// multi-utility computation suite · offline · instant · precise
┌──────────────────────────┐
│ [c] calcalyst_ │
│ computation suite │
└──────────────────────────┘
// select a module to initialize
/ search↵ open firstesc close
// adsenseEMPTY_LEADER_SLOT728×90
// adsenseMOBILE_ANCHOR_SLOT320×50
// keyboard_shortcuts
/focus search
↑↓navigate module list
Enter
open first result from search
open highlighted
compute when module is open
compute when focused in a field
Escclose module · clear selection
⌫
sci.ML-classification-metrics Calculator
Calculates classification metrics: precision = TP/(TP+FP), recall = TP/(TP+FN), F1 = 2×P×R/(P+R), and accuracy from a confusion matrix. Macro-F1 averages F1 equally across classes; weighted-F1 weights by support — imbalanced datasets favour weighted-F1 to avoid penalising dominant classes.
Inputs
Tp
Reference formula or conversion factor shown for context.
Fp
Reference formula or conversion factor shown for context.
Fn
Reference formula or conversion factor shown for context.
Tn
Reference formula or conversion factor shown for context.
Results
F1 score
A numerical rating from the scoring model in use.
precision (PPV)
Sample size or count used in the calculation.
recall (sensitivity)
Sample size or count used in the calculation.
accuracy
The fraction of predictions or measurements that are correct. High accuracy is only meaningful when the class distribution is balanced.
Matthews correlation coefficient MCC
Pearson's r — linear relationship strength and direction. +1: perfect positive. 0: no linear relationship. −1: perfect negative. Rule of thumb: |r| below 0.3 = weak, 0.3–0.7 = moderate, above 0.7 = strong. Correlation does not imply causation.
MCC interpretation
Qualitative summary of what the computed numbers mean in practical terms.