AZERBAIJAN STATE OIL AND INDUSTRY UNIVERSITY
MASTER OF SCIENCE PROGRAM
SYLLABUS
Course unit title Analytics application using Python
Course unit code
Type of course unit Compulsory
Level of course unit Second cycle Master
Year of study 2nd year
Semester when the course unit is 3rd Semester
delivered
Number of ECTS credits allocated 6
Name of lecturers Coordinator: Tural Naghiyev
Class information
Learning outcomes of the course unit Course Description:
In this course, you’ll dive into working with data in Python, learning
how to clean, process, and analyze it effectively. Using libraries like
NumPy, pandas, and matplotlib, along with tools such as Jupyter
Notebook and VS Code, you’ll gain hands-on experience building
practical analytics applications. The emphasis is on solving real-world
business and management problems, so you’ll leave with skills that
are immediately applicable in the workplace.
Learning Outcomes:
By the end of this course, students will be able to:
1. Apply Python programming for structured data analysis.
2. Use NumPy and pandas for data manipulation and
descriptive analytics.
3. Perform data cleaning, preparation, and wrangling.
4. Create visualizations with matplotlib and related
libraries.
5. Apply time series analysis and basic statistical methods.
6. Integrate Python with modelling libraries for applied
analytics.
Mode of delivery Face-to-face
(face-to-face, distance learning)
Prerequisites and co-requisites
Recommended optional programme Jupyter Notebook
components [Link]
Visual Studio Code
[Link]
Recommended or required reading Wes McKinney, Python for Data Analysis: Data Wrangling
with Pandas, NumPy, and IPython, 2nd Edition, O’Reilly
Media.
Reading material: [Link]
Jupyter Notebook Documentation – [Link]
Workshops:
● [Link]
es
● [Link]
Planned learning activities and teaching Classroom lecturing, seminars, laboratory works
methods
Language of instruction English
Work placement(s) ASOIU
Course contents:
Week Topic Practical Focus / Business Case
Introduction to Python & Data Analysis
Why Python for business analytics, intro
1 Workshop I: Install Enviornment
to real datasets (finance, HR, sales).
Workshop II: Simple ML tutorial
Python Basics, Jupyter & Collaboration Tools
Workshop I: Python basics Python syntax, Jupyter, Google Colab,
2
Workshop II: EDA with sweetviz, dtale GitHub basics.
Classwork: EDA analysis with reallife data
Data Structures, Functions & Files
Workshop I: Functions for automation, handling
3
[Link] CSV/Excel reports.
Workshop II: Auto DS for Math
NumPy Basics
Lesson: NumPy quickstart
Customer transaction analysis with arrays
4 Lesson: Data Quality
and vectorized math.
Workshop I: Linear algebra on n-dimensional arrays
Workshop II:
Pandas Basics – DataFrames & Business Stats
Analyzing sales/HR datasets, descriptive
5
From Dataframe to business insight statistics.
Workshop I: Colab Lesson 5
Data Loading & Sources
Working with CSV, Excel, APIs, JSON, and
6 Workshop I: Web Scraping
web scraping for company data.
Workshop I: Python Playwright lib
Data Cleaning & Preparation
Handling missing values, outliers, type
7
Workshop I: Insurance cost analysis conversions, preprocessing business data.
Workshop II: Working with diff file formats
Exploratory Data Analysis (EDA)
Google Looke Studio/Power BI Exploring retail or HR data for insights,
8
Workshop II: Ultimate Looker Studio trend detection, and KPI analysis.
Data Wrangling – Join, Combine & Reshape Merging multiple datasets (sales +
9
Workshop I: ML project with XGBoost marketing + HR) for richer insights.
Business dashboards with matplotlib,
10 Visualization & Dashboards
seaborn, Plotly/Dash.
Aggregation & Group Operations Customer segmentation, regional sales
11
OCR tools: Tesseract, EasyOCR, Docking, [Link] KPIs, HR department analysis.
1. Time Series Analysis Forecasting sales or demand with pandas
12
2. Descriptive statistics time series tools.
Building ML models
13 Model Development & Evaluation (classification/regression), evaluation with
metrics, refinement.
