Why does predict_proba function print the probabilities in reverse order?

Question

I am using scikit-learn to implement classification using Logistic Regression. The class labels are predicted using predict() function, while the predicted probabilities are printed using predict_proba() function.

The code snippet is pasted below:

# Partition the dataset into train and test data
X_train, X_test, y_train, y_test = train_test_split(ds_X, ds_y, test_size=0.33, random_state=42) 

y_pred = logreg.predict(X_test)                             # Predicted class labels from test features
y_predicted_proba = logreg.predict_proba(X_test)            # Predicted probabilities from test features

The predicted labels are printed as

array([1, 1, 1, 1, 1, 1, 1, 1, 0, 1.......... and so on

The corresponding predicted probabilities are printed as

array([[ 0.03667012,  0.96332988],
       [ 0.03638475,  0.96361525],
       [ 0.03809274,  0.96190726],
       [ 0.01746768,  0.98253232],
       [ 0.02742639,  0.97257361],
       [ 0.03676579,  0.96323421],
       [ 0.02881874,  0.97118126],
       [ 0.03082288,  0.96917712],
       [ 0.65332179,  0.34667821],
       [ 0.02091977,  0.97908023],
                   .
                   '
       and so on

Observe,
the first predicted label - 1
the first predicted probability - [ 0.03667012, 0.96332988]

Why is 0.03667012 printed first, instead of 0.96332988 ? Should it have been the other way?

Answer 1

The column 0 is the probability for class 0,

and the column 1 is the probability for the class 1.

If you have n classes the output probabilities shape will be (n_examples, n_classes).