为什么我的命中率显示是NaN啊，前面还可以，后面就不行了

Question

请大家帮我看下吧，改了好多遍了，还是不行……，也不知道是哪里有问题，数据也处理过了，没有空值重复值

Answer 1

#以下是我用到的所有代码

import numpy as np
import pandas as pd

df = pd.read_csv(r'D:/data/睡眠统计.csv',engine='python')

df = df.replace({'性别':{'女性':0, '男性':1}})
df = df.replace({'职业':{'工程师':101, '护士':102, '会计师':103, '科学家':104, '老师':105, '律师':106, 
                       '软件工程师':'107', '销售代表':108, '医生':109, '营业员':1010, '主管':1011}})
df = df.replace({'BMI':{'正常':0, '肥胖':1, '超重':2}})
df = df.replace({'睡眠障碍':{'无':3, '有':4}})

df.isnull().sum()
df = df.fillna(method='bfill')

X = df.drop(columns=['睡眠障碍'])
y = df['睡眠障碍']
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.4,random_state=123,shuffle = True)  
#print(X_train)    #划分的训练集数据
#print(X_test)    #划分的测试级数据
#print(y_train)
#print(y_test)

from sklearn.tree import DecisionTreeClassifier
model = DecisionTreeClassifier(max_depth=3,random_state=123)
model.fit(X_train,y_train)

y_pred = model.predict(X_test)
y_pred[:100]

a = pd.DataFrame()
a['预测值'] = list(y_pred)
a['实际值'] = list(y_test)
a.head(5)   #查看前十行

from sklearn.metrics import confusion_matrix
m = confusion_matrix(y_test, y_pred)  # 传入预测值和真实值
print(m)

a = pd.DataFrame(m, index=['0（无睡眠障碍概率）', '1（有睡眠障碍概率）'], columns=['0（无睡眠障碍概率）', '1（有睡眠障碍概率）'])

#计算命中率
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))

from sklearn.metrics import roc_curve
fpr,tpr,thres = roc_curve(y_test,y_pred_proba[:,1],pos_label=2)

a = pd.DataFrame()
a["阀值"] = list(thres)
a["假报警率"] = list(fpr)
a["命中率"] = list(tpr)
a