MACHINE LEARNING BASED PREDICTING STUDENT’S

GRADE

ABSTRACT

Machine learning has evolved significantly over the past decade, enabling predictive analytics in
various fields, including education. Its application in predicting student grades helps in early
intervention and personalized learning. Traditional system Teacher Assessments and
Observations: Teachers would observe students’ performance, participation, and behavior in
class. They used their professional judgment to assess students' understanding and predict their
future performance. Historical Performance Analysis: Past academic records and grades were
used to predict future performance. Standardized Testing: Students were evaluated through
standardized tests to gauge their academic abilities and predict future grades. Peer Comparisons:
Comparing a student's performance with that of their peers to predict their future grades. Parental
and Socioeconomic Factors: Considering the influence of parents' education level,
socioeconomic status, and involvement in their children's education. Counselor and Advisor
Inputs: School counselors and academic advisors provided insights and predictions based on
their interactions with students. Problem statement are Subjectivity in Teacher Assessments,
Inadequate Analysis of Historical Performance, Challenges with Peer Comparisons. Predictions
based on counselor and advisor inputs can be inconsistent due to varying levels of experience,
subjective judgments, and limited interactions with students, leading to unreliable academic
performance forecasts. Research Motivation Improving the accuracy of grade prediction can help
educators identify at-risk students early and tailor interventions accordingly. Leveraging machine
learning offers the potential to uncover hidden patterns and insights that traditional methods
miss. The proposed system utilizes advanced machine learning algorithms, such as neural
networks and ensemble methods, to predict student grades with higher accuracy. By
incorporating diverse datasets, including behavioral and demographic information, the system
aims to provide a holistic assessment of student performance. This approach enhances predictive
capabilities and supports targeted educational strategies.(ML real time example)
Objective

The objective of this research is to develop a machine learning-based system to predict student
grades with high accuracy. By leveraging advanced algorithms and diverse datasets, the system
aims to identify at-risk students early and provide insights for personalized educational
interventions. This approach seeks to improve academic outcomes by enabling proactive and
targeted support for students.

History

Historically, predicting student performance has relied on various traditional methods. Teachers
would assess students' performance, participation, and behavior in class using their professional
judgment to predict future grades. Historical performance analysis involved using past academic
records and grades to forecast future achievements. Standardized testing was another common
approach, where students' academic abilities were evaluated through uniform tests. Peer
comparisons were also used to predict grades by comparing individual performance with that of
classmates. Additionally, parental and socioeconomic factors were considered, acknowledging
the influence of family background on academic performance. Inputs from school counselors and
advisors provided further predictions based on their interactions with students.

Traditional Systems

Before the advent of machine learning and AI, the traditional systems for predicting student
grades included several key methods. Teacher assessments and observations were primary tools,
relying heavily on educators' subjective evaluations of students' classroom performance.
Historical performance analysis used past grades and academic records as predictors for future
success. Standardized tests were administered to gauge students' capabilities in a consistent
manner. Peer comparisons involved evaluating a student's performance relative to their
classmates. Furthermore, parental and socioeconomic factors, such as parents' education level
and involvement, played a role in grade prediction. Counselors and advisors contributed insights
based on their professional interactions with students, although these were often subjective and
varied in reliability.
Problem Statement

The traditional methods of predicting student grades face several challenges. Teacher
assessments can be highly subjective and influenced by individual biases, leading to inconsistent
evaluations. Analyzing historical performance alone may not capture the complexities of a
student's learning journey. Peer comparisons can be misleading as they do not account for
individual differences and unique learning paces. Predictions based on counselor and advisor
inputs can be inconsistent due to varying levels of experience, subjective judgments, and limited
interactions with students. These limitations result in unreliable academic performance forecasts
and hinder effective early interventions.

Research Motivation

The motivation for this research is to enhance the accuracy of grade predictions to better support
educational outcomes. By improving predictive accuracy, educators can identify at-risk students
early and tailor interventions to meet their specific needs. Machine learning offers the potential
to uncover hidden patterns and insights that traditional methods may overlook. Leveraging
diverse datasets, including behavioral and demographic information, can provide a more
comprehensive assessment of student performance. This research aims to bridge the gap between
traditional methods and advanced predictive analytics to create a more effective and reliable
system for predicting student grades.

Proposed System

The proposed system utilizes advanced machine learning algorithms, such as neural networks
and ensemble methods, to predict student grades with higher accuracy. By incorporating diverse
datasets, including behavioral and demographic information, the system aims to provide a
holistic assessment of student performance. Machine learning models can process large volumes
of data and identify complex patterns that traditional methods may miss. This approach enhances
predictive capabilities and supports targeted educational strategies. The system can provide real-
time insights, enabling educators to make informed decisions and implement timely interventions
to improve student outcomes. By leveraging machine learning, the proposed system aims to
revolutionize grade prediction and support personalized learning experiences.
Introduction

Education is a cornerstone of societal development, and accurate prediction of student

performance is essential for fostering academic success. Traditional methods of grade prediction
often fall short in providing consistent and reliable results due to their subjective nature. Recent
advancements in machine learning have opened new avenues for predictive analytics in
education, offering the potential to enhance the accuracy and reliability of these predictions.
According to a report by the World Economic Forum, the global market for AI in education is
expected to reach $6 billion by 2024, demonstrating the growing interest and investment in
leveraging technology for educational improvement.

Machine learning algorithms, with their ability to process vast amounts of data and uncover
hidden patterns, offer a promising solution for predicting student grades. A study conducted by
Educause Review found that institutions using predictive analytics saw a 10-15% improvement
in student retention rates. This highlights the transformative impact that data-driven insights can
have on educational outcomes. By integrating behavioral, demographic, and academic data,
machine learning models can provide a holistic view of a student's performance, enabling early
identification of at-risk students and facilitating personalized interventions.
 CHAPTER 2

LITERATURE SURVEY

Jayaprakash et al. [1] proposed an improved Random Forest classifier for predicting students'
academic performance in their 2020 paper presented at the International Conference on
Emerging Smart Computing and Informatics (ESCI). The study aimed to enhance the accuracy
of academic performance predictions by utilizing an advanced version of the Random Forest
algorithm. By integrating various features related to student performance, the authors sought to
provide a more robust tool for educational institutions to assess and support students. Their
approach demonstrated the potential of machine learning techniques in improving academic
predictions and offering valuable insights for educational interventions.

Bhutto et al. [2] explored the use of supervised machine learning to predict students' academic
performance in their 2020 paper presented at the International Conference on Information
Science and Communication Technology (ICISCT). Their research focused on applying various
machine learning algorithms to predict academic outcomes based on student data. The study
highlighted the effectiveness of supervised learning methods in forecasting performance and
provided a framework for educational institutions to leverage these techniques for better student
evaluation and support. The work underscored the growing importance of machine learning in
educational data analysis.

Jacob et al. [3] reviewed educational data mining techniques and their applications in their 2015
paper presented at the International Conference on Green Computing and Internet of Things
(ICGCIoT). The study provided a comprehensive overview of different data mining methods
used in education and their potential applications for enhancing teaching and learning processes.
By examining various techniques, the authors aimed to offer insights into how educational data
mining can be utilized to improve academic performance and educational outcomes. Their work
contributed to the understanding of how data-driven approaches can support educational
innovations.
Al Mayahi and Al-Bahri [4] investigated machine learning-based prediction of student academic
success in their 2020 paper presented at the 12th International Congress on Ultra Modern
Telecommunications and Control Systems and Workshops (ICUMT). Their research focused on
developing machine learning models to predict academic success based on student data. The
study aimed to enhance the accuracy of success predictions and provide valuable insights for
educational institutions to better support students. By applying machine learning techniques, the
authors sought to contribute to more effective academic performance forecasting.

Olaperi et al. [5] proposed a framework for academic advice through mobile applications in their
2016 study. The research focused on developing a mobile application framework to provide
academic advice and support to students. By integrating various features and functionalities, the
framework aimed to enhance student engagement and academic performance. The study
highlighted the potential of mobile technology in providing personalized academic support and
improving student outcomes through innovative digital solutions.

The U.S. Department of Education [6] released a statement on the 2019 NAEP results, providing
an overview of the National Assessment of Educational Progress (NAEP) findings. The
statement discussed trends and outcomes related to student performance on the NAEP
assessments, offering insights into educational progress and areas for improvement. The report
served as a valuable resource for educators and policymakers to understand and address
challenges in the education system.

