Sklearn Painting ROC Curve __sklearn

#coding: Utf-8
Print (__doc__)

Import NumPy as NP
From scipy import Interp
Import Matplotlib.pyplot as Plt

From Sklearn import SVM, datasets
From sklearn.metrics import Roc_curve, AUC
From sklearn.cross_validation import Stratifiedkfold

###############################################################################
# data IO and generation, import iris data and prepare

# 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, * n_features)]

###############################################################################
# Classification and ROC analysis
#分类, do ROC analysis

# Run classifier with cross-validation and plot ROC curves
#使用6折交叉验证, and draw Roc curves
CV = Stratifiedkfold (y, n_folds=6)
classifier = SVM. SVC (kernel= ' linear ', probability=true,
Random_state=random_state)

MEAN_TPR = 0.0
MEAN_FPR = Np.linspace (0, 1, 100)
ALL_TPR = []

For I, (train, test) in enumerate (CV):
Print test
#通过训练数据, the SVM linear kernel is used to build the model, and the test set is tested to find out the prediction score.
Probas_ = Classifier.fit (X[train], Y[train]). Predict_proba (X[test)
# Compute ROC curve and area the curve
#通过roc_curve () function, find FPR and TPR, and thresholds
FPR, TPR, thresholds = Roc_curve (y[test), probas_[:, 1])
MEAN_TPR + = Interp (MEAN_FPR, FPR, TPR) #对mean_tpr在mean_fpr处进行插值, calling SciPy () function via INTERP package
Mean_tpr[0] = 0.0 #初始处为0
ROC_AUC = AUC (FPR, TPR)
#画图, only need Plt.plot (FPR,TPR), variable ROC_AUC just record AUC value, through the AUC () function can be calculated
Plt.plot (FPR, TPR, lw=1, label= ' ROC fold%d (area =%0.2f) '% (I, ROC_AUC))

#画对角线
Plt.plot ([0, 1], [0, 1], '--', color= (0.6, 0.6, 0.6), label= ' Luck ')

MEAN_TPR/= Len (CV) #在mean_fpr100个点, interpolation interpolation at each point for multiple averaging
MEAN_TPR[-1] = 1.0 #坐标最后一个点为 (1,1)
MEAN_AUC = AUC (MEAN_FPR, MEAN_TPR) #计算平均AUC值
#画平均ROC曲线
#print Mean_fpr,len (MEAN_FPR)
#print MEAN_TPR
Plt.plot (MEAN_FPR, MEAN_TPR, ' k--',
Label= ' Mean ROC (area =%0.2f) '% Mean_auc, lw=2)

Plt.xlim ([-0.05, 1.05])
Plt.ylim ([-0.05, 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 ()