PyCM Report

Dataset Type :

Note 1 : Recommended statistics for this type of classification highlighted in aqua

Note 2 : The recommendation system assumes the input is the result of classification over the entire dataset, not just a subset. If the confusion matrix is based on test data classification, the recommendation may not be valid.

Confusion Matrix :

Actual Predict
0 1 2
0 13 0 0
1 0 15 1
2 0 1 8

Overall Statistics :

95% CI (0.87637,1.01837)
ACC Macro 0.96491
ARI 0.85267
AUNP 0.96003
AUNU 0.95774
Bangdiwala B 0.90514
Bennett S 0.92105
CBA 0.94213
CSI 0.88426
Chi-Squared 63.95091
Chi-Squared DF 4
Conditional Entropy 0.26121
Cramer V 0.91731
Cross Entropy 1.54701
F1 Macro 0.94213
F1 Micro 0.94737
FNR Macro 0.05787
FNR Micro 0.05263
FPR Macro 0.02665
FPR Micro 0.02632
Gwet AC1 0.92205
Hamming Loss 0.05263
Joint Entropy 1.80822
KL Divergence 0.0
Kappa 0.91898
Kappa 95% CI (0.80968,1.02827)
Kappa No Prevalence 0.89474
Kappa Standard Error 0.05576
Kappa Unbiased 0.91898
Krippendorff Alpha 0.92004
Lambda A 0.90909
Lambda B 0.90909
Mutual Information 1.2858
NIR 0.42105
NPV Macro 0.97335
NPV Micro 0.97368
Overall ACC 0.94737
Overall CEN 0.12066
Overall J (2.68235,0.89412)
Overall MCC 0.91898
Overall MCEN 0.18523
Overall RACC 0.35042
Overall RACCU 0.35042
P-Value 0.0
PPV Macro 0.94213
PPV Micro 0.94737
Pearson C 0.792
Phi-Squared 1.68292
RCI 0.83115
RR 12.66667
Reference Entropy 1.54701
Response Entropy 1.54701
SOA1(Landis & Koch) Almost Perfect
SOA2(Fleiss) Excellent
SOA3(Altman) Very Good
SOA4(Cicchetti) Excellent
SOA5(Cramer) Very Strong
SOA6(Matthews) Very Strong
SOA7(Lambda A) Very Strong
SOA8(Lambda B) Very Strong
SOA9(Krippendorff Alpha) High
SOA10(Pearson C) Strong
Scott PI 0.91898
Standard Error 0.03622
TNR Macro 0.97335
TNR Micro 0.97368
TPR Macro 0.94213
TPR Micro 0.94737
Zero-one Loss 2

Class Statistics :

Class 0 1 2 Description
ACC 1.0 0.94737 0.94737 Accuracy
AGF 1.0 0.94598 0.92641 Adjusted F-score
AGM 1.0 0.94912 0.94334 Adjusted geometric mean
AM 0 0 0 Difference between automatic and manual classification
AUC 1.0 0.94602 0.9272 Area under the ROC curve
AUCI Excellent Excellent Excellent AUC value interpretation
AUPR 1.0 0.9375 0.88889 Area under the PR curve
BB 1.0 0.9375 0.88889 Braun-Blanquet similarity
BCD 0.0 0.0 0.0 Bray-Curtis dissimilarity
BM 1.0 0.89205 0.85441 Informedness or bookmaker informedness
CEN 0 0.15625 0.23166 Confusion entropy
DOR None 315.0 224.0 Diagnostic odds ratio
DP None 1.37739 1.29576 Discriminant power
DPI None Limited Limited Discriminant power interpretation
ERR 0.0 0.05263 0.05263 Error rate
F0.5 1.0 0.9375 0.88889 F0.5 score
F1 1.0 0.9375 0.88889 F1 score - harmonic mean of precision and sensitivity
F2 1.0 0.9375 0.88889 F2 score
FDR 0.0 0.0625 0.11111 False discovery rate
FN 0 1 1 False negative/miss/type 2 error
FNR 0.0 0.0625 0.11111 Miss rate or false negative rate
FOR 0.0 0.04545 0.03448 False omission rate
FP 0 1 1 False positive/type 1 error/false alarm
FPR 0.0 0.04545 0.03448 Fall-out or false positive rate
G 1.0 0.9375 0.88889 G-measure geometric mean of precision and sensitivity
GI 1.0 0.89205 0.85441 Gini index
GM 1.0 0.94598 0.92641 G-mean geometric mean of specificity and sensitivity
HD 0 2 2 Hamming distance
IBA 1.0 0.87963 0.79247 Index of balanced accuracy
ICSI 1.0 0.875 0.77778 Individual classification success index
IS 1.54749 1.15482 1.90808 Information score
J 1.0 0.88235 0.8 Jaccard index
LS 2.92308 2.22656 3.75309 Lift score
MCC 1.0 0.89205 0.85441 Matthews correlation coefficient
MCCI Very Strong Strong Strong Matthews correlation coefficient interpretation
MCEN 0 0.24044 0.33219 Modified confusion entropy
MK 1.0 0.89205 0.85441 Markedness
N 25 22 29 Condition negative
NLR 0.0 0.06548 0.11508 Negative likelihood ratio
NLRI Good Good Fair Negative likelihood ratio interpretation
NPV 1.0 0.95455 0.96552 Negative predictive value
OC 1.0 0.9375 0.88889 Overlap coefficient
OOC 1.0 0.9375 0.88889 Otsuka-Ochiai coefficient
OP 1.0 0.93836 0.90605 Optimized precision
P 13 16 9 Condition positive or support
PLR None 20.625 25.77778 Positive likelihood ratio
PLRI None Good Good Positive likelihood ratio interpretation
POP 38 38 38 Population
PPV 1.0 0.9375 0.88889 Precision or positive predictive value
PR 0.34211 0.42105 0.23684 Positive rate
PRE 0.34211 0.42105 0.23684 Prevalence
Q None 0.99367 0.99111 Yule Q - coefficient of colligation
QI None Strong Strong Yule Q interpretation
RACC 0.11704 0.17729 0.05609 Random accuracy
RACCU 0.11704 0.17729 0.05609 Random accuracy unbiased
TN 25 21 28 True negative/correct rejection
TNR 1.0 0.95455 0.96552 Specificity or true negative rate
TON 25 22 29 Test outcome negative
TOP 13 16 9 Test outcome positive
TOPR 0.34211 0.42105 0.23684 Test outcome positive rate
TP 13 15 8 True positive/hit
TPR 1.0 0.9375 0.88889 Sensitivity, recall, hit rate, or true positive rate
Y 1.0 0.89205 0.85441 Youden index
dInd 0.0 0.07728 0.11634 Distance index
sInd 1.0 0.94535 0.91774 Similarity index

Generated By PyCM Version 4.6