Final Exam_Moschou Niki

THEMA 1

  • Arxika elegxoume an kapoia metavlhth prepei na afairethei (visualize) –>oxi
  • Xrhsimopoioume to select attributes kai afairoyme tis 5,8,,10,11,13,15,16
  • Dokimazoume diaforous algorithmous kai epilegoume ton Bagging-J48 me pososto epityxias 74,13
  • Afairoume tis idies  metavlhtes kai apo to test set kai to apothikevoyme
  • Efarmozoume ton idio algorithmo me supply test to neo test set

THEMA 2

  • Xrhsimopoioyme toys JRIP kai PART
  •  Exoume toys akolouthous kanones me vash ta kalitera pososta epityxias

PART

ELONGATEDNESS <= 41 AND
MAX.LENGTH ASPECT RATIO > 7: opel (132.0/65.0)

Ean elongatedness einai mikrotero toy 41 kai max.legth ratio megalytero toy 7, tote opel me 132 swsta kai 65 lanthasmena

MAX.LENGTH ASPECT RATIO > 8 AND
HOLLOWS RATIO > 189 AND
SKEWNESS ABOUT_MAJOR > 63: van (107.0/2.0)

 
SCALED VARIANCE_MINOR > 309 AND
DISTANCE CIRCULARITY <= 76 AND
SKEWNESS ABOUT_MINOR <= 10 AND
SKEWNESS ABOUT_MAJOR > 64 AND
CIRCULARITY > 41: bus (107.0/1.0)

ELONGATEDNESS <= 41 AND
MAX.LENGTH ASPECT RATIO <= 7 AND
COMPACTNESS > 95: bus (70.0/1.0)
JRIP

(MAX.LENGTH ASPECT RATIO >= 9) and
(DISTANCE CIRCULARITY >= 100) and
(SCALED VARIANCE_MAJOR <= 231) => (71.0/9.0)

ELONGATEDNESS >= 43) and
(MAX.LENGTH ASPECT RATIO >= 9) and
(DISTANCE CIRCULARITY >= 73) => (86.0/0.0)

 

https://dataminingntua.files.wordpress.com/2009/06/final1.pdf

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s