housing-data

               2010              2011             2012                 2013               2014                      2015                  2016                   2017
10th %ile:    909.7   1315.7 (144.6%)	  1400.0 (106.4%)	  1675.0 (119.6%)	  1748.3 (104.4%)	  2000.0 (114.4%)	  2195.0 (109.8%)	  2000.0 (91.1%)
20th %ile:   1115.0   1783.0 (159.9%)	  1850.0 (103.8%)	  2100.0 (113.5%)	  2200.0 (104.8%)	  2600.0 (118.2%)	  2600.0 (100.0%)	  2500.0 (96.2%)
30th %ile:   1650.0   2099.0 (127.2%)	  2199.0 (104.8%)	  2500.0 (113.7%)	  2695.0 (107.8%)	  2975.6 (110.4%)	  2995.0 (100.7%)	  2850.0 (95.2%)
40th %ile:   1800.0   2399.0 (133.3%)	  2462.0 (102.6%)	  2800.0 (113.7%)	  3000.0 (107.1%)	  3250.0 (108.3%)	  3400.0 (104.6%)	  3191.3 (93.9%)
50th %ile:   2084.0   2600.0 (124.8%)	  2700.0 (103.8%)	  3195.0 (118.3%)	  3395.0 (106.3%)	  3525.0 (103.8%)	  3750.0 (106.4%)	  3500.0 (93.3%)
60th %ile:   2334.0   2995.0 (128.3%)	  3000.0 (100.2%)	  3500.0 (116.7%)	  3700.0 (105.7%)	  3895.0 (105.3%)	  4154.3 (106.7%)	  3900.0 (93.9%)
70th %ile:   2565.0   3500.0 (136.5%)	  3495.0 (99.9%)	  4200.0 (120.2%)	  4200.0 (100.0%)	  4375.0 (104.2%)	  4695.0 (107.3%)	  4350.0 (92.7%)
80th %ile:   2890.0   4250.0 (147.1%)	  4000.0 (94.1%)	  5160.0 (129.0%)	  4900.0 (95.0%)	  4950.0 (101.0%)	  5377.0 (108.6%)	  4900.0 (91.1%)
90th %ile:   3735.3   5998.3 (160.6%)	  5465.0 (91.1%)	  7250.0 (132.7%)	  6250.0 (86.2%)	  6417.0 (102.7%)	  6500.0 (101.3%)	  5995.7 (92.2%)

main.go

package main

import (
	"bufio"
	"flag"
	"fmt"
	"log"
	"os"
	"regexp"
	"sort"
	"strconv"

	"github.com/kevinburke/housing-inventory-analysis/stats"
)

var parseRx = regexp.MustCompile(`\$[0-9]{2,10}`)

func getPrice(linePrices []string) int {
	if len(linePrices) == 0 {
		return -1
	}
	prices := make([]int, len(linePrices))
	for i := range linePrices {
		if len(linePrices[i]) < 2 {
			panic("too short: " + linePrices[i])
		}
		price, err := strconv.Atoi(linePrices[i][1:])
		if err != nil {
			panic(err)
		}
		prices[i] = price
	}
	if len(linePrices) == 1 {
		return prices[0]
	}
	if prices[0] < 200 && prices[1] < 200 {
		return -1
	}
	if prices[1] > prices[0] {
		return prices[1]
	}
	return prices[0]
}

func main() {
	flag.Parse()
	samples := make([]stats.Sample, 0)
	for i := 0; i < flag.NArg(); i++ {
		f, err := os.Open(flag.Arg(i))
		if err != nil {
			log.Fatal(err)
		}
		defer f.Close()
		bs := bufio.NewScanner(f)
		prices := make([]float64, 0)
		for bs.Scan() {
			linePrices := parseRx.FindAllString(bs.Text(), -1)
			if len(linePrices) > 0 {
				price := getPrice(linePrices)
				if price < 0 || price > 100000 {
					// sf is expensive, but not *that* expensive
					continue
				}
				prices = append(prices, float64(price))
			}
		}
		if err := bs.Err(); err != nil {
			log.Fatal(err)
		}
		sort.Float64s(prices)
		samples = append(samples, stats.Sample{Xs: prices})
	}
	fmt.Printf("total:  ")
	for i := 0; i < len(samples); i++ {
		if i > 0 {
			fmt.Printf("%14d\t", len(samples[i].Xs))
		} else {
			fmt.Printf("%11d\t", len(samples[i].Xs))
		}
	}
	fmt.Printf("\n")
	for i := float64(1); i <= 9; i++ {
		fmt.Printf("%dth %%ile: ", int(i)*10)
		for j := 0; j < len(samples); j++ {
			fmt.Printf("%8.1f ", samples[j].Percentile(0.1*i))
			if j > 0 {
				diff := 100 * samples[j].Percentile(0.1*i) / samples[j-1].Percentile(0.1*i)
				fmt.Printf("(%.1f%%)\t", diff)
			}
		}
		fmt.Printf("\n")
	}
}