BHARTI PUBLIC SCHOOL
MAYUR VIHAR PHASE – 3
Practical File
CBSE 2025-2026 Examination
Artificial Intelligence (417)
Submitted by:
H. ARNESHWAR
Class – 10th C
Roll no. 17
Submitted to: -
Mr. Yuvraj Sharma
CERTIFICATE
This is to certify that ______________of class 10th C has
completed his/her practical file of the subject
Computer Science under the guidance of Computer
Science teacher Mr. Yuvraj Sharma during the year
2025-2026. This project is submitted as part of the
partial fulfillment of the syllabus prescribed by the
CBSE Board.
The work done by the student is original and has been
carried out with sincerity and dedication.
Internal Examiner External Examiner
Principal Signature
ACKNOWLEDGEMENT
Firstly, I express my heartfelt gratitude to the Almighty, without whom
all this would never have been possible.
Secondly, I would like to express my special thanks and gratitude to our
principle ma’am Dr. S. Sabharwal and Thirdly, Computer Science
teacher Mr. Yuvraj Sharma for guiding me immensely through the
course of my practical file who gave us the opportunity and fruitful
guidance to do this practical file.
As per CBSE curriculum , by doing this practical we got enriched with
a lot of information which can help us in our future. His constructive
advice and constant motivation have been responsible for the successful
completion of my practical file.
My sincere thanks to my parents for their motivation and support.
INDEX
S.N. Objective Date of Teacher’s Sign
Performance
1. AI - CHATBOT 16 MAY 2025
2.
WAP TO INPUT 5 ELEMENTS EACH IN TWO LISTS.
ADD THE ELEMENTS OF BOTH THE LISTS AND 23 MAY 2025
DISPLAY THE NEW LIST WITH ITS LENGTH.
3.
ORANGE DATA MINING PROJECT
i) Using the Palmer Penguins dataset, develop an AI
model that applies statistical and machine learning
techniques to predict the species of a penguin based
on features such as bill length, bill depth, flipper
length, and body mass. Explain the methodology,
30MAY 2025
preprocessing steps, model selection, and
evaluation metrics used to measure the model’s
performance.
ii) Design a CV based AI model that can analyze
underwater images and detect early signs of coral
bleaching. Describe the dataset requirements,
preprocessing techniques, feature extraction models
and model evaluation strategy. Discuss how this
system can help in marine conservation effort. 11 JULY 2025
iii) Develop an AI based NLP model to perform
sentiment analysis, on customer reviews, social
media posts, or news articles. Explain the data
collection process, text pre-processing steps, feature
representation methods, model training, and
evaluation metrics. Also discuss possible 18 JULY 2025
applications of the system in business and society.
4. PYTHON PROJECTS
1. Create a chatbot that provides a 4 JULY 2025
motivational quote. The menu should have:
a) Morning Motivation
b) Study Motivation
c) Workout Motivation
d) Exit
Each option should print a different
motivational quote.
2. Write a program to input 5 elements each
in two lists. Add (concatenate) the elements
of both the lists and display the new list
with its length.
25 JULY 2025
3. Write a program to calculate mean,
median and mode using Numpy
1 AUGUST 2025
4. Write a program to display line charts 8 AUGUST 2025
from (2,5) to (9,10).
5. Write a program to display a scatter chart 22 AUGUST
for the following points (2,5),(9,10),(8,3), 2025
(5,7),(6,18)
6. Read the csv file saved in your system 29 AUGUST
and display 10 rows 2025
7. Read csv file saved in your system and 12 SEPTEMBER
display its information 2025
8. Write a program to read an image and 19 SEPTEMBER
display using Python . 2025
9. Write a program to read an image and 26 SEPTEMBER
identify its shape using Python. 2025
10. Write a program to input a string and 3 OCTOBER
display the count of vowels and consonants 2025
in the string.
11. Write a program to input three sides of a 17
triangle and display whether a triangle can OCTOBER2025
be formed with the inputs or not. If a
triangle can be formed then display whether
the triangle will be scalene, isosceles or
equilateral triangle
12. Write a program to input a number and
display whether it is palindrome or not
24 OCTOBER
2025
13. Write a program to input a number and 31 OCTOBER
display whether it is prime or not. 2025
14. Write a program to input two numbers
and swap both the numbers without using
the third number.
15. Using Numpy package: 7 NOVEMBER
2025
a) Create a 4X2 array with random integers.
b) Create a 3X3 array with all zeros.
ORANGE DATA MINING
PROJECT
QUESTION 2
Using Orange Data Mining tool, create the following
a) "Using the Palmer Penguins dataset, develop an AI model that applies statistical and machine learning
techniques to predict the species of a penguin based on features such as bill length, bill depth, flipper length, and
body mass. Explain the methodology, preprocessing steps, model selection, and evaluation metrics used to
measure the model’s performance."
