roc.ipynb

print(__doc__)

import numpy as np
from scipy import interp
import matplotlib.pyplot as plt
from itertools import cycle

from sklearn import svm, datasets
from sklearn.metrics import roc_curve, auc
from sklearn.model_selection import StratifiedKFold


# import some data to play with
iris = datasets.load_iris()
X = iris.data
y = iris.target
X, y = X[y != 2], y[y != 2]
n_samples, n_features = X.shape

# Add noisy features
random_state = np.random.RandomState(0)
X = np.c_[X, random_state.randn(n_samples, 200 * n_features)]
print X

from sklearn.linear_model import LinearRegression
from sklearn.linear_model import LogisticRegression
from sklearn import svm, datasets

classifier = svm.SVC(kernel='linear', probability=True,
                     random_state=random_state)
# Run classifier with cross-validation and plot ROC curves
cv = StratifiedKFold(n_splits=6)

mean_tpr = 0.0
mean_fpr = np.linspace(0, 1, 100)

colors = cycle(['cyan', 'indigo', 'seagreen', 'yellow', 'blue', 'darkorange'])
lw = 2

i = 0
for (train, test), color in zip(cv.split(X, y), colors):
    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])
    mean_tpr += interp(mean_fpr, fpr, tpr)
    mean_tpr[0] = 0.0
    roc_auc = auc(fpr, tpr)
    plt.plot(fpr, tpr, lw=lw, color=color,
             label='ROC fold %d (area = %0.2f)' % (i, roc_auc))

    i += 1
plt.plot([0, 1], [0, 1], linestyle='--', lw=lw, color='k',
         label='Luck')

mean_tpr /= cv.get_n_splits(X, y)
mean_tpr[-1] = 1.0
mean_auc = auc(mean_fpr, mean_tpr)
plt.plot(mean_fpr, mean_tpr, color='g', linestyle='--',
         label='Mean ROC (area = %0.2f)' % mean_auc, lw=lw)

plt.xlim([-0.05, 1.05])
plt.ylim([-0.05, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC curves')
plt.legend(loc="lower right")
plt.show()