A GLOBAL CERTIFICATION

REPORT ON

AI-900: Microsoft Azure AI Fundamentals

Submitted in partial fulfillment for award of degree of
Bachelor of Technology

In

Computing and Information Technology

SUBMITTED
BY
Sandesh.
S.V
R17CS357

UNDER THE GUIDANCE OF

Prof. Spoorthi Rakesh

Associate Professor

School of Computing and Information

Technology REVA UNIVERSITY
Rukmini Knowledge Park, Kattigenahalli,
Yelahanka, Bangalore-560064
2021

1
 School of Computing and Information Technology

DECLARATION

I, Sandesh. S.V hereby declare that the Course entitled “AI-900:

Microsoft Azure AI Fundamentals” which is being submitted as
report of Global certification course of 8th semester towards the
Bachelor of Technology Degree C&IT, with the support of AI&ML
Bundled with Microsoft Certification on Azure AI by ATS at
School of Computing and Information Technology, REVA
University. This report is an authentic record of course completion by
me in partial fulfillment of the requirements for the award of degree for
the academic year 2020-21.

Date: 14-06-2021 Sandesh. S.V

Place: Bengaluru
 ACKNOWLEDGEMENT

Eventually I am grateful to God Almighty and a number of individuals whose

professional guidance, assistance and encouragement have made it a pleasure
endeavor to undertake this Course.

I would like to express my sincere gratitude to the esteemed REVA University,

Bangalore for the wonderful opportunity given to me in carrying out this Course.

I wish to express heartfelt thanks to my research supervisor, Prof. Spoorthi

Rakesh, Associate Professor, Affiliation, for her valuable guidance, motivation
during my course. She/he has been a source of inspiration and his/her tireless
guidance and incredible effort has enabled to complete this course successfully.
His/her Simplicity, honesty, patience, generosity, and perfectness are qualities that
have inspired me a lot.

I express my deepest gratitude to Dr. P. Shyama Raju, Chancellor, REVA

University, Bangalore, for the environment and infrastructure provided to carry out
and complete my course under one roof in REVA University campus, Bangalore.

I owe my deepest gratitude to Dr. Surendra Rao Shankapal, I/C Vice-Chancellor

REVA University, Bangalore, for his continues support, encouragement.

It is a pleasure to express my gratitude whole heartily thanks to Dr. Sunilkumar S.

Manvi, Director, School of Computing and Information Technology, REVA
University, Bangalore, to timely process the research related tasks.

Sandesh. S.V
 CERTIFICATE
This is to certify that the Global Certification Course entitled “AI-900: Microsoft
Azure AI” carried out by Sandesh. S.V, R17CS357 a bonafide student of REVA
University, Bangalore, in partial fulfilment for the award of Bachelor of Technology
in school of Computing and Information Technology during the year 2020-2021. It
is certified that all corrections/suggestions indicated for Internal Assessment have
been incorporated in the report deposited in the departmental library. This report has
been approved as it satisfies the academic requirements in respect of Global
Certification Course prescribed for the said degree.

Signature of Guide Signature of Director

<Prof.Spoorthi Rakesh> <Name>
<Associate Professor> <Designation>
<School of CSE> <Department>

External Viva

External Examiners Signature with date

1………………........ 1…………….……..
COURSE COMPLETION CERTIFICATE
 TABLE OF CONTENTS

CHAPTER TITLE PAGE NUMBER

I Course Description 7

a. Introduction 7

b. Objective 7

II Overview of the Course 7-10

a. Need and Purpose of the course 7

b. Contents Covered 8-10

III Technical Description

a. Technologies Involved 10

b. Challenges Faced 10

c. Professional growth and 11

Learning
d. Assignments Completed 11-13

IV Conclusion 13
 I. COURSE DESCRIPTION

a) Introduction
Machine learning is an application of artificial intelligence (AI) that
provides systems the ability to automatically learn and improve from
experience without being explicitly programmed. Machine
learning focuses on the development of computer programs that can access
data and use it to learn for themselves. Based on the style and method
involved, Machine Learning Algorithms are divided into three major
types: Supervised Learning, Unsupervised Learning, and Reinforcement
Learning.
b) Objectives
Gain an overall knowledge about Machine learning (ML) , its various
types. Learn about the different algorithms used for each type of ML and
compare their accuracies, efficiency, and performance to pick the right
model for a given problem. Explore the Microsoft Azure service and know
the different models that can be built using it.

II. OVERVIEW OF THE COURSE

a) Need and purpose of the course

The main aim of the course is to introduce us to this huge branch of

Artificial Intelligence (AI) that is- ML. In the computer science world ML
has been a strong buzzword these days and is being used in almost all
aspects of life to improve the quality and efficiency of it. This being the
current situation, having knowledge about ML not only gives us an edge
over other but we can also try and come up with brilliant ideas and find
solutions to any issues we maybe facing.

b) Course Contents

1. Introduction to Machine Learning and Python

 Machine learning is an application of artificial intelligence (AI) that
provides systems the ability to automatically learn and improve from
experience without being explicitly programmed. Machine
learning focuses on the development of computer programs that can
access data and use it to learn for themselves. Based on the style and
method involved, Machine Learning Algorithms are divided into three
major types: Supervised Learning, Unsupervised Learning, and
Reinforcement Learning.