Rimadana et al. [7] examined the prediction of student academic performance using machine
learning and time management skill data in their 2019 paper presented at the International
Seminar on Research of Information Technology and Intelligent Systems (ISRITI). Their study
aimed to integrate time management skills into performance predictions to enhance the accuracy
of forecasting academic success. By applying machine learning techniques, the authors sought to
provide a more comprehensive approach to predicting student outcomes and supporting
academic achievement.

Mohd Nasir et al. [8] reviewed student attendance systems using Near-Field Communication
(NFC) technology in their 2015 paper published in the *LNCS* series. Their research explored
the application of NFC technology in monitoring and managing student attendance. The study
highlighted the advantages of using NFC for attendance tracking and its potential impact on
educational administration. By providing a detailed review, the authors aimed to offer insights
into the effectiveness and implementation of NFC-based attendance systems.

Xu et al. [9] investigated the prediction of academic performance associated with internet usage
behaviors using machine learning algorithms in their 2019 paper published in *Computers in
Human Behavior*. Their research focused on analyzing internet usage patterns to predict
academic performance. By applying machine learning techniques, the study aimed to uncover
correlations between online behaviors and academic outcomes, offering valuable insights for
educational institutions to address potential issues and improve student performance.

Hasan et al. [10] proposed a machine learning algorithm for predicting students' performance in
their 2019 paper presented at the 10th International Conference on Computing, Communication
and Networking Technologies (ICCCNT). The study focused on developing a machine learning
model to forecast student performance based on various input features. The research aimed to
enhance the accuracy of performance predictions and provide educational institutions with tools
to better support students and improve academic outcomes.

Scikit-learn [11] is a comprehensive machine learning library for Python, offering various tools
and algorithms for data analysis and model building. The documentation provides detailed
information on the library's features, including its implementation of various machine learning
algorithms, preprocessing techniques, and evaluation metrics. Scikit-learn is widely used in the
machine learning community for its ease of use and extensive functionality.

TensorFlow [12] is an open-source machine learning framework developed by Google, designed

for building and training machine learning models. The documentation offers insights into
TensorFlow's capabilities, including its support for deep learning, neural networks, and various
optimization techniques. TensorFlow is a popular choice for developing complex machine
learning models and has a strong presence in both research and industry applications.

The UCI Machine Learning Repository [13] is a widely used resource for machine learning
datasets, providing access to a diverse collection of data for research and experimentation. The
repository includes datasets for various domains, including education, health, and finance,
making it a valuable resource for researchers and practitioners in the field of machine learning.

Nurafifah et al. [14] reviewed predicting students' graduation time using machine learning
algorithms in their 2019 paper published in the *International Journal of Modern Education and
Computer Science*. Their study focused on applying machine learning techniques to estimate
students' graduation timelines based on academic data. The research aimed to improve the
accuracy of graduation time predictions and offer insights for educational institutions to better
plan and support students throughout their academic journey.
 CHAPTER 3

EXISTING ALGORITHM

3.1 Traditional System Overview (Before Using AI)

Before the integration of AI and machine learning in educational systems, student grade
prediction relied on traditional methods rooted in human judgment and standardized
assessments. Teacher Assessments and Observations were a primary tool, where teachers
evaluated students based on classroom performance, participation, and behavior. These
assessments were largely subjective, depending on the teacher's perception and experience.
Another common method was Historical Performance Analysis, where educators predicted
future grades based on past academic records. While useful, this approach often failed to
consider changes in a student’s learning abilities or external factors influencing performance.

Standardized Testing played a significant role, providing a uniform measure of students’

academic abilities. However, these tests typically focused on specific areas and did not
account for individual learning differences or holistic development. Peer Comparisons were
also used, wherein a student’s performance was evaluated relative to their classmates. This
method, while offering a competitive perspective, lacked personalization and often failed to
recognize unique learning trajectories.

Additionally, Parental and Socioeconomic Factors were considered, acknowledging the

impact of a student’s home environment on academic performance. However, these factors
could introduce biases and lead to generalized assumptions. Lastly, Counselor and Advisor
Inputs provided a more personalized prediction based on one-on-one interactions with
students. However, the effectiveness of these inputs varied widely depending on the
counselor's experience, the frequency of interactions, and their ability to understand and
analyze student needs comprehensively.

Overall, these traditional methods, though foundational, were limited in their ability to
provide accurate and objective predictions, often leading to inconsistent and sometimes
biased outcomes.
3.2 Limitations of Traditional Systems (Before Using AI)

Subjectivity in Teacher Assessments:

Teachers' evaluations of students were heavily reliant on their personal judgment,

which could introduce biases and inconsistencies.

Factors such as favoritism, mood, and teaching style could influence the accuracy of
these assessments, leading to potential misjudgments of a student's abilities.

Inadequate Analysis of Historical Performance:

Predicting future performance based solely on past grades failed to account for
students’ growth, changes in learning pace, or external factors that could affect
academic outcomes.

This method often overlooked a student's potential for improvement or regression,

providing an incomplete picture of their future academic prospects.

Limitations of Standardized Testing:

Standardized tests offered a narrow evaluation of academic abilities, often focusing

on specific subjects and ignoring other crucial skills such as creativity, critical
thinking, and problem-solving.

These tests did not account for individual learning styles or external factors, leading
to potential misinterpretation of a student's true capabilities.

Challenges with Peer Comparisons:

Comparing students to their peers could lead to unhealthy competition and stress, as it
did not consider individual learning trajectories and personal circumstances.

This approach often failed to recognize the unique strengths and weaknesses of each
student, instead promoting a one-size-fits-all assessment.

Biases in Considering Parental and Socioeconomic Factors:

 While parental education level and socioeconomic status can influence academic
performance, relying on these factors could lead to biased predictions and reinforce
stereotypes.

This approach sometimes generalized students' potential based on their backgrounds,

ignoring individual effort and personal circumstances.

Inconsistencies in Counselor and Advisor Inputs:

The effectiveness of predictions from counselors and advisors varied significantly

depending on their experience, frequency of student interactions, and subjective
interpretations.

Limited interactions with students could result in incomplete assessments, and

varying levels of expertise among counselors led to inconsistent and sometimes
unreliable predictions.

Lack of Real-Time Data Analysis:

Traditional methods did not leverage real-time data, making it difficult to identify at-
risk students or intervene promptly.

The static nature of these methods meant that they could not adapt quickly to changes
in a student's academic or personal life, often leading to delayed or ineffective
interventions.
 CHAPTER 4

PROPOSED ALGORITHM

The Machine Learning-Based Predicting Student Grades project aims to enhance grade
prediction accuracy using advanced machine learning techniques. This approach addresses the
limitations of traditional methods, which often rely on subjective teacher assessments and
inconsistent predictions from counselors.

Figure 4.1: block diagram

Key Aspects

1. Traditional Methods:

o Teacher assessments, historical performance, standardized tests, peer

comparisons, parental factors, and counselor inputs.

2. Challenges:

o Subjectivity and bias in assessments, inadequate analysis of historical data,

unreliable peer comparisons, and inconsistent counselor predictions.

3. Motivation:
 o Improve prediction accuracy, enable early intervention for at-risk students, and
support personalized learning strategies.

4. Proposed System:

o Utilizes machine learning algorithms (e.g., CatBoost, XGBoost) to analyze

diverse datasets and provide a holistic view of student performance.

5. Implementation:

o Data is cleaned and transformed, models are trained and evaluated, and
performance metrics are generated to assess and refine predictions.

Step 1: Dataset

The first step in the research procedure involves gathering and preparing the dataset. For this
project, we use the dataset [Link], which contains various student attributes
and their academic scores. This dataset serves as the foundation for our machine learning model,
providing the necessary data to train and test our algorithms. Each record in the dataset includes
features such as math, reading, and writing scores, along with demographic information about
the students. Ensuring that the dataset is comprehensive and representative of the student
population is crucial for achieving reliable and generalizable results.

Step 2: Dataset Preprocessing

Once the dataset is collected, the next step is preprocessing. This involves cleaning the data to
ensure its quality and suitability for analysis. We start by removing any null values, which could
skew the results if left unaddressed. After handling missing data, we perform label encoding on
categorical variables. This transformation converts categorical text data into numerical format,
which is essential for machine learning algorithms that require numerical inputs. This step
ensures that all data is in a format that can be effectively processed by our models.
Step 3: Label Encoding

Label encoding is a specific preprocessing technique used to convert categorical variables into
numerical labels. In this step, we utilize LabelEncoder from the scikit-learn library to encode
categorical features such as gender and parental education into numerical values. This
transformation allows machine learning models to interpret these variables, which otherwise
would not be usable in their raw form. By converting text-based categories into numerical labels,
we prepare the dataset for the subsequent modeling steps.

