FFT_Bayes
On average:
Tune for Opt: 21.6 seconds /per data set/per repeat
Tune for D2H: 26.4 seconds/per data set/per repeat
| data | Accuracy_build | Dist2Heaven_build | LOC_AUC_build | AVE-Build | Accuracy_eval | Dist2Heaven_eval | LOC_AUC_eval | AVE-Eval |
|---|---|---|---|---|---|---|---|---|
| @poi | 12.46 | 11.03 | 13.79 | 12.4 | 2.8 | 2.61 | 2.75 | 2.7 |
| @lucene | 9.76 | 10.23 | 12.94 | 11 | 2.52 | 2.48 | 2.64 | 2.5 |
| @Camel | 16.21 | 12.46 | 17.33 | 15.3 | 3.21 | 2.81 | 3.34 | 3.1 |
| @log4j | 9.21 | 10.15 | 10.02 | 9.8 | 2.64 | 2.38 | 2.47 | 2.5 |
| @xerces | 11.5 | 10.79 | 13.76 | 12 | 2.8 | 2.56 | 2.9 | 2.8 |
| @velocity | 10.48 | 10.1 | 11.19 | 10.6 | 2.45 | 2.37 | 2.49 | 2.4 |
| @Xalan | 13.9 | 12.76 | 21.03 | 15.9 | 3.1 | 2.95 | 3.48 | 3.2 |
| @ivy | 9.79 | 9.49 | 10.63 | 10 | 2.38 | 2.32 | 2.46 | 2.4 |
| @synapse | 10.17 | 9.4 | 9.57 | 9.7 | 2.37 | 2.28 | 2.33 | 2.3 |
| @Jedit | 11.08 | 11.2 | 10.92 | 11.1 | 2.73 | 2.75 | 2.63 | 2.7 |
| Average | 11.456 | 10.761 | 13.118 | 11.78 | 2.7 | 2.551 | 2.749 | 2.66 |
SVM and EM.# Expectation Maximization
EM = GaussianMixture(random_state=SEED, n_components=2, covariance_type='spherical')
......
if isGMM:
clf.means_ = np.array([X_train[y_train == i].mean(axis=0)
for i in xrange(clf.n_components)])
clf.fit(X_train)
I got one question, when run the FFT code.
Here, LOC_AUC is set as the criteria, where are the LOC_AUC scores of all learners on test data?
I see everything except for LOC_AUC in the "----- PERFORMANCES ON TEST DATA -----" section.
...................... LOC_AUC ......................
----- PERFORMANCES FOR ALL FFTs on Training Data -----
CLF PRE REC SPE FPR NPV ACC F_1 LOC_AUC
FFT(0) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(1) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(2) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(3) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(4) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(5) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(6) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(7) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(8) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(9) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(10) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(11) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(12) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(13) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(14) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
FFT(15) 0.000 0.000 0.000 1.000 0.000 0.000 0.000 -0.749
The best tree found on training data is: FFT(0)
| noc < 0.0 --> 'Bug!' False Alarm: 0, Hit: 0
| | noc < 0.0 --> 'Bug!' False Alarm: 0, Hit: 0
| | | noc < 0.0 --> 'Bug!' False Alarm: 0, Hit: 0
| | | | noc < 0.0 --> 'Bug!' False Alarm: 0, Hit: 0
| | | | noc < 0.0 --> 'Good' Correct Rej: 161, Miss: 281
----- CONFUSION MATRIX -----
TP FP TN FN
0 0 161 281
----- PERFORMANCES ON TEST DATA -----
CLF PRE REC SPE FPR NPV ACC F_1 Dist2Heaven
FFT(0) 0.000 0.000 1.000 0.000 0.364 0.364 0.000 0.707
SL 0.778 0.573 0.714 0.286 0.489 0.624 0.660 0.363
NB 0.871 0.192 0.950 0.050 0.403 0.468 0.315 0.572
EM 1.000 0.004 1.000 0.000 0.365 0.367 0.007 0.704
SMO 0.707 0.858 0.379 0.621 0.604 0.683 0.775 0.450
I noticed that you normalized dist2heaven to [0,1], recently . Does it mean that your results would be different from what we got say in December? and I also need to rerun my experiment to recalculate it?
