# Characters classification — Data

来源：https://www.kaggle.com/competitions/2018-characters-classification/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

#Data
Data stored as numpy arrays (use function [numpy.load](https://docs.scipy.org/doc/numpy/reference/generated/numpy.load.html) to restore data) and compressed with bzip2.

Train set is splitted into 4 parts. Each file econtains matrix of shape [Nх2]. Grayscale image of character is stored at the first column. At the second column is unicode number of character.

Test set is just array of grayscale images.

#Example
    import numpy as np
    import matplotlib as pyplot

    data = np.load('train-1.npy')
    width, height = 8, 8

    plt.figure(figsize=(16, 20))
    for n, (image, tag) in enumerate(data, 1):
        if n > width * height:
            break
        plt.subplot(height, width, n)
        plt.title(tag)
        plt.imshow(image, cmap='gray')