adaboostROC.py

import numpy as np
import urllib
import os
from sklearn import metrics
from sklearn.svm import SVC
import matplotlib.pyplot as plt  
from sklearn import svm,datasets  
from sklearn.metrics import roc_curve,auc
from sklearn import cross_validation  
from sklearn.externals.six.moves import zip
from sklearn.datasets import make_gaussian_quantiles
from sklearn.ensemble import AdaBoostClassifier
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier

# open the source data file
path2 = "G:\dynamicanalyze\dynamicfeauture7.txt"
raw_data= open(path2,'r')
# download the file
# load the CSV file as a numpy matrix
dataset = np.loadtxt(raw_data,delimiter=",")
# separate the data from the target attributes
X = dataset[:,1:49]
y = dataset[:,0]
# Add noisy features to make the problem harder  
random_state = np.random.RandomState(0)  
#n_samples, n_features = X.shape  
#X = np.c_[X, random_state.randn(n_samples, 200 * n_features)]  
  
# shuffle and split training and test sets  
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=.3,random_state=0)  

bdt_real = AdaBoostClassifier(
    DecisionTreeClassifier(max_depth=2),
    n_estimators=50,
    learning_rate=1)

bdt_discrete = AdaBoostClassifier(
    DecisionTreeClassifier(max_depth=2),
    n_estimators=50,
    learning_rate=1.5,
    algorithm="SAMME")

bdt_real.fit(X_train, y_train)
bdt_discrete.fit(X_train, y_train)

real_test_errors = []
discrete_test_errors = []

for real_test_predict, discrete_train_predict in zip(
        bdt_real.staged_predict(X_test), bdt_discrete.staged_predict(X_test)):
    real_test_errors.append(
        1. - accuracy_score(real_test_predict, y_test))
    discrete_test_errors.append(
        1. - accuracy_score(discrete_train_predict, y_test))

n_trees_discrete = len(bdt_discrete)
n_trees_real = len(bdt_real)

# Boosting might terminate early, but the following arrays are always
# n_estimators long. We crop them to the actual number of trees here:
discrete_estimator_errors = bdt_discrete.estimator_errors_[:n_trees_discrete]
real_estimator_errors = bdt_real.estimator_errors_[:n_trees_real]
discrete_estimator_weights = bdt_discrete.estimator_weights_[:n_trees_discrete]

y_score = bdt_real.fit(X_train, y_train).decision_function(X_test)  
  
# Compute ROC curve and ROC area for each class  
fpr,tpr,threshold = roc_curve(y_test, y_score) 
roc_auc = auc(fpr,tpr) 
  
plt.figure()  
lw = 2  
plt.figure(figsize=(10,10))  
plt.plot(fpr, tpr, color='darkorange',  
         lw=lw, label='ROC curve (area = %0.2f)' % roc_auc) ###假正率为横坐标，真正率为纵坐标做曲线  
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')  
plt.xlim([0.0, 1.0])  
plt.ylim([0.0, 1.05])  
plt.xlabel('False Positive Rate')  
plt.ylabel('True Positive Rate')  
plt.title('Receiver operating characteristic example')  
plt.legend(loc="lower right")  
plt.show()