Machine Learning

OFFER LETTER/APPROVAL LETTER FROM THE

COMPANY

i
 Machine Learning

INTERNSHIP COMPLETION CERTIFICATE

ii
 Machine Learning

DECLARATION

I Vaibhav Gururaj Hegde, student of final year B.E Information Science and
Engineering, PES Institute of Technology and Management, Shivamogga hereby declare that
the internship on “Machine Learning and visualization using Python” has been independently
carried out by me under the supervision of my Internship Coordinator Mr. Viany S K, Assistant
Professor, Department of Information Science and Engineering, PESITM, Shivamogga and
submitted to the partial fulfillment of the requirement for the award of the B.E degree in
Information Science and Engineering by the Visvesvaraya Technological University, Belagavi
during the academic year 2023-2024

I declare that to the best of my knowledge I have not submitted the matter embodied to
any other University or Institutions for the award of any other degree.

Vaibhav Hegde
4PM20IS050

iii
 Machine Learning

ACKNOWLEDGEMENT

The internship opportunity I had with Vivarttana Technologies Pvt. Ltd., is a great
chance for learning and professional development. Therefore, I consider myself as a very lucky
individual as I was provided with an opportunity to be a part of it. I am also grateful for having a
chance to meet so many wonderful people and professionals who led me through this internship
period.

I take this opportunity to express my deep sense of gratitude to Dr. Yuvaraju B N,

Principal, PESITM, Shivamogga, for his kind support, guidance and encouragement throughout
the course of this dissertation work.

I would like to express my sincere gratitude to Ms. Shanthala, HR Manager, Vivarttana

Technologies Pvt. Ltd., for his keen interest and invaluable support throughout the course of
this work.

I am highly grateful to Dr. Prasanna Kumar H R, Professor and Head of the

Department, IS&E, PESITM, Shivamogga for his kind support and encouragement throughout
thecourse of this work.

I extend my gratitude to the Internship coordinator Mr. Vinay S K, Assistant Professor,

PESITM, Shivamogga for providing me an opportunity to fulfill my most cherished desire of
reaching my goal.

My humble gratitude to the Internal guide Mrs. Damini T K Assistant Professor,

PESITM, Shivamogga who provided valuable inputs which in turn aided me to successfully
complete the internship.

I would like to thank all the teaching and non-teaching staff of Department of IS&E for
their kind Co-operation during the course of the work. The support provided by the College and
Departmental library is gratefully acknowledged.

I perceive as this opportunity as a big milestone in my career development. I will strive

to use gained skills and knowledge in the best possible way, and I will continue to work on the
rest of the project, in order to attain desired career objectives.

Finally, I am thankful to my parents and friends, who helped me in one way or the other
throughout my project work.

Vaibhav Hegde
4PM20IS050
v
 Machine Learning

ABSTRACT

This project represents a water quality prediction model which is developed by using advanced
machine learning techniques. Various algorithms are used like Naïve Bayesian Classifier and
Random Forest Algorithm. Evaluation metrics demonstrate the model's reliability. Results indicate
its potential for real-time monitoring and early warnings, contributing to sustainable water
management and public health protection. Future work includes additional data integration and
continuous refinement for improved predictive capabilities.

vi
 Machine Learning

TABLE OF CONTENTS

Topics Page No.

Declaration iii
Acknowledgement iv
Abstract v
Chapter 1: Introduction about Internship 1-2
1.1 Introduction 1
1.2 Objectives of the Internship 1-2
1.3 Title of the Internship 2
1.4 Statement of the Problem 2
1.5 Aim of the project 2

Chapter 2: Company Profile 3-5

2.1 Industry Profile 3
2.2 Product and Services 4
2.3 Vision 5

Chapter 3: Technology 6-7

3.1 Machine Learning 6
3.2 Python 7
3.3 Anaconda Navigator 7

Chapter 4: System Requirement Specification 8

4.1 Software Requirements 8

4.2 Hardware Requirements 8

vii
 Machine Learning

Chapter 5: Implementation 9 – 12

5.1 Pseudocode 9
5.1.1 Importing the modules 9
5.1.2 Splitting of Data 9
5.1.3 Random Forest Algorithm 10
10
5.1.4 Naïve Bayes Theorem

5.2 Snapshots 11-12

Conclusion 13

vii
 Machine Learning

LIST OF FIGURES

Figure number Figure name Page number

2.1 Viavrttana Logo 3

2.2 Product and Services 4

5.1 Bar Graph for Portability count 11

5.2 Pie Chart for Portability Count 11

5.3 Bar Graph for Model Accuracy 12

viii
 Machine Learning

CHAPTER 1

INTRODUCTION ABOUT INTERNSHIP

1.1 Introduction

Internships serve as practical learning experiences for students and individuals, allowing them
to apply theoretical knowledge in real-world settings. Participants engage in hands-on work,
gaining valuable insights and skills relevant to their field of study or career aspirations. I got an
opportunity to work in Vivarttana Technologies Pvt Ltd where I got experience in working
about machine learning technologies. These opportunities often include mentorship from
experienced professionals, fostering personal and professional development. Interns collaborate
on actual projects, enhancing their problem-solving, communication, and teamwork skill.

