PSM倾向匹配法，Python报错：Average Accuracy: nan%

在使用psm倾向匹配法的时候，运行到：m.fit_scores(balance=True, nmodels=100) Python报错：
Fitting Models on Balanced Samples: 1\100Error: Unable to coerce to Series, length must be 1: given 45310
Fitting Models on Balanced Samples: 1\100Error: Unable to coerce to Series, length must be 1: given 45310
Fitting Models on Balanced Samples: 1\100Error: Unable to coerce to Series, length must be 1: given 45310
Fitting Models on Balanced Samples: 1\100Error: Unable to coerce to Series, length must be 1: given 45310
Fitting Models on Balanced Samples: 1\100Error: Unable to coerce to Series, length must be 1: given 45310

Average Accuracy: nan%

想实现：
Fitting Models on Balanced Samples: 100\100
Average Accuracy: 66.06%

这样的结果

相关代码：

data.head()
test = data[data.if_follow == 1]
control = data[data.if_follow ==0]
m = Matcher(test,control,yvar="if_follow",exclude=["device_uuid","day_follow_pv","bros_user","bros_pv","dura","preserve_users","interact_user","interact_times","day","last_actday"])
np.random.seed(20170925)
m.fit_scores(balance=True, nmodels=100)

多谢~

你给的数据太多了,你的模型数据报错为
Unable to coerce to Series, length must be 1: given 45310
无法强制为系列，长度必须为1:得到45310
你看看是否是数据问题还是顺序问题

想问下楼主解决了吗，遇到一样的问题