Step 4: CatBoost

With the data prepared, we then proceed to train and evaluate the existing model, CatBoost.
CatBoost is a gradient boosting algorithm known for its efficiency with categorical features and
robustness against overfitting. We either load a pre-trained CatBoost model from disk or train a
new model if none exists. The model is trained on the preprocessed dataset, and its performance
is evaluated using various metrics to determine how well it predicts student grades based on the
features provided.

Step 5: XGBoost

Following the evaluation of the CatBoost model, we introduce the proposed model, XGBoost.
XGBoost is another powerful gradient boosting algorithm that is widely used for its performance
and scalability. We train the XGBoost model on the same dataset used for CatBoost and adjust
hyperparameters to optimize its performance. This model is expected to provide a different
perspective on grade prediction, leveraging its unique features and capabilities to potentially
achieve better results.

Step 6: Performance Comparison

After training both CatBoost and XGBoost models, we perform a comprehensive comparison of
their performance. This involves evaluating various metrics such as accuracy, precision, recall,
and F1-score for each model. We use confusion matrices and classification reports to visualize
and interpret the performance differences between the two algorithms. This step helps identify
which model provides better predictions and is more suitable for the grade prediction task.

Step 7: Prediction of Output with XGBoost

Finally, we use the trained XGBoost model to predict outcomes on the test data. The test data,
which was not used during the training phase, provides an unbiased evaluation of the model's
performance. By applying the XGBoost model to this unseen data, we can assess how well it
generalizes to new examples and predict student grades with the model’s learned patterns. This
prediction step is crucial for validating the effectiveness of the proposed approach and for
demonstrating its practical utility in predicting student performance.

4.2 Data Splitting & Preprocessing

Data Splitting:

Data splitting is a critical step in preparing a dataset for machine learning. It involves dividing
the dataset into two main subsets: the training set and the test set. The training set is used to train
the machine learning models, while the test set is reserved for evaluating their performance. This
separation helps ensure that the models are tested on data they have not seen before, providing a
more accurate assessment of their generalization ability. In this project, we use an 80-20 split,
where 80% of the data is allocated for training and 20% is set aside for testing. This partitioning
helps in assessing the model’s accuracy and effectiveness in predicting student grades on new
data.

Data Preprocessing:

1. Handling Missing Values: The initial step in preprocessing is to address any missing
values in the dataset. Missing data can arise for various reasons and can lead to biased or
inaccurate model predictions if not properly managed. We handle missing values by
either imputing them with appropriate statistical measures (e.g., mean, median) or by
removing rows or columns with excessive missing data. This step ensures that the dataset
is complete and ready for further analysis.
 2. Feature Engineering: Feature engineering involves creating new features or modifying
existing ones to better represent the underlying patterns in the data. For instance, in this
project, we calculate the average score (total) across math, reading, and writing scores to
create a composite feature that represents overall student performance. This feature
provides a consolidated view of student achievement and can improve the model’s
predictive power.
3. Label Encoding: Label encoding is used to convert categorical variables into numerical
format. This step is essential because machine learning algorithms typically require
numerical input. We use the LabelEncoder from the scikit-learn library to transform
categorical features such as gender and parental education into numeric values. This
encoding process ensures that categorical data can be effectively utilized by the machine
learning models.
4. Normalization and Scaling: To ensure that all features contribute equally to the model
training process, we apply normalization or scaling techniques. Scaling is particularly
important when features vary significantly in magnitude. We use the StandardScaler from
scikit-learn to standardize features by removing the mean and scaling to unit variance.
This step helps in achieving better model performance and convergence.
5. Discretization: For the purpose of classification, we discretize continuous features into
categorical bins. For example, the total score is divided into grade categories (A, B, C, D,
E) using predefined bins. This discretization converts continuous performance scores into
categorical grades, simplifying the prediction task into a classification problem.
6. Data Splitting (Train-Test Split): Finally, the processed data is split into training and
test sets. The train_test_split function from scikit-learn is used to randomly partition the
data, ensuring that the training set is used to build the models and the test set is reserved
for evaluation. This step helps in assessing how well the model generalizes to new,
unseen data and provides an unbiased evaluation of its performance.

4.3 ML Model Building

4.3.1 Existing Algorithm: CatBoost

What is CatBoost Algorithm?

CatBoost is a gradient boosting algorithm developed by Yandex, designed to handle categorical
features efficiently and improve model performance. It is particularly well-suited for datasets
with a large number of categorical variables and is known for its robustness and ease of use.

How It Works:

CatBoost builds upon the gradient boosting framework, which involves training multiple
decision trees sequentially to minimize the error of previous models. The key innovation of
CatBoost is its handling of categorical features. Unlike traditional gradient boosting methods that
require manual encoding of categorical variables, CatBoost incorporates categorical features
directly into the training process. It uses a technique called “ordered boosting,” which helps
prevent overfitting by using permutations of the data to compute predictions and gradients. This
method improves the generalization ability of the model.

Architecture:

CatBoost's architecture consists of several key components:

1. Categorical Feature Handling: CatBoost can process categorical features without

extensive preprocessing. It applies techniques like target encoding and category statistics
to incorporate categorical variables effectively.
2. Gradient Boosting Framework: It builds decision trees iteratively, with each tree
correcting the errors of the previous ones. This iterative approach helps in minimizing the
loss function and improving prediction accuracy.
3. Ordered Boosting: This technique uses permutations of the data to compute gradients,
reducing the risk of overfitting and enhancing the model's ability to generalize.

Disadvantages:

 Training Time: CatBoost can be computationally intensive and time-consuming,

especially for large datasets with many features.
 Model Complexity: The model’s internal workings, including its handling of categorical
features, can be complex to interpret.
  Resource Usage: CatBoost may require significant memory and processing power,
particularly for very large datasets.

4.3.2 Proposed Algorithm: XGBoost

What is XGBoost Algorithm?

XGBoost (Extreme Gradient Boosting) is a widely used gradient boosting framework that is
known for its high performance and scalability. Developed by Tianqi Chen, XGBoost has
become popular in machine learning competitions and practical applications due to its ability to
handle large datasets and complex data patterns.

How It Works:

XGBoost builds upon the gradient boosting framework by enhancing the efficiency and
effectiveness of the training process. It constructs decision trees sequentially, where each tree is
trained to correct the errors of the previous ones. XGBoost incorporates several advanced
techniques:

1. Regularization: It includes L1 (Lasso) and L2 (Ridge) regularization to reduce

overfitting and improve model generalization.
2. Boosting with Tree Pruning: Trees are built using a depth-first approach and pruned to
prevent overfitting, improving the model’s performance and efficiency.
3. Column Subsampling: XGBoost uses column subsampling to randomly select features
for each tree, enhancing the model's robustness and reducing overfitting.
4. Handling Missing Values: It can handle missing values directly during training, making
it more flexible for real-world data with incomplete information.

Architecture:

XGBoost's architecture includes:

1. Gradient Boosting Framework: Similar to other boosting methods, XGBoost builds

trees sequentially, with each tree focusing on the residual errors of the previous ones.
 2. Regularization and Pruning: XGBoost uses regularization techniques to control model
complexity and tree pruning to optimize the model’s structure.
3. Parallel Processing: It leverages parallel processing and distributed computing to handle
large-scale datasets efficiently.

Advantages:

 High Performance: XGBoost is known for its speed and accuracy, making it a popular
choice for competitive machine learning tasks.
 Regularization: The inclusion of L1 and L2 regularization helps in controlling
overfitting and enhancing model generalization.
 Flexibility: XGBoost can handle various types of data, including missing values, and can
be tuned for different tasks through its extensive set of hyperparameters.
 Scalability: It supports distributed computing and parallel processing, enabling it to
handle large datasets effectively.

CHAPTER 5

UML DIAGRAMS

UML stands for Unified Modeling Language. UML is a standardized general-purpose modeling
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. In its current form UML is comprised
of two major components: a Meta-model and a notation. In the future, some form of method or
process may also be added to; or associated with, UML.
The Unified Modeling Language is a standard language for specifying, Visualization,
Constructing and documenting the artifacts of software system, as well as for business modeling
and other non-software systems. The UML represents a collection of best engineering practices
that have proven successful in the modeling of large and complex systems. The UML is a very
important part of developing objects-oriented software and the software development process.
The UML uses mostly graphical notations to express the design of software projects.