Changes are made here
https://github.com/ai-se/FFT_Jack/blob/master/helpers.py#L60
Added state of the art learners[SL, NB, EM , SMO ].
(table9 of https://pdfs.semanticscholar.org/d0e1/5417371a0b863fc80d2af42a0c54ef65e374.pdf has four rows. picked one learner from each row.
Constructing FFT based on the distance to heaven, i.e. (0, 1) point in the ROC plot
Tried multiple dataset. data from https://zenodo.org/communities/seacraft/search?page=1&size=20&q=&keywords=ck. Some of the data sets Rahul mentions in fig5 of https://arxiv.org/pdf/1609.03614.pdf
training on: poi-1.5.csv, poi-2.0.csv, poi-2.5.csv
testing on: poi-3.0.csv
#### Performance for all FFT generated. ####
-------------------------------------------------------
ID MCU PRE REC SPEC ACC F1
0 1.5 0.3 0.9 0.1 0.9 0.4 0.5
1 1.6 0.3 1.0 0.1 0.9 0.4 0.4
2 1.7 0.3 0.8 0.3 0.7 0.5 0.5
3 1.6 0.3 0.9 0.3 0.7 0.4 0.4
4 1.6 0.3 0.8 0.4 0.6 0.5 0.5
5 1.6 0.3 0.8 0.3 0.7 0.5 0.5
6 1.7 0.3 0.5 0.5 0.5 0.5 0.4
7 1.6 0.3 0.6 0.5 0.5 0.5 0.4
8 1.3 0.4 0.5 0.7 0.3 0.6 0.4
9 1.3 0.4 0.5 0.7 0.3 0.6 0.4
10 1.3 0.4 0.4 0.8 0.2 0.7 0.4
11 1.4 0.4 0.4 0.8 0.2 0.7 0.4
12 1.4 0.5 0.3 0.9 0.1 0.7 0.3
13 1.3 0.4 0.2 0.9 0.1 0.7 0.3
14 1.3 0.5 0.1 1.0 0.0 0.7 0.2
15 1.4 0.4 0.1 0.9 0.1 0.7 0.2
-------------------------------------------------------
The selected FFT id is :8
The selected FFT constructed as the following tree:
lcom < 36.0 --> 'Good' Correct Rej: 304, Miss: 85
| rfc > 28.5 --> 'Bug!' False Alarm: 88, Hit: 61
| | lcom < 46.0 --> 'Bug!' False Alarm: 41, Hit: 29
| | | avg_cc < 0.8333 --> 'Bug!' False Alarm: 21, Hit: 10
| | | avg_cc > 0.8333 --> 'Good' Correct Rej: 40, Miss: 10
#### Performance of the best FFT ####
=======================================
TP FP TN FN
200 300 688 190
MCU PRE REC SPEC FPR ACC F1
2.6 0.4 0.5 0.7 0.3 0.6 0.4
#### Performance of the State-Of-The-Art Models ####
=======================================
SL 0.6 0.1 0.9 0.1 0.4 0.2
NB 0.8 0.8 0.7 0.3 0.8 0.8
EM 0.0 0.0 1.0 0.0 0.4 0.0
SMO 0.7 0.8 0.5 0.5 0.7 0.8
training on: lucene-2.0.csv, lucene-2.2.csv
testing on: lucene-2.4.csv
#### Performance for all FFT generated. ####
-------------------------------------------------------
ID MCU PRE REC SPEC ACC F1
0 1.5 0.4 0.9 0.2 0.8 0.4 0.5
1 1.5 0.3 1.0 0.1 0.9 0.4 0.5
2 1.4 0.4 0.9 0.3 0.7 0.5 0.5
3 1.5 0.4 0.9 0.3 0.7 0.5 0.5
