In [33]:

    

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm, datasets
from sklearn.metrics import roc_curve, auc
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.multiclass import OneVsRestClassifier
from scipy import interp

%matplotlib inline

# Import some data to play with
iris = datasets.load_iris()
X = iris.data
y = iris.target
print X[0:2]
print y[0:2]

# Binarize the output
y = label_binarize(y, classes=[0, 1, 2])
n_classes = y.shape[1]
print y[0]

# Add noisy features to make the problem harder
random_state = np.random.RandomState(0)
n_samples, n_features = X.shape

print X.shape
X = np.c_[X, random_state.randn(n_samples, 200 * n_features)]

print X.shape

# shuffle and split training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5, random_state=0)

print X_train.shape

# Learn to predict each class against the other
classifier = OneVsRestClassifier(svm.SVC(kernel='linear', probability=True, random_state=random_state))
y_score = classifier.fit(X_train, y_train).decision_function(X_test)

# Compute ROC curve and ROC area for each class
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
    fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_score[:, i])
    roc_auc[i] = auc(fpr[i], tpr[i])

print y_test.shape
print y_score.shape

# Compute micro-average ROC curve and ROC area
fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_score.ravel())
roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])

y_test.ravel()
y_score.ravel()

#############################################################################
# Plot of a ROC curve for a specific class
plt.figure()
plt.plot(fpr[2], tpr[2], label='ROC curve (area = %0.2f)' % roc_auc[2])
plt.plot([0, 1], [0, 1], 'k--')
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()

print tpr[2]


    

    




[[ 5.1  3.5  1.4  0.2]
 [ 4.9  3.   1.4  0.2]]
[0 0]
[1 0 0]
(150, 4)
(150, 804)
(75, 804)
(75, 3)
(75, 3)






    













    




[ 0.04166667  0.08333333  0.125       0.125       0.16666667  0.20833333
  0.25        0.25        0.25        0.25        0.29166667  0.29166667
  0.33333333  0.33333333  0.375       0.41666667  0.41666667  0.45833333
  0.5         0.5         0.54166667  0.54166667  0.58333333  0.58333333
  0.58333333  0.58333333  0.58333333  0.58333333  0.58333333  0.58333333
  0.625       0.66666667  0.66666667  0.70833333  0.75        0.75
  0.79166667  0.79166667  0.79166667  0.79166667  0.83333333  0.83333333
  0.83333333  0.875       0.875       0.91666667  0.91666667  0.91666667
  0.95833333  0.95833333  0.95833333  0.95833333  1.          1.          1.
  1.          1.          1.          1.          1.          1.          1.
  1.          1.          1.          1.          1.          1.          1.
  1.          1.          1.          1.          1.          1.        ]

In [28]:

    

##############################################################################
# Plot ROC curves for the multiclass problem

# Compute macro-average ROC curve and ROC area

# First aggregate all false positive rates
all_fpr = np.unique(np.concatenate([fpr[i] for i in range(n_classes)]))

# Then interpolate all ROC curves at this points
mean_tpr = np.zeros_like(all_fpr)
for i in range(n_classes):
    mean_tpr += interp(all_fpr, fpr[i], tpr[i])

# Finally average it and compute AUC
mean_tpr /= n_classes

fpr["macro"] = all_fpr
tpr["macro"] = mean_tpr
roc_auc["macro"] = auc(fpr["macro"], tpr["macro"])

# Plot all ROC curves
plt.figure()
plt.plot(fpr["micro"], tpr["micro"],
         label='micro-average ROC curve (area = {0:0.2f})'
               ''.format(roc_auc["micro"]),
         linewidth=2)

plt.plot(fpr["macro"], tpr["macro"],
         label='macro-average ROC curve (area = {0:0.2f})'
               ''.format(roc_auc["macro"]),
         linewidth=2)

for i in range(n_classes):
    plt.plot(fpr[i], tpr[i], label='ROC curve of class {0} (area = {1:0.2f})'
                                   ''.format(i, roc_auc[i]))

plt.plot([0, 1], [0, 1], 'k--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Some extension of Receiver operating characteristic to multi-class')
plt.legend(loc="lower right")
plt.show()


    

In [ ]: