How to read csv file and train data by Softmax regression in Tensorflow

I have one problem when training data. My problem is read csv file, then use softmax classification to estimate the grade of student (A,B or C) based on their time of study and attendance the class.

Grade of students with study and attendace time

I define, then load csv file as

COLUMNS = ["studytime", "attendance", "A", "B", "C"]
FEATURES = ["studytime", "attendance"]
LABEL = ["A", "B", "C"]
training_set = pd.read_csv("hw1.csv", skipinitialspace=True,
                       skiprows=1, names=COLUMNS)

After that I define tensor for features and lable like this

feature_cols = [tf.contrib.layers.real_valued_column(k) for k in FEATURES]
labels = [tf.contrib.layers.real_valued_column(k) for k in LABEL]

Then I follow the way to train softmax with MNIST data at Tensorflow for MNIST

But I don't how to define batch_xs and batch_ys to train in this loop

for _ in range(1000):
batch_xs=????
batch_ys=????
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

Could you help me to figure out this problem?

Thanks in advance,