# Plot ad hoc mnist instances
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import numpy

from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Convolution2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
K.set_image_dim_ordering('th')

# fix random seed for reproducibility
seed = 7
np.random.seed(seed)

"""
# ALTERNATE METHOD USING CSV!
#fetch the train data
data = pd.read_csv("train.csv")
train_data = data.iloc[:,1:].values
X_train = np.reshape((train_data),(train_data.shape[0],1,28,28)).astype('float32')
y_train = data.iloc[:,0:1].values
print X_train.shape
print y_train.shape

#fetch the test data
dataTest = pd.read_csv("test.csv")
test_data = dataTest.values
X_test = np.reshape((test_data),(test_data.shape[0],1,28,28)).astype('float32')
#print X_test.shape
"""

# METHOD USING KERAS!
"""
#[pixels][width][height] ::: For grayscale, pixel = 1, RGB, pixel = 3
"""
from keras.datasets import mnist
(X_train, y_train), (X_test, y_test) = mnist.load_data()

# reshape to be [samples][pixels][width][height]
X_train = X_train.reshape(X_train.shape[0], 1, 28, 28).astype('float32')
X_test = X_test.reshape(X_test.shape[0], 1, 28, 28).astype('float32')
#print X_train.shape

# normalize inputs from 0-255 to 0-1
X_train = X_train / 255
X_test = X_test / 255
#print y_train.shape
#print y_test.shape

# one hot encode outputs
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]
#print y_train
#print y_train.shape
#print y_test.shape
###############################################################################################################

"""
#ADAM gradient descent algorithm is used to learn the weights.
"""

def larger_model():
    # create model
    model = Sequential()
    model.add(Convolution2D(30, 5, 5, border_mode='valid', input_shape=(1, 28, 28), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Convolution2D(15, 3, 3, activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dense(50, activation='relu'))
    model.add(Dense(num_classes, activation='softmax'))
    # Compile model
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model

# build the model
model = larger_model()
# Fit the model
model.fit(X_train, y_train, validation_data=(X_test, y_test), nb_epoch=100, batch_size=200, verbose=2)
# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("Baseline Error: %.2f%%" % (100-scores[1]*100))

#storing the model in an h5 file
model.save('my_model.h5')