处理特征向量和离散特征

在最新的腾讯的社交广告大赛中，数据如下，如何处理这种向量的特征

比如intersets1,interests2....

LBS,950,
age,4,
carrier,1,
consumptionAbility,2,
ct,3 1,
education,7,
gender,2,
interest1,93 70 77 86 109 47 75 69 45 8 29 49 83 6 46 36 11 44 30 118 76 48 28 106 59 67 41 114 111 71 9,
interest2,46 19 13 29,
interest5,52 100 72 131 116 11 71 12 8 113 28 73 6 132 99 76 46 62 121 59 129 21 93,
kw1,664359 276966 734911 103617 562294,
kw2,11395 79112 115065 77033 36176,
marriageStatus,11,
os,2,
topic1,9826 105 8525 5488 7281,
topic2,9708 5553 6745 7477 7150,
uid,26325489

首先上代码

def batch_predict(data,index):
    one_hot_feature=['LBS','age','carrier','consumptionAbility','education','gender','house','os','ct','marriageStatus','advertiserId','campaignId', 'creativeId',
           'adCategoryId', 'productId', 'productType']
    vector_feature=['appIdAction','appIdInstall','interest1','interest2','interest3','interest