IDFS3101 - Fundamentals of Data Science
Overview
This course provides a comprehensive foundational introduction to the computational mechanics of Data Science using Python, structured around the industry-standard methodologies of the Python Data Science Handbook by Jake VanderPlas. It focuses on the technical, mathematical, and algorithmic tools required to read, clean, transform, visualize, and model complex experimental datasets.
Students will develop core computational competencies across the five structural layers of the Python data science stack: shell-based interactive computing (IPython), fast vectorized array mathematics (NumPy), structured data manipulation engines (Pandas), scientific visualization frameworks (Matplotlib and Seaborn), and foundational machine learning architectures (Scikit-Learn). The course details specific data problems, including handling missing entry types, vectorized string operations, time-series data parsing, high-dimensional feature engineering, and the mathematical mechanics of estimators.
Additionally, the course addresses critical algorithmic governance, profiling bias auditing, and personal data masking rules in accordance with regulatory laws (e.g., Indonesian UU PDP / GDPR). Through real-world case scenarios and extensive hands-on programming labs, students will gain the professional ability to deploy reproducible, publication-grade analytical pipelines to solve enterprise optimization problems.
Learning Hours Composition:
- 42 hours face to face, consisting of 14 sessions of lecturing, tutorial or workshop.
- 28 hours of Structured Learning and Guided Group Discussions
- 65 hours of Independent, Project-Based Learning
Managing Faculty:
Credit Point:
3 Credit(s)
Learning Hours:
45 hours x 3 CPs = 135 hours
