Softanza
StartFrançais
Softanza
StartFrançais
Reference · stzLogisticRegression

TrainingAccuracy()

Needing standardised features is the normal requirement for stochastic gradient descent, not a defect here -- but nothing surfaced the failure. This does: a diverged model scores around chance on data it has already seen, where a converged one scores near 1.

Basic examples (1)

Softanza
o = new stzLogisticRegression(new stzTrainingSet([
		[ [0.0], "lo" ], [ [0.1], "lo" ], [ [0.2], "lo" ],
		[ [0.8], "hi" ], [ [0.9], "hi" ], [ [1.0], "hi" ] ]))
o.Train(300)
# the weight has the sign the data implies
? o.Weights()[1] > 0
# low input -> low class
? o.Classify([0.05])
# high input -> high class
? o.Classify([0.95])
# ...and the boundary sits between them
? o.Probability([0.05]) < 0.5 and o.Probability([0.95]) > 0.5
# it fits its own training data
? o.TrainingAccuracy()
# Why() still narrates
? StzFindFirst("P('hi')", o.Why()) > 0
Output
1
lo
hi
1
1
1

run on 2026-10-02 04:23 inside the library at commit 0e72e2e2c; taken from numeric_logistic_narrated.ring(opens in a new tab)

The extensions of this method

Each extension, and whether it exists for this method; an extension that exists combines with the others (FindSTCS).

Extension
Exists
What it adds · The names
Q
no
does what the method does, then returns the object, so the call can be chained
QQ
no
chains on the next, more specific type of object (the Q ladder)
QQQ
no
chains on the most specific type of object (the Q ladder)
QRT
no
returns the result as an object of the requested type
CS
no
takes a case-sensitivity flag
ST
no
takes the position to start from (StartingAt)
IB
no
takes bounds that are included (IncludingBounds)
XT
no
the extended form: more parameters than the base method
XTT
no
yet another extension: a further extended form, after XT
Z
no
includes the position in what it returns
ZZ
no
returns positions as sections, [start, end]
W
no
selects by a condition
WF
no
selects by a condition, with the expressive keywords (@NextItem, @PreviousItem...)
D
no
takes a direction, forward or backward (Directional)
F
no
takes a function (the condition or the update is given as a function); the forms document also uses F for the future form, which defers the action
Many
no
works on a collection of items instead of one (the plural form)
Except
no
takes exceptions, what to leave out (the exceptional form)
U
no
returns the result without duplication

Every example is a test file of the library, run inside the library for this page; only those whose output kept every promise their file wrote are shown.

See also