In [1]:

    

%load_ext watermark


    

In [2]:

    

%watermark -d -a "Sebastian Raschka" -v -p scikit-learn,numpy,matplotlib


    

    




Sebastian Raschka 02/10/2014 

CPython 3.4.1
IPython 2.0.0

scikit-learn 0.15.2
numpy 1.9.0
matplotlib 1.4.0

In [3]:

    

%matplotlib inline


    

In [5]:

    

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm, datasets
from sklearn.cross_validation import train_test_split
from sklearn.metrics import roc_curve, auc

random_state = np.random.RandomState(0)

# Import some data to play with
iris = datasets.load_iris()
X = iris.data
y = iris.target

# Make it a binary classification problem by removing the third class
X, y = X[y != 2], y[y != 2]
n_samples, n_features = X.shape

# Add noisy features to make the problem harder
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 = train_test_split(X, y, test_size=.5,
                                                    random_state=123)

# Run classifier
classifier = svm.SVC(kernel='linear', probability=True)
probas_ = classifier.fit(X_train, y_train).predict_proba(X_test)

# Compute ROC curve and area the curve
fpr, tpr, thresholds = roc_curve(y_test, probas_[:, 1])
roc_auc = auc(fpr, tpr)

# Plot ROC curve

fig = plt.figure(figsize=(7,5))
ax = fig.add_subplot(111)

plt.plot(fpr, tpr, color='lightblue', lw=2, label='ROC curve')
plt.plot([0, 1], [0, 1], color='black', lw=2, linestyle='dotted', label='random guessing')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.0])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic (ROC)')
plt.legend(loc="lower right")
ax.annotate('AUC = %0.2f' %roc_auc, xy=(0.35, 0.6))
plt.show()


    

In [ ]: