Pendahuluan
Package Installation
library(tidyverse) #Include beberapa packages termasuk ggplot
library(dplyr)
library(reshape2)
library(ggcorrplot)Data
data <- read.csv("https://raw.githubusercontent.com/gerrydito/Sains-Data-S2/master/Praktikum/Visualisasi%20Data/house_price.csv", header = TRUE, sep=",")
str(data)## 'data.frame': 4600 obs. of 18 variables:
## $ date : chr "2014-05-02 00:00:00" "2014-05-02 00:00:00" "2014-05-02 00:00:00" "2014-05-02 00:00:00" ...
## $ price : num 313000 2384000 342000 420000 550000 ...
## $ bedrooms : num 3 5 3 3 4 2 2 4 3 4 ...
## $ bathrooms : num 1.5 2.5 2 2.25 2.5 1 2 2.5 2.5 2 ...
## $ sqft_living : int 1340 3650 1930 2000 1940 880 1350 2710 2430 1520 ...
## $ sqft_lot : int 7912 9050 11947 8030 10500 6380 2560 35868 88426 6200 ...
## $ floors : num 1.5 2 1 1 1 1 1 2 1 1.5 ...
## $ waterfront : int 0 0 0 0 0 0 0 0 0 0 ...
## $ view : int 0 4 0 0 0 0 0 0 0 0 ...
## $ condition : int 3 5 4 4 4 3 3 3 4 3 ...
## $ sqft_above : int 1340 3370 1930 1000 1140 880 1350 2710 1570 1520 ...
## $ sqft_basement: int 0 280 0 1000 800 0 0 0 860 0 ...
## $ yr_built : int 1955 1921 1966 1963 1976 1938 1976 1989 1985 1945 ...
## $ yr_renovated : int 2005 0 0 0 1992 1994 0 0 0 2010 ...
## $ street : chr "18810 Densmore Ave N" "709 W Blaine St" "26206-26214 143rd Ave SE" "857 170th Pl NE" ...
## $ city : chr "Shoreline" "Seattle" "Kent" "Bellevue" ...
## $ statezip : chr "WA 98133" "WA 98119" "WA 98042" "WA 98008" ...
## $ country : chr "USA" "USA" "USA" "USA" ...Visualisasi
Korelasi
ggplot(data, aes(x = sqft_above, y = sqft_lot)) +
geom_point() +
labs(title = "Scatter Plot", x = "sqft_aboce", y = "sqft_lot") +
theme_classic()
data$kategori_rumah <- ifelse(data$yr_built >= 2000, "rumah 2000an", "rumah 90an")
ggplot(data, aes(x = sqft_above, y = sqft_lot, color = kategori_rumah)) +
geom_point() +
labs(title = "Scatter Plot Rumah Tahun 2000an dan 90an", x = "sqft_above", y = "sqft_lot", color = "Kategori") +
theme_minimal()
ggplot(data, aes(x = sqft_above, y = sqft_lot, color = kategori_rumah)) +
geom_point() +
labs(title = "Scatter Plot Rumah Tahun 2000an dan 90an", x = "sqft_above", y = "sqft_lot", color = "Kategori") +
facet_wrap(~ kategori_rumah) +
theme_minimal()
Matrix Plot
Heatmap/Corellogram
data_numerik <- select_if(data, is.numeric)
str(data_numerik)## 'data.frame': 4600 obs. of 13 variables:
## $ price : num 313000 2384000 342000 420000 550000 ...
## $ bedrooms : num 3 5 3 3 4 2 2 4 3 4 ...
## $ bathrooms : num 1.5 2.5 2 2.25 2.5 1 2 2.5 2.5 2 ...
## $ sqft_living : int 1340 3650 1930 2000 1940 880 1350 2710 2430 1520 ...
## $ sqft_lot : int 7912 9050 11947 8030 10500 6380 2560 35868 88426 6200 ...
## $ floors : num 1.5 2 1 1 1 1 1 2 1 1.5 ...
## $ waterfront : int 0 0 0 0 0 0 0 0 0 0 ...
## $ view : int 0 4 0 0 0 0 0 0 0 0 ...
## $ condition : int 3 5 4 4 4 3 3 3 4 3 ...
## $ sqft_above : int 1340 3370 1930 1000 1140 880 1350 2710 1570 1520 ...
## $ sqft_basement: int 0 280 0 1000 800 0 0 0 860 0 ...
## $ yr_built : int 1955 1921 1966 1963 1976 1938 1976 1989 1985 1945 ...
## $ yr_renovated : int 2005 0 0 0 1992 1994 0 0 0 2010 ...data_melt <- cor(data_numerik[sapply(data_numerik,is.numeric)])
data_melt <- melt(data_melt)
ggplot(data_melt, aes(x = Var1, y = Var2, fill = value)) +
geom_tile() +
labs(title = "Correlation Heatmap",
x = "Variable 1",
y = "Variable 2")
ggplot(data_melt, aes(Var1, Var2, fill = value)) +
geom_tile(color = "white") +
scale_fill_gradient2(low = "blue", mid = "white", high = "red", midpoint = 0, limits = c(-1,1), name="Korelasi") +
labs(title = "Corellogram") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust=1))
data_corrl <- round(cor(data_numerik), 1)
data_corrl <- cor(data_corrl)
ggcorrplot(data_corrl)
ggcorrplot(data_corrl, method = "circle")
Piecewise Constant (Fungsi Tangga)
mod_tangga = lm(sqft_above ~ cut(sqft_lot,3),data=data)
summary(mod_tangga)##
## Call:
## lm(formula = sqft_above ~ cut(sqft_lot, 3), data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1457 -637 -237 473 7583
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1827.02 12.72 143.588 <2e-16 ***
## cut(sqft_lot, 3)(3.58e+05,7.16e+05] 154.64 352.28 0.439 0.661
## cut(sqft_lot, 3)(7.16e+05,1.08e+06] 182.98 862.43 0.212 0.832
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 862.3 on 4597 degrees of freedom
## Multiple R-squared: 5.169e-05, Adjusted R-squared: -0.0003834
## F-statistic: 0.1188 on 2 and 4597 DF, p-value: 0.888ggplot(data,aes(x=sqft_above, y=sqft_lot)) +
geom_point(alpha=0.55, color="black") +
stat_smooth(method = "lm",
formula = y~cut(x,3),
lty = 1, col = "red",se = F)+
theme_bw()
## Locally Estimated Scatter Plot Smoothing (LOESS)
Non linear Outlier
ggplot(data, aes(x = sqft_above, y = sqft_lot)) +
geom_point(color = "blue", size = 3, alpha = 0.6) +
geom_smooth(method = "loess", color = "red", linetype = "dashed", size = 1.5) +
labs(
x = "Sqft Above",
y = "Sqft Lot",
title = "LOESS Visualization of Sqft Above vs. Sqft Lot",
subtitle = "Smoothed scatterplot with LOESS curve",
caption = "Datanya Pak Geri"
) +
theme_minimal() ## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## `geom_smooth()` using formula = 'y ~ x'