GOALS: The Primary goals in the design of the UML are as follows:

 Provide users a ready-to-use, expressive visual modeling Language so that they can develop
and exchange meaningful models.

 Provide extendibility and specialization mechanisms to extend the core concepts.

 Be independent of particular programming languages and development process.

 Provide a formal basis for understanding the modeling language.

 Encourage the growth of OO tools market.

 Support higher level development concepts such as collaborations, frameworks, patterns and
components.

 Integrate best practices.

Class diagram
The class diagram is used to refine the use case diagram and define a detailed design of the
system. The class diagram classifies the actors defined in the use case diagram into a set of
interrelated classes. The relationship or association between the classes can be either an "is-a" or
"has-a" relationship. Each class in the class diagram was capable of providing certain
functionalities. These functionalities provided by the class are termed "methods" of the class.
Apart from this, each class may have certain "attributes" that uniquely identify the class.

Figure-5.1: Class Diagram

Sequence Diagram

A sequence diagram in Unified Modeling Language (UML) is a kind of interaction diagram that
shows how processes operate with one another and in what order. It is a construct of a Message
Sequence Chart. A sequence diagram shows, as parallel vertical lines (“lifelines”), different
processes or objects that live simultaneously, and as horizontal arrows, the messages exchanged
between them, in the order in which they occur. This allows the specification of simple runtime
scenarios in a graphical manner.

Figure-5.2: Sequence Diagram

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
components in a system. An activity diagram shows the overall flow of control.
 Figure-5.3: Activity Diagram

Data flow diagram

A data flow diagram (DFD) is a graphical representation of how data moves within an
information system. It is a modeling technique used in system analysis and design to illustrate
the flow of data between various processes, data stores, data sources, and data destinations
within a system or between systems. Data flow diagrams are often used to depict the structure
and behavior of a system, emphasizing the flow of data and the transformations it undergoes as it
moves through the system.

Figure-5.4: Dataflow Diagram

Component diagram: Component diagram describes the organization and wiring of the
physical components in a system.

Figure-5.5: Component Diagram

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. Its purpose is to present a
graphical overview of the functionality provided by a system in terms of actors, their goals
(represented as use cases), and any dependencies between those use cases. 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-5.6: use case diagram

Deployment Diagram:

A deployment diagram in UML illustrates the physical arrangement of hardware and software
components in the system. It visualizes how different software artifacts, such as data processing
scripts and model training components, are deployed across hardware nodes and interact with
each other, providing insight into the system’s infrastructure and deployment strategy.

Figure-5.7: Deployment Diagram

Architectural Block Diagram

An architectural block diagram offers a high-level view of a system’s structure, showcasing the
main components and their interactions. It represents how major modules, such as data sources,
processing units, and evaluation components, are organized and how they communicate with
each other to accomplish the system’s objectives. This diagram helps in understanding the
overall design and flow of the system.

Figure-5.8: architectural block diagram

 CHAPTER 6

SOFTWARE ENVIRONMENT

What is Python?

Below are some facts about Python.

 Python is currently the most widely used multi-purpose, high-level programming

language.
 Python allows programming in Object-Oriented and Procedural paradigms. Python
programs generally are smaller than other programming languages like Java.
 Programmers have to type relatively less and indentation requirement of the language,
makes them readable all the time.
 Python language is being used by almost all tech-giant companies like – Google,
Amazon, Facebook, Instagram, Dropbox, Uber… etc.
The biggest strength of Python is huge collection of standard library which can be used for the
following –

 Machine Learning
 GUI Applications (like Kivy, Tkinter, PyQt etc. )
 Web frameworks like Django (used by YouTube, Instagram, Dropbox)
 Image processing (like Opencv, Pillow)
 Web scraping (like Scrapy, BeautifulSoup, Selenium)
 Test frameworks
 Multimedia
Advantages of Python

1. Extensive Libraries
Python downloads with an extensive library and it contain code for various purposes like regular
expressions, documentation-generation, unit-testing, web browsers, threading, databases, CGI,
email, image manipulation, and more. So, we don’t have to write the complete code for that
manually.

2. Extensible

As we have seen earlier, Python can be extended to other languages. You can write some of your
code in languages like C++ or C. This comes in handy, especially in projects.

3. Embeddable

Complimentary to extensibility, Python is embeddable as well. You can put your Python code in
your source code of a different language, like C++. This lets us add scripting capabilities to our
code in the other language.

4. Improved Productivity

The language’s simplicity and extensive libraries render programmers more productive than
languages like Java and C++ do. Also, the fact that you need to write less and get more things
done.

5. IOT Opportunities

Since Python forms the basis of new platforms like Raspberry Pi, it finds the future bright for the
Internet Of Things. This is a way to connect the language with the real world.

6. Simple and Easy

When working with Java, you may have to create a class to print ‘Hello World’. But in Python,
just a print statement will do. It is also quite easy to learn, understand, and code. This is why
when people pick up Python, they have a hard time adjusting to other more verbose languages
like Java.

7. Readable
Because it is not such a verbose language, reading Python is much like reading English. This is
the reason why it is so easy to learn, understand, and code. It also does not need curly braces to
define blocks, and indentation is mandatory. This further aids the readability of the code.

8. Object-Oriented

This language supports both the procedural and object-oriented programming paradigms. While
functions help us with code reusability, classes and objects let us model the real world. A class
allows the encapsulation of data and functions into one.

9. Free and Open-Source

Like said earlier, Python is freely available. But not only can you download Python for free, but
you can also download its source code, make changes to it, and even distribute it. It downloads
with an extensive collection of libraries to help you with your tasks.

10. Portable

When you code your project in a language like C++, you may need to make some changes to it if
you want to run it on another platform. But it isn’t the same with Python. Here, you need to code
only once, and you can run it anywhere. This is called Write Once Run Anywhere (WORA).
However, you need to be careful enough not to include any system-dependent features.

11. Interpreted

Lastly, will say that it is an interpreted language. Since statements are executed one by one,
debugging is easier than in compiled languages.

Any doubts till now in the advantages of Python? Mention in the comment section.

Advantages of Python Over Other Languages

1. Less Coding

Almost all of the tasks done in Python requires less coding when the same task is done in other
languages. Python also has an awesome standard library support, so you don’t have to search for
any third-party libraries to get your job done. This is the reason that many people suggest
learning Python to beginners.

2. Affordable

Python is free therefore individuals, small companies or big organizations can leverage the free
available resources to build applications. Python is popular and widely used so it gives you better
community support.

The 2019 Github annual survey showed us that Python has overtaken Java in the most popular
programming language category.

3. Python is for Everyone

Python code can run on any machine whether it is Linux, Mac or Windows. Programmers need
to learn different languages for different jobs but with Python, you can professionally build web
apps, perform data analysis and machine learning, automate things, do web scraping and also
build games and powerful visualizations. It is an all-rounder programming language.

Disadvantages of Python

So far, we’ve seen why Python is a great choice for your project. But if you choose it, you should
be aware of its consequences as well. Let’s now see the downsides of choosing Python over
another language.

1. Speed Limitations

We have seen that Python code is executed line by line. But since Python is interpreted, it often
results in slow execution. This, however, isn’t a problem unless speed is a focal point for the
project. In other words, unless high speed is a requirement, the benefits offered by Python are
enough to distract us from its speed limitations.

2. Weak in Mobile Computing and Browsers

While it serves as an excellent server-side language, Python is much rarely seen on the client-
side. Besides that, it is rarely ever used to implement smartphone-based applications. One such
application is called Carbonnelle.
The reason it is not so famous despite the existence of Brython is that it isn’t that secure.

3. Design Restrictions

As you know, Python is dynamically-typed. This means that you don’t need to declare the type
of variable while writing the code. It uses duck-typing. But wait, what’s that? Well, it just means
that if it looks like a duck, it must be a duck. While this is easy on the programmers during
coding, it can raise run-time errors.

4. Underdeveloped Database Access Layers

Compared to more widely used technologies like JDBC (Java DataBase Connectivity) and
ODBC (Open DataBase Connectivity), Python’s database access layers are a bit underdeveloped.
Consequently, it is less often applied in huge enterprises.

