import matplotlib.pyplot as plt
import numpy as np
import random
import pandas as pd

# 'price.csv' is the renamed raw data file downloaded from
# https://data.gov.sg/dataset/resale-flat-prices
# original file name :
# resale-flat-prices-based-on-registration-date-from-jan-2017-onwards

data = pd.read_csv('price.csv')
x = data['resale_price']

plt.rcParams.update({'font.size': 16})
fig, axs = plt.subplots(tight_layout=True)
axs.hist(x, bins=30)
plt.title('Singapore public housing 2017-01 to 2020-10')
plt.xlabel('resale price')
plt.ylabel('count')

sample_mean = x.sample(30).mean()
pop_mean = x.mean()
pop_std = x.std()

print(pop_mean) # preview the values
print(sample_mean)

plt.axvline(pop_mean) # guiding lines
plt.axvline(sample_mean)

plt.show()

# figure is then modified in GIMP