Question

我最近在为我的项目使用sklearn而苦苦挣扎。我想构建一个分类器并将我的数据分为六组。总样本量为88然后我将数据分成火车（66）和测试（22）我完全按照sklearn文档显示，这是我的代码

from sklearn.multiclass import OneVsRestClassifier
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis as QDA

clf = OneVsRestClassifier(QDA())
QDA_score = clf.fit(train,label).decision_function(test)
from sklearn.metrics import roc_curve, auc
from sklearn.metrics import roc_curve
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(3):
     fpr[i], tpr[i], _ = roc_curve(label_test[:, i], QDA_score[:, i])
     roc_auc[i] = auc(fpr[i], tpr[i])
from itertools import cycle
import matplotlib.pyplot as plt
plt.figure()
lw = 2

colors = cycle(['aqua', 'darkorange', 'cornflowerblue'])
for i, color,n in zip(range(3), colors,['_000','_15_30_45','60']):
plt.plot(fpr[i], tpr[i], color=color, lw=lw,
         label='ROC curve of {0} (area = {1:0.2f})'
         ''.format(n , roc_auc[i]))
plt.plot([0, 1], [0, 1], 'k--', lw=lw)
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC for multi-classes')
plt.legend(loc="lower right")
plt.show()

链接是我的结果。但是，每次运行代码时，结果都会发生变化。我想知道是否有可以将其与Cross验证相结合并计算每个班级的平均和稳定ROC

谢谢！

Answer 1

如果没有更多的数据详细信息以及您尝试解决的问题的复杂性，很难说清楚，但像您这样的不规则学习表现可能表明您的数据集太小而不适合数据的不规则性和复杂性，所以每次你采样时都会得到一个不同的火车数据集。

您还可以查看常见的测试与列车停止技术k-fold交叉验证。

更新： K折叠交叉验证基本上是将数据切割成k个部分，然后进行k次学习过程并平均其结果，其中每次数据的不同部分是测试数据集，其余k-1部分是训练数据集

Answer 2

您可以使用cross_val_predict首先获得交叉验证的概率，然后绘制每个类别的ROC曲线。

使用虹膜数据的示例

import matplotlib.pyplot as plt
from sklearn import svm, datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.metrics import roc_curve, auc
from sklearn.multiclass import OneVsRestClassifier
from sklearn.model_selection import cross_val_predict
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis as QDA

iris = datasets.load_iris()
X = iris.data
y = iris.target

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

clf = OneVsRestClassifier(QDA())
y_score = cross_val_predict(clf, X, y, cv=10 ,method='predict_proba')

fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
    fpr[i], tpr[i], _ = roc_curve(y_bin[:, i], y_score[:, i])
    roc_auc[i] = auc(fpr[i], tpr[i])
colors = cycle(['blue', 'red', 'green'])
for i, color in zip(range(n_classes), colors):
    plt.plot(fpr[i], tpr[i], color=color, lw=lw,
             label='ROC curve of class {0} (area = {1:0.2f})'
             ''.format(i, roc_auc[i]))
plt.plot([0, 1], [0, 1], 'k--', lw=lw)
plt.xlim([-0.05, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic for multi-class data')
plt.legend(loc="lower right")
plt.show()

要获取每个折叠的ROC，请执行以下操作：

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


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)]

# Classification and ROC analysis

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

tprs = []
aucs = []
mean_fpr = np.linspace(0, 1, 100)

i = 0
for train, test in cv.split(X, y):
    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])
    tprs.append(interp(mean_fpr, fpr, tpr))
    tprs[-1][0] = 0.0
    roc_auc = auc(fpr, tpr)
    aucs.append(roc_auc)
    plt.plot(fpr, tpr, lw=1, alpha=0.3,
             label='ROC fold %d (AUC = %0.2f)' % (i, roc_auc))

    i += 1
plt.plot([0, 1], [0, 1], linestyle='--', lw=2, color='r',
         label='Luck', alpha=.8)

mean_tpr = np.mean(tprs, axis=0)
mean_tpr[-1] = 1.0
mean_auc = auc(mean_fpr, mean_tpr)
std_auc = np.std(aucs)
plt.plot(mean_fpr, mean_tpr, color='b',
         label=r'Mean ROC (AUC = %0.2f $\pm$ %0.2f)' % (mean_auc, std_auc),
         lw=2, alpha=.8)

std_tpr = np.std(tprs, axis=0)
tprs_upper = np.minimum(mean_tpr + std_tpr, 1)
tprs_lower = np.maximum(mean_tpr - std_tpr, 0)
plt.fill_between(mean_fpr, tprs_lower, tprs_upper, color='grey', alpha=.2,
                 label=r'$\pm$ 1 std. dev.')

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()

如何计算多类交叉验证的平均ROC

2 个答案: