数据挖掘-统计特征

def cnt_fea(data,feature,train_num):
    data['flag'] = '-'
    for fea in feature:
        print(fea)
        data[fea] = data[fea].map(data[fea].value_counts())
    for i in range(len(feature)-1):
        for j in range(i+1,len(feature)):
            col = [feature[i],feature[j],'cnt']
            print(col)
            data['temp'] = data[feature[i]].astype(str) + data['flag'] + data[feature[j]].astype(str)
            data['_'.join(col)] = data['temp'].map(data['temp'].value_counts())
    del data['flag']
    train = data.iloc[:train_num]
    test = data.iloc[train_num:].reset_index(drop=True)
    return train,test这里插入代码片