2. Essential Python packages for Machine Learning

 Numpy- NumPy, which stands for Numerical Python, is a

library consisting of multidimensional array objects and a
collection of routines for processing those arrays. Using
NumPy, mathematical and logical operations on arrays can be
performed.

 Pandas- Pandas is an open-source, BSD-licensed Python

library providing high-performance, easy-to-use data structures
and data analysis tools for the Python programming language.
Python with Pandas is used in a wide range of fields including
academic and commercial domains including finance,
economics, Statistics, analytics, etc.

 Matplotlib- Matplotlib is a Python Library used for plotting,

this python library provides and objected-oriented APIs for
integrating plots into applications.

 Seaborn- Seaborn is a Python data visualization library based

on matplotlib. It provides a high-level interface for drawing
attractive and informative statistical graphics.

 Scikit-learn- Scikit-learn provides a range of supervised and

unsupervised learning algorithms via a consistent interface in
Python. It is licensed under a permissive simplified BSD
license and is distributed under many Linux distributions,
encouraging academic and commercial use.
3. Data Cleaning and Preprocessing

 Handling missing data:

1. Dropping

2. Filling in with zero for numerical columns

3. Imputer Class

 Dealing with categorical variables:

1. Label Encoding

2. One hot encoding

4. Data Analysis and Visualization

Data analysis is the process of cleaning, analyzing, interpreting,

and visualizing data to discover valuable insights that drive smarter
and more effective business decisions. Representation of data
learnt using graphs, charts, or other visual formats.

5. Streamlit and Heroku

Streamlit is an open-source app framework for Machine Learning

and Data Science teams. Heroku is a platform as a service (PaaS)
that enables developers to build, run, and operate applications
entirely in the cloud. These two platforms are mainly used for
deployment of the ML models as a webpage or on the cloud which
aids in making them portable and easily accessible.

6. Model Deployment on Azure

Microsoft Azure is a cloud computing service from Microsoft.

Azure offers a range of software as a service (SaaS), platform as a
service (PaaS) and infrastructure as a service (IaaS) options for
deploying applications and services on Microsoft-managed data
center infrastructure. Microsoft Azure Machine Learning (Azure
ML) provides a set of modern tools and ML frameworks for
 developers to create their own machine learning and AI services.
We dealt with the following three types of models:

● Automated machine learning

● Designer method
● Collaborative Notebooks

III. Technical Descriptions

a) Technologies involved

The language used to code throughout the course was Python, as it is user-
friendly when it comes to coding ML models providing a large collection of
packages that make the model building process a smooth and simple. The
other technology involved was Microsoft Azure AI service which helps build
complex machine learning models with just a couple of clicks and also allows
the user to customize the model, use their own dataset, compare among
different algorithms, visualize then and pick the best one.

b) Challenges faced

 Models not trained well due to insufficient data or data disturbances.

 Prolonged periods for training the models

 Non-satisfactory accuracies due to various reasons.

c) Professional Growth and Learning

This certification introduced the Microsoft Azure tool which is

powerful and efficient application to collect, manipulate, track,
visualize and handle data and build ML models. With ML being a
 major technology that companies are expecting their employees to
have knowledge about, this course is a greatly helped gain knowledge
about the field. This serves as a good platform for us to pick up any
profession involving ML and focus on honing the specificalities
required for the role we desire.

d) Assignments

Completed Assignment-1:

The main goal of this project is to predict hotel cancellations by using

the features in the given dataset. This problem is an example of
supervised learning and the task at hand is prediction. The data
preprocessing is done all the missing and irrelevant values are
handled. The dataset is split into test and train data on which the Extra
Trees Regression Algorithm was implemented. A satisfactory score
RMSE score of 0.77 was obtained. The results of the model are as
shown below
Assignment-2: The main goal of this project is to predict the price of
the flight by using the features in the given dataset. Data
preprocessing was done to handle missing values and the features
were selected. The dataset is split into test and train data on which the
Logistic regression algorithm was applied. The prediction would be
made according to the users input provide on the webpage which was
deployed using Streamlit as shown in the images below.
IV. Conclusion: Machine learning is being used in many aspects of our daily
life to improve its quality. This course has provided a very clear idea of
machine learning and how we can use it in real-life applications. I now have
a very good understanding of the entire life cycle of how a model is coded
and deployed. Azure tool provides a wide range of ML algorithms that can be
used to build a model without having to code. With ML being the boom in
the technical world right now this course will prove an added skill at my
workplace.