import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import seaborn as sns
from sklearn.model_selection import train_test_split
import tensorflow as tf
from keras.utils.np_utils import to_categorical  # convert to one-hot-encoding
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D
from keras.optimizers import RMSprop
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ReduceLROnPlateau

from keras.backend import tensorflow_backend

config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
session = tf.Session(config=config)
tensorflow_backend.set_session(session)

np.random.seed(2)

Y_train = np.load("kmnist-train-labels.npz")["arr_0"].astype(np.int)
X_train = np.load("kmnist-train-imgs.npz")["arr_0"].astype(np.float)
test = np.load("kmnist-test-imgs.npz")["arr_0"].astype(np.float)

X_train = X_train / 255.0
test = test / 255.0

X_train = X_train[:, :, :, np.newaxis]
test = test[:, :, :, np.newaxis]
Y_train = to_categorical(Y_train, num_classes=10)
random_seed = 2

X_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size=0.1, random_state=random_seed)

model = Sequential()

model.add(Conv2D(filters=32, kernel_size=(5, 5), padding='Same',
                 activation='relu', input_shape=(28, 28, 1)))
model.add(Conv2D(filters=32, kernel_size=(5, 5), padding='Same',
                 activation='relu'))
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='Same',
                 activation='relu'))
model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='Same',
                 activation='relu'))
model.add(MaxPool2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(64, activation="relu"))
model.add(Dropout(0.5))
model.add(Dense(10, activation="softmax"))
optimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)

model.compile(optimizer=optimizer, loss="categorical_crossentropy", metrics=["accuracy"])
learning_rate_reduction = ReduceLROnPlateau(monitor='val_acc',
                                            patience=3,
                                            verbose=1,
                                            factor=0.5,
                                            min_lr=0.0001)
epochs = 1  # Turn epochs to 30 to get 0.9967 accuracy
batch_size = 86

datagen = ImageDataGenerator(
    featurewise_center=False,  # set input mean to 0 over the dataset
    samplewise_center=False,  # set each sample mean to 0
    featurewise_std_normalization=False,  # divide inputs by std of the dataset
    samplewise_std_normalization=False,  # divide each input by its std
    zca_whitening=False,  # apply ZCA whitening
    rotation_range=10,  # randomly rotate images in the range (degrees, 0 to 180)
    zoom_range=0.1,  # Randomly zoom image
    width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
    height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
    horizontal_flip=False,  # randomly flip images
    vertical_flip=False)  # randomly flip images

datagen.fit(X_train)

history = model.fit_generator(datagen.flow(X_train, Y_train, batch_size=batch_size),
                              epochs=epochs, validation_data=(X_val, Y_val),
                              verbose=2, steps_per_epoch=X_train.shape[0] // batch_size
                              , callbacks=[learning_rate_reduction])

results = model.predict(test)
results = np.argmax(results,axis = 1)
results = pd.Series(results,name="Label")
submission = pd.concat([pd.Series(range(1,10001),name = "ImageId"),results],axis = 1)
submission.to_csv("submit.csv",index=False)