import numpy as np
import pandas as pd
import tensorflow as tf

tf.enable_eager_execution()

N_FEATURES = 10
N_SAMPLES = 100
N_OUTPUTS = 2
BATCH_SIZE = 8
EPOCHS = 5

# prepare fake data
train_x = pd.DataFrame(np.random.rand(N_SAMPLES, N_FEATURES))
train_x.to_csv('train_x.csv', index=False)
train_y = pd.DataFrame(np.random.rand(N_SAMPLES, N_OUTPUTS))
train_y.to_csv('train_y.csv', index=False)

def create_model():
    model = tf.keras.models.Sequential([
        tf.keras.layers.Dense(N_OUTPUTS, input_shape=(N_FEATURES,)),
        tf.keras.layers.Activation('linear'),
    ])
    model.compile('sgd', 'mse')

    return model

train_x = tf.data.experimental.CsvDataset('train_x.csv', [tf.float32] * N_FEATURES, header=True)
train_y = tf.data.experimental.CsvDataset('train_y.csv', [tf.float32] * N_OUTPUTS, header=True)
dataset = tf.data.Dataset.zip((train_x, train_y))
dataset = dataset.batch(BATCH_SIZE)
dataset = dataset.repeat(EPOCHS)

model = create_model()
model.fit(dataset, steps_per_epoch=N_SAMPLES/BATCH_SIZE, epochs=EPOCHS)