Created
May 7, 2019 09:45
-
-
Save HViktorTsoi/ea689c472a92bd26083add3925f774e1 to your computer and use it in GitHub Desktop.
计算ROC曲线
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import scipy | |
import scipy.io as scio | |
import numpy as np | |
import cv2 | |
import sklearn | |
from sklearn.decomposition import PCA | |
from sklearn.neighbors import KNeighborsClassifier | |
from sklearn import metrics | |
import matplotlib.pyplot as plt | |
import pickle as pkl | |
import matplotlib | |
def calc_roc(y_score, y_test, n_classes): | |
""" | |
计算roc曲线 | |
:param y_score: 预测的置信度 形状为 m x n_classes 其中m为样本数 n_classes是类别数 每个元素代表第i个样本预测为第j类的置信度 | |
:param y_test: gt 形状为m x 1 | |
:param n_classes: 类别数 | |
:return: tpr, fpr | |
""" | |
fpr = dict() | |
tpr = dict() | |
roc_auc = dict() | |
y_test_bin = sklearn.preprocessing.label_binarize(y_test, classes=range(1, n_classes + 1)) | |
# 计算所有类别的tpr和fpr | |
for class_id in range(n_classes): | |
fpr[class_id], tpr[class_id], _ = metrics.roc_curve(y_test_bin[:, class_id], y_score[:, class_id]) | |
roc_auc[class_id] = metrics.auc(fpr[class_id], tpr[class_id]) | |
all_fpr = np.unique(np.concatenate([fpr[i] for i in range(n_classes)])) | |
mean_tpr = np.zeros_like(all_fpr) | |
for i in range(n_classes): | |
# 插值 | |
mean_tpr += scipy.interp(all_fpr, fpr[i], tpr[i]) | |
mean_tpr /= n_classes | |
return ( | |
all_fpr, mean_tpr | |
) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def face_recognize(pca_components, n_neighbor): | |
""" | |
使用pca对人脸进行识别 | |
:param pca_components: 降维后保留的特征数目 | |
:param n_neighbor: 邻居阈值 | |
:return: | |
""" | |
data = pkl.load(open('./data/PIE.pkl', 'rb')) | |
dataset = np.array(data['fea']) | |
labels = np.squeeze(np.array(data['gnd'])) | |
split = np.array(data['isTest']) | |
print('数据集大小: ', dataset.shape) | |
# 数据集划分 | |
test_idx = np.where(split == 1)[0] | |
# 训练集是全集和测试集的差 | |
train_idx = list(set(range(len(dataset))) - set(test_idx)) | |
X_test, y_test = dataset[test_idx], labels[test_idx] | |
X_train, y_train = dataset[train_idx], labels[train_idx] | |
# 降维器 | |
decomposer = PCA(n_components=pca_components) | |
# 这里无需减去平均脸, 因为sklearn的实现中已经减去了数据集的均值 | |
decomposer.fit(X_train) | |
# 进行特征降维 | |
X_train_decompose = decomposer.transform(X_train) | |
X_test_decompose = decomposer.transform(X_test) | |
# 分类 | |
classifier = KNeighborsClassifier(n_neighbors=n_neighbor) | |
classifier.fit(X_train_decompose, y_train) | |
# 预测 | |
y_pred = classifier.predict(X_test_decompose) | |
acc = metrics.accuracy_score(y_test, y_pred) | |
print('ACC: {}%'.format(acc * 100)) | |
# 画roc曲线 | |
fpr, tpr = calc_roc(classifier.predict_proba(X_test_decompose), y_test, n_classes=len(set(y_test))) | |
plt.plot(fpr, tpr) | |
plt.xlabel('fpr') | |
plt.ylabel('tpr') | |
plt.tight_layout() | |
plt.savefig('./outputs/roc_pca_baeline.png.png') | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment