from scipy.cluster import hierarchy
import pandas as pd
from matplotlib import pyplot as plt


def start():
    data = pd.read_csv('sberbank_data.csv', index_col='id')
    x = data[['full_sq', 'price_doc']]
    plt.figure(1, figsize=(16, 9))
    plt.title('Дендрограмма кластеризации цен')

    prices = [0, 0, 0, 0]
    for ind, val in x.iterrows():
        val = val['price_doc'] / val['full_sq']
        if val < 100000:
            prices[0] = prices[0] + 1
        elif val < 300000:
            prices[1] = prices[1] + 1
        elif val < 500000:
            prices[2] = prices[2] + 1
        else:
            prices[3] = prices[3] + 1
    print('Результаты подчсёта ручного распределения:')
    print('низких цен:'+str(prices[0]))
    print('средних цен:'+str(prices[1]))
    print('высоких цен:'+str(prices[2]))
    print('премиальных цен:'+str(prices[3]))

    hierarchy.dendrogram(hierarchy.linkage(x, method='single'),
                         truncate_mode='lastp',
                         p=15,
                         orientation='top',
                         leaf_rotation=90,
                         leaf_font_size=8,
                         show_contracted=True)

    plt.show()


start()