Skip to content

Commit

Permalink
perf(dataset): removed a fair amount of null instances (#27)
Browse files Browse the repository at this point in the history 
* perf(dataset): removed a fair amount of `null` instances

* chore(labels): more clean-up

* chore(labels): removed/edited a few instances

* chore(labels): added more data

* fix(index): category partitions no longer auto-saved

The category partitions used to be saved everytime
`Learner.getStats()`/`Learner.getCategoryPartition()` were called which lead in duplicated files and
an undesirable side-effect.

* chore(playground): update

Updated the files after a saved dry run
  • Loading branch information
@Berkmann18
Berkmann18 authored Aug 26, 2019
1 parent 35464db commit 3133582
Show file tree
Hide file tree
Showing 10 changed files with 910 additions and 1,384 deletions.
158 changes: 79 additions & 79 deletions playground/categoryPartitions.json
View file
Original file line number Diff line number Diff line change
@@ -1,63 +1,63 @@
{
"blog": {
"overall": 3,
"test": 1,
"test": 0,
"validation": 0,
"train": 2
"train": 3
},
"bug": {
"overall": 20,
"test": 3,
"validation": 1,
"train": 16
"validation": 2,
"train": 15
},
"business": {
"overall": 3,
"test": 1,
"test": 0,
"validation": 0,
"train": 2
"train": 3
},
"code": {
"overall": 57,
"test": 6,
"validation": 8,
"train": 43
"overall": 58,
"test": 10,
"validation": 6,
"train": 42
},
"content": {
"overall": 2,
"test": 1,
"validation": 0,
"train": 1
"overall": 4,
"test": 0,
"validation": 1,
"train": 3
},
"design": {
"overall": 11,
"test": 0,
"validation": 2,
"train": 9
"overall": 12,
"test": 2,
"validation": 3,
"train": 7
},
"doc": {
"overall": 23,
"test": 4,
"validation": 4,
"train": 15
"validation": 1,
"train": 18
},
"eventOrganizing": {
"overall": 4,
"overall": 5,
"test": 0,
"validation": 1,
"train": 3
"validation": 0,
"train": 5
},
"example": {
"overall": 2,
"test": 1,
"validation": 1,
"train": 0
"overall": 3,
"test": 0,
"validation": 0,
"train": 3
},
"financial": {
"overall": 4,
"test": 1,
"validation": 1,
"train": 2
"overall": 6,
"test": 2,
"validation": 0,
"train": 4
},
"fundingFinding": {
"overall": 2,
Expand All @@ -66,105 +66,105 @@
"train": 2
},
"ideas": {
"overall": 26,
"overall": 27,
"test": 1,
"validation": 4,
"train": 21
"validation": 7,
"train": 19
},
"infra": {
"overall": 14,
"test": 6,
"validation": 2,
"train": 6
"overall": 15,
"test": 1,
"validation": 4,
"train": 10
},
"maintenance": {
"overall": 30,
"test": 4,
"validation": 2,
"train": 24
"test": 7,
"validation": 4,
"train": 19
},
"null": {
"overall": 197,
"test": 27,
"validation": 34,
"train": 136
"overall": 93,
"test": 16,
"validation": 12,
"train": 65
},
"platform": {
"overall": 23,
"test": 7,
"overall": 26,
"test": 5,
"validation": 5,
"train": 11
"train": 16
},
"plugin": {
"overall": 4,
"test": 1,
"validation": 0,
"overall": 6,
"test": 2,
"validation": 1,
"train": 3
},
"projectManagement": {
"overall": 6,
"overall": 9,
"test": 0,
"validation": 1,
"train": 5
"validation": 3,
"train": 6
},
"question": {
"overall": 5,
"overall": 6,
"test": 0,
"validation": 1,
"train": 4
"validation": 0,
"train": 6
},
"review": {
"overall": 3,
"test": 0,
"validation": 1,
"train": 2
"validation": 2,
"train": 1
},
"security": {
"overall": 10,
"test": 2,
"validation": 1,
"train": 7
"test": 4,
"validation": 2,
"train": 4
},
"talk": {
"overall": 2,
"overall": 3,
"test": 0,
"validation": 0,
"train": 2
"train": 3
},
"test": {
"overall": 12,
"test": 3,
"validation": 0,
"test": 1,
"validation": 2,
"train": 9
},
"tool": {
"overall": 13,
"test": 2,
"test": 1,
"validation": 3,
"train": 8
"train": 9
},
"translation": {
"overall": 1,
"test": 1,
"overall": 2,
"test": 0,
"validation": 0,
"train": 0
"train": 2
},
"tutorial": {
"overall": 3,
"test": 1,
"overall": 5,
"test": 0,
"validation": 1,
"train": 1
"train": 4
},
"userTesting": {
"overall": 3,
"test": 0,
"validation": 0,
"train": 3
"validation": 1,
"train": 2
},
"video": {
"overall": 3,
"test": 0,
"validation": 0,
"train": 3
"test": 1,
"validation": 1,
"train": 1
}
}
42 changes: 21 additions & 21 deletions playground/confusionMatrix.txt
View file
Original file line number Diff line number Diff line change
@@ -1,30 +1,30 @@
Actual \ Predicted blog bug business code content design doc eventOrganizing example financial fundingFinding ideas infra maintenance null platform plugin projectManagement question review security talk test tool translation tutorial userTesting video
-------------------- ---- ---- -------- ---- ------- ------ ---- --------------- ------- --------- -------------- ----- ----- ----------- ----- -------- ------ ----------------- -------- ------ -------- ---- ---- ---- ----------- -------- ----------- -----
blog 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
bug 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 2.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
business 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
code 0.00 0.00 0.00 2.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 4.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
content 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
design 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
doc 0.00 0.00 0.00 0.00 0.00 0.00 3.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
blog 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
bug 0.00 2.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
business 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
code 0.00 0.00 0.00 4.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 6.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
content 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
design 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
doc 0.00 0.00 0.00 0.00 0.00 0.00 2.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 2.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
eventOrganizing 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
example 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
financial 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
example 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
financial 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 2.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
fundingFinding 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
ideas 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
infra 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 3.00 0.00 3.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
maintenance 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 2.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
null 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 25.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00
platform 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 6.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
plugin 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
ideas 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
infra 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
maintenance 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 4.00 3.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
null 0.00 0.00 0.00 2.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 14.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
platform 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 3.00 2.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
plugin 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 2.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
projectManagement 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
question 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
review 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
security 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
security 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 4.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
talk 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
test 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 2.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00
tool 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00
translation 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
tutorial 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
test 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00
tool 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
translation 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
tutorial 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
userTesting 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
video 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
video 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 1.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Loading

0 comments on commit 3133582

Please sign in to comment.