Course Objectives: |
Data science is a field that includes many disciplines such as statistics, mathematics, computer science, and data analysis. The aim of this course is to provide students with current approaches, models and application technologies in the field of data science. |
Course Content: |
Introduction to data analysis tool in Python, Descriptive Statistics, Python Libraries (NumPy, Pandas, Matplotlib, Scikit-Learn) for Data Science, Data preprocessing with Scikit- Learn, Supervised Learning, Random Forest, XGBoost, Support Vector Machine, Confusion Matrix, ROC, Unsupervised Learning, Hierarchical Clustering, Gaussian,Model Mixture,Density-Based Spatial clustering of Applications with Noise (DBSCAN),Introduction to Deep Learning, Perceptron, Linear Algebra for Deep Learning,
Gradient-based Optimization, Convolutions Neural Network
|
Week |
Subject |
Related Preparation |
1) |
Meet & General Concept about Data Science
Introduction of the curriculum |
|
1) |
Unsupervised Learning
Hierarchical Clustering, Gaussian Model Mixture |
|
2) |
Python for Data Science
Python, Jupyter Notebooks, Numpy |
|
3) |
Python for Data Science
Numpy, Pandas |
|
4) |
Python for Data Science
Numpy, Pandas, Matplotlib, Seaborn |
|
5) |
Python for Data Science
Matplotlib, Seaborn |
|
6) |
Supervised Learning
Support Vector Machine |
|
7) |
Different Performance Evaluation Metrics
Confusion Matrix, ROC, F1 Score |
|
8) |
Supervised Learning
Random Forest, XGBoost |
|
9) |
Unsupervised Learning
Hierarchical Clustering, Gaussian Model Mixture |
|
10) |
Unsupervised Learning
Hierarchical Clustering, Gaussian Model Mixture Based Spatial clustering of Applications with Noise (DBSCAN) |
|
11) |
Introduction to Deep Learning
General Concept, Perceptron |
|
12) |
Introduction to Deep Learning
Linear Algebra for Deep Learning
|
|
13) |
Introduction to Deep Learning
Gradient-based Optimization |
|
14) |
Introduction to Convolutions Neural Network
|
|
15) |
Convolutions Neural Network |
|
16) |
Final Homework |
|
Course Notes / Textbooks: |
Deniz Kılınç, Nezahat Başeğmez. Uygulamalarla Veri Bilimi, 2018, Abaküs |
References: |
Jake VarderPlas, Python Data Science Handbook, 2017, O’REILLY
François Chollet, Deep Learning with Python, 2017, MANNING
Ethem Alpaydın, Yapay Öğrenme, Boğaziçi
Haldun Akpınar, Data, Papatya Bilim |
|
Program Outcomes |
Level of Contribution |
1) |
It has a wide range of interdisciplinary approaches to management information systems, primarily business and computer engineering. |
3 |
2) |
Comprehends the management information systems in terms of technical, organizational and managerial aspects and uses the current programming language by knowing the logic of programming. |
3 |
3) |
Uses different information technologies and systems for understanding and solving various business problems. |
2 |
4) |
Interpret the data, concepts and ideas in the field of management information systems with scientific and technological methods. |
3 |
5) |
Analyze the needs for an information system and analyze the processes of analysis, design and implementation of the database. |
2 |
6) |
Gains technical and managerial contributions to IT projects and takes responsibility. |
1 |
7) |
Solve complex business and informatics problems by using various statistical techniques and numerical methods and make analyzes using statistical programs effectively. |
2 |
8) |
Uses a foreign language at the B1 General Level in terms of European Language Portfolio criteria according to the level of education. |
1 |
9) |
Develops teamwork, negotiation, leadership and entrepreneurship skills. |
1 |
10) |
Has universal ethical values, social responsibility awareness and sufficient legal knowledge. |
1 |
11) |
Develops positive attitudes related to lifelong learning and identifies individual learning needs and carries out studies to correct them. |
1 |
12) |
Students will be able to communicate their ideas and solutions both written and orally, and present and publish them on both national and international platforms. |
1 |
13) |
It uses information and communication technologies together with computer software at the advanced level of European Computer Driving License required by the field. |
3 |