[英]HOW TO FIND AND PLOT AUC score from TPR and FPR
我有不同閾值的真陽性率和假陽性率。 現在我需要在不使用 sckit-learn 庫的情況下計算 AUC_ROC 曲線。
TPR and FPR values are below:
TPR = [0.0001,0.0002,0.0003,0.0004,0.0005,0.0006,0.0007,0.0008,0.0009,0.001]
FPR = [0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0]
有人可以告訴如何計算分數。 我使用了 numpy.trapz(TPR,FPR)。 但是輸出很奇怪。 你能建議如何做到這一點嗎？
也許，輸入數組應該包含邊界點（ (0,0) 和 (1,1) ），以便np.trapz正常工作。 此外，讓所有 FPR 為零似乎很奇怪
將sklearn的roc_auc_score用作指標時，如何找到錯誤率？
[英]How to find the error rate when sklearn's roc_auc_score is used as metrics?
在 y_true 變量中查找單個 class 1 的 roc/auc/auc-roc 分數
[英]find roc/auc/auc-roc score for single class 1's in y_true variable
StatsModels 的預測 function 如何與 scikit-learn 的 roc_auc_score 交互？
[英]How does the predict function of StatsModels interact with roc_auc_score of scikit-learn?
玩家領先兩分后如何從分數列表中查找剩余分數
[英]How to find remaining scores from score list after a player is ahead by two
聲明:本站的技術帖子網頁，遵循CC BY-SA 4.0協議，如果您需要轉載，請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.