Penguin Species Prediction using Machine Learning
Introduction
The Palmer Penguins dataset contains information about different species of
penguins, such as Adelie, Gentoo, and Chinstrap. The aim of this project is to build
a machine learning model that can predict the species of a penguin using features
like bill length, bill depth, flipper length, and body mass.
Methodology
We use supervised machine learning techniques to train the model. The dataset is
divided into training and testing sets. The model learns from the training data and
then predicts the species for new penguins.
Data Preprocessing
● Missing values are handled by removing or filling them.
● Categorical data (like island or sex) is converted into numeric form using
encoding.
● All numeric values are scaled or normalized so that they are in a similar
range.
Model Selection
We can use models like Logistic Regression, Decision Tree, or Random Forest to
classify penguin species. Among these, Decision Trees and Random Forests usually
give good accuracy for this kind of data.
Evaluation
The model is tested using metrics such as:
● Accuracy: Measures how many predictions were correct.
● Confusion Matrix: Shows the correctly and incorrectly predicted species.
● Precision, Recall, and F1 Score: Help understand how well the model performs for each
species.
Conclusion
This project shows how machine learning can be used to classify animals based on
measurable features. It helps in biological research and understanding species
diversity.
DATA ACQUISATION -
● Collect Training and Testing Data of Palmer Penguins with features like -
Length of Beaks, Colors of feather, Size etc.
● Data must be in a csv file.
Input the Training Data into a File Widget.
Input the Testing Data into a File Widget.
DATA EXPLORATION -
1. Add Feature Statistics widget. (Training data - Feature Statistics)
1.1 Double - click to open Feature statistics
[Link] Impute widget (allows you to choose strategy to fill missing values)
2.1 Double Click on Impute Widget-
Select - Remove instances with unknown values radio button and Apply.
[Link] the widgets. (The missing values are filled now)
3.1 Double click the Feature Statistics to check values.
4. Add Select Columns widget, open it, Drag the species feature to the target
box.
(Impute - Select columns)
5. Add Data Sampler - (Select Columns)
5.1 Double click on Data Sampler
Select “fixed proportion of data” and move the slider to 80%.
6. Add 2 Data info widgets.
(Data Sampler - Data info) (Data Sampler - Data info(1))
6.1 Double click on line connecting Data Sampler to data info - notice
that,
Data Sample — Data.
Double click on line connecting Data Sampler to data info(1) - change
to, Remaining Data — Data.
MODELLING -
Add Test and Score. (Data Sampler - Test and Score)
Add Tree Algorithm. (Test and Score - Tree Algorithm)
EVALUATION -
[Link] Data Sampler to Test and score again. It will add another
connection.
1.1 Double click on any line. Change the connection from Data Sample to
Data and from Remaining Data to Test Data.
2. Add Predictions to view the prediction by the model. (Test Data –
Predictions)
Important
2.1 Connect Data sampler to the Tree Algorithm.
2.2 Connect the Tree to Predictions.
OUTPUT
b) "Design a computer vision-based AI system that can analyze underwater images and detect early
signs of coral bleaching. Describe the dataset requirements, preprocessing techniques (such as image
augmentation and noise removal), feature extraction methods (e.g., CNNs), and the model evaluation
strategy. Discuss how this system can help in marine conservation efforts."
Coral Bleaching Detection using Computer Vision
Introduction
Coral reefs are important for marine life. Due to climate change, many corals are
turning white — a process known as coral bleaching. This project uses Artificial
Intelligence and Computer Vision to detect early signs of bleaching from
underwater images.
Dataset Requirements
We need a collection of underwater coral images labeled as “healthy” or
“bleached.” The dataset should include images taken under different lighting and
water conditions.
Preprocessing Techniques
● Image Enhancement : Resizing, Brightness Adjustment, Grayscale
Conversion
● Image Augmentation: Rotation, flipping, and brightness adjustments are
done to increase data variety.
● Normalization: Pixel values are scaled between 0 and 1 for consistency.
Feature Extraction
Convolutional Neural Networks (CNNs) automatically detect and learn patterns
such as color fading or texture changes.
Model Evaluation
Performance is checked using:
● Accuracy
● Precision and Recall
● F1-Score
● Confusion Matrix
Conclusion
This AI system can help marine scientists monitor coral health automatically. It
supports conservation by identifying bleaching early and protecting coral
ecosystems.
PROBLEM SCOPING - Coral Bleaching
● Occurs when corals lose their vibrant colors and turn white.
● The primary cause is CLIMATE CHANGE.