5. Simple

No, we’re not kidding. Python’s simplicity can indeed be a problem. Take my example. I don’t
do Java, I’m more of a Python person. To me, its syntax is so simple that the verbosity of Java
code seems unnecessary.

This was all about the Advantages and Disadvantages of Python Programming Language.

History of Python

What do the alphabet and the programming language Python have in common? Right, both start
with ABC. If we are talking about ABC in the Python context, it's clear that the programming
language ABC is meant. ABC is a general-purpose programming language and programming
environment, which had been developed in the Netherlands, Amsterdam, at the CWI (Centrum
Wiskunde &Informatica). The greatest achievement of ABC was to influence the design of
Python. Python was conceptualized in the late 1980s. Guido van Rossum worked that time in a
project at the CWI, called Amoeba, a distributed operating system. In an interview with Bill
Venners1, Guido van Rossum said: "In the early 1980s, I worked as an implementer on a team
building a language called ABC at Centrum voor Wiskunde en Informatica (CWI). I don't know
how well people know ABC's influence on Python. I try to mention ABC's influence because I'm
indebted to everything I learned during that project and to the people who worked on it. "Later
on in the same Interview, Guido van Rossum continued: "I remembered all my experience and
some of my frustration with ABC. I decided to try to design a simple scripting language that
possessed some of ABC's better properties, but without its problems. So I started typing. I
created a simple virtual machine, a simple parser, and a simple runtime. I made my own version
of the various ABC parts that I liked. I created a basic syntax, used indentation for statement
grouping instead of curly braces or begin-end blocks, and developed a small number of powerful
data types: a hash table (or dictionary, as we call it), a list, strings, and numbers."

Python Development Steps

Guido Van Rossum published the first version of Python code (version 0.9.0) at [Link] in
February 1991. This release included already exception handling, functions, and the core data
types of list, dict, str and others. It was also object oriented and had a module system.

Python version 1.0 was released in January 1994. The major new features included in this release
were the functional programming tools lambda, map, filter and reduce, which Guido Van
Rossum never liked. Six and a half years later in October 2000, Python 2.0 was introduced. This
release included list comprehensions, a full garbage collector and it was supporting unicode.
Python flourished for another 8 years in the versions 2.x before the next major release as Python
3.0 (also known as "Python 3000" and "Py3K") was released. Python 3 is not backwards
compatible with Python 2.x. The emphasis in Python 3 had been on the removal of duplicate
programming constructs and modules, thus fulfilling or coming close to fulfilling the 13th law of
the Zen of Python: "There should be one -- and preferably only one -- obvious way to do
it."Some changes in Python 7.3:

Print is now a function.

 Views and iterators instead of lists

 The rules for ordering comparisons have been simplified. E.g., a heterogeneous list
cannot be sorted, because all the elements of a list must be comparable to each other.
 There is only one integer type left, i.e., int. long is int as well.
  The division of two integers returns a float instead of an integer. "//" can be used to have
the "old" behaviour.
 Text Vs. Data Instead of Unicode Vs. 8-bit
Purpose

We demonstrated that our approach enables successful segmentation of intra-retinal layers—

even with low-quality images containing speckle noise, low contrast, and different intensity
ranges throughout—with the assistance of the ANIS feature.

Python

Python is an interpreted high-level programming language for general-purpose programming.

Created by Guido van Rossum and first released in 1991, Python has a design philosophy that
emphasizes code readability, notably using significant whitespace.

Python features a dynamic type system and automatic memory management. It supports multiple
programming paradigms, including object-oriented, imperative, functional and procedural, and
has a large and comprehensive standard library.

 Python is Interpreted − Python is processed at runtime by the interpreter. You do not need
to compile your program before executing it. This is similar to PERL and PHP.
 Python is Interactive − you can actually sit at a Python prompt and interact with the
interpreter directly to write your programs.
Python also acknowledges that speed of development is important. Readable and terse code is
part of this, and so is access to powerful constructs that avoid tedious repetition of code.
Maintainability also ties into this may be an all but useless metric, but it does say something
about how much code you have to scan, read and/or understand to troubleshoot problems or
tweak behaviors. This speed of development, the ease with which a programmer of other
languages can pick up basic Python skills and the huge standard library is key to another area
where Python excels. All its tools have been quick to implement, saved a lot of time, and several
of them have later been patched and updated by people with no Python background - without
breaking.

Modules Used in Project

NumPy

NumPy is a general-purpose array-processing package. It provides a high-performance

multidimensional array object, and tools for working with these arrays.

It is the fundamental package for scientific computing with Python. It contains various features
including these important ones:

 A powerful N-dimensional array object

 Sophisticated (broadcasting) functions
 Tools for integrating C/C++ and Fortran code
 Useful linear algebra, Fourier transform, and random number capabilities
Besides its obvious scientific uses, NumPy can also be used as an efficient multi-dimensional
container of generic data. Arbitrary datatypes can be defined using NumPy which allows NumPy
to seamlessly and speedily integrate with a wide variety of databases.

Pandas

Pandas is an open-source Python Library providing high-performance data manipulation and

analysis tool using its powerful data structures. Python was majorly used for data munging and
preparation. It had very little contribution towards data analysis. Pandas solved this problem.
Using Pandas, we can accomplish five typical steps in the processing and analysis of data,
regardless of the origin of data load, prepare, manipulate, model, and analyze. 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 2D plotting library which produces publication quality figures in a variety
of hardcopy formats and interactive environments across platforms. Matplotlib can be used in
Python scripts, the Python and IPython shells, the Jupyter Notebook, web application servers,
and four graphical user interface toolkits. Matplotlib tries to make easy things easy and hard
things possible. You can generate plots, histograms, power spectra, bar charts, error charts,
scatter plots, etc., with just a few lines of code. For examples, see the sample plots and thumbnail
gallery.
For simple plotting the pyplot module provides a MATLAB-like interface, particularly when
combined with IPython. For the power user, you have full control of line styles, font properties,
axes properties, etc, via an object oriented interface or via a set of functions familiar to
MATLAB users.

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. Python

Python is an interpreted high-level programming language for general-purpose programming.

Created by Guido van Rossum and first released in 1991, Python has a design philosophy that
emphasizes code readability, notably using significant whitespace.

Python features a dynamic type system and automatic memory management. It supports multiple
programming paradigms, including object-oriented, imperative, functional and procedural, and
has a large and comprehensive standard library.

 Python is Interpreted − Python is processed at runtime by the interpreter. You do not need
to compile your program before executing it. This is similar to PERL and PHP.
 Python is Interactive − you can actually sit at a Python prompt and interact with the
interpreter directly to write your programs.
Python also acknowledges that speed of development is important. Readable and terse code is
part of this, and so is access to powerful constructs that avoid tedious repetition of code.
Maintainability also ties into this may be an all but useless metric, but it does say something
about how much code you have to scan, read and/or understand to troubleshoot problems or
tweak behaviors. This speed of development, the ease with which a programmer of other
languages can pick up basic Python skills and the huge standard library is key to another area
where Python excels. All its tools have been quick to implement, saved a lot of time, and several
of them have later been patched and updated by people with no Python background - without
breaking.

Install Python Step-by-Step in Windows and Mac

Python a versatile programming language doesn’t come pre-installed on your computer devices.
Python was first released in the year 1991 and until today it is a very popular high-level
programming language. Its style philosophy emphasizes code readability with its notable use of
great whitespace.

The object-oriented approach and language construct provided by Python enables programmers
to write both clear and logical code for projects. This software does not come pre-packaged with
Windows.

How to Install Python on Windows and Mac

There have been several updates in the Python version over the years. The question is how to
install Python? It might be confusing for the beginner who is willing to start learning Python but
this tutorial will solve your query. The latest or the newest version of Python is version 3.7.4 or
in other words, it is Python 3.

Note: The python version 3.7.4 cannot be used on Windows XP or earlier devices.

Before you start with the installation process of Python. First, you need to know about your
System Requirements. Based on your system type i.e. operating system and based processor, you
must download the python version. My system type is a Windows 64-bit operating system. So
the steps below are to install python version 3.7.4 on Windows 7 device or to install Python 3.
Download the Python Cheatsheet [Link] steps on how to install Python on Windows 10, 8 and
7 are divided into 4 parts to help understand better.

Download the Correct version into the system

Step 1: Go to the official site to download and install python using Google Chrome or any other
web browser. OR Click on the following link: [Link]
Now, check for the latest and the correct version for your operating system.

Step 2: Click on the Download Tab.

