import os, cv2, random
import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
from matplotlib import ticker
import seaborn as sns
#%matplotlib inline 

from keras.models import Sequential
from keras.layers import Input, Dropout, Flatten, Convolution2D, MaxPooling2D, Dense, Activation
from keras.optimizers import RMSprop
from keras.callbacks import ModelCheckpoint, Callback, EarlyStopping
from keras.utils import np_utils

TRAIN_DIR = '../input/train/'
TEST_DIR = '../input/test/'

ROWS = 32
COLS = 32
CHANNELS = 1

train_images = [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR)] # use this for full dataset
train_dogs =   [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR) if 'dog' in i]
train_cats =   [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR) if 'cat' in i]

test_images =  [TEST_DIR+i for i in os.listdir(TEST_DIR)]


# slice datasets for memory efficiency on Kaggle Kernels, delete if using full dataset
train_images = train_dogs[:1000] + train_cats[:1000]
random.shuffle(train_images)
test_images =  test_images[:25]

def read_image(file_path):
    img = cv2.imread(file_path, cv2.IMREAD_GRAYSCALE) #cv2.IMREAD_GRAYSCALE
    return cv2.resize(img, (ROWS, COLS), interpolation=cv2.INTER_CUBIC)


def prep_data(images):
    count = len(images)
    data = np.ndarray((count, CHANNELS, ROWS, COLS), dtype=np.uint8)

    for i, image_file in enumerate(images):
        image = read_image(image_file)
        data[i] = image.T
        if i%250 == 0: print('Processed {} of {}'.format(i, count))
    
    return data

train = prep_data(train_images)
test = prep_data(test_images)

print("Train shape: {}".format(train.shape))
print("Test shape: {}".format(test.shape))

labels = []
for i in train_images:
    if 'dog' in i:
        labels.append(1)
    else:
        labels.append(0)

sns.countplot(labels)
sns.plt.title('Cats and Dogs')

def show_cats_and_dogs(idx):
    cat = read_image(train_cats[idx])
    dog = read_image(train_dogs[idx])
    pair = np.concatenate((cat, dog), axis=1)
    plt.figure(figsize=(10,5))
    plt.imshow(pair)
    plt.show()
    
for idx in range(0,5):
    show_cats_and_dogs(idx)
    
optimizer = RMSprop(lr=1e-4)
objective = 'binary_crossentropy'


def catdog():
    
    model = Sequential()

    model.add(Convolution2D(32, 1, 1, border_mode='same', input_shape=(1, ROWS, COLS), activation='relu'))
    model.add(Convolution2D(32, 1, 1, border_mode='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(1, 1)))

    model.add(Convolution2D(64, 1, 1, border_mode='same', activation='relu'))
    model.add(Convolution2D(64, 1, 1, border_mode='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(1, 1)))
    
    model.add(Convolution2D(128, 1, 1, border_mode='same', activation='relu'))
    model.add(Convolution2D(128, 1, 1, border_mode='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(1, 1)))
    
    model.add(Convolution2D(256, 1, 1, border_mode='same', activation='relu'))
    model.add(Convolution2D(256, 1, 1, border_mode='same', activation='relu'))
#     model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))
    model.add(MaxPooling2D(pool_size=(1, 1)))

#     model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))
#     model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))
#     model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))
#     model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Flatten())
    model.add(Dense(256, activation='relu'))
    model.add(Dropout(0.5))
    
    model.add(Dense(256, activation='relu'))
    model.add(Dropout(0.5))

    model.add(Dense(1))
    model.add(Activation('sigmoid'))

    model.compile(loss=objective, optimizer=optimizer, metrics=['accuracy'])
    return model


model = catdog()