Bank defaults prediction using FDIC dataset (80/100) about machine-learning-and-reinforcement-learning-in-finance HOT 2 OPEN

Hi, I found that the grader need the gradient to run n_epochs*n_batches times. But I think the random_batch function did not go through all X_trainTf is rarely seen in other ML implementation.

for epoch in range(n_epochs):        
        for batch_index in range(n_batches):
            X_trainTf_batch, y_trainTf_batch = random_batch(X_trainTf, y_trainTf, batch_size)
            sess.run([optimizer, loss], feed_dict={X: X_trainTf_batch, 
                                                   y: y_trainTf_batch})
    y_proba_val = sess.run(y_proba, feed_dict={X: X_testTf})

from machine-learning-and-reinforcement-learning-in-finance.

@minori111 , I see. Would you be able to post a screen shot of this set of code clearing the grader? And if so, would you like to make a pull request for it? (:

from machine-learning-and-reinforcement-learning-in-finance.