Step 3: You can either select the Download Python for windows 3.7.4 button in Yellow Color or
you can scroll further down and click on download with respective to their version. Here, we are
downloading the most recent python version for windows 3.7.4
Step 4: Scroll down the page until you find the Files option.

Step 5: Here you see a different version of python along with the operating system.

 To download Windows 32-bit python, you can select any one from the three options:
Windows x86 embeddable zip file, Windows x86 executable installer or Windows x86
web-based installer.
 To download Windows 64-bit python, you can select any one from the three options:
Windows x86-64 embeddable zip file, Windows x86-64 executable installer or Windows
x86-64 web-based installer.
Here we will install Windows x86-64 web-based installer. Here your first part regarding which
version of python is to be downloaded is completed. Now we move ahead with the second part in
installing python i.e. Installation
Note: To know the changes or updates that are made in the version you can click on the Release
Note Option.

Installation of Python

Step 1: Go to Download and Open the downloaded python version to carry out the installation
process.

Step 2: Before you click on Install Now, Make sure to put a tick on Add Python 3.7 to PATH.

Step 3: Click on Install NOW After the installation is successful. Click on Close.
With these above three steps on python installation, you have successfully and correctly installed
Python. Now is the time to verify the installation.

Note: The installation process might take a couple of minutes.

Verify the Python Installation

Step 1: Click on Start

Step 2: In the Windows Run Command, type “cmd”.

Step 3: Open the Command prompt option.

Step 4: Let us test whether the python is correctly installed. Type python –V and press Enter.

Step 5: You will get the answer as 3.7.4

Note: If you have any of the earlier versions of Python already installed. You must first uninstall
the earlier version and then install the new one.

Check how the Python IDLE works

Step 1: Click on Start

Step 2: In the Windows Run command, type “python idle”.

Step 3: Click on IDLE (Python 3.7 64-bit) and launch the program

Step 4: To go ahead with working in IDLE you must first save the file. Click on File > Click on
Save
Step 5: Name the file and save as type should be Python files. Click on SAVE. Here I have
named the files as Hey World.

Step 6: Now for e.g. enter print (“Hey World”) and Press Enter.

You will see that the command given is launched. With this, we end our tutorial on how to install
Python. You have learned how to download python for windows into your respective operating
system.

Note: Unlike Java, Python does not need semicolons at the end of the statements otherwise it
won’t work.
 CHAPTER 7

SYSTEM REQUIREMENTS

SOFTWARE REQUIREMENTS

The functional requirements or the overall description documents include the product perspective
and features, operating system and operating environment, graphics requirements, design
constraints and user documentation.

The appropriation of requirements and implementation constraints gives the general overview of
the project in regard to what the areas of strength and deficit are and how to tackle them.

 Python IDLE 3.7 version (or)

 Anaconda 3.7 (or)
 Jupiter (or)
 Google colab
HARDWARE REQUIREMENTS

Minimum hardware requirements are very dependent on the particular software being developed
by a given Enthought Python / Canopy / VS Code user. Applications that need to store large
arrays/objects in memory will require more RAM, whereas applications that need to perform
numerous calculations or tasks more quickly will require a faster processor.

 Operating system : Windows, Linux

 Processor : minimum intel i3
 Ram : minimum 4 GB
 Hard disk : minimum 250GB
 CHAPTER 8

FUNCTIONAL REQUIREMENTS

OUTPUT DESIGN

Outputs from computer systems are required primarily to communicate the results of processing
to users. They are also used to provides a permanent copy of the results for later consultation.
The various types of outputs in general are:

 External Outputs, whose destination is outside the organization

 Internal Outputs whose destination is within organization and they are the
 User’s main interface with the computer.
 Operational outputs whose use is purely within the computer department.
 Interface outputs, which involve the user in communicating directly.
OUTPUT DEFINITION

The outputs should be defined in terms of the following points:

 Type of the output

 Content of the output
 Format of the output
 Location of the output
 Frequency of the output
 Volume of the output
 Sequence of the output
It is not always desirable to print or display data as it is held on a computer. It should be decided
as which form of the output is the most suitable.

INPUT DESIGN

Input design is a part of overall system design. The main objective during the input design is as
given below:
  To produce a cost-effective method of input.
 To achieve the highest possible level of accuracy.
 To ensure that the input is acceptable and understood by the user.
INPUT STAGES

The main input stages can be listed as below:

 Data recording
 Data transcription
 Data conversion
 Data verification
 Data control
 Data transmission
 Data validation
 Data correction
INPUT TYPES

It is necessary to determine the various types of inputs. Inputs can be categorized as follows:

 External inputs, which are prime inputs for the system.

 Internal inputs, which are user communications with the system.
 Operational, which are computer department’s communications to the system?
 Interactive, which are inputs entered during a dialogue.
INPUT MEDIA

At this stage choice has to be made about the input media. To conclude about the input media
consideration has to be given to;

 Type of input
 Flexibility of format
 Speed
 Accuracy
 Verification methods
 Rejection rates
  Ease of correction
 Storage and handling requirements
 Security
 Easy to use
 Portability
Keeping in view the above description of the input types and input media, it can be said that
most of the inputs are of the form of internal and interactive. As

Input data is to be the directly keyed in by the user, the keyboard can be considered to be the
most suitable input device.

ERROR AVOIDANCE

At this stage care is to be taken to ensure that input data remains accurate form the stage at which
it is recorded up to the stage in which the data is accepted by the system. This can be achieved
only by means of careful control each time the data is handled.

ERROR DETECTION

Even though every effort is make to avoid the occurrence of errors, still a small proportion of
errors is always likely to occur, these types of errors can be discovered by using validations to
check the input data.

DATA VALIDATION

Procedures are designed to detect errors in data at a lower level of detail. Data validations have
been included in the system in almost every area where there is a possibility for the user to
commit errors. The system will not accept invalid data. Whenever an invalid data is keyed in,
the system immediately prompts the user and the user has to again key in the data and the system
will accept the data only if the data is correct. Validations have been included where necessary.

The system is designed to be a user friendly one. In other words the system has been designed to
communicate effectively with the user. The system has been designed with popup menus.

USER INTERFACE DESIGN

It is essential to consult the system users and discuss their needs while designing the user
interface:

USER INTERFACE SYSTEMS CAN BE BROADLY CLASIFIED AS:

 User initiated interface the user is in charge, controlling the progress of the user/computer
dialogue. In the computer-initiated interface, the computer selects the next stage in the
interaction.
 Computer initiated interfaces
In the computer-initiated interfaces the computer guides the progress of the user/computer
dialogue. Information is displayed and the user response of the computer takes action or displays
further information.

USER INITIATED INTERGFACES

User initiated interfaces fall into two approximate classes:

 Command driven interfaces: In this type of interface the user inputs commands or queries
which are interpreted by the computer.
 Forms oriented interface: The user calls up an image of the form to his/her screen and
fills in the form. The forms-oriented interface is chosen because it is the best choice.
COMPUTER-INITIATED INTERFACES

The following computer – initiated interfaces were used:

 The menu system for the user is presented with a list of alternatives and the user chooses
one; of alternatives.
 Questions – answer type dialog system where the computer asks question and takes
action based on the basis of the users reply.
Right from the start the system is going to be menu driven, the opening menu displays the
available options. Choosing one option gives another popup menu with more options. In this
way every option leads the users to data entry form where the user can key in the data.

ERROR MESSAGE DESIGN

The design of error messages is an important part of the user interface design. As user is bound
to commit some errors or other while designing a system the system should be designed to be
helpful by providing the user with information regarding the error he/she has committed.

This application must be able to produce output at different modules for different inputs.

PERFORMANCE REQUIREMENTS

Performance is measured in terms of the output provided by the application. Requirement

specification plays an important part in the analysis of a system. Only when the requirement
specifications are properly given, it is possible to design a system, which will fit into required
environment. It rests largely in the part of the users of the existing system to give the
requirement specifications because they are the people who finally use the system. This is
because the requirements have to be known during the initial stages so that the system can be
designed according to those requirements. It is very difficult to change the system once it has
been designed and on the other hand designing a system, which does not cater to the
requirements of the user, is of no use.

