library(readr)
data <- read_csv("/Users/sunyang/Downloads/data.csv")
## Rows: 4600 Columns: 18
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): street, city, statezip, country
## dbl (13): price, bedrooms, bathrooms, sqft_living, sqft_lot, floors, waterf...
## dttm (1): date
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
library(ggplot2)
options(repr.plot.width = 12, repr.plot.height = 8)
data <- read.csv(file = '/Users/sunyang/Downloads/data.csv')
head(data)
tail(data)
print(paste("Number of records: ", nrow(data)))
## [1] "Number of records: 4600"
print(paste("Number of features: ", ncol(data)))
## [1] "Number of features: 18"
summary(data)
## date price bedrooms bathrooms
## Length:4600 Min. : 0 Min. :0.000 Min. :0.000
## Class :character 1st Qu.: 322875 1st Qu.:3.000 1st Qu.:1.750
## Mode :character Median : 460943 Median :3.000 Median :2.250
## Mean : 551963 Mean :3.401 Mean :2.161
## 3rd Qu.: 654962 3rd Qu.:4.000 3rd Qu.:2.500
## Max. :26590000 Max. :9.000 Max. :8.000
## sqft_living sqft_lot floors waterfront
## Min. : 370 Min. : 638 Min. :1.000 Min. :0.000000
## 1st Qu.: 1460 1st Qu.: 5001 1st Qu.:1.000 1st Qu.:0.000000
## Median : 1980 Median : 7683 Median :1.500 Median :0.000000
## Mean : 2139 Mean : 14852 Mean :1.512 Mean :0.007174
## 3rd Qu.: 2620 3rd Qu.: 11001 3rd Qu.:2.000 3rd Qu.:0.000000
## Max. :13540 Max. :1074218 Max. :3.500 Max. :1.000000
## view condition sqft_above sqft_basement
## Min. :0.0000 Min. :1.000 Min. : 370 Min. : 0.0
## 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:1190 1st Qu.: 0.0
## Median :0.0000 Median :3.000 Median :1590 Median : 0.0
## Mean :0.2407 Mean :3.452 Mean :1827 Mean : 312.1
## 3rd Qu.:0.0000 3rd Qu.:4.000 3rd Qu.:2300 3rd Qu.: 610.0
## Max. :4.0000 Max. :5.000 Max. :9410 Max. :4820.0
## yr_built yr_renovated street city
## Min. :1900 Min. : 0.0 Length:4600 Length:4600
## 1st Qu.:1951 1st Qu.: 0.0 Class :character Class :character
## Median :1976 Median : 0.0 Mode :character Mode :character
## Mean :1971 Mean : 808.6
## 3rd Qu.:1997 3rd Qu.:1999.0
## Max. :2014 Max. :2014.0
## statezip country
## Length:4600 Length:4600
## Class :character Class :character
## Mode :character Mode :character
##
##
##
colnames(data)
## [1] "date" "price" "bedrooms" "bathrooms"
## [5] "sqft_living" "sqft_lot" "floors" "waterfront"
## [9] "view" "condition" "sqft_above" "sqft_basement"
## [13] "yr_built" "yr_renovated" "street" "city"
## [17] "statezip" "country"
unique(data$city)
## [1] "Shoreline" "Seattle" "Kent"
## [4] "Bellevue" "Redmond" "Maple Valley"
## [7] "North Bend" "Lake Forest Park" "Sammamish"
## [10] "Auburn" "Des Moines" "Bothell"
## [13] "Federal Way" "Kirkland" "Issaquah"
## [16] "Woodinville" "Normandy Park" "Fall City"
## [19] "Renton" "Carnation" "Snoqualmie"
## [22] "Duvall" "Burien" "Covington"
## [25] "Inglewood-Finn Hill" "Kenmore" "Newcastle"
## [28] "Mercer Island" "Black Diamond" "Ravensdale"
## [31] "Clyde Hill" "Algona" "Skykomish"
## [34] "Tukwila" "Vashon" "Yarrow Point"
## [37] "SeaTac" "Medina" "Enumclaw"
## [40] "Snoqualmie Pass" "Pacific" "Beaux Arts Village"
## [43] "Preston" "Milton"
maindf <- data[,c("price","bedrooms","sqft_living","floors",
