# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load in 

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory

import os
print(os.listdir("../input"))

# Any results you write to the current directory are saved as output.

import keras 
from keras.utils import to_categorical
from keras import layers
from keras import models
from keras import optimizers


test_data = pd.read_csv('../input/test.csv')
train_data = pd.read_csv('../input/train.csv')

train_x = train_data.loc['0':, 'pixel0':]
train_y = train_data.loc['0':, 'label']

train_x = np.array(train_x).reshape(42000, 28, 28, 1)
test_data = np.array(test_data).reshape(28000, 28, 28, 1)

train_x = train_x.astype('float32') / 255
test_data = test_data.astype('float32') / 255

train_y = to_categorical(train_y)

model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.Dropout(0.2))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dropout(0.2))
model.add(layers.Dense(129, activation='relu'))
model.add(layers.Dropout(0.2))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))

model.compile(optimizer=optimizers.RMSprop(lr=2e-4),
              loss='categorical_crossentropy',
              metrics=['accuracy'])
              
model.fit(train_x, train_y, epochs=100, batch_size=128)

prediction = model.predict_classes(test_data)

submission = pd.DataFrame({"ImageId": list(range(1,len(prediction)+1)),
                         "Label": prediction})
submission.to_csv("submission.csv", index=False, header=True)