import numpy as np
import tensorflow as tf
import pickle as pkl
from functools import reduce
from skimage.transform import resize


def to_one_hot(y):
    shape_one_hot = (np.size(y, 0), 36)
    one_hot_vectors = np.zeros(shape_one_hot)
    for i, label in enumerate(y):
        one_hot_vectors[i, label] = 1
    return one_hot_vectors

def rescale_images(x, new_shape):
    with tf.Session() as sess:
        to_resize = tf.image.resize_area(x.reshape([len(x), 56, 56, 1]), new_shape)
        resized = sess.run(to_resize)
    resized = resized.reshape([len(resized), reduce(lambda x, y: x * y, new_shape)])
    return resized


def next_batch(x_train, y_train, batch_size):
    idx = np.arange(0, len(x_train))
    np.random.shuffle(idx)
    batch_idx = idx[:batch_size]

    batch_x = x_train[batch_idx]
    batch_y = y_train[batch_idx]

    return batch_x, batch_y


def get_accuracy(x_val, y_val, x, y, y_, sess, keep_prob):
    correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    return sess.run(accuracy, feed_dict={x: x_val, y_: y_val, keep_prob: 1.0})

def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)

def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')


def train_model(x_train, y_train, x_val, y_val):
    # hyperparameters
    batch_size = 50
    epochs = 150

    # dimensions
    input_shape = np.size(x_train, 1)
    output_shape = 36

    x = tf.placeholder(tf.float32, [None, input_shape], name="network_input")
    y_ = tf.placeholder(tf.float32, [None, output_shape], name="network_output")

    x_image = tf.reshape(x, [-1, 28, 28, 1])

    W_conv1 = weight_variable([5, 5, 1, 32])
    b_conv1 = bias_variable([32])

    h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
    h_pool1 = max_pool_2x2(h_conv1)

    W_conv2 = weight_variable([5, 5, 32, 64])
    b_conv2 = bias_variable([64])

    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
    h_pool2 = max_pool_2x2(h_conv2)

    W_fc1 = weight_variable([7 * 7 * 64, 1024])
    b_fc1 = bias_variable([1024])

    h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

    W_fc2 = weight_variable([1024, 36])
    b_fc2 = bias_variable([36])

    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

    cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
    optimizer = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
    correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    sess = tf.InteractiveSession()
    sess.run(tf.global_variables_initializer())

    for epoch_idx in range(epochs):
        for batch_idx in range(400):
            batch_x, batch_y = next_batch(x_train, y_train, batch_size)
            sess.run(optimizer, feed_dict={x: batch_x, y_: batch_y, keep_prob: 0.75})
        val_accuracy = accuracy.eval(feed_dict={x: x_val, y_: y_val, keep_prob: 1.0})
        print("Epoch %d, validation accuracy %g" % (epoch_idx, val_accuracy))


def load_data(filename):
    with open(filename, 'rb') as file:
        x_train, y_train, x_val, y_val = pkl.load(file)
    return x_train, y_train, x_val, y_val


def save_data(filename, data):
    with open(filename, 'wb') as output:
        pkl.dump(data, output, pkl.HIGHEST_PROTOCOL)


if __name__ == '__main__':
    x_train, y_train, x_val, y_val = load_data('rotated-15_17.05.pkl')
    y_train = to_one_hot(y_train)
    y_val = to_one_hot(y_val)
    x_train = rescale_images(x_train, [28, 28])
    x_val = rescale_images(x_val, [28, 28])
    train_model(x_train, y_train, x_val, y_val)