对测试集进行测试，只提供了思路，程序是不能用的

from sklearn.externals import joblib
import pandas as pd
import numpy
from sklearn.preprocessing import OneHotEncoder
#import link_and_train
#拼接测试集，测试集进行one-hot编码
onehot = OneHotEncoder()
addata = pd.read_csv("adFeature.csv")
testdata = pd.read_csv("test1.csv")
userdata = pd.read_csv("userFeature.data")
data = pd.merge(testdata,userdata)
data = pd.merge(data,addata)

data.to_csv("predict_data.csv",index=False)

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("--------------------------------------------------------------------")
print("--------------------------------------------------------------------")
test = onehot.transform(userdata)

print(test)
print(numpy.shape(test))

print("开始预测。。。")
for one in range(19000) :
    for xx in range(1,155):
        model = joblib.load("%d.model"%(xx))
        result = model.predict(test[one])
        s1 = 0
        s2 = 0
        if result == -1:
            s1+=1
        elif result == 1:
            s2+=1
    s = 0
    if s1 > s2 :
        print(one,"uid:",data["uid"][one],"aid:",data["aid"][one],"result:",s1/114)
    elif s2>s1 :
        print(one, "uid:", data["uid"][one], "aid:", data["aid"][one], "result:", s2/114)
    else:
        print("impossible")