python sklearn中'float'和'str'的实例之间不支持'<'

Question

当我使用SVM分类时，有4000个数据项我有一个问题：

'<' not supported between instances of 'float' and 'str'

但是当我使用250个数据项时，一切都很好。

这是代码：

import pandas as pd  
import numpy as np  
import matplotlib.pyplot as plt  
from numpy import ndarray
from sklearn import svm
from sklearn.model_selection import train_test_split  
from matplotlib import style
style.use("ggplot")

bankdata = pd.read_csv("data/vector_label.csv")
X = bankdata.drop('label', axis=1)  
y = bankdata['label']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20,random_state=109)
svclassifier = svm.SVC(kernel='linear')  
svclassifier.fit(X_train, y_train)    

有数据：

v1,v2,v3,v..,v100,label
-2.0491536259651184,-1.213379144668579,1.9480481743812559,50.15884351730347,POSITIF

我该怎么办？