CODEWITHSUNDEEP
pythonscikit-learnlogistic-regressionsigmoid
Vardaan Khanted
Vardaan Khanted

Reputation: 87

How to Convert Predict proba output from scikit learn to sigmoid

I am trying to use the predict_proba(X) from scikit learn to output probabilities, it returns a 2-d array with the probability of each class.

My understanding is that the function return logits, I am trying to convert them to Sigmoid using the following function

def sigmoid(x):
  return 1 / (1 + math.exp(-x))

If the 2-D array is of the form

probability class 1 probability class 2
0.8 0.2
0.7 0.3

What is the logic to just return a single probability based on these rows and the sigmoid function?

Thank you in advance

Upvotes: 0

Views: 1173

Answers (1)

Priya
Priya

Reputation: 743

predict_proba() gives you the probabilities for the target (0 and 1 in your case) in array form. The number of probabilities for each row is equal to the number of categories in target variable (assuming 2 in your case).

So if you want only probabilities of getting the output as only 1, then you could do

model.predict_proba(test)[:,1]

Alternately, if you want only the probabilities of getting zero then

model.predict_proba(test)[:,0]

Upvotes: 2

Related Questions