4 1.3 0.4 0.8 0.4 0.6 0.5 0.5
5 1.3 0.4 0.8 0.4 0.6 0.5 0.5
6 1.3 0.5 0.6 0.6 0.4 0.6 0.5
7 1.3 0.4 0.7 0.6 0.4 0.6 0.5
8 1.3 0.5 0.5 0.7 0.3 0.6 0.5
9 1.2 0.4 0.5 0.7 0.3 0.6 0.5
10 1.2 0.5 0.4 0.8 0.2 0.7 0.4
11 1.3 0.4 0.4 0.8 0.2 0.6 0.4
12 1.2 0.7 0.3 0.9 0.1 0.7 0.4
13 1.2 0.5 0.2 0.9 0.1 0.7 0.3
14 1.2 0.8 0.1 1.0 0.0 0.7 0.2
15 1.2 0.5 0.1 1.0 0.0 0.7 0.1
-------------------------------------------------------
The selected FFT id is :7
The selected FFT constructed as the following tree:
dam > 0.6443243245 --> 'Bug!' False Alarm: 84, Hit: 58
| cbo < 6.0 --> 'Good' Correct Rej: 73, Miss: 17
| | wmc < 6.0 --> 'Good' Correct Rej: 33, Miss: 11
| | | max_cc < 2.0 --> 'Good' Correct Rej: 14, Miss: 3
| | | max_cc > 2.0 --> 'Bug!' False Alarm: 14, Hit: 3
#### Performance of the best FFT ####
=======================================
TP FP TN FN
122 196 240 62
MCU PRE REC SPEC FPR ACC F1
2.7 0.4 0.7 0.6 0.4 0.6 0.5
#### Performance of the State-Of-The-Art Models ####
=======================================
SL 0.8 0.3 0.9 0.1 0.6 0.5
NB 0.7 0.7 0.6 0.4 0.7 0.7
EM 0.0 0.0 1.0 0.0 0.4 0.0
SMO 0.7 0.9 0.4 0.6 0.7 0.8
training on: ivy-1.1.csv, ivy-1.4.csv
testing on: ivy-2.0.csv
#### Performance for all FFT generated. ####
-------------------------------------------------------
ID MCU PRE REC SPEC ACC F1
0 1.7 0.1 0.9 0.1 0.9 0.2 0.2
1 1.9 0.1 1.0 0.1 0.9 0.2 0.2
2 1.8 0.1 0.9 0.3 0.7 0.3 0.2
3 1.7 0.1 0.9 0.2 0.8 0.3 0.2
4 1.8 0.2 0.8 0.4 0.6 0.4 0.3
5 1.8 0.1 0.9 0.3 0.7 0.4 0.2
6 1.8 0.2 0.7 0.5 0.5 0.5 0.3
7 1.7 0.1 0.7 0.5 0.5 0.5 0.2
8 1.6 0.2 0.6 0.7 0.3 0.7 0.3
9 1.7 0.2 0.6 0.6 0.4 0.6 0.2
10 1.7 0.2 0.4 0.8 0.2 0.7 0.3
11 1.9 0.2 0.5 0.7 0.3 0.7 0.3
12 1.6 0.3 0.4 0.9 0.1 0.8 0.3
13 1.7 0.2 0.3 0.8 0.2 0.8 0.2
14 1.6 0.5 0.2 1.0 0.0 0.9 0.3
15 1.6 0.1 0.1 0.9 0.1 0.9 0.1
-------------------------------------------------------
The selected FFT id is :8
The selected FFT constructed as the following tree:
lcom < 9.5 --> 'Good' Correct Rej: 151, Miss: 15
| moa > 0.0 --> 'Bug!' False Alarm: 42, Hit: 13
| | ca > 2.0 --> 'Bug!' False Alarm: 31, Hit: 6
| | | ca > 1.0 --> 'Bug!' False Alarm: 13, Hit: 2
| | | ca < 1.0 --> 'Good' Correct Rej: 28, Miss: 2
#### Performance of the best FFT ####
=======================================
TP FP TN FN
42 172 358 34
MCU PRE REC SPEC FPR ACC F1
3.2 0.2 0.6 0.7 0.3 0.7 0.3
