如何找到plot ROC曲线的真阳性率和假阳性率？

Question

How to draw a ROC curse using "matplotlib.pyplot". Its x-axis is "False Positive Rate", and y-axis is "True Positive Rate".

I have recall and precison with me. I know recall is true positive rate. However i dont know how to find false positive rate to plot ROC curve. It becomes easier to plot the curve when i have TPR and FPR with me. Here is a snapshot of the dataframe fow which i would like to dinf ROC curve. 'label_Num' is the actual value and 'prediction' is the predicted value.

Answer 1

You could use scikit-learn to generate the values to generate your ROC curve:

from sklearn.metrics import roc_curve

fpr, tpr, thresholds = roc_curve(y_true=y_true, y_score=y_pred)
plt.plot(fpr, tpr)

You just need to provide y_true and y_pred, which correspond to label_Num and prediction in your table.