Skip to content
Dr. İsmail Hakkı KINALIOĞLU

Data Science with Python

A hands-on walk through the full workflow of reading, cleaning, exploring and modelling data with NumPy, pandas, plotting libraries and scikit-learn.
Semester
Fall semester
Level
Undergraduate
Credits
2+0
Length
16 weeks
Weekly syllabus

Course aims

To enable students to analyse a real dataset end to end, present findings with appropriate charts, and build and evaluate basic machine learning models.

Learning outcomes

Students who complete this course will be able to:

  1. Reads, cleans, merges and summarises data with pandas.
  2. Performs exploratory data analysis and presents findings with suitable charts.
  3. Builds regression and classification models and compares their performance.
  4. Presents the analysis as a reproducible notebook and a short report.

Assessment

Component Weight
Midterm exam (week 8) 40%
Final exam (week 16) 60%

Resources

  • Wes McKinney, Python for Data Analysis, O’Reilly
  • Jake VanderPlas, Python Data Science Handbook, O’Reilly
  • scikit-learn kullanıcı kılavuzu / user guide: scikit-learn.org

 

Weekly syllabus

  1. 1
    Week 1 Introduction to data science and the data science process
  2. 2
    Week 2 Jupyter notebooks and a Python refresher
  3. 3
    Week 3 Array computing with NumPy
  4. 4
    Week 4 pandas: Series and DataFrame
  5. 5
    Week 5 Reading and writing data; data sources
  6. 6
    Week 6 Data cleaning: missing and invalid values
  7. 7
    Week 7 Transforming, merging and grouping data
  8. 8
    Week 8 Exam Midterm exam
  9. 9
    Week 9 Visualisation with Matplotlib and seaborn
  10. 10
    Week 10 Exploratory data analysis
  11. 11
    Week 11 Descriptive statistics and hypothesis testing
  12. 12
    Week 12 Regression with scikit-learn
  13. 13
    Week 13 Classification and model evaluation
  14. 14
    Week 14 Clustering and dimensionality reduction
  15. 15
    Week 15 Project presentations
  16. 16
    Week 16 Exam Final exam

Fall semester courses