#### Performance of the State-Of-The-Art Models ####
=======================================
SL 0.4 0.3 0.9 0.1 0.9 0.3
NB 0.2 0.8 0.6 0.4 0.7 0.3
EM 0.0 0.0 1.0 0.0 0.9 0.0
SMO 0.3 0.2 0.9 0.1 0.8 0.2
training on: synapse-1.0.csv, synapse-1.1.csv
testing on: synapse-1.2.csv
#### Performance for all FFT generated. ####
-------------------------------------------------------
ID MCU PRE REC SPEC ACC F1
0 2.0 0.2 1.0 0.1 0.9 0.3 0.3
1 1.9 0.2 1.0 0.1 0.9 0.2 0.3
2 1.9 0.2 0.9 0.3 0.7 0.4 0.3
3 2.0 0.2 1.0 0.3 0.7 0.4 0.3
4 1.9 0.2 0.9 0.4 0.6 0.4 0.3
5 1.9 0.2 0.9 0.4 0.6 0.4 0.3
6 2.1 0.2 0.7 0.5 0.5 0.6 0.3
7 2.1 0.2 0.9 0.4 0.6 0.5 0.3
8 1.8 0.3 0.6 0.7 0.3 0.7 0.4
9 1.8 0.2 0.7 0.6 0.4 0.6 0.3
10 1.8 0.3 0.5 0.8 0.2 0.8 0.4
11 1.8 0.3 0.5 0.8 0.2 0.7 0.4
12 1.7 0.4 0.4 0.9 0.1 0.8 0.4
13 1.8 0.3 0.4 0.8 0.2 0.8 0.3
14 1.7 0.6 0.2 1.0 0.0 0.8 0.3
15 1.8 0.3 0.1 0.9 0.1 0.8 0.2
-------------------------------------------------------
The selected FFT id is :8
The selected FFT constructed as the following tree:
rfc < 25.0 --> 'Good' Correct Rej: 168, Miss: 17
| lcom > 13.0 --> 'Bug!' False Alarm: 46, Hit: 23
| | amc > 40.0 --> 'Bug!' False Alarm: 39, Hit: 9
| | | wmc < 6.0 --> 'Bug!' False Alarm: 13, Hit: 3
| | | wmc > 6.0 --> 'Good' Correct Rej: 30, Miss: 4
#### Performance of the best FFT ####
=======================================
TP FP TN FN
70 196 396 42
MCU PRE REC SPEC FPR ACC F1
3.5 0.3 0.6 0.7 0.3 0.7 0.4
#### Performance of the State-Of-The-Art Models ####
=======================================
SL 0.9 0.2 1.0 0.0 0.7 0.4
NB 0.4 0.8 0.4 0.6 0.6 0.5
EM 0.0 0.0 1.0 0.0 0.7 0.0
SMO 0.5 0.7 0.7 0.3 0.7 0.6
training on: velocity-1.4.csv, velocity-1.5.csv
testing on: velocity-1.6.csv
#### Performance for all FFT generated. ####
-------------------------------------------------------
ID MCU PRE REC SPEC ACC F1
0 1.4 0.6 0.9 0.2 0.8 0.6 0.8
1 1.5 0.6 1.0 0.2 0.8 0.6 0.7
2 1.4 0.7 0.9 0.4 0.6 0.7 0.8
3 1.5 0.6 0.9 0.3 0.7 0.7 0.8
4 1.5 0.7 0.8 0.5 0.5 0.6 0.7
5 1.3 0.7 0.8 0.4 0.6 0.6 0.7
6 1.3 0.7 0.6 0.6 0.4 0.6 0.7
7 1.4 0.7 0.7 0.6 0.4 0.6 0.7
8 1.5 0.7 0.6 0.6 0.4 0.6 0.6
9 1.5 0.7 0.6 0.6 0.4 0.6 0.6
10 1.5 0.8 0.4 0.8 0.2 0.6 0.6
11 1.5 0.7 0.4 0.8 0.2 0.6 0.5
12 1.4 0.8 0.3 0.9 0.1 0.5 0.4
13 1.5 0.7 0.3 0.8 0.2 0.6 0.5
14 1.6 1.0 0.1 1.0 0.0 0.5 0.2
15 1.5 0.7 0.1 0.9 0.1 0.5 0.2
