Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
51 Cards in this Set
- Front
- Back
No guarantee that there are meaningful pattern |
UNSUPERVISED LEARNING |
|
6 association rule mining |
Item set Support count Support Frequent itemset Association rule Confidence |
|
find rules that will predict the occurence of an item |
ASSOCIATION RULE MINING |
|
support is greater or equal to minimum support |
FREQUENT ITEMSET |
|
finding hidden pattern within data |
UNSUPERVISED LEARNING |
|
no easy way to measure errors |
UNSUPERVISED LEARNING |
|
implication expression |
ASSOCIATION RULE |
|
find occurence of 1 item in relation to 1 item |
ASSOCIATION RULE MINING |
|
group items together that has the same characteristic. |
CLUSTERING |
|
collection of one or more item |
ITEM SET |
|
Finding groups of objects in a group will be similat to one another |
CLUSTERING |
|
ask data from the web |
WEB MINING |
|
may minimum # na gusto ireach |
FREQUENT ITEMSET |
|
Frequency on occurence af an itemset |
SUPPORT COUNT |
|
measure how often item lumabas |
CONFIDENCE |
|
reduce the size of large data sets |
SUMMARIZATION |
|
fraction of transactions contain an itemset |
SUPPORT |
|
groupings as a result of an extrnal specification |
RESULT OF A QUERY |
|
areas are not identical |
GRAPH PARTITIONING |
|
set of nested cluster |
HIERARCHICAL CLUST |
|
What is not cluster analysis |
SUPERVISED CLASSIFICATION SIMPLE SEGMENTATION RESULT OF A QUERY GRAPH PARTITIONING |
|
have a class label information |
SUPERVISED CLASSIFICATION |
|
non overlapping subsets |
PARTITIONAL CLUSTERING |
|
tree like diagram that records the sequence of merge |
DENDOGRAM |
|
related document for browsing |
UNDERSTANDING |
|
each cluster associated with centroid |
K MEANS CLUSTERING |
|
visualized as dendogram |
HIERARCHICAL CLUSTERING |
|
most popular hierarchical technique |
AGGLOMERATIVE CLUSTERING ALGORITH |
|
mean of the point in the cluster |
CENTROID |
|
measured by euclidean dustance |
CLOSENESS |
|
CODE FOR PLOTING |
library(cluster) |
|
filtered out |
STOP WORDS |
|
basic algorithm |
STRAIGHT FORWARD |
|
data colection via web crawlers |
WEB CONTENT OR STRUCTURE MINING |
|
HTML, XML ,text format |
WEB MINING |
|
related to data mining and text |
WEB MINING |
|
pre processing post processing web content mining search engine mining |
WEB CONTENT MINING |
|
textual content on the web |
WEB CONTENT OR STRUCTURE MINING |
|
generate structure summary |
WEB STRUCTURE MINING |
|
largest repository data |
WEB MINING |
|
hindi lang text pwedeng image, videos etc. |
WEB DATA |
|
semi-automated process |
TEXT MINING |
|
1st impost structure to the data then mine the structure data |
TEXT MINING |
|
reducing inflected words |
STEMMING |
|
large collection of structure texts |
CORPHA (CORPUS) |
|
nakaarrange accdg. to table |
STRUCTURED DATA |
|
categorized block of text |
TOKENING |
|
Determing the lifetime value of clients |
WEB MINING |
|
sequenrial patterns |
DATA MINING TECHNIQUES |
|
loses all order specific |
BAG OF TOKEN APPROACH |
|
single word or phrase |
TERM |