1.2 Objective of the Internship

As partial fulfilment of the requirements of the Bachelor of Engineering program of

Visvesvaraya Technological University, I was assigned to Vivarttana Technologies Pvt. Ltd.,
for four-week internship program. The Primary objective of the internship id to generate a
thorough understanding of the workplace relationship, performing of the activities and
engaging oneself in the working environment. In a way, it was more to get practical
implication of all the studies, theories that I had acquired so far. This would help me to pave
way towards growth in my academic as well as personal development. Apart from general
objectives, the specific objectives are highlighted below:

• To acquire exposure in the working environment resulting in the development of

practical knowledge, confidence and diplomacy.

• To learn and apply theoretical knowledge practically in the workplace.

• To develop interpersonal, managerial and communication skills.

1
Dept. Of IS&E, PESITM, Shivamogga
 Machine Learning

• To come up with the possible strategies to gain competitive advantage

• To be a valuable asset for the organization by contributing positive aspects.

• To fulfil the partial requirement for the Bachelor of Engineering program of
Visvesvaraya Technological University.

1.3 Title of Internship

The title of the Internship is “Water Quality Prediction”. The project aims at predicting
the quality of water sample and it used to tell that the water is drinkable or not. This project
helps the user to choose the drinkable water which is clean and disease free.

1.4 Statement of the Problem

The challenge is to develop an accurate water quality prediction model using advanced
machine learning. Current methods lack precision, hindering timely responses to fluctuations.
The goal is to integrate diverse datasets, to create a reliable tool for real-time prediction. This
addresses the pressing need for proactive water resource management, supporting ecosystem
health and public well-being.

1.5 Aim of the project

• Create an advanced machine learning model to accurately predict water quality parameters.

• Account for dynamic changes in water quality over time and across different locations,
ensuring the model’s adaptability

• Explore the efficacy of different algorithms such as neural networks, decision trees, and
ensemble methods for water quality prediction.

• Train and validate the predictive model using a robust dataset obtained from various
monitoring stations, ensuring its reliability.

2
Dept. Of IS&E, PESITM, Shivamogga
 Machine Learning

CHAPTER 2
COMPANY PROFILE

2.1 Industry Profile

Vivarttana Technologies Pvt Ltd is an IT Services and IT Consulting company. They
provide quality service at affordable prices and offer a wide range of services in Web
development, Data Science, Machine Learning and cloud computing. They are constantly
on the learning agenda and this helps to grow continually by developing and sharing
skills, knowledge and ideas from our innovative and enthusiastic environment.

Fig 2.1 Vivarttana Logo

Their services to IT companies have reduced the hiring cycle time and led to cost effective
measures to source the best talent from on and off campus. they have transformed many lives by
imparting 360 degree learning – Domain, Process & Technology, keeping focus on Customer
Experience and Operational Excellence objectives.

3
Dept. Of IS&E, PESITM, Shivamogga
 Machine Learning

2.2 Products and Services

Fig 2.2: Product and Services

Consulting:
Today, business and technology innovation are inextricably linked and the demand for technology-
enabled business transformation services is rapidly growing. Vivarttana Technology professionals
help clients resolve their most critical information and technology challenges.

Software Product Development:

Vivarttana product division is to build products to address business problems in the market and
business solutions to their customers. We have expertise in handling a wide range of technology
platforms that are needed across the spectrum to capture, store, process and analysis big data. We
have a team of brilliant young minds with an average experience of a decade, who have delivered
compelling applications to our customers. Our team of subject matter experts provide well rounded
advice encompassing issues of cost, product, quality, performance, reliability and serviceability.

Internship:
Internship program is conducted for a period ranging from 1 month (for students) to 6 months
(for graduates). On completion of internship program, certification of completion will be awarded to
the candidate. You would be ready for industry requirements to perform the job.

4
Dept. Of IS&E, PESITM, Shivamogga
 Machine Learning

2.3 Vision

• Dependability: We aim to keep all our products performance to be able to accomplish its
assigned mission.
• Consistency: We work to keep all the technologies consistently in reach for customer useand
satisfaction.
• Ownership: We are accountable for all the actions we take and keep customer feelings indue
regard.
• Integrity: We provide good value and satisfy customers expectation, being ethical, fairand
transparent.
.

5
Dept. Of IS&E, PESITM, Shivamogga
 Machine Learning

CHAPTER 3
TECHNOLOGY

3.1 Machine Learning

• Machine learning is a field of artificial intelligence where computers learn from data
to make predictions or decisions.

• It involves three main types: supervised learning (using labeled data), unsupervised
learning (finding patterns in unlabeled data), and reinforcement learning (making
decisions based on feedback).

• Common algorithms include linear regression, decision trees, and neural networks.
Applications range from image recognition to predictive analytics.