-------------------------------------------------------
The selected FFT id is :7
The selected FFT constructed as the following tree:
ca > 2.0 --> 'Bug!' False Alarm: 45, Hit: 94
| ca < 1.0 --> 'Good' Correct Rej: 42, Miss: 24
| | lcom > 1.0 --> 'Good' Correct Rej: 19, Miss: 21
| | | cbo < 3.0 --> 'Good' Correct Rej: 11, Miss: 12
| | | cbo > 3.0 --> 'Bug!' False Alarm: 11, Hit: 16
#### Performance of the best FFT ####
=======================================
TP FP TN FN
220 112 144 114
MCU PRE REC SPEC FPR ACC F1
2.9 0.7 0.7 0.6 0.4 0.6 0.7
#### Performance of the State-Of-The-Art Models ####
=======================================
SL 0.4 0.9 0.2 0.8 0.4 0.5
NB 0.3 1.0 0.0 1.0 0.4 0.5
EM 0.0 0.0 1.0 0.0 0.7 0.0
SMO 0.3 0.3 0.7 0.3 0.5 0.3
First of all, I find the performance of the SOA learners are not stable for each run.
To solve the above issue, I fixed the seed to be 666.
# simple logistic
SL = LogisticRegression(random_state=SEED)
# Naive Bayes
NB = GaussianNB()
# Expectation Maximization
EM = GaussianMixture(random_state=SEED, init_params='kmeans', n_components=2)
# Support Vector Machines
SMO = LinearSVC(random_state=SEED)
Note that the SOA learners are same when data set is fixed.
@timm When we build FFT, If we split on the median of the training data and choose the cue/feature by finding the one with highest goal_chase at test data, then are we cheating because other learners won't see the test data.
python fft.py
version wmc dit noc cbo rfc \
count 352.0 352.000000 352.000000 352.000000 352.000000 352.000000
mean 2.0 11.284091 1.792614 0.369318 13.232955 34.036932
std 0.0 15.148232 1.244773 1.318279 16.571085 44.679566
min 2.0 1.000000 1.000000 0.000000 1.000000 1.000000
25% 2.0 3.000000 1.000000 0.000000 5.000000 6.000000
50% 2.0 6.000000 1.000000 0.000000 8.000000 19.000000
75% 2.0 13.000000 2.000000 0.000000 16.000000 40.000000
max 2.0 157.000000 6.000000 17.000000 150.000000 312.000000
lcom ca ce npm ... \
count 352.000000 352.000000 352.000000 352.000000 ...
mean 131.579545 6.880682 5.164773 9.036932 ...
std 712.192029 13.938917 8.931273 12.636099 ...
min 0.000000 0.000000 0.000000 0.000000 ...
25% 0.000000 1.000000 1.000000 2.000000 ...
50% 6.000000 3.000000 2.000000 5.000000 ...
75% 45.250000 6.000000 5.000000 11.000000 ...
max 11794.000000 147.000000 75.000000 142.000000 ...
