Python Data Project

Step-by-Step Beginner Guide

Student Performance Analysis & Score Prediction

6 Steps VS Code 3 Charts ML Model

Follow one by one Run on your computer Visualize your data Predict exam scores

What You Will Learn

✓ Create a CSV dataset and load it with pandas

✓ Check and fix missing values and duplicate rows

✓ Build 3 charts: scatter plot, bar chart, and heatmap

✓ Train a Linear Regression model to predict scores

✓ Upload your finished project to GitHub

Tools You Need

Tool Purpose How to Get

Python 3.x Programming language [Link]/downloads

VS Code Code editor [Link]

Python Extension Run Python in VS Code VS Code Extensions tab

pip packages pandas, matplotlib, etc. Run: pip install ... (Step 1)

GitHub account Upload & share your project [Link] (free)

Tip: Open VS Code, press Ctrl+` to open the Terminal. All commands run there.
 1 Setup — Create Project Folder & Install Libraries

Step 1a — Create your project folder

Open your Terminal in VS Code (Ctrl + `) and run these commands:

mkdir student-project
cd student-project
code .

Note: The last command code . opens VS Code inside your new folder.

Step 1b — Install required libraries

In the VS Code Terminal, run this one command:

pip install pandas matplotlib seaborn scikit-learn

Step 1c — Create the dataset file

In VS Code, create a new file called [Link] and paste this inside:

student_id,gender,study_hours,attendance,previous_score,final_score
1,Male,2,65,55,60
2,Female,4,80,70,78
3,Male,1,50,40,45
4,Female,5,90,85,88
5,Male,3,75,65,70
6,Female,6,95,90,92
7,Male,2,60,50,58
8,Female,4,85,72,80
9,Male,3,70,60,68
10,Female,5,88,82,86
11,Male,1,45,38,42
12,Female,6,96,91,94
13,Male,2,67,57,62
14,Female,4,82,74,79
15,Male,3,73,63,69

What each column means:

Column Meaning

student_id Unique ID number for each student

gender Male or Female

study_hours Hours studied per day

attendance Attendance percentage (0-100)

previous_score Score in the last exam

final_score Final exam score (we will predict this!)

Tip: Save every file with Ctrl+S before running it.

 2 Load & Inspect Your Data

Create a new file called [Link] in your project folder. Add the code below and run it with the green
Play button or press F5.

import pandas as pd

# Load the dataset

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

# Show first 5 rows

print('=== First 5 Rows ===')
print([Link]())

# Show column info

print('\n=== Dataset Info ===')
print([Link]())

# Show basic statistics

print('\n=== Summary Statistics ===')
print([Link]())

What the output means:

Function What It Shows

[Link]() First 5 rows of your data

[Link]() Column names, data types, and if any values are missing

[Link]() Average, min, max, and standard deviation for each number column

Tip: df is short for DataFrame. Think of it as a spreadsheet table inside Python.

Note: Expected output: You should see a table with 15 rows and 6 columns. No errors means your
file path is correct!
 3 Clean Your Data

Real-world data is messy. We need to handle missing values and remove duplicates before we can
analyse anything. Add this to your [Link] file:

# Check for missing values

print('Missing values in each column:')
print([Link]().sum())

# Fill missing numbers with the average of that column

num_cols = ['study_hours', 'attendance', 'previous_score', 'final_score']
for col in num_cols:
df[col] = df[col].fillna(df[col].mean())

# Remove any duplicate rows

df = df.drop_duplicates()

print('\nCleaning done!')
print('Total rows after cleaning:', len(df))
print('Missing values after cleaning:')
print([Link]().sum())

Why do we do this?

Problem Solution Why It Matters

Missing value (empty cell) Fill with column average Keeps all rows, no data lost

Duplicate rows drop_duplicates() Prevents wrong calculations

Wrong data type Use astype() to convert Math only works on numbers

Tip: isnull().sum() counts empty cells per column. If you see all zeros after cleaning, you are done!
 4 Explore Data with 3 Charts (EDA)

EDA means Exploratory Data Analysis — looking at the data visually to find patterns. Add each chart
to your [Link] file and run.