"sqft_lot", "condition", "view", "yr_built")]
head(maindf)
maindf$oldbuilt <- as.integer(format(Sys.Date(), "%Y")) - maindf$yr_built
drops <- c("yr_built")
maindf = maindf[ , !(names(maindf) %in% drops)]
cor(maindf)
## price bedrooms sqft_living floors sqft_lot
## price 1.00000000 0.20033629 0.43041003 0.15146080 0.050451295
## bedrooms 0.20033629 1.00000000 0.59488406 0.17789490 0.068819355
## sqft_living 0.43041003 0.59488406 1.00000000 0.34485027 0.210538454
## floors 0.15146080 0.17789490 0.34485027 1.00000000 0.003749750
## sqft_lot 0.05045130 0.06881935 0.21053845 0.00374975 1.000000000
## condition 0.03491454 0.02507986 -0.06282598 -0.27501339 0.000558114
## view 0.22850417 0.11102800 0.31100944 0.03121095 0.073906741
## oldbuilt -0.02185683 -0.14246104 -0.28777522 -0.46748066 -0.050706346
## condition view oldbuilt
## price 0.034914537 0.22850417 -0.02185683
## bedrooms 0.025079856 0.11102800 -0.14246104
## sqft_living -0.062825979 0.31100944 -0.28777522
## floors -0.275013395 0.03121095 -0.46748066
## sqft_lot 0.000558114 0.07390674 -0.05070635
## condition 1.000000000 0.06307728 0.39969823
## view 0.063077281 1.00000000 0.06446506
## oldbuilt 0.399698234 0.06446506 1.00000000
library(ggcorrplot)
corr <- round(cor(maindf), 1)
# Plot
ggcorrplot(corr,
type = "lower",
lab = TRUE,
lab_size = 5,
colors = c("tomato2", "white", "springgreen3"),
title="Correlogram of Housing Dataset",
ggtheme=theme_bw)
pairs(~bedrooms + sqft_living + floors + condition, data = maindf,
main = "Scatterplot Matrix")
theme_set(theme_bw())
g <- ggplot(maindf, aes(bedrooms, floors))
g + geom_count(col="tomato3", show.legend=F) +
labs(y="floors",
x="bedrooms",
title="Bedrooms vs Floors")
plot(x = maindf$sqft_living, y = maindf$sqft_lot,
xlab = "sqft_living",
ylab = "sqft_lot",
xlim = c(0, 3000),
ylim = c(0, 20000),
main = "sqft_living vs sqft_lot"
)
ggplot(maindf,aes(y=price,x=sqft_living)) +
geom_point() +
xlim(0, 9000) +
ylim(0, 5000000) +
geom_smooth(formula = y ~ x,method="lm")
## Warning: Removed 5 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 5 rows containing missing values or values outside the scale range
## (`geom_point()`).
linearmodel = lm(price~bedrooms + sqft_living + floors + sqft_lot + condition + view + oldbuilt,
data = maindf)
summary(linearmodel)
##
## Call:
## lm(formula = price ~ bedrooms + sqft_living + floors + sqft_lot +
## condition + view + oldbuilt, data = maindf)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2051655 -131243 -18918 89678 26356050
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.758e+05 5.646e+04 -3.113 0.001861 **
## bedrooms -5.371e+04 1.022e+04 -5.255 1.55e-07 ***
## sqft_living 2.806e+02 1.097e+01 25.588 < 2e-16 ***
## floors 6.329e+04 1.620e+04 3.907 9.46e-05 ***
## sqft_lot -7.094e-01 2.116e-01 -3.352 0.000809 ***
## condition 2.870e+04 1.204e+04 2.384 0.017159 *
## view 5.880e+04 1.018e+04 5.773 8.28e-09 ***
## oldbuilt 2.099e+03 3.036e+02 6.914 5.37e-12 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 500500 on 4592 degrees of freedom
## Multiple R-squared: 0.2132, Adjusted R-squared: 0.212
## F-statistic: 177.7 on 7 and 4592 DF, p-value: < 2.2e-16