Closed rodrigo-arenas closed 3 years ago
Merging #67 (a8a706d) into master (e9dfb5c) will not change coverage. The diff coverage is
100.00%
.
@@ Coverage Diff @@
## master #67 +/- ##
=========================================
Coverage 100.00% 100.00%
=========================================
Files 19 19
Lines 726 725 -1
=========================================
- Hits 726 725 -1
Impacted Files | Coverage Δ | |
---|---|---|
sklearn_genetic/callbacks/early_stoppers.py | 100.00% <100.00%> (ø) |
Continue to review full report at Codecov.
Legend - Click here to learn more
Δ = absolute <relative> (impact)
,ø = not affected
,? = missing data
Powered by Codecov. Last update e9dfb5c...a8a706d. Read the comment docs.
Hello
I have the results in the console . would you please tell me how i can delect NaN
3= max-depth ,Balanced_accuracy_bayer= 0.890
gen nevals fitness fitness_std fitness_max fitness_min
0 5 nan nan nan nan
1 7 0.980865 0.00113267 0.982649 0.979315
INFO: ThresholdStopping callback met its criteria
INFO: Stopping the algorithm
cv_results :::::: GAFeatureSelectionCV(cv=StratifiedKFold(n_splits=4, random_state=0, shuffle=True),
estimator=RandomForestClassifier(class_weight='balanced_subsample',
max_depth=4),
generations=10, mutation_probability=0.01,
population_size=5, return_train_score=True,
scoring=make_scorer(my_score_loss_func))
[[205 0]
[ 5 7]]
balanced_accuracy_sklearn: 4_GESA549NR3C1_RFC:: 0.7917
balanced_accuracy_bayer: 4_GES__A549NR3C1___RFC:: 0.9881
This PR adds the parameter
generations
to the DeltaThreshold callback.Now it compares the maximum and minimum values of a metric from the last generations, instead of just the current and previous ones. The default value is 2, so the behavior remains the same as in previous versions.
This is an implementation of the described in issue #64