#!/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)
target_scaler = preprocessing.MinMaxScaler()
target = target_scaler.fit_transform(target)

# 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'):
    # TODO use name scopes

    sess = tf.InteractiveSession()

    vecInput = tf.placeholder(tf.float32, [13], name="input")
    numTarget = tf.placeholder(tf.float32, [1], name="target")

    vecBias = tf.Variable(tf.zeros([13]), name="bias")
    # vecWeights is not a true vector, it is turned by 90 degrees
    vecWeights = tf.Variable(tf.zeros([1, 13]), name="weight")

    # sum((i + b) * w)
    matWeighted = tf.mul(tf.add(vecInput, vecBias), vecWeights)
    vecNetinput = tf.reduce_sum(matWeighted, 1)
    vecLayerOutput = tf.sigmoid(vecNetinput)

    # since this is the last layer, vecOutput is a numOutput
    numOutput = tf.reduce_sum(vecLayerOutput)  # TODO needed?

    numDifference = tf.sub(numOutput, numTarget)
    numMSE = tf.square(numDifference)
    train_step = tf.train.GradientDescentOptimizer(0.01).minimize(numMSE)

    # summaries
    summaryBias = tf.histogram_summary("bias", vecBias)
    summaryWeights = tf.histogram_summary("weigths", vecWeights)
    summaryDifference = tf.scalar_summary(["difference"], numDifference)
    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())


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

        # TODO run a complete set
        result = sess.run([summaries, train_step],
                          feed_dict={
                            vecInput: x_train[count],
                            numTarget: [y_train[count]]
                          })
        writer.add_summary(result[0], count * trainsteps + i)  # TODO this slows down

print("finished training")

# yt = [y_test]
# # debug
# print(" --------- ")
# print("mean difference to test data: ")
# TODO