Introduction to Data Science (4V, 2Ü) Prof. Ernst, WS 2019/20
Content
Tentative list of course topics:
- Introduction: What is Data Science
- Learning Theory
- Regression
- Classification
- Clustering and Tree-Based Methods
- Unsupervised Learning
Notices
| Room Change | On Thursday 5 December 2019 instead of the class lecture there will be an extra lab tutorial from 13:45 to 15:15 in the computer room (738, Rh39/41). |
|---|---|
| Cancellations | There will be no DS lectures during the week of November 11-15. On Thursday, November 14, Jan Blechschmidt will hold an additional Q & A session on Python programming and other lab-related issues in the computer room (738, Rh39/41). |
| First Class | Monday, October 14, 2019. |
| First Exercise Lab | Monday, October 14, 2019. |
Listing of this course in the electronic Vorlesungsverzeichnis (course directory):
Keine Lehrveranstaltung gefunden.
Lecture
Literature
- James, Witten, Hastie & Tibshirani. An Introduction to Statistical Learning – with Applications in R. Springer 2013. Available online by follow this link.
- Here's a continually updated annotated reading list for the course (06.02.2020).
Slides
- What is Data Science? (10.10.2019)
- Learning Theory (28.10.2019)
- Linear Regression (18.11.2019)
- Classification (28.11.2019)
- Resampling Methods (12.12.2019)
- Linear Model Selection and Regularization (13.01.2020)
- Nonlinear Regression Models (13.01.2020)
- Tree-Based Methods (23.01.2020)
- Unsupervised Learning (03.02.2020)
Exercises
The exercise labs take place in the computer pool of the Mathematics Computing Service. To carry out the programming tasks, everybody needs a valid login which can be picked up at Margit Matt's office (Rh 39/room 704). All programming tasks can be carried out on our Jupyter Hub or on your own laptop. The Jupyter Hub can be accessed inside the university network or via VPN.Problem sheets
- Problem set 01 (no submission)
- Problem set 02 (due 2019-10-28)
- Problem set 03 (due 2019-11-04)
- Problem set 04 (due 2019-11-18)
- Problem set 05 (no submission)
- Problem set 06 (due 2019-11-25)
- Problem set 07 (due 2019-12-02)
- Problem set 08 (due 2019-12-09)
- Problem set 09 (no submission)
- Problem set 10 (due 2019-12-16)
- Problem set 11 (due 2020-01-06)
- Problem set 12 (due 2020-01-11)
- Problem 1
- Problem 2
- wine-train.csv
- wine-test.csv
- Problem 3
- Advertising.csv (same as above)
- Problem set 13 (due 2020-01-27)
- Problem set 14 (no submission)
- Problem set 15 (no submission)
- Problem 1
- Problem 2
- housing.csv (same as above)
Installation
If you want to install your own Jupyter environment, we suggest the following procedure: Get the latest version of miniconda from this page and follow the steps in the installation dialogue. Create a new environment viaconda create --name ds2019Activate the
ds2019 environment via
conda activate ds2019or (depending on your system)
source activate ds2019and install the required packages (this list is continually updated)
conda install -c conda-forge jupyter numpy scipy pandas matplotlibPlease refer to Conda (Installation) and Conda (Managing environments) for further information.