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

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

data_scaler = preprocessing.MinMaxScaler()
data = data_scaler.fit_transform(data)

# use sklearn to fit the data values between 0 and 1
x_train, x_test, y_train, y_test = train_test_split(
    data, target, train_size=0.9
)


with tf.device('/cpu:0'):
    sess = tf.InteractiveSession()

    vecInput = tf.placeholder(tf.float32, [13], name="input")
    # 'unfitted' means not squeezed between 0 and 1, but real values
    numUnfittedTarget = tf.placeholder(tf.float32, [1], name="target")

    # numbers to scale the output between 0-1 and back to prices
    numFactor = tf.placeholder(tf.float32, [1], name="factor")
    numOffset = tf.placeholder(tf.float32, [1], name="offset")

    vecBias = tf.Variable(tf.random_uniform([13], minval=0, maxval=1), name="bias")
    vecBias = tf.Print(vecBias, [vecBias], "vecbias")
    # vecWeights is not a true vector, it is turned by 90 degrees
    vecWeights = tf.Variable(tf.random_uniform([1, 13], minval=0, maxval=1), name="weight")
    vecWeights = tf.Print(vecWeights, [vecWeights], "vecweights")

    # sum((i + b) * w)
    matWeighted = tf.mul(tf.add(vecInput, vecBias), vecWeights)
    matWeighted = tf.Print(matWeighted, [matWeighted], "matweighted: ")  # DEBUG
    vecNetinput = tf.reduce_sum(matWeighted, 1)
    vecNetinput = tf.Print(vecNetinput, [vecNetinput], "netinput: ")  # DEBUG
    vecLayerOutput = tf.sigmoid(vecNetinput)
    vecLayerOutput = tf.Print(vecLayerOutput, [vecLayerOutput], "vecLayerOutput: ")  # DEBUG

    # since this is the last layer, vecOutput is a numOutput
    numOutput = tf.reduce_sum(vecLayerOutput)
    # unscale the output
    numUnfittedOutput = tf.add(tf.mul(numOutput, numFactor), numOffset)
    numUnfittedOutput = tf.Print(numUnfittedOutput, [numUnfittedOutput], "unfitted output: ")  # DEBUG

    numUnfittedTarget = tf.Print(numUnfittedTarget, [numUnfittedTarget], "numUnfittedTarget: ")  # DEBUG
    numDifference = tf.sub(numUnfittedOutput, numUnfittedTarget)
    numDifference = tf.Print(numDifference, [numDifference], "numDifference: ")
    numMSE = tf.reduce_sum(tf.square(numDifference))
    numMSE = tf.Print(numMSE, [numMSE], "MSE: ")

    summaryMSE = tf.scalar_summary("MSE", numMSE)
    summaryDifference = tf.scalar_summary("Mean difference", numDifference)
    summaries = tf.merge_all_summaries()
    writer = tf.train.SummaryWriter("/tmp/boston_logs", sess.graph_def)

    # all variables have to be specified here
    sess.run(tf.initialize_all_variables())
    train_step = tf.train.GradientDescentOptimizer(0.01).minimize(numMSE)


factor = max(target) - min(target)
offset = min(target)

for count in range(0, len(x_train)):
    trainsteps = 100
    print("count " + str(count))
    for i in range(0, trainsteps):  # 100 epochs
        if i % 10 == 9:
            feed = {
                vecInput: x_test[0],
                numUnfittedTarget: [y_test[0]],
                numFactor: [factor],
                numOffset: [offset]
            }
            result = sess.run([summaries, numMSE], feed_dict=feed)
            #print("test " + result[0])
            #writer.add_summary(result[0], count * trainsteps + i)

        sess.run(train_step,
                 feed_dict={
                     vecInput: x_train[count],
                     numUnfittedTarget: [y_train[count]],
                     numFactor: [factor],
                     numOffset: [offset]
                 })

print("finished training")

#yt = [y_test]
## debug
#print(" --------- ")
#print("mean difference to test data: ")
#print(sess.run(mse, feed_dict={input_matrix: x_test, real: yt, fact: factor, offs: offset}))
#print(sess.run(diff, feed_dict={input_matrix: x_test, real: yt, fact: factor, offs: offset}))