ROC曲线

import matplotlib.pylab as plt
from scipy import interp
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import roc_curve,auc
from sklearn.model_selection import StratifiedKFold
import matplotlib.patches as patches
import numpy as np 
import pandas as pd 

# 导入数据，查看特征名称，标签数量和数据信息
data = pd .read_csv('./voice.csv')
print(data.columns)
label_value_count = data.label.value_counts()
print(label_value_count)
print(data.info())

Index(['meanfreq', 'sd', 'median', 'Q25', 'Q75', 'IQR', 'skew', 'kurt',
       'sp.ent', 'sfm', 'mode', 'centroid', 'meanfun', 'minfun', 'maxfun',
       'meandom', 'mindom', 'maxdom', 'dfrange', 'modindx', 'label'],
      dtype='object')
male      
female    
Name: label, dtype: int64
<class 'pandas.core.frame.DataFrame'>
RangeIndex:  entries,  to 
Data columns (total  columns):
meanfreq     non-null float64
sd           non-null float64
median       non-null float64
Q25          non-null float64
Q75          non-null float64
IQR          non-null float64
skew         non-null float64
kurt         non-null float64
sp.ent       non-null float64
sfm          non-null float64
mode         non-null float64
centroid     non-null float64
meanfun      non-null float64
minfun       non-null float64
maxfun       non-null float64
meandom      non-null float64
mindom       non-null float64
maxdom       non-null float64
dfrange      non-null float64
modindx      non-null float64
label        non-null object
dtypes: float64(), object()
memory usage: 519.9+ KB
None

# 转换规则 : male = 1, female = 0
dict = {'label':{'male':,'female':}}     
data.replace(dict,inplace = True)           
x = data.loc[:, data.columns != 'label']
y = data.loc[:,'label']

random_state = np.random.RandomState()
clf = RandomForestClassifier(random_state=random_state)
cv = StratifiedKFold(n_splits=,shuffle=False)

fig1 = plt.figure(figsize=[,])
ax1 = fig1.add_subplot(,aspect = 'equal')
ax1.add_patch(
    patches.Arrow(0.45,0.5,-0.25,0.25,width=0.3,color='green',alpha = 0.5)
    )
ax1.add_patch(
    patches.Arrow(0.5,0.45,0.25,-0.25,width=0.3,color='red',alpha = 0.5)
    )

tprs = []
aucs = []
mean_fpr = np.linspace(,,)
i = 
for train,test in cv.split(x,y):
    prediction = clf.fit(x.iloc[train],y.iloc[train]).predict_proba(x.iloc[test])
    fpr, tpr, t = roc_curve(y[test], prediction[:, ])
    tprs.append(interp(mean_fpr, fpr, tpr))
    roc_auc = auc(fpr, tpr)
    aucs.append(roc_auc)
    plt.plot(fpr, tpr, lw=, alpha=0.3, label='ROC fold %d (AUC = %0.2f)' % (i, roc_auc))
    i= i+

plt.plot([,],[,],linestyle = '--',lw = ,color = 'black')
mean_tpr = np.mean(tprs, axis=)
mean_auc = auc(mean_fpr, mean_tpr)
plt.plot(mean_fpr, mean_tpr, color='blue',
         label=r'Mean ROC (AUC = %0.2f )' % (mean_auc),lw=, alpha=)

plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC')
plt.legend(loc="lower right")
plt.text(0.32,0.7,'More accurate area',fontsize = )
plt.text(0.63,0.4,'Less accurate area',fontsize = )
plt.show()