Python: how to calculate true positive, true negative, false positive, and false negative

Question

How can I compute true positive, true negative, false positive, and false negative using confusion matrix or using predicted class and true class?

Answer 1

You can use functions of sklearn library or a simple python script to caculate true positive, true negative, false positive, and false negative. Here are two approaches; you can try one of these:

Approach 1:

>>> y_true = [1, 0, 1, 0, 0, 1, 1, 0, 1]

>>> y_pred = [1, 1, 0, 0, 1, 1, 1, 1, 0]

>>> from sklearn.metrics import confusion_matrix

>>> confusion_matrix(y_true, y_pred)

array([[1, 3],

       [2, 3]], dtype=int64)

>>> confusion_matrix(y_true, y_pred).ravel()

array([1, 3, 2, 3], dtype=int64)

>>> tn, fp, fn, tp = confusion_matrix(y_true, y_pred).ravel()

>>> tn, fp, fn, tp

(1, 3, 2, 3)

 Approach 2:

>>> y_true = [1, 0, 1, 0, 0, 1, 1, 0, 1]

>>> y_pred = [1, 1, 0, 0, 1, 1, 1, 1, 0]

>>> (tn, fp, fn, tp) = (0,0,0,0)

>>> for i in range(len(y_true)):

...     if (y_true[i]==1 and y_pred[i] ==1):

...             tp+=1

...     elif (y_true[i]==1 and y_pred[i] ==0):

...             fn+=1

...     elif (y_true[i]==0 and y_pred[i] ==1):

...             fp+=1

...     elif (y_true[i]==0 and y_pred[i] == 0):

...             tn+=1

...

>>> tn, fp, fn, tp

(1, 3, 2, 3)