Implementing logistic regression using TensorFlow

We herein use 90% of the first 300,000 samples for training, the remaining 10% for testing, and assume that X_train_enc, Y_train, X_test_enc, and Y_test contain the correct data:

1. First, we import TensorFlow, transform X_train_enc and X_test_enc into a numpy array, and cast X_train_enc, Y_train, X_test_enc, and Y_test to float32:

   >>> import tensorflow as tf
   >>> X_train_enc = X_train_enc.toarray().astype('float32')
   >>> X_test_enc = X_test_enc.toarray().astype('float32')
   >>> Y_train = Y_train.astype('float32')
   >>> Y_test = Y_test.astype('float32')
   

2. We use the tf.data API to shuffle and batch data:

   >>> batch_size = 1000
   >>> train_data = tf.data.Dataset.from_tensor_slices((X_train_enc, Y_train))
   >>> train_data = train_data.repeat().shuffle(5000).batch...