对每块训练集的前99000数据训练，后1000数据集进行测试

from sklearn.neighbors import KNeighborsClassifier
from sklearn.externals import joblib
onehot = OneHotEncoder()
for b in range(1,115):
    addata = pd.read_csv("adFeature.csv")
    userdata = pd.read_csv("userFeature_%d_part_bat.csv"%(b*100000))
    traindata = pd.read_csv("train.csv")
    data = pd.merge(userdata,traindata)
    data = pd.merge(data,addata)
    #data.to_csv("111.csv")
    #列出所有特征值，遍历,uid是用户唯一标识，不应该算作特征

    userfeature = ["age","carrier","consumptionAbility","ct","education","gender","house","interest1","interest2","interest3","interest4","interest5","kw1","kw2","kw3","marriageStatus","os","topic1","topic2","topic3","LBS","appIdAction","appIdInstall","campaignId","creativeId","creativeSize","adCategoryId","advertiserId","productId","productType"]
    #for index in data[feature] :
    userdata = []
    for index in range(len(data["uid"])):
        feature_li = []
        for feature in userfeature:
            # a = data[feature]
            # print(a[0],type(a[index]),isinstance(a[0],(numpy.int64)))

            if isinstance(data[feature][index],numpy.int64):
                feature_li.append(int(data[feature][index]))
            elif isinstance(data[feature][index],numpy.float64):
                feature_li.append(0)#缺失值用0填充，这是不合理的，有待改进
            elif isinstance(data[feature][index], numpy.float):
                feature_li.append(0)
            else :
                trans = data[feature][index].strip().split(" ")
                trans = map(int,trans)
                trans = sorted(trans)
                #print(trans)
                s = 0
                for num in trans :
                    s += num
                feature_li.append(s)
        # print(feature_li)
        userdata.append(feature_li)
    userdata = numpy.array(userdata)
    onehot.fit(userdata)
    print("--------------------------------------------------------------------")
    Y = numpy.array(data["label"])
    print("--------------------------------------------------------------------")
    X = onehot.transform(userdata)
    print(X)
    print(numpy.shape(X))
    knn = KNeighborsClassifier()
    model = knn.fit(X[:99000],Y[:99000])
    joblib.dump(model,"%d.model"%(b))
    result = model.predict(X[-900:])
    print("-----------------------------------------------------------------------")
    #print(Y[-900:])
    print("--------------------------------------------------------------------------")
    s = 0
    for i in range(len(result)):
        if result[i] == Y[-900:][i] :
            s +=1
    a = s/len(result)
    f = open("result.txt","a",encoding="utf-8")
    f.write(str(a))
    print(a)