无序高基数类别特征（例如城市，省份这样的

‘’‘无序高基数类别特征（例如城市，省份这样的）：
我们用目标编码，为减小过拟合现象，采用5折交叉验证的思路，转化特征值，见下图’’’

def kfold_stats_feature(train, test, feats, k):
    folds = StratifiedKFold(n_splits=k, shuffle=True, random_state=6666)  # 这里最好和后面模型的K折交叉验证保持一致

    train['fold'] = None
    for fold_, (trn_idx, val_idx) in enumerate(folds.split(train, train['isDefault'])):
        train.loc[val_idx, 'fold'] = fold_

    kfold_features = []
    for feat in feats:
        nums_columns = ['isDefault']
        for f in nums_columns:
            colname = feat + '_' + f + '_kfold_mean'
            kfold_features.append(colname)
            train[colname] = None
            for fold_, (trn_idx, val_idx) in enumerate(folds.split(train, train['isDefault'])):
                tmp_trn = train.iloc[trn_idx]
                order_label = tmp_trn.groupby([feat])[f].mean()
                tmp = train.loc[train.fold == fold_, [feat]]
                train.loc[train.fold == fold_, colname] = tmp[feat].map(order_label)
                # fillna
                global_mean = train[f].mean()
                train.loc[train.fold == fold_, colname] = train.loc[train.fold == fold_, colname].fillna(global_mean)
            train[colname] = train[colname].astype(float)

        for f in nums_columns:
            colname = feat + '_' + f + '_kfold_mean'
            test[colname] = None
            order_label = train.groupby([feat])[f].mean()
            test[colname] = test[feat].map(order_label)
            # fillna
            global_mean = train[f].mean()
            test[colname] = test[colname].fillna(global_mean)
            test[colname] = test[colname].astype(float)
    del train['fold']
    return train, test

target_encode_cols = ['postCode', 'regionCode', 'homeOwnership', 'employmentTitle','title']
kflod_num=5 #5折交叉验证
train, test = kfold_stats_feature(train, test, target_encode_cols, kflod_num)