dam moa mfa cam ic cbm \
count 352.000000 352.000000 352.000000 352.000000 352.000000 352.000000
mean 0.616224 0.715909 0.290908 0.490831 0.357955 0.636364
std 0.459940 1.441737 0.385164 0.254585 0.733601 1.781077
min 0.000000 0.000000 0.000000 0.055223 0.000000 0.000000
25% 0.000000 0.000000 0.000000 0.299074 0.000000 0.000000
50% 1.000000 0.000000 0.000000 0.444444 0.000000 0.000000
75% 1.000000 1.000000 0.670918 0.666667 0.250000 0.250000
max 1.000000 12.000000 1.000000 1.000000 4.000000 18.000000
amc max_cc avg_cc bug
count 352.000000 352.000000 352.000000 352.000000
mean 18.489722 3.187500 1.214294 0.159091
std 27.032755 3.848123 0.816136 0.498119
min 0.000000 0.000000 0.000000 0.000000
25% 4.666667 1.000000 0.800000 0.000000
50% 10.388199 2.000000 1.000000 0.000000
75% 21.434615 4.000000 1.446925 0.000000
max 203.500000 29.000000 6.500000 3.000000
[8 rows x 22 columns]
max_level = 4,
all trees generated = 16
-------------------------------------------------------
ID MCU PRE REC SPEC ACC F1
0 1.3 0.1 1.0 0.2 0.3 0.2
1 1.3 0.1 1.0 0.1 0.2 0.2
2 1.3 0.1 1.0 0.3 0.4 0.3
3 1.3 0.1 1.0 0.2 0.3 0.2
4 1.1 0.2 0.9 0.4 0.5 0.3
5 1.0 0.2 1.0 0.3 0.4 0.3
6 1.1 0.2 0.8 0.5 0.6 0.3
7 1.0 0.2 1.0 0.4 0.5 0.3
8 1.1 0.2 0.8 0.6 0.7 0.4
9 1.1 0.2 0.9 0.6 0.6 0.3
10 1.1 0.3 0.7 0.8 0.8 0.4
11 1.1 0.2 0.7 0.8 0.8 0.4
12 1.1 0.4 0.4 0.9 0.8 0.4
13 1.1 0.3 0.4 0.9 0.8 0.3
14 1.1 0.8 0.2 1.0 0.9 0.3
15 1.1 0.2 0.1 0.9 0.9 0.1
-------------------------------------------------------
The selected tree id is :14
wmc < 7.0 --> 'Good' Correct Rej: 99, Miss: 3
| cbo < 12.0 --> 'Good' Correct Rej: 46, Miss: 6
| | wmc < 15.0 --> 'Good' Correct Rej: 22, Miss: 4
| | | moa > 1.0 --> 'Bug!' False Alarm: 2, Hit: 6
| | | moa < 1.0 --> 'Good' Correct Rej: 7, Miss: 8
=======================================
TP FP TN FN
12 4 348 42
MCU PRE REC SPEC ACC F1
2.1 0.8 0.2 1.0 0.9 0.3
=======================================
max_level = 4,
all trees generated = 16
-------------------------------------------------------
ID MCU PRE REC SPEC ACC F1
0 1.0 0.1 1.0 0.1 0.2 0.2
1 1.0 0.1 1.0 0.0 0.1 0.1
2 1.0 0.1 1.0 0.3 0.3 0.2
3 1.0 0.1 1.0 0.2 0.2 0.2
4 1.3 0.1 1.0 0.3 0.3 0.2
5 1.3 0.1 1.0 0.3 0.3 0.2
6 1.3 0.1 0.9 0.5 0.5 0.2
7 1.2 0.1 1.0 0.4 0.4 0.2
8 1.9 0.1 1.0 0.2 0.3 0.2
9 1.9 0.1 1.0 0.1 0.2 0.1
10 1.7 0.1 0.9 0.4 0.4 0.2
11 1.6 0.1 1.0 0.3 0.4 0.2
12 2.3 0.1 0.9 0.4 0.4 0.2
13 1.9 0.1 1.0 0.2 0.2 0.2
14 2.4 0.1 0.5 0.5 0.5 0.2
15 1.4 0.1 1.0 0.0 0.1 0.1
-------------------------------------------------------