The requirement specification for any system can be broadly stated as given below:

 The system should be able to interface with the existing system

 The system should be accurate
 The system should be better than the existing system
 The existing system is completely dependent on the user to perform all the duties.
 CHAPTER 9

SOURCE CODE

import numpy as np

import pandas as pd

import joblib

# Visualization

import [Link] as plt

import seaborn as sns

%matplotlib inline

from [Link] import LabelEncoder

#Scaling

from [Link] import StandardScaler

#Train Test Split

from sklearn.model_selection import train_test_split

# Models
from [Link] import KNeighborsClassifier

from sklearn.linear_model import LogisticRegression

from [Link] import RandomForestClassifier

from [Link] import DecisionTreeClassifier

from [Link] import SVC

#Evaluation

from [Link] import classification_report

from [Link] import confusion_matrix

import os

import numpy as np

import pandas as pd

import [Link] as plt

from [Link] import LabelEncoder

import seaborn as sns

from [Link] import resample

import warnings

[Link]("ignore")

from [Link] import resample

from sklearn.model_selection import train_test_split

import os

import joblib

from [Link] import DecisionTreeClassifier

from [Link] import

accuracy_score,confusion_matrix,classification_report,precision_score,recall_score,f1_score

#pip install openpyxl

df=pd.read_csv(r'[Link]')

[Link]()

df = resample(df, replace=True, n_samples=10000, random_state=42)

df['total']=(df['math score']+df['reading score'] + df['writing score'])/3

df['total']

[Link]()

df=[Link](columns=['math score','reading score','writing score'])

df

[Link]().sum()

[Link]()

# Initialize the LabelEncoder

le= LabelEncoder()
# Loop through each column in the DataFrame

for column in [Link]:

if df[column].dtype == 'object':

df[column] = le.fit_transform(df[column])

[Link]()

[Link]()

[Link]().sum()

## Regresssion converting to Classification Problems

df = [Link](df)

# Define the discretization bins and labels

bins = [0, 34, 49, 74, 89, 100]

labels = ['E', 'D', 'C', 'B', 'A']

df['grade_category'] = [Link](df['total'], bins=bins, labels=labels)

[Link]()

## Converting Output Variable also

[Link]()
# Initialize the LabelEncoder

le= LabelEncoder()

df1=le.fit_transform(df['grade_category'])

df1=[Link](df1)

[Link]()

[Link]()

# he

## drop output column

[Link](['grade_category','total'],axis=1)

## Add new column

df['grade_category']=df1

## Our Transformed Final Data

[Link]()

df=[Link]('total',axis=1)

df=[Link](df)

[Link]()

[Link]().sum()

#X_test=X_test.drop('total',axis=1)
# Create a count plot for the 'Caudal_impulses' column

[Link](figsize=(10, 6))

ax = [Link](data=df, x='grade_category')

[Link]('grade_category')

[Link]('Count')

[Link]('Count of Class Values')

for p in [Link]:

[Link](f'{p.get_height()}', (p.get_x() + p.get_width() / 2., p.get_height()),

ha='center', va='center', fontsize=10, color='black', xytext=(0, 5),

textcoords='offset points')

[Link]()

X = [Link](columns=['grade_category'])

y=df['grade_category']

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

labels=['E','D','C','B','A']

#defining global variables to store accuracy and other metrics

precision = []

recall = []

fscore = []
accuracy = []

#function to calculate various metrics such as accuracy, precision etc

def calculateMetrics(algorithm, testY,predict):

p = precision_score(testY, predict,average='macro') * 100

r = recall_score(testY, predict,average='macro') * 100

f = f1_score(testY, predict,average='macro') * 100

a = accuracy_score(testY,predict)*100

[Link](a)

[Link](p)

[Link](r)

[Link](f)

print(algorithm+' Accuracy : '+str(a))

print(algorithm+' Precision : '+str(p))

print(algorithm+' Recall : '+str(r))

print(algorithm+' FSCORE : '+str(f))

report=classification_report(predict, testY,target_names=labels)

print('\n',algorithm+" classification report\n",report)

conf_matrix = confusion_matrix(testY, predict)

 [Link](figsize =(5, 5))

ax = [Link](conf_matrix, xticklabels = labels, yticklabels = labels, annot = True,

cmap="Blues" ,fmt ="g");

ax.set_ylim([0,len(labels)])

[Link](algorithm+" Confusion matrix")

[Link]('True class')

[Link]('Predicted class')

[Link]()

[Link]()

## Model

from catboost import CatBoostClassifier

import joblib

import os

if [Link]('model/[Link]'):

# Load the trained model from the file

CBC = [Link]('model/[Link]')

print("CatBoost model loaded successfully.")

predict = [Link](X_test)
 calculateMetrics("CatBoostClassifier", predict, y_test)

else:

# Train the model

CBC = CatBoostClassifier(max_depth=14, n_estimators=100, learning_rate=0.01, verbose=0)

[Link](X_train, y_train)

# Save the trained model to a file

[Link](CBC, 'model/[Link]')

print("CatBoost model saved successfully.")

predict = [Link](X_test)

calculateMetrics("CatBoostClassifier", predict, y_test)

from xgboost import XGBClassifier

import joblib

import os

if [Link]('model/[Link]'):

# Load the trained model from the file

XGB = [Link]('model/[Link]')

print("XGBoost model loaded successfully.")

 predict = [Link](X_test)

calculateMetrics("XGBoostClassifier", predict, y_test)

else:

# Train the model

XGB = XGBClassifier(max_depth=32, n_estimators=200, learning_rate=0.01)

[Link](X_train, y_train)

# Save the trained model to a file

[Link](XGB, 'model/[Link]')

print("XGBoost model saved successfully.")

predict = [Link](X_test)

calculateMetrics("XGBoostClassifier", predict, y_test)

 CHAPTER 10

10.1 Implementation and Description

Implementation Overview

In this chapter, we present the implementation and results of applying machine learning
algorithms to predict student grades. The primary focus is on evaluating the performance of two
algorithms: CatBoost and XGBoost. The implementation process involved several stages, from
data preprocessing to model training and evaluation. We used Python and its associated libraries
for this task, leveraging pandas for data manipulation, scikit-learn for model training and
evaluation, and joblib for model persistence.

Data Preprocessing

Before training the models, the dataset underwent a comprehensive preprocessing phase. We
began by handling missing values to ensure data integrity. Categorical variables were
transformed using Label Encoding to convert them into a numerical format suitable for machine
learning models. Continuous features, such as student scores, were normalized to ensure that all
features contributed equally to the model's training process. Additionally, we discretized the
continuous scores into categorical grades (A, B, C, D, E) to simplify the prediction task into a
classification problem. The dataset was then split into training and testing subsets to evaluate
model performance effectively.

Model Training and Evaluation

We implemented and trained two machine learning models: CatBoost and XGBoost. CatBoost, a
gradient boosting algorithm designed for categorical feature handling, was initially used. We
took advantage of CatBoost's ordered boosting technique, which helps in reducing overfitting
and improving generalization. The model was trained on the preprocessed training data, and its
performance was evaluated on the test set. The evaluation metrics included accuracy, precision,
recall, and F1 score, along with a confusion matrix to visualize classification performance.

Following CatBoost, we introduced XGBoost, another powerful gradient boosting algorithm

known for its scalability and high performance. XGBoost's features, such as regularization and
column subsampling, were leveraged to enhance the model's effectiveness. Similar to CatBoost,
XGBoost was trained on the same dataset, and its performance was assessed using the same
metrics. The comparative analysis of these models provided insights into their strengths and
weaknesses.

