TU Wien:AKSTA Statistical Computing VU (Filzmoser)

Ähnlich benannte LVAs (Materialien):

AKSTA Statistical Computing VO (Posekany) (TU Wien, 0 Materialien)
AKSTA Statistical Computing VU (Filzmoser) (TU Wien, 0 Materialien)
AKSTA Statistical Computing VU (Posekany) (TU Wien, 2 Materialien)
AKSTA Statistical Computing VU (Vana Gür) (TU Wien, 1 Material)

Daten[Bearbeiten | Quelltext bearbeiten]

Vortragende	~~Prof. Filzmoser Peter~~, Prof. Posekany Alexandra (SS21)
ECTS	3
Abteilung	Stochastik und Wirtschaftsmathematik
Wann	Sommersemester
Links	tiss:107106

Zuordnungen
Master Data Science	Pflichtmodul FDS/FD - Fundamentals of Data Science - Foundations
Bachelor Medizinische Informatik	Wahlmodul Statistische Datenanalyse
Bachelor Software & Information Engineering	Wahlmodul Statistische Datenanalyse

Mattermost: Channel "aksta-statistical-computing" • Register • Mattermost-Infos

Inhalt[Bearbeiten | Quelltext bearbeiten]

Programming in R (basics, and focus on solving problems related to statistical aspects of Data Science)
How to read in data from files, clean them, organize them.
some parts of the "tidyverse"
Data visualization with R (base, ggplot2)
basic SQL

DataCamp courses in SS21:

Data Visualization in R
Fundamentals of Bayesian Data Analysis in R
Intermediate R
Introduction to Data visualization with ggplot2
Introduction to R
Introduction to the Tidyverse
Machine Learning with caret in R
Building Web Applications with Shiny in R
Bayesian Modeling with RJAGS (optionally, to improve your grades)

Ablauf[Bearbeiten | Quelltext bearbeiten]

This class makes use of the platform DataCamp. Students get (time-limited) access to the platform where they can (have to) take relevant courses, related to programming in R. Including how to read in, handle, visualize data, etc. The access allows also to do other classes, not related to R, such as for Python, SQL, and more, which is very nice!

There are also weekly classes where some material is discussed [I did not attend, so can't say anything, someone else please fill in ;-)]

SS20: Attendance of 50% of classes is required now. During class, there is an exercise to be done after an "impulse talk". The deadline for the in-class exercises is 23:55 of the same day (there is no requirement to finish in class). The in-class exercises account for 30% of the grade, if attended. The other 70% of the grade consist of the DataCamp exercises.

SS21: You got access to DataCamp and had to hand in 10 exercises as R markdown file (.Rmd) with the PDF you generated. The exercises comprised usually to do a DataCamp course and copy (nearly) every code chunk from DataCamp into a Rmd file and to add your own comments that describe the code. Sometimes you also get some PDF which explains course relevant topics, which also contains some exercises, which you had to add as code chunk in the R markdown file, including comments. Due to covid there was nearly no interaction between students and teaching assistants or professors -- with one exemption of online guidance meetings and some email responses. A tuwel forum was provided for us students, which was not regularly checked by teachers or teaching assistants. It was really cumbersome to comment code you have done in DataCamp. It was very repetitive. The DataCamp courses we had to do also were not always of good quality, unfortunately.

Benötigte/Empfehlenswerte Vorkenntnisse[Bearbeiten | Quelltext bearbeiten]

Some knowledge in R will make the start easier, but there are at least two courses, namely "Introduction to R" and "Intermediate R" that will get you started from zero. These will teach you about the basic variables, data structures, etc., as well as programming, control flow, functions, etc. in R. More in-depth R classes follow then and should deepen your understanding.