alan-turing-institute / MLJTuning.jl / 118

Committed 3 Apr 2020 - 2:24 coverage: 85.424% (+2.0%) from 83.404%

Build # 118

Build Type

Pull #30

travis-ci-com

Committed by

web-flow

Commit Message

more doc tweaks

Pull Request Pull Request #30: Implement RandomSearch

Run Details

56 of 58 new or added lines in 3 files covered. (96.55%)

4 existing lines in 3 files now uncovered.

252 of 295 relevant lines covered (85.42%)

985.97 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

77.78

/src/tuning_strategy_interface.jl

## TYPES TO BE SUBTYPED

abstract type TuningStrategy <: MLJBase.MLJType end
MLJBase.show_as_constructed(::Type{<:TuningStrategy}) = true


## METHODS TO BE IMPLEMENTED

# for initialization of state (compulsory)
setup(tuning::TuningStrategy, model, range, verbosity) = range

# for building each element of the history:
result(tuning::TuningStrategy, history, state, e, metadata) =
    (measure=e.measure, measurement=e.measurement)

# for generating batches of new models and updating the state (but not
# history):
function models! end

# for extracting the optimal model (and its performance) from the
# history:
function best(tuning::TuningStrategy, history)
   measurements = [h[2].measurement[1] for h in history]
   measure = first(history)[2].measure[1]
   if orientation(measure) == :score
       measurements = -measurements
   end
   best_index = argmin(measurements)
   return history[best_index]
end

# for selecting what to report to the user apart from the optimal
# model:
tuning_report(tuning::TuningStrategy, history, state) = (history=history,)

# for declaring the default number of models to evaluate:
default_n(tuning::TuningStrategy, range) = DEFAULT_N

1	## TYPES TO BE SUBTYPED
2
3	abstract type TuningStrategy <: MLJBase.MLJType end
4	MLJBase.show_as_constructed(::Type{<:TuningStrategy}) = true	!
5
6
7	## METHODS TO BE IMPLEMENTED
8
9	# for initialization of state (compulsory)
UNCOV 10	setup(tuning::TuningStrategy, model, range, verbosity) = range	!
11
12	# for building each element of the history:
13	result(tuning::TuningStrategy, history, state, e, metadata) =	5,314×
14	(measure=e.measure, measurement=e.measurement)
15
16	# for generating batches of new models and updating the state (but not
17	# history):
18	function models! end
19
20	# for extracting the optimal model (and its performance) from the
21	# history:
22	function best(tuning::TuningStrategy, history)
23	measurements = [h[2].measurement[1] for h in history]	195×
24	measure = first(history)[2].measure[1]
25	if orientation(measure) == :score	77×
26	measurements = -measurements
27	end
28	best_index = argmin(measurements)	1,428×
29	return history[best_index]	65×
30	end
31
32	# for selecting what to report to the user apart from the optimal
33	# model:
34	tuning_report(tuning::TuningStrategy, history, state) = (history=history,)	40×
35
36	# for declaring the default number of models to evaluate:
37	default_n(tuning::TuningStrategy, range) = DEFAULT_N	8×

alan-turing-institute / MLJTuning.jl / 118

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous