sklearn - Cross validation with multiple scores

Question

I would like to compute the recall, precision and f-measure of a cross validation test for different classifiers. scik

Answer 1

You can use the following code in order to compute Accuracy, Precision, Recall and any other metrics by fitting your estimator only once per cross-validation step.

def get_true_and_pred_CV(estimator, X, y, n_folds, cv, params):
    ys = []
    for train_idx, valid_idx in cv:
        clf = estimator(**params)
        if isinstance(X, np.ndarray):
            clf.fit(X[train_idx], y[train_idx])
            cur_pred = clf.predict(X[valid_idx])
        elif isinstance(X, pd.DataFrame):
            clf.fit(X.iloc[train_idx, :], y[train_idx]) 
            cur_pred = clf.predict(X.iloc[valid_idx, :])
        else:
            raise Exception('Only numpy array and pandas DataFrame ' \
                            'as types of X are supported')

        ys.append((y[valid_idx], cur_pred))
    return ys


def fit_and_score_CV(estimator, X, y, n_folds=10, stratify=True, **params):
    if not stratify:
        cv_arg = sklearn.cross_validation.KFold(y.size, n_folds)
    else:
        cv_arg = sklearn.cross_validation.StratifiedKFold(y, n_folds)

    ys = get_true_and_pred_CV(estimator, X, y, n_folds, cv_arg, params)    
    cv_acc = map(lambda tp: sklearn.metrics.accuracy_score(tp[0], tp[1]), ys)
    cv_pr_weighted = map(lambda tp: sklearn.metrics.precision_score(tp[0], tp[1], average='weighted'), ys)
    cv_rec_weighted = map(lambda tp: sklearn.metrics.recall_score(tp[0], tp[1], average='weighted'), ys)
    cv_f1_weighted = map(lambda tp: sklearn.metrics.f1_score(tp[0], tp[1], average='weighted'), ys)

    # the approach below makes estimator fit multiple times
    #cv_acc = sklearn.cross_validation.cross_val_score(algo, X, y, cv=cv_arg, scoring='accuracy')
    #cv_pr_weighted = sklearn.cross_validation.cross_val_score(algo, X, y, cv=cv_arg, scoring='precision_weighted')
    #cv_rec_weighted = sklearn.cross_validation.cross_val_score(algo, X, y, cv=cv_arg, scoring='recall_weighted')   
    #cv_f1_weighted = sklearn.cross_validation.cross_val_score(algo, X, y, cv=cv_arg, scoring='f1_weighted')
    return {'CV accuracy': np.mean(cv_acc), 'CV precision_weighted': np.mean(cv_pr_weighted),
            'CV recall_weighted': np.mean(cv_rec_weighted), 'CV F1_weighted': np.mean(cv_f1_weighted)}

I frequently use these functions instead of cross_val_score to compute multiple statistics altogether. You can change quality metrics by the desired.