DATA ACQUISATION -
1. Collect pictures of Bleached and Unbleached images of Corals.
2. Name them “Bleached” and “Unbleached” accordingly.
DATA EXPLORATION -
Input training data:(Import images - Image viewer / Image Embedding)
Image Viewer -
Data table of training data set:(Image embedding - Data Table)
Data Table -
MODELLING -
Adding Algorithm Models:
1. Logistic Regression
2. SVM
3. Random Forest
Add Test and score to view prediction values
(Classification Accuracy, Recall, F1 score, Precision)
Test and score Evaluations-
Add Confusion matrix (to view Evaluation results)
SVM Evaluation -
Random Forest -
Logistic Regression -
Add Testing dataset -
Input testing data:(Import images(1) - Image viewer(1) / Image Embedding(1))
Add Predictions to see trained Model’s Prediction -
Important
Add another Logistic Regression algorithm.
(Image embedding - Logistic Regression - Prediction)
OUTPUT
c) "Develop an AI-based Natural Language Processing (NLP) model to perform sentiment analysis on
customer reviews, social media posts, or news articles. Explain the data collection process, text
preprocessing steps (tokenization, stopword removal, stemming/lemmatization), feature representation
methods (Bag of Words, TF-IDF, or word embeddings), model training, and evaluation metrics. Also
discuss possible applications of the system in business and society."
Sentiment Analysis using Natural Language Processing (NLP)
Introduction
Sentiment analysis is a Natural Language Processing (NLP) technique that helps
identify the emotion or opinion in a piece of text. The project aims to find whether
a text (like a review or social media post) expresses a positive, negative, or neutral
sentiment.
Data Collection
Text data is collected from websites, social media platforms, or online product
reviews. The data is labeled according to the sentiment it expresses.
Text Preprocessing
● Tokenization: Breaking text into smaller words or tokens.
● Stopword Removal: Removing common words like “the”, “is”, etc.
● Stemming/Lemmatization: Converting words to their base form (e.g.,
running → run).
● Lowercasing and Punctuation Removal: Cleaning the text for better
processing.
Feature Representation
Text is converted into numbers using:
● Bag of Words (BoW) or TF-IDF (Term Frequency–Inverse Document
Frequency).
● Word Embeddings like Word2Vec or BERT for deeper understanding of
word meanings.
Model Training
Models like Logistic Regression can be used to train and predict sentiment.
Evaluation
We use metrics like:
● Accuracy
● Precision, Recall, and F1 Score
● Confusion Matrix
Conclusion
Sentiment analysis is very useful for companies to understand customer feedback,
improve services, and monitor brand reputation. It also helps governments and
organizations study public opinion on important topics.
DATA ACQUISATION -
1. Get a movie review data set ( which includes negative, positive and neutral
comments)
1.1 Add a new file. Upload the dataset into the file.
1.2 Add Corpus widget and connect the file to it. (File – Corpus)
1.3 Add a Data Table and connect it to Corpus. (Corpus - Data Table)
1.4 Add a Corpus viewer. Connect it to the Corpus. (Corpus - Corpus viewer)
Double click on the Corpus viewer to see the comments.
DATA EXPLORATION -
1. Add Preprocess Text. Connect it to Corpus (Corpus – Preprocess Text)
MODELLING -
1. Add Sentiment Analysis. (Preprocess Text — Sentiment Analysis)
EVALUATION -
1. Add a Data Table and connect the output of sentiment analysis to it.
(Sentiment Analysis - Data Table)
2. Open the Data Table to view the output of Sentiment Analysis.
3. Add another Corpus viewer to see the based on selected feature.
OUTPUT
DATA TABLE’S RESULT IS THE OUTPUT.
PYTHON PROGRAMS
Output #1
1. Create a chatbot that provides a motivational quote. The menu should
have:
a) Morning Motivation
b) Study Motivation
c) Workout Motivation
d) Exit
Each option should print a different motivational quote.
Output #2
2. Write a program to input 5 elements each in two lists. Add
(concatenate) the elements of both the lists and display the new
list with its length.
OUTPUT #3
3. Write a program to calculate mean, median and
mode using Numpy
OUTPUT #4
4. Write a program to display line chart from (2,5) to
(9,10).
OUTPUT #5
5. Write a program to display a scatter chart for the
following points (2,5),(9,10),(8,3),(5,7),(6,18)
OUTPUT #6
6. Read the csv file saved in your system and
display 10 rows
OUTPUT #7
7. Read csv file saved in your system and display its
information.
OUTPUT #8
8. Write a program to read an image and display
using Python
OUTPUT #9
9. Write a program to read an image and identify its
shape using Python
OUTPUT #10
10. Write a program to input a string and display the
count of vowels and consonants in the string
OUTPUT #11
11. Write a program to input three sides of a
triangle and display whether a triangle can be
formed with the inputs or not. If a triangle can be formed
then display whether the triangle will be scalene,
isosceles or equilateral triangle.
OUTPUT #12
12. Write a program to input a number and display
whether it is palindrome or not
OUTPUT #13
13. Write a program to input a number and display whether
it is prime or not.
OUTPUT #14
14. Write a program to input two numbers and swap
both the numbers without using the third number
OUTPUT #15
15. Using Numpy package:
a) Create a 4X2 array with random integers.
b) Create 3X3 array with all zeros.