PSZK | H
-
1149 Budapest, Buzogány utca 10
-
12. | Telefon: (+36
-
1) 469
-
6692
| Fax
: (+36
-
1) 469
-
6627
| www.bgf.hu
Közgazdasági Informatikai Intézeti
Tanszék
SYLLABUS
Data Science
Course title:
Data Science
Course code:
Status:
Contact hours:
1 lecture + 2 practice per week
Credits:
5
Prerequisites:
Course unit leader:
Tutor(s):
Attila Petróczi
petro
cziattila@gmail.com
Aims and objectives
To introduce the
basic
of the modern data driven business decision making
process.
To
arouse the interest
for system
-
theoretic thinking,
system
-
approaching
knowledge
and analysis processes.
To acquaint
the
studen
ts with
the advantages of
software supported analysis in business environment. Discuss the advantages and
disadvantages of data
-
mining models.
As in the real business life
decision making is
used to be based on
data analyses, students should to be familiar
with data
gathering, data cleansing, data storing and data analysis methods and software.
Aim is to provide for the students useable and applicable data analyses method
and data
-
mining software skills.
Learning outcomes
The student will be able to so
lve a complicated analysi
s
tasks alone. The student
will have the appropriate knowledge of analysis process and a toolset for the
solution in business situations.
PSZK | H
-
1149 Budapest, Buzogány utca 10
-
12. | Telefon: (+36
-
1) 469
-
6600 | Fax:
(+36
-
1) 469
-
6610 | www.bgf.hu
Methodology
This subject underlines the distinctive role of
lectures that
will be carried
out each
week during the term.
These lectures intent
to transfer basic theoretical knowledge.
Lectures are followed by practice, where students are given practical knowledge, IT
usage competences and problem solving tasks regarding to
business analysis and
data
-
mining.
These lessons also give the competence of using
data
-
mining models
and software.
Course schedule
Consultations
(semester weeks)
Topic
1
st
–
2
nd
Lecture:
Elements
: Business Intelligence, Data
-
mining,
Statistics, Data Science, Business An
alyst, Data Scientist
.
Practice:
Introduction of programing environment, Unix
commands, AWK scripting language
.
3
rd
–
4
th
Lecture:
Analysis processes and methods. Data structures,
Streaming API, Data Cleansing
.
Practice:
Text file processing, cleansing in
Python
.
JSON objects
in practice.
5
th
-
6
th
Lecture:
Database, Data Warehouse,
NoSQL. Relation algebra
and SQL. Map
-
Reduce and Hadoop basics.
Practice:
The connection of relational algebra and SQL. Map
-
Reduce implementation in Python.
7
th
-
8
th
Lecture:
B
asics of Data
-
mining, data
-
mining software and
frameworks.
Characterize data.
Practice:
Characterizing data using software:
descriptive
statistics, charts, statistical tests.
9
th
-
10
th
Lecture:
Data preparation
Practice:
Data preparation with Data
-
mining
software.
11
th
-
12
th
Lecture:
Data
-
mining models (clustering, classification,
association). Case study.
Practice:
Data
-
mining models in practice
.
PSZK | H
-
1149 Budapest, Buzogány utca 10
-
12. | Telefon: (+36
-
1) 469
-
6600 | Fax:
(+36
-
1) 469
-
6610 | www.bgf.hu
Course policies
Students a
re expected to attend lectures and carry out tasks during practice
lessons.
Assignments
Exam requirements: the condition for seminar grade is 2 compulsorily written end
-
term exam papers
, 2 end
-
term practice exams
and one team project task
.
To have a pass seminar grade one has to get minimally 61% of th
e summarized
scores of th
e 4
end
-
term exams,
50% of the team project task
.
The condition for signature: attending seminars and writing
2
end
-
term papers.
Assessment and grading
The fina
l mark will be composed of the 5
above mentioned assignments.
Grading:
the points (percentages
)
corresponding
to marks from 1
-
5.
0
-
60%
Fail (1)
61
-
69%
Pass (2)
70
-
79%
Fair (3)
80
-
89%
Good (4)
90
-
100%
Excellent (5)
Set readings
-
The material for lectures and seminars.
Recommended readings
-
Larose, Daniel T.,
Discovering Knowledge in Data: An I
ntroduction to Data
Mining, Wiley
-
Interscience, 2004.
-
Lar
ose, Daniel T.,
Data Mining Methods and Models, Wiley
-
Interscience,
2006.
Enter the password to open this PDF file:
File name:
-
File size:
-
Title:
-
Author:
-
Subject:
-
Keywords:
-
Creation Date:
-
Modification Date:
-
Creator:
-
PDF Producer:
-
PDF Version:
-
Page Count:
-
Preparing document for printing…
0%
Σχόλια 0
Συνδεθείτε για να κοινοποιήσετε σχόλιο