Data Test column Predicted accu- Predicted ac- success
racy curacy

4
6. . CONCLUSION AND FUTURE SCOPE

6 . 1 CO NC LU SIO N

This project is developed for the prediction of heart disease using the heart data of patients. The
results and the outputs of the project show that the most accurate algorithm among the deployed
algorithms are Random Forest and Logistic Regression with 90.16% and 89.1% of accuracy
scores respectively. All the accuracy scores, as mentioned are compared and efficient one is
cho- sen among them. The target variable output of the model is generated based on the
accuracy scores of all the algorithms.

As the Random Forest builds multiple decision trees, it ensures to compute the output from the
major trees that contribute to produce the output accurately. The trees and the outputs are en-
hanced through proper training. On the other hand, the likelihood of the event that is about to
happen is statistically predicted precisely using the Logistic Regression approach. By estimating
the probabilities of the variables, the outputs are predicted.

Hence, in regard to the subject, we conclude that the Machine Learning is the most emerging
and beneficial in almost all the sectors and fields of studies. It finds its use in almost all the
applica- tions of medical and biomedical fields. The models can be altered in the way they work
for dif- ferent kinds of datasets. By using these kinds of techniques and computer predicted
values, we can classify the disease fast with reduced cost. This project helped us enrich our
knowledge of several Machine Learning Algorithms and the way ML organizes the synaptic
signals for classi- fication and progression of the data. We have learned how to develop ML
algorithmic models and use its functionalities.

4
6 . 1 FU TU RE S COPE

This work can be extended and enhanced by deploying even more efficient algorithms and em-
ploying the mechanisms and techniques of Deep Learning. Dynamic webpages and Mobile Ap-
plications with enhanced features such as Mobile Phone communication can be created and de-
ployed for easier and effectively enhanced access. While operating in the real time, with the pa-
tient’s consent, we can collect the contact number of the patient and use it for applications such
as communicating about the health care advices and suggestions. If a patient’s heart is predicted
as unhealthy, the doctors and the hospitals contacts nearby can be sent to the patient o the
mobile number in case of any emergency. Easier communication access can be provided. This
extension is just an indefinite conception. It can be enhanced, promoted and executed as per the
convenience in any form.

4
 7. . REFERENCES

[1]. Rairikar, A., Kulkarni, V., Sabale, V., Kale, H., & Lamgunde, A. (2017, June). Heart
disease prediction using data mining techniques. In 2017 International Conference on Intelligent
Compu- ting and Control (I2C2) (pp. 1-8). IEEE.

[2]. Gandhi, Monika, and Shailendra Narayan Singh. "Predictions in heart disease using tech-
niques of data mining." In 2015 International Conference on Futuristic Trends on
Computational Analysis and Knowledge Management (ABLAZE), pp. 520-525. IEEE, 2015.

[3]. Chen, A. H., Huang, S. Y., Hong, P. S., Cheng, C. H., & Lin, E. J. (2011, September).
HDPS: Heart disease prediction system. In 2011 Computing in Cardiology (pp. 557-560). IEEE.

[4]. Aldallal, A., & Al-Moosa, A. A. A. (2018, September). Using Data Mining Techniques to
Predict Diabetes and Heart Diseases. In 2018 4th International Conference on Frontiers of
Signal Processing (ICFSP) (pp. 150- 154). IEEE.

[5]. Sultana, Marjia, Afrin Haider, and Mohammad Shorif Uddin. "Analysis of data mining
tech- niques for heart disease prediction." In 2016 3rd International Conference on Electrical
Engineer- ing and Information Communication Technology (ICEEICT), pp. 1-5. IEEE, 2016.

[6].Al Essa, Ali Radhi, and Christian Bach. "Data Mining and Warehousing." American
Society for Engineering Education (ASEE Zone 1) Journal (2014).

[7].Shetty, Deeraj, Kishor Rit, Sohail Shaikh, and Nikita Patil. "Diabetes disease prediction
using data mining." In 2017 International Conference on Innovations in Information, Embedded
and Communication Systems (ICIIECS), pp. 1-5. IEEE, 2017.

[8]. Methaila, Aditya, Prince Kansal, Himanshu Arya, and Pankaj Kumar. "Early heart disease
prediction using data mining techniques." Computer Science & Information Technology Journal
(2014): 53-59.

[9].[Link]

[10].[Link]

4
 APPENDIX: SOURCE CODE

#Importing libraries
import numpy as np
import pandas as pd
import [Link] as plt
%matplotlib inline

data = pd.read_csv('[Link]')

[Link]()
[Link]()

[Link]().sum()
[Link]()

import seaborn as sns

corr = [Link]()
[Link](figsize = (15,15))
[Link](corr, annot = True)

corr
sns.set_style('whitegrid')
[Link](x = 'target', data = data)

dataset = [Link]()
[Link]()

X = [Link](['target'], axis = 1)
y = dataset['target']

[Link]

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 42)

from [Link] import RandomForestClassifier

model = RandomForestClassifier(n_estimators=20)
[Link](X_train, y_train)

pred = [Link](X_test)
pred[:10]

5
from [Link] import confusion_matrix
confusion_matrix(y_test, pred)

from [Link] import accuracy_score

print(f"Accuracy of model is {round(accuracy_score(y_test, pred)*100, 2)}%")

## Hyperparameter Tuning

from sklearn.model_selection import RandomizedSearchCV

classifier = RandomForestClassifier(n_jobs = -1)

from [Link] import randint

param_dist={'max_depth':[3,5,10,None],
'n_estimators':[10,100,200,300,400,500],
'max_features':randint(1,31), 'criterion':
['gini','entropy'], 'bootstrap':[True,False],
'min_samples_leaf':randint(1,31),
}

search_clfr = RandomizedSearchCV(classifier, param_distributions = param_dist, n_jobs=-1,

n_iter = 40, cv = 9)

search_clfr.fit(X_train, y_train)

params = search_clfr.best_params_
score = search_clfr.best_score_
print(params)
print(score)

classifier=RandomForestClassifier(n_jobs=-1, n_estimators=400,bootstrap= False,crite-

rion='gini',max_depth=5,max_features=3,min_samples_leaf= 7)

[Link](X_train, y_train)

confusion_matrix(y_test, [Link](X_test))

print(f"Accuracy is {round(accuracy_score(y_test, [Link](X_test))*100,2)}%")

import pickle
[Link](classifier, open('[Link]', 'wb'))