Chart 1 — Study Hours vs Final Score (Scatter Plot)

import [Link] as plt

[Link](figsize=(8, 5))
[Link](df['study_hours'], df['final_score'],
color='purple', s=80, alpha=0.7)
[Link]('Study Hours Per Day')
[Link]('Final Score')
[Link]('Study Hours vs Final Score')
[Link](True, alpha=0.3)
plt.tight_layout()
[Link]('chart1_study_hours.png') # saves image to your folder
[Link]()

Chart 2 — Average Score by Gender (Bar Chart)

gender_avg = [Link]('gender')['final_score'].mean()

[Link](figsize=(6, 4))
gender_avg.plot(kind='bar', color=['#1E88E5', '#F4511E'], edgecolor='white')
[Link]('Gender')
[Link]('Average Final Score')
[Link]('Average Score by Gender')
[Link](rotation=0)
plt.tight_layout()
[Link]('chart2_gender.png')
[Link]()

Chart 3 — Correlation Heatmap

import seaborn as sns

[Link](figsize=(8, 5))
[Link](df[num_cols].corr(), annot=True, cmap='Blues', fmt='.2f')
[Link]('Correlation Heatmap')
plt.tight_layout()
[Link]('chart3_heatmap.png')
[Link]()

Tip: In the heatmap, a value close to 1.0 means two columns increase together. Look for the strong
link between previous_score and final_score!
 5 Build a Machine Learning Model

We will train a Linear Regression model. Give it study hours, attendance, and previous score — it will
predict the final score.

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LinearRegression
from [Link] import mean_squared_error, r2_score

# X = input features, y = what we want to predict

X = df[['study_hours', 'attendance', 'previous_score']]
y = df['final_score']

# Split into 80% training data and 20% testing data

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

# Create and train the model

model = LinearRegression()
[Link](X_train, y_train)

# Test the model

y_pred = [Link](X_test)
print('R2 Score :', round(r2_score(y_test, y_pred), 3))
print('MSE :', round(mean_squared_error(y_test, y_pred), 3))

# Predict score for a brand new student

import pandas as pd
new_student = [Link]({
'study_hours' : [4],
'attendance' : [85],
'previous_score' : [75]
})
predicted = [Link](new_student)
print('\nPredicted final score:', round(predicted[0], 2))

Key terms explained:

Term Simple Meaning

Features (X) The input data we use to make a prediction

Target (y) The value we want to predict (final_score)

Train split 80% Data the model learns from

Test split 20% Data used to check if the model is accurate

R2 Score Accuracy score. 1.0 = perfect. Aim for above 0.85

MSE Average prediction error. Lower is better

Tip: If your R2 Score is above 0.9, your model is working very well!
 6 Upload to GitHub

GitHub is where developers share their code. Uploading your project here creates your first portfolio
item!

Step 6a — Create a [Link] file

Create a new file called [Link] in your project folder and paste this:

# Student Performance Analysis

## Project Overview
This project analyses student study habits and predicts
final exam scores using Linear Regression.

## Tools Used
Python, Pandas, Matplotlib, Seaborn, Scikit-learn

## Steps
1. Load and inspect dataset
2. Clean missing values and duplicates
3. Create 3 visualisation charts
4. Train a Linear Regression model
5. Predict score for a new student

## How to Run
```
pip install pandas matplotlib seaborn scikit-learn
python [Link]
```

## Author
Your Name Here

Step 6b — Push to GitHub

First, create a free account at [Link] and make a new repository named student-project. Then
run these commands in your VS Code Terminal:

git init
git add .
git commit -m "Initial commit: student performance project"
git branch -M main
git remote add origin [Link]
git push -u origin main

Note: Replace YOUR_USERNAME with your actual GitHub username. VS Code may ask you to
log in to GitHub the first time.
Your final project folder should look like this:
student-project/
[Link] <- your dataset
[Link] <- all your Python code
chart1_study_hours.png
chart2_gender.png
chart3_heatmap.png
[Link] <- project description

Tip: After pushing, open your GitHub profile. You will see the project listed. Share that link with your
instructor!
 Submission Checklist

1 Dataset [Link] is created with 15+ rows []

2 Load df = pd.read_csv() runs without errors []

3 Clean Missing values and duplicates are removed []

4 Chart 1 Scatter plot: study hours vs final score []

5 Chart 2 Bar chart: average score by gender []

6 Chart 3 Heatmap showing correlations []

7 ML Model Linear Regression model trained and tested []

8 Prediction New student score is predicted and printed []

9 [Link] Project description file is complete []

10 GitHub Repository created and code pushed []

11 Submit GitHub link sent to instructor []

Congratulations! You have completed your first Data Science project. This
is now your portfolio. Keep building!