House data analysis

house1.py

import csv
import numpy


def _read_csv(file_name):
    house_list = []
    with open(file_name, 'r') as f:
        reader = csv.DictReader(f)
        for house in reader:
            house_list.append((house['price'], house['bd'], house['sqft'],  house['date'].split('/')[-1]))
    return house_list

def _filter_by_bd(houses, min, max):
    house_list = []
    for price, bd, sqft, year in houses:
        for num in range(min, max+1):
            if str(num)+'bd' == bd:
                house_list.append((price, bd, sqft, year))
    return house_list

def _filter_by_year(houses):
    house_dict = {}
    for bd, sqft, price, year in houses:
        house_dict.setdefault(str(year), []).append((bd, sqft, price))
    return house_dict


## SCRIPT begins
house_list = _read_csv('seattle_w_header.csv')

print 'There are a total of', len(house_list), 'houses sold.'

house_by_year_dict = _filter_by_year(house_list)
print 'houses sold in 2019:', len(house_by_year_dict['2019'])
print 'houses sold in 2018:', len(house_by_year_dict['2018'])

min = 0
max = 10
filter_house = _filter_by_bd(house_list, min, max)
print min, 'to', max, 'bedrooms:', len(filter_house)

for i in range(min, max+1):
    bedroom = _filter_by_bd(filter_house, i, i)
    price_list = []
    for price, bd, sqft, year in bedroom:
        try:
            price_list.append(int(price))
        except:
            pass
    arr = numpy.array(price_list, dtype='int')
    print str(i) + ' bedrooms:', len(price_list)
    print 'mean', arr.mean(), '\tmedian', numpy.median(arr), '\tmin', numpy.min(arr), '\tmax', numpy.max(arr)
    print ''