INTERNATIONAL

SUMMER SCHOOL
2025
SYLLABUS
Academic year 2024/2025
 International Summer School 2025

Academic and language requirements

Courses are open to Undergraduate and Graduate students providing that applicants have the pre-requisites
specified in the course’s syllabus.

Courses are taught and assessed in English. For non-native speakers of English, B2 (CEFR) or equivalent (TOEFL IBT
72, IELTS 5.0, TOEIC 750) is highly recommended.

Additional information
For details about study programmes offered by EM Normandie please contact:

Adam AHARRAM, International Project Manager

[email protected]

2
 International Summer School 2025

COURSE TITLE Introduction to Data Analysis Using Python and ChatGPT

Catchphrase Make GPT code for you

Session & Campus Session 1, Le Havre campus

Teaching delivery On campus, attendance mandatory
Workload (1h = 60 min) 30 class-hours + Independent learning hours ECTS credits 6
Professors Farrokh SHEIKHAHMADI PhD, [email protected]
Assistant Professor at EM Normandie Business School
Pre-requisite(s) None
for attending the course /
Level of studies
Learning goal(s)  Understand the fundamentals of Python programming.
 Work with essential Python libraries like Pandas, NumPy, and Matplotlib to analyze and visualize data.
 Use ChatGPT to assist with coding tasks, problem-solving, and conceptual understanding.
Learning objective(s)  Coding simple programs with python
 Using AI to facilitate coding
 Getting familiarized with data analysis tools in python

Add text, e. g. By the end of this course, participants are able to:
 Understand python codes
 Write Python programs
 Understand the utility of programming languages in data analysis
 Understand the use of AI in programming

Learning outcome(s)  To understand coding and logical algorithms

 To understand the utility of programming in business analysis
 To understand the role of AI in coding
Course description Contents:
Session 1: Introduction to Data Analysis and Tools (3 hours)

• Overview of Data Analysis:

o What is data analysis? Real-world applications in business, science, and
more.
o Why is data analysis important in decision-making?
• Introduction to Python:
o Why Python is the preferred language for data analysis.

3
International Summer School 2025

o Overview of Python’s ecosystem for data analysis (Pandas, NumPy,

Matplotlib).
• Introduction to ChatGPT:
o How ChatGPT can assist in coding, debugging, and explaining concepts.
o Using ChatGPT to help understand complex concepts and accelerate
learning.
• Setting Up the Python Environment:
o Installing Anaconda and Jupyter Notebooks.
o Navigating Jupyter notebooks and running Python code interactively.
• Basic Python Syntax:
o Variables, data types (strings, integers, floats), basic operations.
o Hands-on exercises to practice writing simple Python code.
Session 2: Programming Basics in Python (3 hours)

• Introduction to Python Data Structures:

o Lists, dictionaries, tuples, and sets.
o Why these data structures matter in data analysis.
• Control Flow in Python:
o Conditional statements (if, else, elif).
o Loops (for and while loops).
o Examples of how to use these structures in basic programs.
• Hands-On Practice:
o Writing Python code using control flow.
o ChatGPT support to troubleshoot and enhance understanding.
Session 3: Working with functions in Python (3 hours)

• Fonctions:
o What are functions and why are they important?

4
International Summer School 2025

o Creating and calling functions in Python.

o Using ChatGPT to help generate function code and understand logic flow.
• Hands-On Practice:
o Writing Python code using control flow and functions.
o Loading and exploring datasets using Pandas.
Session 4: Practice and Revision (3 hours)

• Hands-On Practice:
o Writing Python code excercises.
Session 5: Working with files in python (3 hours)

• Reading and Writing Files:

o Reading data from CSV, Excel, and text files using Python.
• Introduction to Pandas Library:
o What is Pandas and how does it help with data analysis?
o Basic concepts: DataFrames, Series.
• Hands-On Practice:
o Loading and exploring datasets using Pandas.
o Using ChatGPT for explanations and assistance with Pandas operations.
Session 6: Data Cleaning and Preparation (3 hours)

• Importance of Data Cleaning:

o Why cleaning data is critical for accurate analysis.
o Identifying common issues (missing data, duplicates, outliers).
• Techniques for Cleaning Data:
o Handling missing values: filling, dropping, and imputing.
o Dealing with duplicates and erroneous data.
o Transforming data: filtering, sorting, and renaming columns.

5
International Summer School 2025

• Using ChatGPT for Data Cleaning:

o ChatGPT as a guide for code troubleshooting and debugging.
• Hands-On Practice:
o Applying cleaning techniques on a messy dataset with guidance from
ChatGPT.
Session 7: Data Analysis Basics (3 hours)

• Descriptive Statistics:
o Measures of central tendency: mean, median, mode.
o Measures of spread: variance, standard deviation.
o Grouping and aggregating data in Pandas.
• Using NumPy for Mathematical Operations:
o Basic mathematical functions and arrays.
• Hands-On Practice:
o Analyzing datasets using statistical measures with Pandas and NumPy.
o ChatGPT assistance in writing and debugging analysis code.
Session 8: Data Visualization (3 hours)

• Introduction to Data Visualization:

o Why visualizing data is essential for interpretation.
o Different types of visualizations: bar charts, line graphs, scatter plots, and
histograms.
• Plotting with Matplotlib and Seaborn:
o Creating basic plots with Matplotlib.
o Customizing plots: labels, colors, titles, and legends.
o Advanced visualization techniques with Seaborn (heatmaps, box plots).
• Using ChatGPT for Visualizations:
o How ChatGPT can help create and refine visualizations.

6
 International Summer School 2025

• Hands-On Practice:
o Creating a variety of visualizations from datasets.
o Guided practice on choosing the right type of visualization for different
data.
Session 9: Advanced Data Analysis Techniques (3 hours)

• Correlation and Regression Analysis:

o Understanding correlation and how to compute it.
o Basics of linear regression analysis.
o Interpreting the results of regression analysis.
• Hands-On Practice:
o Running correlation and regression analysis on datasets.
o Using ChatGPT for assistance with more complex analytical tasks.
Session 10: More exercises and practices (3 hours)

• Hands-On Project Work:

o Students work on some projects with support from the instructor and
ChatGPT.

Teaching Material Textbook/Reference (optional): Python for Data Analysis by Wes McKinney.

Tools:

• Python (via Anaconda), Jupyter notebooks.

• ChatGPT for coding assistance.
• Key libraries: Pandas, NumPy, Matplotlib, Seaborn.

Evaluation criteria Continuous assessment: 40% Final assessment:60%

- Exercises and homework - Open book questions
Recommended readings • Python for Data Analysis by Wes McKinney.

• Python Programming for Data Analysis by José Unpingco