使用交叉验证去验证逻辑回归

import pandas as pd 
Data=pd.read_csv ('C:\\Dataset.csv',index_col='SNo')
feature_cols=['A','B','C','D','E']
X=Data[feature_cols]

Y=Data['Status'] 
Y1=Data['Status1']  # predictions from elsewhere
Y2=Data['Status2'] # predictions from elsewhere

from sklearn.linear_model import LogisticRegression
logreg=LogisticRegression()
logreg.fit(X_train,y_train)

from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

from sklearn import metrics, cross_validation
predicted = cross_validation.cross_val_predict(logreg, X, y, cv=10)
metrics.accuracy_score(y, predicted) 

from sklearn.cross_validation import cross_val_score
accuracy = cross_val_score(logreg, X, y, cv=10,scoring='accuracy')
print (accuracy)
print (cross_val_score(logreg, X, y, cv=10,scoring='accuracy').mean())

from nltk import ConfusionMatrix 
print (ConfusionMatrix(list(y), list(predicted)))
#print (ConfusionMatrix(list(y), list(yexpert)))

# sensitivity:
print (metrics.recall_score(y, predicted) )

import matplotlib.pyplot as plt 
probs = logreg.predict_proba(X)[:, 1] 
plt.hist(probs) 
plt.show()

# use 0.5 cutoff for predicting 'default' 
import numpy as np 
preds = np.where(probs > 0.5, 1, 0) 
print (ConfusionMatrix(list(y), list(preds)))

# check accuracy, sensitivity, specificity 
print (metrics.accuracy_score(y, predicted)) 

#ROC CURVES and AUC 
# plot ROC curve 
fpr, tpr, thresholds = metrics.roc_curve(y, probs) 
plt.plot(fpr, tpr) 
plt.xlim([0.0, 1.0]) 
plt.ylim([0.0, 1.0]) 
plt.xlabel('False Positive Rate') 
plt.ylabel('True Positive Rate)') 
plt.show()

# calculate AUC 
print (metrics.roc_auc_score(y, probs))

# use AUC as evaluation metric for cross-validation 
from sklearn.cross_validation import cross_val_score 
logreg = LogisticRegression() 
cross_val_score(logreg, X, y, cv=10, scoring='roc_auc').mean()