This fast-paced class is intended for getting students interested in data science up to speed:
We start with an introduction to the field of "Data Science" and into the overall Data Science Process.
The primary focus of the rest of the course is on gaining fundamental knowledge for Data processing, that is, preparation, cleansing and storage of data, which typically takes the largest part of any data science project. We will learn how to deal with different data formats and how to use methods and tools to integrate data from various sources, plus how to resolve quality issues such as duplicates, encoding errors, missing values, etc. within raw data.
The integrated data can then be used for further data analytics tasks (cf. course 2 in this SBWL).
The students will practice approaches and techniques using the Python programming language in an interactive environment.
All course material is available on this web page: http://data.wu.ac.at/datascience/dataprocessing1_ws17/
Overall, students shall gain fundamental knowledge for dealing with different data formats and in using methods and tools to integrate data from various sources in this course. This includes:
* Hands-on experience in processing and preparing data for data science tasks with Python.
* An understanding of how to use the Python standard library to write programs, access the various data science tools.
* Working knowledge of the Python tools ideally suited for data science tasks, including:
* Accessing data (e.g., tabular (CSV), tree (JSON), graph shaped (RDF) data but also databases)
* Cleansing and normalizing data
* Sorting, filtering and grouping data
* Tools and algorithms for data transformation
* Connection to and loading data into a database system and indexing techniques, for faster access of data in a database
The course will focus on in-class code walkthroughs to present high-quality, well-commented code that students can later reference.
The course will balance project work and small homework assignments.
The students will be able to apply new learned concepts and methods directly in the class using real world Open Data data sources.
Repitition quizes: 25%
In-class participation: 25%
Homeworks: 50% (homeworks will mainly consist of adaptations and discussion of the practical examples presented in class)
The SBWL entry is coupled with an entry course consisting of 2 3hrs tutorials and an exam, cf. course 2230.
Please be aware that for all courses in this SBWL registration is only possibly for students who successfully have completed the entry course (Einstieg in die SBWL: Data Science).
Note that for courses within the SBWL "Data Science" we can only accept students enrolled in one of WU's bachelor programmes who qualify for starting an SBWL; particularly, we cannot accept students from other courses and programmes enrolled at WU as 'Mitbeleger' only.
If you have questions on the course or on the homework send an email to the lecturers with the subject"[2184 Data Processing 1]"
If you need an individual appointment with one of the lecturers, in order to request an appointment send an email to email@example.com with the subject “[2184 Data Processing 1]”