ml_framework.py 文件源码

def get_data_preprocessor_balancing(params, y):
    d_balancing = params['layer_dict_list'][1]

    if params['balancing'] == str(d_balancing['None']) or params['balancing'] == 'None':
        # for fp: ['ExtraTreesClassifier', 'LinearSVC'] + clf: ['DecisionTreeClassifier', 'ExtraTreesClassifier', 'LinearSVC', 'SVC', 'RandomForestClassifier', 'SGDClassifier']
        params['class_weight'] = None
        # for clf: ['Adasample_weightBoostClassifier', 'GradientBoostingClassifier']
        params['sample_weight'] = None
    elif params['balancing'] == str(d_balancing['weighting']) or params['balancing'] == 'weighting':
        # for fp: ['ExtraTreesClassifier', 'LinearSVC'] + clf: ['DecisionTreeClassifier', 'ExtraTreesClassifier', 'LinearSVC', 'SVC', 'RandomForestClassifier', 'SGDClassifier']
        params['class_weight'] = 'auto'
        # for clf: ['AdaBoostClassifier', 'GradientBoostingClassifier']
        if len(y.shape) > 1:
            offsets = [2 ** i for i in range(y.shape[1])]
            y_ = np.sum(y * offsets, axis=1)
        else:
            y_ = y
        unique, counts = np.unique(y_, return_counts=True)
        cw = 1. / counts
        cw = cw / np.mean(cw)
        sample_weight = np.ones(y_.shape)
        for i, ue in enumerate(unique):
            mask = y_ == ue
            sample_weight[mask] *= cw[i]
        params['sample_weight'] = sample_weight

    return params