# 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)
import matplotlib.pyplot as plt, matplotlib.image as mpimg
from sklearn.model_selection import train_test_split
from sklearn import svm


# leggo i dati:
# - leggo le prime 5000 immagini
# - le feature delle immagini sono i valori da 1 in poi
# - i label delle immagini sono i valori nella prima colonna
train_df = pd.read_csv('../input/train.csv')
images = train_df.iloc[0:5000, 1:]
labels = train_df.iloc[0:5000, :1]
train_images, test_images, train_labels, test_labels = train_test_split(images, labels, train_size=0.8, random_state=0)


# visualizzo la prima immagine per vedere come viene
demo_image = train_images.iloc[1].as_matrix()
demo_image = demo_image.reshape((28,28))
plt.imshow(demo_image, cmap='gray')
plt.title(train_labels.iloc[1,0])