• Challenges include ensuring data quality and addressing interpretability issues in

complex models.

• Overall, machine learning transforms how computers analyze data, automate tasks,
and make informed decisions.

3.2 Python
• Python is a versatile, high-level programming language known for its simplicity and
readability.

• It supports a wide range of applications, from web development and data analysis to
artificial intelligence.

• Python's extensive libraries, such as NumPy and TensorFlow, make it a popular

choice for scientific computing and machine learning.

• Its syntax emphasizes code readability, reducing the cost of program maintenance and
development.

• Python is platform-independent, allowing code to run seamlessly across different

systems.

6
 Machine Learning
• Its vibrant community and large ecosystem contribute to its continual growth and
relevance in various industries.

3.3 Anaconda Navigator

• Anaconda Navigator is a user-friendly graphical interface for managing and launching

applications within the Anaconda distribution.

• It simplifies the use of Python and its associated libraries for data science, machine
learning, and scientific computing.

• With Navigator, users can easily manage environments, install packages, and launch
popular applications such as Jupyter Notebooks or Spyder IDE.

• It streamlines the process of setting up and navigating through different Python

environments and tools, making it particularly convenient for data scientists and
developers.

7
 Machine Learning

CHAPTER 4

SYSTEM REQUIREMENTS SPECIFICATION

4.1Software Requirements

• Windows Operating System

• Platform: anaconda Navigator (Jupyter Notebook)

• Languages Used: Python

• Domain: Machine Learning

4.2Hardware Requirements

• Processor: Intel Core Processor

• RAM Size: 4 GB

• Hard Disk: 500 GB

• Display: 800 x 600 or higher-resolution display with 256 colors.

8
Dept. Of IS&E, PESITM, Shivamogga
 Machine Learning

CHAPTER 5

IMPLEMENTATION
5.1 Pseudocode:
Pseudocode is sometimes used as a detailed step in the process of developing a program. It
allows designers or lead programmers to express the design in great detail and provides
programmers a detailed template for the next step of writing code in a specific programming
language.

5.1.1 Importing the modules

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

To import a module in Python, use the "import" keyword followed by the module name. This
allows access to the functions, classes, or variables defined in that module. Importing enables code
reuse and organization, enhancing the efficiency of Python programming.

5.1.2 Splitting of Data

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(Input, Output, test_size = 0.2, random_state=0)

To split data in Python, use functions like train_test_split from libraries like scikit-learn. This
process divides a dataset into training and testing sets for model evaluation. Splitting is crucial for
assessing a model's performance on unseen data, ensuring its generalization.

9
Dept. Of IS&E, PESITM, Shivamogga
 Machine Learning

5.1.3 Random Forest Algorithm

from sklearn.ensemble import RandomForestClassifier

from sklearn.metrics import accuracy_score
classifier_RF = RandomForestClassifier()
classifier_RF = classifier_RF.fit(X_train, y_train)
y_pred_RF = classifier_RF.predict(X_test)
Accuracy_RF = accuracy_score(y_test,y_pred_RF)
print("Model Accuracy of Random Forest Algorithm:",Accuracy_RF)

Random Forest is an ensemble machine learning algorithm that builds multiple decision trees
during training and outputs the mode of the classes for classification or the average prediction for
regression. It improves accuracy and reduces overfitting by combining the predictions of multiple
tree

5.1.4 Naïve Bayes Theorem

from sklearn.naive_bayes import GaussianNB

NB = GaussianNB()

NB.fit(X_train,y_train)

predict_NB = NB.predict(X_test)

Acuracy_NB = NB.score(X_test,predict_NB)

print("Model Accuracy of Naive Bayes Algorithm:",Acuracy_NB)

Naive Bayes is a probabilistic algorithm based on Bayes' theorem, making assumptions of

independence between features. It's commonly used for classification tasks in machine
learning, providing a simple and efficient method for predicting class probabilities.

10
Dept. Of IS&E, PESITM, Shivamogga
 Machine Learning

5.2 Snapshots

Fig 5.1 Bar Graph for Portability Count

Fig 5.2 Pie Chart for Portability Count

11
Dept. Of IS&E, PESITM, Shivamogga
 Machine Learning

Fig 5.3 Bar Graph to represent model Accuracy

12
Dept. Of IS&E, PESITM, Shivamogga
 Machine Learning

CONCLUSION

The Water Quality Prediction project successfully demonstrates the power of advanced machine
learning in accurately assessing and managing water quality. The developed predictive model,
considering diverse parameters and temporal variations, offers a reliable tool for real-time
monitoring and early warnings. This technological approach aligns with sustainability goals,
contributing to ecosystem preservation and public health. Continuous model refinement and
exploration of additional data sources remain essential for further enhancing predictive capabilities.
The project marks a significant stride toward leveraging technology for responsible water resource
management, promoting environmental health, and ensuring community well-being.

13
Dept. Of IS&E, PESITM, Shivamogga