import numpy as np
import sys, os
import paddle.v2 as paddle

# init
paddle.init(use_gpu=False, trainer_count=1)

# network config
x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(13))
y_predict = paddle.layer.fc(input=x,
                                size=1,
                                act=paddle.activation.Linear())
y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
cost = paddle.layer.square_error_cost(input=y_predict, label=y)

# create parameters
parameters = paddle.parameters.create(cost)

test_data_creator = paddle.dataset.uci_housing.test()
test_data = []
test_label = []

for item in test_data_creator():
    test_data.append((item[0],))
    test_label.append(item[1])
    if len(test_data) == 5:
        break

print test_data

probs = paddle.infer(
    output_layer=y_predict, parameters=parameters, input=test_data)

for i in xrange(len(probs)):
    print "label=" + str(test_label[i][0]) + ", predict=" + format(probs[i][0] * 1000)
    print "label=" + str(test_label[i][0]) + ", predict=" + str(probs[i][0])

label=8.5, predict=2.0623545789e+40
label=8.5, predict=2.06235e+37
label=5.0, predict=3.06239234827e+40
label=5.0, predict=3.06239e+37
label=11.9, predict=1.27370274449e+40
label=11.9, predict=1.2737e+37
label=27.9, predict=9.41573153244e+39
label=27.9, predict=9.41573e+36
label=17.2, predict=7.69269013059e+39
label=17.2, predict=7.69269e+36