Metrics

In our library you should use metrics inherited from Base Class. We have already made some wrappers around Sklearn Metrics.

Base Class

class modelgym.metrics.Metric(scoring_function, requires_proba=False, is_min_optimal=False, name='default_name')

Metric class is a wrapper around sklearn.metrics class, with additional information: when optimizing this metric, should we minimize it (like log_loss) or maximize (like accuracy), and whether it’s calculation requires computed probabilities (like roc_auc).

Of course, not only sklearn.metrics could be wrapped into this class

Parameters:

• scoring_function (types.FunctionType) – wrapped scoring function
• requires_proba (bool) – whether calculation of metric requires computed probabilities
• is_min_optimal (bool) – is the less the better
• name (str) – name of metric

Sklearn Metrics

class modelgym.metrics.Accuracy(name='accuracy')

Bases: modelgym.metrics.Metric

class modelgym.metrics.F1(name='f1_score')

Bases: modelgym.metrics.Metric

class modelgym.metrics.Logloss(name='logloss')

Bases: modelgym.metrics.Metric

class modelgym.metrics.Mse(name='mse')

Bases: modelgym.metrics.Metric

class modelgym.metrics.Precision(name='precision')

Bases: modelgym.metrics.Metric

class modelgym.metrics.Recall(name='recall')

Bases: modelgym.metrics.Metric

class modelgym.metrics.RocAuc(name='roc_auc')

Bases: modelgym.metrics.Metric