The selected tree id is :0
rfc > 19.0 --> 'Bug!' False Alarm: 88, Hit: 14
| wmc > 3.0 --> 'Bug!' False Alarm: 46, Hit: 2
| | wmc > 2.0 --> 'Bug!' False Alarm: 28, Hit: 0
| | | wmc > 2.0 --> 'Bug!' False Alarm: 0, Hit: 0
| | | wmc < 2.0 --> 'Good' Correct Rej: 20, Miss: 0
=======================================
TP FP TN FN
32 324 40 0
MCU PRE REC SPEC ACC F1
2.1 0.1 1.0 0.1 0.2 0.2
=======================================
max_level = 4,
all trees generated = 16
-------------------------------------------------------
ID MCU PRE REC SPEC ACC F1
0 1.4 0.0 0.0 1.0 0.9 0.0
1 2.4 0.0 0.5 0.5 0.5 0.0
2 1.6 0.0 0.0 1.0 0.9 0.0
3 2.1 0.1 0.5 0.8 0.7 0.2
4 1.3 0.0 0.0 1.0 0.9 0.0
5 1.8 0.1 0.5 0.8 0.7 0.2
6 1.4 0.0 0.0 1.0 0.9 0.0
7 1.6 0.2 0.3 0.9 0.8 0.3
8 1.0 0.0 0.0 1.0 0.9 0.0
9 1.5 0.1 0.5 0.8 0.7 0.2
10 1.1 0.0 0.0 1.0 0.9 0.0
11 1.3 0.2 0.3 0.9 0.8 0.3
12 1.0 0.0 0.0 1.0 0.9 0.0
13 1.2 0.2 0.3 0.9 0.8 0.3
14 1.0 0.0 0.0 1.0 0.9 0.0
15 1.1 0.3 0.2 1.0 0.9 0.2
-------------------------------------------------------
The selected tree id is :0
dit < 1.0 --> 'Bug!' False Alarm: 0, Hit: 0
| dit < 1.0 --> 'Bug!' False Alarm: 0, Hit: 0
| | dit < 1.0 --> 'Bug!' False Alarm: 0, Hit: 0
| | | dit < 1.0 --> 'Bug!' False Alarm: 0, Hit: 0
| | | dit > 1.0 --> 'Good' Correct Rej: 109, Miss: 15
=======================================
TP FP TN FN
0 0 218 30
MCU PRE REC SPEC ACC F1
2.8 0.0 0.0 1.0 0.9 0.0
=======================================
max_level = 4,
all trees generated = 16
-------------------------------------------------------
ID MCU PRE REC SPEC ACC F1
0 1.1 0.1 1.0 0.1 0.2 0.2
1 1.1 0.1 1.0 0.0 0.1 0.2
2 1.1 0.1 1.0 0.3 0.4 0.2
3 1.1 0.1 1.0 0.2 0.3 0.2
4 1.3 0.1 1.0 0.3 0.4 0.2
5 1.3 0.1 1.0 0.3 0.3 0.2
6 1.3 0.2 0.9 0.5 0.5 0.3
7 1.4 0.1 1.0 0.4 0.4 0.2
8 1.2 0.2 0.8 0.6 0.7 0.3
9 1.2 0.2 0.8 0.6 0.6 0.3
10 1.2 0.3 0.6 0.8 0.8 0.4
11 1.1 0.2 0.7 0.8 0.8 0.3
12 1.1 0.3 0.5 0.9 0.8 0.4
13 1.1 0.3 0.5 0.9 0.8 0.3
14 1.1 0.5 0.3 1.0 0.9 0.4
15 1.2 0.2 0.2 0.9 0.9 0.2
-------------------------------------------------------
The selected tree id is :10
wmc < 6.5 --> 'Good' Correct Rej: 108, Miss: 3
| npm > 12.0 --> 'Bug!' False Alarm: 31, Hit: 10
| | lcom < 28.0 --> 'Good' Correct Rej: 29, Miss: 1
| | | wmc < 12.0 --> 'Bug!' False Alarm: 10, Hit: 4
| | | wmc > 12.0 --> 'Good' Correct Rej: 14, Miss: 5
=======================================
TP FP TN FN
28 82 302 18
MCU PRE REC SPEC ACC F1
2.4 0.3 0.6 0.8 0.8 0.4
=======================================
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.