#!/usr/bin/python3
from sklearn import datasets
from sklearn import preprocessing
from sklearn.cross_validation import train_test_split
import numpy as np
import tensorflow as tf

dataset = datasets.load_boston()
data, target = dataset.data, dataset.target

data_scaler = preprocessing.MinMaxScaler()
target_scaler = preprocessing.MinMaxScaler()

data = data_scaler.fit_transform(data)
target = target_scaler.fit_transform(target)

np.random.seed(0)

x_train, x_test, y_train, y_test = train_test_split(
    data, target, train_size=0.85
)


x = tf.placeholder(tf.float32, [None, 13], name="input")
W = tf.Variable(tf.zeros([13, 1]), name="weight")
b = tf.Variable(tf.zeros([1]), name="bias")

y = tf.add(tf.matmul(x, W), b)

y_ = tf.placeholder(tf.float32, name="target")
rmsle = tf.reduce_mean(tf.sqrt(tf.log(y_) - tf.log(y)))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(rmsle)

init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

last = 0
batchsize = 50
next_last = last + batchsize
while next_last < len(x_train):
    print("running next batch")
    next_last = last + batchsize
    if next_last > len(x_train):
        next_last = len(x_train)

    xt = x_train[last:next_last]
    yt = y_train[last:next_last]
    sess.run(train_step, feed_dict={x: xt, y_: yt})
    last = next_last

print("finished training")

diff = tf.sub(y, y_)
print(sess.run(diff, feed_dict={x: x_test, y_: y_test}))