Using PyCaret/AutoML to automate
model building and comparison; students
14 AutoML & Final Project Presentations
present end-to-end analytics projects
(EDA → Dashboard → Model → Insights).
Suggested Teaching Rhythm
● 15 min theory → 30 min coding → 10 min discussion → 60 min hands-on → 20 min review
● Keep lessons interactive every 10–15 minutes
● Use short and real-life datasets (100–1000 rows) for fast results
● End every session with 4 takeaway skill students can name aloud
Overall Flow
Phase Time Description Type
1. Warm-up 0–15 - Short review of last lesson (2–3 quiz questions)- Show a Discussion /
& Recap min real-world analytics example related to today’s topic Q&A
2. Concept & 15–40 - Introduce new topic conceptually (slides, visuals, or Lecture
Theory min whiteboard)- Explain why it matters for analytics (use cases)
3. Guided 40–75 - Instructor demonstrates topic in Jupyter Notebook- Demo /
Live Coding min Step-by-step with short student questions Interactive
BREAK Students rest / quick chat / reset focus
4. Student 85–130 - Students complete 3–5 tasks based on the demo- Instructor Practice /
Workshop min walks around, answers questions-collaboration in pairs Hands-on
5. Challenge Task 130–14 - One “open-ended” task: analyze, clean, or visualize Challenge
or Mini-Project 5 min something interesting- creativity and independent thinking
6. Wrap-up & 145–15 - Summarize key learning points- Assign homework or short Discussion
Reflection 0 min reflection (“What did you learn today?”)
Capstone Project
Students will complete a comprehensive project applying Python analytics and machine learning to
real-world datasets. The goal is to combine technical skills with practical problem-solving in business and
public sector contexts.
Projects will include:
▪ Data collection and cleaning (structured and unstructured sources)
▪ Exploratory data analysis and visualization
▪ Predictive modelling with Python ML libraries (scikit-learn, statsmodels, XGBoost)
▪ Domain-specific workshops and applications:
Water Management for Government: Using time series and ML models to predict river
levels, monitor water quality, and optimize resource distribution.
Financial Analytics: Developing predictive models for credit scoring, fraud detection,
risk assessment, and portfolio optimization.
Emergency Analytics: Leveraging real-time and historical data to analyze fire incidents,
disaster response times, and resource allocation for emergency services. Includes case
studies on wildfire data, emergency call center analytics, and predictive modelling for risk
management.
▪ Insight generation for decision-making: translating analytics into actionable policy or business
strategies.
The project culminates in a presentation and written report where students demonstrate their ability to
design, build, and communicate analytics solutions.
Important:
Data analytics with R – I year
Analytics application using Python – II year
Both subjects are complementary to each other, and the instructor should distinguish their focus:
In Python subject → emphasize applications, automation, dashboards, real-world projects.
In R subject → emphasize statistics, methodology, visualization, research analysis.
Common Core (applies to both R & Python)
● Work with data (collecting, cleaning, preparing)
● Analyze data (statistics, trends, EDA)
● Visualize data (dashboards, charts)
● Apply analytics (real business/government cases)
● Machine learning (optional)
Analytic Application Using Python
Focus: scalability, automation, business apps
● ✅ Learn Python basics – code, functions, automation
● ✅ Data engineering tasks – APIs, JSON, scraping, big datasets
● ✅ Libraries for analysis (Pandas, NumPy, Scikit-learn, PyCaret, Dash)
● ✅ Build dashboards, web apps, automation scripts
● ✅ More applied to business use-cases (finance, HR, retail, government, emergency analytics)
WORKLOAD
Activities Number Duration Total Workload
(hour) (hour)
Course duration in class 14 3 42
Preparation for Midterm Exam 1 18 18
Individual or Group Work 7 10 70
Midterm Exam 1 3 3
Paper/Project 1 13 13
(including preparation and presentation)
Homework 12 1 12
Preparation for the Final Exam 1 20 20
Final Exam 1 3 3
Total Workload 181
Total Workload/30(h) 6.03
ECTS Credit of the Course 6