10.2 Dataset Description

Dataset Description:

 gender: The gender of the student (either 'female' or 'male').

 race/ethnicity: The racial/ethnic group the student belongs to (represented as groups A,

B, C, D, etc.).

 parental level of education: The highest education level achieved by the student's
parent(s) (e.g., 'bachelor's degree', 'some college', 'associate's degree', etc.).

 lunch: The type of lunch the student receives (either 'standard' or 'free/reduced').

 test preparation course: Whether the student completed a test preparation course (either
'completed' or 'none').

 math score: The student's score in math (ranging from 0 to 100).

 reading score: The student's score in reading (ranging from 0 to 100).

 writing score: The student's score in writing (ranging from 0 to 100).

 total: This is a new column created by taking the average of the math score, reading
score, and writing score. It represents the overall performance of the student across the
three subjects.
10.3 Result and Description

Figure 10.1 Classification report of Catboost Classifier

The CatBoostClassifier model has an accuracy of 61.4%, meaning it correctly classifies about
61.4% of the instances overall. However, the precision is low at 27.2%, indicating that many of
the predicted positive instances are actually incorrect. The recall, at 58.1%, shows that the model
is identifying just over half of the actual positive cases, but it's missing a significant portion. The
F1-Score of 27.09% reflects the poor balance between precision and recall, suggesting that while
the model is decent at catching positives, it struggles with making accurate positive predictions
and requires improvement, possibly through hyperparameter tuning or addressing class
imbalance.
 Figure 10.2: Confusion Matrix of CatboostClassifer

Figure 10.2 shows that the image depicts a confusion matrix for a CatBoostClassifier. A
confusion matrix is a visualization tool used in machine learning to evaluate the performance of
classification models. It helps understand how well a model predicts the correct class for each
data point.
 Figure 10.3: Confusion Matrix of Xgboost Classifier

Figure 10.3 shows the A confusion matrix is a visualization tool that evaluates the
performance of a classification model. It shows how well the model correctly predicted the
true classes of data points. By analyzing the diagonal elements (correctly classified) and off-
diagonal elements (misclassified), you can assess the model's accuracy, precision, recall, and F1-
score for each class. This information helps identify strengths, weaknesses, and areas for
improvement in the model's performance.
 Figure 10.4: Classification report of XGboost Classifier

Figure 10.4 shows the XGBoost model achieved an accuracy of 63.6%, meaning it correctly
classified 63.6% of instances., the precision is relatively low at 34.69%, indicating a high
number of false positives (incorrect predictions of the positive class). The recall is 48.65%,
showing the model correctly identifies less than half of the actual positive cases. The F1-score,
which balances precision and recall, is 36.87%, suggesting that the model struggles to strike a
good balance between the two. Overall, while the accuracy is moderate, the low precision and
F1-score indicate the need for model improvement, possibly through tuning or feature
engineering.
 CHAPTER 11

CONCLUSION AND FUTURE SCOPE

Conclusion

The integration of machine learning into educational systems represents a significant

advancement in the way student performance is assessed and predicted. Traditional methods,
while foundational, have several inherent limitations, such as subjectivity, bias, and a lack of
adaptability to real-time data. These methods often rely on human judgment and standardized
testing, which can lead to inconsistent and sometimes inaccurate predictions of student grades.
By contrast, machine learning offers a more objective, data-driven approach that can analyze
vast amounts of diverse data, uncover hidden patterns, and provide more accurate and timely
predictions.

The application of machine learning to predict student grades is not just about replacing
traditional methods but enhancing them by incorporating insights that human assessors might
overlook. For instance, machine learning models can analyze behavioral data, demographic
information, and academic history simultaneously, offering a holistic view of a student’s
potential. This comprehensive assessment allows educators to identify at-risk students earlier and
intervene with personalized learning strategies, ultimately leading to better academic outcomes.

Furthermore, the use of advanced algorithms like neural networks and ensemble methods enables
the system to continuously learn and improve over time. As more data is fed into the system, its
predictive accuracy increases, making it a valuable tool for educators and administrators. This
continuous learning process helps in adapting to the ever-changing educational landscape,
ensuring that the predictions remain relevant and accurate.

In conclusion, machine learning-based grade prediction systems offer a promising solution to the
challenges faced by traditional methods. They provide a more accurate, objective, and
comprehensive assessment of student performance, which can lead to more effective educational
strategies and improved student outcomes. As educational institutions continue to adopt these
technologies, the potential for personalized learning, early intervention, and overall academic
success will only grow, paving the way for a more efficient and equitable education system.

Future Scope

The future of machine learning in education is filled with possibilities, as the technology
continues to evolve and become more sophisticated. One of the most promising areas for future
development is the personalization of learning experiences. Machine learning algorithms can be
used to create highly personalized learning paths for students based on their strengths,
weaknesses, learning styles, and interests. This could involve tailoring course content,
assignments, and even assessments to meet the unique needs of each student, thereby
maximizing their potential for success.

Another potential future development is the integration of machine learning with other emerging
technologies, such as artificial intelligence (AI), big data, and the Internet of Things (IoT). For
example, IoT devices in classrooms could collect real-time data on student engagement,
participation, and even emotional states. Machine learning algorithms could then analyze this
data to provide immediate feedback to teachers and students, helping to create a more responsive
and adaptive learning environment.

Moreover, machine learning can play a crucial role in addressing educational inequalities. By
analyzing data related to socioeconomic factors, access to resources, and educational
opportunities, machine learning models can identify students who are at risk of falling behind
due to systemic inequalities. Educators and policymakers can then use these insights to design
targeted interventions and allocate resources more effectively, ensuring that all students have an
equal opportunity to succeed.

In terms of institutional benefits, machine learning can be used to optimize administrative

processes, such as admissions, resource allocation, and curriculum development. Predictive
analytics could help institutions forecast enrollment trends, allocate resources more efficiently,
and design curricula that better align with future job market demands. This could lead to more
effective and sustainable educational institutions that are better equipped to meet the needs of
both students and society.
Lastly, the ethical implications of using machine learning in education should not be overlooked.
As the technology becomes more integrated into educational systems, it will be crucial to address
issues related to data privacy, bias in algorithms, and the potential for misuse. Future
developments should prioritize transparency, fairness, and accountability to ensure that machine
learning is used in ways that truly benefit students and society as a whole.
 REFERENCES

[1] S. Jayaprakash, S. Krishnan, and V. Jaiganesh. "Predicting Students' Academic Performance

Using an Improved Random Forest Classifier." In *2020 International Conference on Emerging
Smart Computing and Informatics (ESCI)*, Pune, India, pp. 238–243, March 2020.

[2] E.S. Bhutto, I.F. Siddiqui, Q.A. Arain, and M. Anwar. "Predicting Students’ Academic
Performance Through Supervised Machine Learning." In *2020 International Conference on
Information Science and Communication Technology (ICISCT)*, Karachi, Pakistan, pp. 1–6,
February 2020.

[3] J. Jacob, K. Jha, P. Kotak, and S. Puthran. "Educational Data Mining Techniques and Their
Applications." In *2015 International Conference on Green Computing and Internet of Things
(ICGCIoT)*, pp. 1344–1348, October 2015.

[4] K. Al Mayahi and M. Al-Bahri. "Machine Learning Based Predicting Student Academic
Success." In *2020 12th International Congress on Ultra Modern Telecommunications and
Control Systems and Workshops (ICUMT)*, Brno, Czech Republic, pp. 264–268, October 2020.

[5] Y. Olaperi, L. Fernandez-Sanz, J. Medina, and S. Misra. "Framework for Academic Advice
Through Mobile Applications." *2016*.

[6] "Statement from Secretary DeVos on 2019 NAEP Results," U.S. Department of Education.
*Accessed 24 Feb 2021*.

[7] M.R. Rimadana, S.S. Kusumawardani, P.I. Santosa, and M.S.F. Erwianda. "Predicting
Student Academic Performance Using Machine Learning and Time Management Skill Data." In
*2019 International Seminar on Research of Information Technology and Intelligent Systems
(ISRITI)*, Yogyakarta, Indonesia, pp. 511–515, December 2019.

[8] M.A.H. bin Mohd Nasir, M.H. bin Asmuni, N. Salleh, and S. Misra. "A Review of Student
Attendance System Using Near-Field Communication (NFC) Technology." In *Gervasi, O., et
al. (eds.) ICCSA 2015. LNCS*, vol. 9158, pp. 738–749. Springer, Cham, 2015.
[9] X. Xu, J. Wang, H. Peng, and R. Wu. "Prediction of Academic Performance Associated with
Internet Usage Behaviors Using Machine Learning Algorithms." *Computers in Human
Behavior*, vol. 98, pp. 166–173, 2019.

[10] H.M.R. Hasan, A.S.A. Rabby, M.T. Islam, and S.A. Hossain. "Machine Learning Algorithm
for Student’s Performance Prediction." In *2019 10th International Conference on Computing,
Communication and Networking Technologies (ICCCNT)*, Kanpur, India, pp. 1–7, July 2019.

[11] "Scikit-learn: Machine Learning in Python—scikit-learn 0.24.2 Documentation." *Accessed

04 May 2021*.

[12] "TensorFlow." *Accessed 04 May 2021*.

[13] "UCI Machine Learning Repository." *Accessed 28 Feb 2021*.

[14] M.S. Nurafifah, S. Abdul-Rahman, S. Mutalib, N.H.A. Hamid, and A.M.A. Malik. "Review
on Predicting Students’ Graduation Time Using Machine Learning Algorithms." *International
Journal of Modern Education and Computer Science*, vol. 11, no. 7, pp. 1, 2019.