SPPU · Second Year Electrical Engineering · 2024 Pattern (Revised)
Fundamentals of Data Science & Machine Learning
MDM-272-ELE · Semester IV · 2 credits · CCE 40 + end-semester 60
Unit 1: Python for Data Science
6 hoursJupyter and Google Colab; int, float, string, list, tuple and dictionary types; functions, arrays and data frames; classes and objects; reading and writing CSV files.
Marks: 12 in the end-semester exam · CCE: Unit test (15 marks, Units 1 & 2)
- Python environments: Jupyter and Colab
- Python data types and functions
- Classes and objects in Python
- Reading and writing CSV files
Unit 2: Data Science and Electrical Applications
6 hoursData science concepts, components and lifecycle; NumPy and Pandas; mean, median, mode and standard deviation; load forecasting by curve fitting, bill prediction in smart grids and fault prediction; roles in data science.
Marks: 12 in the end-semester exam · CCE: Unit test (15 marks, Units 1 & 2)
- Data science lifecycle
- NumPy and Pandas
- Descriptive statistics
- Data science in electrical engineering
Unit 3: Data Acquisition, Visualisation and Hypothesis Testing
6 hoursData from SCADA, IoT sensors and meters; structured and unstructured data; time series; handling missing values, outliers and duplicates; line plots, histograms, box plots and scatter plots; null and alternate hypotheses, p-values, type I and II errors, t- and z-tests.
Marks: 12 in the end-semester exam · CCE: Assignments or case study (15 marks, Units 3 & 4)
- Data sources: SCADA, IoT sensors and meters
- Data preprocessing
- Visualisation with Matplotlib and Seaborn
- Hypothesis testing basics
Unit 4: Introduction to Machine Learning
6 hoursConcept and scope of ML; AI versus ML versus deep learning; supervised and unsupervised learning; the ML pipeline; predictive maintenance, load and outage forecasting, fault classification.
Marks: 12 in the end-semester exam · CCE: Assignments or case study (15 marks, Units 3 & 4)
- What machine learning is
- AI, machine learning and deep learning
- Supervised and unsupervised learning
- The machine learning pipeline
- Machine learning in electrical engineering
Unit 5: Basic ML Algorithms and Evaluation
6 hoursscikit-learn and model building; linear regression for load forecasting, k-nearest neighbours for fault classification, k-means for load profiles; confusion matrix, accuracy, precision, recall, F1 and cross-validation.
Marks: 12 in the end-semester exam · CCE: Seminar, open-book test or quiz (10 marks, Unit 5)
- Linear regression
- K-nearest neighbours
- K-means clustering
- Model evaluation metrics
- Cross-validation
Unit contents are summarised from the official SPPU syllabus . AiCanCode.org is not affiliated with Savitribai Phule Pune University.