diff options
| author | mike <mike1994vink@gmail.com> | 2021-04-15 13:42:35 +0200 |
|---|---|---|
| committer | mike <mike1994vink@gmail.com> | 2021-04-15 13:42:35 +0200 |
| commit | 24c8870eb5d47f9a8fb78d9fe65a1c41ba72c64d (patch) | |
| tree | a76a1a54ba13887f03f46704b4deae0311e21ad5 /images/feature_selection_classification.uxf | |
| parent | a82fc7e9dc1901c3f342318f14643531d9ad787f (diff) | |
update
Diffstat (limited to 'images/feature_selection_classification.uxf')
| -rw-r--r-- | images/feature_selection_classification.uxf | 331 |
1 files changed, 331 insertions, 0 deletions
diff --git a/images/feature_selection_classification.uxf b/images/feature_selection_classification.uxf new file mode 100644 index 0000000..87023a6 --- /dev/null +++ b/images/feature_selection_classification.uxf @@ -0,0 +1,331 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<diagram program="umlet" version="14.3.0"> + <zoom_level>10</zoom_level> + <element> + <id>UMLClass</id> + <coordinates> + <x>30</x> + <y>50</y> + <w>470</w> + <h>60</h> + </coordinates> + <panel_attributes>halign=left +Data mining goal: + +Feature selection and classification project plan</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>UMLSpecialState</id> + <coordinates> + <x>30</x> + <y>170</y> + <w>20</w> + <h>20</h> + </coordinates> + <panel_attributes>type=initial</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>40</x> + <y>170</y> + <w>90</w> + <h>30</h> + </coordinates> + <panel_attributes>lt=<-</panel_attributes> + <additional_attributes>70.0;10.0;10.0;10.0</additional_attributes> + </element> + <element> + <id>UMLState</id> + <coordinates> + <x>110</x> + <y>150</y> + <w>200</w> + <h>60</h> + </coordinates> + <panel_attributes>Obtain interesting dataset +from the sql project plan</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>UMLState</id> + <coordinates> + <x>370</x> + <y>140</y> + <w>140</w> + <h>90</h> + </coordinates> + <panel_attributes>Prepare data +for modelling +with the +mulset R package</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>UMLSpecialState</id> + <coordinates> + <x>690</x> + <y>130</y> + <w>160</w> + <h>100</h> + </coordinates> + <panel_attributes>type=decision +All datasets used +for modelling?</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>300</x> + <y>170</y> + <w>90</w> + <h>30</h> + </coordinates> + <panel_attributes>lt=<-</panel_attributes> + <additional_attributes>70.0;10.0;10.0;10.0</additional_attributes> + </element> + <element> + <id>UMLState</id> + <coordinates> + <x>560</x> + <y>140</y> + <w>100</w> + <h>90</h> + </coordinates> + <panel_attributes>Multiple of +datasets are +generated</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>500</x> + <y>170</y> + <w>80</w> + <h>30</h> + </coordinates> + <panel_attributes>lt=<-</panel_attributes> + <additional_attributes>60.0;10.0;10.0;10.0</additional_attributes> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>650</x> + <y>170</y> + <w>60</w> + <h>30</h> + </coordinates> + <panel_attributes>lt=<-</panel_attributes> + <additional_attributes>40.0;10.0;10.0;10.0</additional_attributes> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>100</x> + <y>220</y> + <w>690</w> + <h>140</h> + </coordinates> + <panel_attributes>lt=<- +[NO]</panel_attributes> + <additional_attributes>50.0;120.0;10.0;120.0;10.0;30.0;670.0;30.0;670.0;10.0</additional_attributes> + </element> + <element> + <id>UMLState</id> + <coordinates> + <x>540</x> + <y>290</y> + <w>150</w> + <h>110</h> + </coordinates> + <panel_attributes>Train and validate +a selection of +classifiers on training +set, using +cross validation</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>UMLState</id> + <coordinates> + <x>720</x> + <y>300</y> + <w>150</w> + <h>80</h> + </coordinates> + <panel_attributes>Filter models with +bad +AUROC, specificity, +or sensitivity</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>680</x> + <y>330</y> + <w>60</w> + <h>30</h> + </coordinates> + <panel_attributes>lt=<-</panel_attributes> + <additional_attributes>40.0;10.0;10.0;10.0</additional_attributes> + </element> + <element> + <id>UMLState</id> + <coordinates> + <x>150</x> + <y>300</y> + <w>150</w> + <h>70</h> + </coordinates> + <panel_attributes>Split data in training +and test set</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>290</x> + <y>320</y> + <w>70</w> + <h>30</h> + </coordinates> + <panel_attributes>lt=<-</panel_attributes> + <additional_attributes>50.0;10.0;10.0;10.0</additional_attributes> + </element> + <element> + <id>UMLState</id> + <coordinates> + <x>340</x> + <y>310</y> + <w>150</w> + <h>60</h> + </coordinates> + <panel_attributes>Set random seed</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>480</x> + <y>330</y> + <w>80</w> + <h>30</h> + </coordinates> + <panel_attributes>lt=<-</panel_attributes> + <additional_attributes>60.0;10.0;10.0;10.0</additional_attributes> + </element> + <element> + <id>UMLState</id> + <coordinates> + <x>900</x> + <y>310</y> + <w>180</w> + <h>60</h> + </coordinates> + <panel_attributes>Compare models in +terms of +training and test AUROC</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>860</x> + <y>330</y> + <w>60</w> + <h>30</h> + </coordinates> + <panel_attributes>lt=<-</panel_attributes> + <additional_attributes>40.0;10.0;10.0;10.0</additional_attributes> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>760</x> + <y>220</y> + <w>250</w> + <h>110</h> + </coordinates> + <panel_attributes>lt=<-</panel_attributes> + <additional_attributes>10.0;10.0;230.0;10.0;230.0;90.0</additional_attributes> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>840</x> + <y>80</y> + <w>90</w> + <h>120</h> + </coordinates> + <panel_attributes>lt=<- +[YES]</panel_attributes> + <additional_attributes>70.0;10.0;10.0;100.0</additional_attributes> + </element> + <element> + <id>UMLState</id> + <coordinates> + <x>910</x> + <y>40</y> + <w>150</w> + <h>90</h> + </coordinates> + <panel_attributes>Compute +variable +importance +for models +using caret package</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>980</x> + <y>120</y> + <w>80</w> + <h>70</h> + </coordinates> + <panel_attributes>lt=<-</panel_attributes> + <additional_attributes>60.0;50.0;10.0;50.0;10.0;10.0</additional_attributes> + </element> + <element> + <id>UMLState</id> + <coordinates> + <x>1040</x> + <y>140</y> + <w>140</w> + <h>70</h> + </coordinates> + <panel_attributes>Perform +correlation analysis +and visualise +results</panel_attributes> + <additional_attributes/> + </element> + <element> + <id>Relation</id> + <coordinates> + <x>1100</x> + <y>200</y> + <w>80</w> + <h>80</h> + </coordinates> + <panel_attributes>lt=<-</panel_attributes> + <additional_attributes>60.0;60.0;10.0;60.0;10.0;10.0</additional_attributes> + </element> + <element> + <id>UMLSpecialState</id> + <coordinates> + <x>1160</x> + <y>250</y> + <w>20</w> + <h>20</h> + </coordinates> + <panel_attributes>type=final</panel_attributes> + <additional_attributes/> + </element> +</diagram> |
