# 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

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from tensorflow import keras
from sklearn.model_selection import train_test_split
from tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers import Dense, Flatten, Conv2D, Dropout

img_rows, img_cols = 28, 28
num_classes = 10

def data_prep(raw):
    out_y = keras.utils.to_categorical(raw.label, num_classes)

    num_images = raw.shape[0]
    x_as_array = raw.values[:,1:]
    x_shaped_array = x_as_array.reshape(num_images, img_rows, img_cols, 1)
    out_x = x_shaped_array / 255
    return out_x, out_y

def data_preptest(raw):
    

    num_images = raw.shape[0]
    x_shaped_array = raw.values.reshape(num_images, img_rows, img_cols, 1)
    out_x = x_shaped_array / 255
    return out_x

train_file = "../input/digit-recognizer/train.csv"
raw_data = pd.read_csv(train_file)
x, y = data_prep(raw_data)

test_file = "../input/digit-recognizer/test.csv"
raw_datatest = pd.read_csv(test_file)
x1= data_preptest(raw_datatest)


model=Sequential()
model.add(Conv2D(20, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=(img_rows, img_cols, 1)))
model.add(Conv2D(20, kernel_size=(3, 3), activation='relu'))

model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer='adam',
              metrics=['accuracy'])
model.fit(x, y,
          batch_size=128,
          epochs=2,
          validation_split = 0.2)


y1=model.predict_classes(x1, verbose=2)


sub_df = pd.DataFrame()
sub_df["ImageId"] = list(range(1, x1.shape[0] + 1))
sub_df["Label"] = y1
sub_df.to_csv("submission.csv",header=True, index=False)

print("Amount of test points:", x1.shape[0])
print("Amount of predictions:", len(y1))

sub_df.head()

# you could use any filename. We choose submission here