---恢复内容开始---
1. k_fold = KFold(n_split, shuffle) 构造KFold的索引切割器
k_fold.split(indices) 对索引进行切割。
参数说明:n_split表示切割的份数,假设切割的份数为10,那么有9份是训练集有1份是测试集,shuffle是否进行清洗,indices表示需要进行切割的索引值
import numpy as np from sklearn.model_selection import KFold indices = np.arange(20) k_fold = KFold(n_splits=10, shuffle=False) train_test_set = k_fold.split(indices) for (train_set, test_set) in train_test_set: print(train_set) print(test_set)
2.np.logical_and(pred_issame, test_issame) # 如果pred_issame中的元素和test_issame都是True, 返回的也是True,否者返回的是False
参数说明:pred_issame输入的bool数组,test_issame输入的bool数组
import numpy as np pred_issame = np.array([True, True, False, False]) actual_issame = np.array([False, True, False, False]) print(np.logical_and(pred_issame, actual_issame))
# [False True False False]
3. np.logical_not(pred_issame) # 将输入的True转换为False,False转换为Train
参数说明: pred_issame 表示输入的bool数组
import numpy as np pred_issame = np.array([True, True, False, False]) print(np.logical_not(pred_issame)) # [False False True True]
第一步:构造indices的索引值,使用KFold对incides进行train_set和test_set的生成
第二步: 使用np.arange(0, 4, 0.4) 构造threshold的列表,循环threshold列表
第三步:
第一步: 使用np.less(dist, threshold) 来获得预测结果
第二步:
tp = np.logical_and(pred_issame, actual_issame) # 正样本被判定为正样本
fp = np.logical_and(pre_issame, np.logical_not(actual_issame)) # 负样本被判断为正样本
tn = np.logical_and(np.logical_not(pre_issame), np.logical_not(actual_issame)) # 负样本判断为负样本
fn = np.logical_and(np.logical_not(pre_issame), actual_issame) # 正样本被判断为负样本
tpr = 0 if tp + fn == 0 else float(tp) / float(tp + fn) # 召回率
fpr = 0 if fp + tn == 0 else float(tn) / float(fp + tn)
accur = (tp + tn) / (tp+fp+fn+tn)
第四步:使用threshold_max = np.argmax(accur) # 获得准确率最大的索引值,即为thresholds最好的索引值
def calculate_roc(thresh, dist, actual_issame): pre_issame = np.less(dist, thresh) tp = np.sum(np.logical_and(pre_issame, actual_issame)) # 正样本被预测为正样本 fp = np.sum(np.logical_and(pre_issame, np.logical_not(actual_issame))) # 负样本被预测为正样本 tn = np.sum(np.logical_and(np.logical_not(pre_issame), np.logical_not(actual_issame))) # 负样本被预测为负样本 fn = np.sum(np.logical_and(np.logical_not(pre_issame), actual_issame)) # 正样本被预测为负样本 tpr = 0 if tp + tn == 0 else float(tp) / float(tp + fn) fpr = 0 if tp + fn == 0 else float(tn) / float(fp + tn) accur = ((tp + tn) / dist.size) return tpr, fpr, accur # import numpy as np from sklearn.model_selection import KFold distance = np.array([0.1, 0.2, 0.3, 0.25, 0.33, 0.20, 0.18, 0.24]) actual_issame = np.array([True, True, False, False, False, True, True, False]) k_fold = KFold(n_splits=4, shuffle=False) indices = np.arange(len(distance)) for k_num, (train_set, test_set) in enumerate(k_fold.split(indices)): thresholds = np.arange(0, 1, 0.04) accuracy = np.zeros(len(thresholds)) for threshold_index, threshold in enumerate(thresholds): _, _, accuracy[threshold_index] = calculate_roc(threshold, distance[train_set], actual_issame[train_set]) max_threshold = np.argmax(accuracy) print(thresholds[max_threshold])
---恢复内容结束---