PENDAHULUAN

Tentang Visualisasi Besaran Data

  1. Merupakan visualisasi yang paling dasar dalam menggambarkan keadaan dari suatu waktu, kondisi, maupun entitas

  2. Memberikan perbandingan antar kategori dan antar waktu

Beberapa diagram yang dapat digunakan untuk visualisasi besaran data adalah sebagai berikut.

  1. Bar Chart
  2. Pie Chart
  3. Stacked-Bar Chart
  4. Lollipop Chart (Needle Chart)
  5. Group Bar Chart

Package Installation

library(tidyverse) 
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.0
## ✔ purrr     1.0.1     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(ggridges)
library(GGally) 
## Registered S3 method overwritten by 'GGally':
##   method from   
##   +.gg   ggplot2
library(plotly) 
## 
## Attaching package: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following object is masked from 'package:graphics':
## 
##     layout

DATA

data_house <- read.csv("https://raw.githubusercontent.com/gerrydito/Sains-Data-S2/master/Praktikum/Visualisasi%20Data/house_price.csv", header = TRUE, sep=",")

str(data_house)
## '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" ...

PENDAHULUAN

Bar Chart

ggplot(data_house, aes(x = city)) +
  geom_bar(fill = "steelblue") +
  labs(title = "Jumlah Rumah per Kota", x = "Kota", y = "Jumlah Rumah") +
  theme_classic() +
  coord_flip()

Sorting Data

Bar chart dari jumlah rumah yang paling besar

data_house%>%count(city)%>%
  ggplot()+
  geom_col(aes(x=fct_reorder(as.factor(city),n),y=n), fill="steelblue", 
           width=0.4) +
    scale_y_continuous(expand = c(0,0))+
    coord_flip() +
    ggtitle("Jumlah Rumah Setiap Kota") +
    xlab("") +
    ylab("Jumlah Rumah") +
    theme_classic() +
    theme(plot.title = element_text(hjust = .5, size = 30))

Hanya memunculkan Top 10 dan menginput angka pada chart nya

data_house %>%
  count(city) %>%
  slice_max(n = 10, order_by = n) %>% # gunakan arrange(n) untuk mengurutkan sebaliknya
  ggplot() +
  geom_col(aes(x = fct_reorder(as.factor(city), n), y = n), fill = "steelblue", width = 0.4) +
  geom_text(aes(x = fct_reorder(as.factor(city), n), y = n, label = n),
            position = position_stack(vjust = 0.5), color = "white", size = 3) +
  scale_y_continuous(expand = c(0, 0)) +
  coord_flip() +
  ggtitle("Top 10 Kota dengan Jumlah Rumah Terbanyak") +
  xlab("") +
  ylab("Jumlah Rumah") +
  theme_classic() +
  theme(plot.title = element_text(hjust = 0.5, size = 15))

Lollipop Chart

data_house %>%
  count(city) %>%
  arrange(desc(n)) %>% # gunakan arrange(n) untuk mengurutkan sebaliknya
  ggplot() +
  geom_segment(aes(x = fct_reorder(as.factor(city), n), xend = fct_reorder(as.factor(city), n), y = 0, yend = n), color = "green") +
  geom_point(aes(x = fct_reorder(as.factor(city), n), y = n), color = "red", size = 2) +
  scale_y_continuous(expand = c(0, 0)) +
  coord_flip() +
  ggtitle("Jumlah Rumah Setiap Kota") +
  xlab("") +
  ylab("Jumlah Rumah") +
  theme_light() +
  theme(plot.title = element_text(hjust = 0.5))

Data Agregate

Before Agregate

ggplot(data_house,
  mapping = aes(x = reorder(city, price), y = price)) +
  geom_segment(aes(x = reorder(city, price), xend = reorder (city, price), y = 0 , yend = price), color = "red") +
  geom_point(color = "green", sie = 4, alpha = 0.6) +
  coord_flip() +
  theme_classic()
## Warning in geom_point(color = "green", sie = 4, alpha = 0.6): Ignoring unknown
## parameters: `sie`

ggplot(data_house, aes(x = reorder(city, price), y = price)) +
  geom_col(fill = "steelblue") +
  geom_text(aes(label = price), vjust = -0.5, color = "black", size = 3) +
  coord_flip() +
  ggtitle("Agregasi Harga Rumah di Setiap Kota") +
  xlab("Kota") +
  ylab("Total Harga Rumah") +
  theme_classic()

After Agregate

data_house %>%
  group_by(city) %>%
  summarize(total_price = sum(price)) %>%
  arrange(desc(total_price)) %>%
  slice_head(n = 10) %>% #hanya top 10 yang ditampilkan
  ggplot(aes(x = reorder(city, total_price), y = total_price)) +
  geom_col(fill = "steelblue") +
  geom_text(aes(label = total_price), vjust = -0.5, color = "black", size = 3) +
  coord_flip() +
  ggtitle("Top 10 Kota dengan Total Harga Rumah Tertinggi") +
  xlab("Kota") +
  ylab("Total Harga Rumah") +
  theme_classic()

Grouped Bar Char

Digunakan jika ingin mengetahui 2 peubah

Contoh: mengelempokan berdasarkan waktu dan kotanya:

data_stacked <- data_house %>%
  filter(city %in% c("Seattle", "Bellevue")) %>%
  filter(yr_built %in% c(2014, 2013, 2012))

ggplot(data_stacked, aes(x = as.factor(yr_built), y = price, fill = as.factor(city))) +
  geom_bar(stat = "identity", position = "dodge", width = 0.7, color = "white") +
  labs(fill = "Kota") +
  ggtitle("Total Harga Rumah per Kota dan Tahun Pembangunan") +
  xlab("Tahun Pembangunan") +
  ylab("Total Harga Rumah") +
  scale_fill_manual(values = c("Seattle" = "steelblue", "Bellevue" = "darkorange")) +
  theme_minimal()

Stacked Bar Char

Digunakan ketika ingin membandingkan sedikit peubah (2-3 peubah)

ggplot(data_stacked, aes(x = as.factor(yr_built), y = price, fill = as.factor(city))) +
  geom_bar(stat = "identity") +
  labs(fill = "Kota") +
  ggtitle("Total Harga Rumah per Kota dan Tahun Pembangunan") +
  xlab("Tahun Pembangunan") +
  ylab("Total Harga Rumah") +
  scale_fill_manual(values = c("Seattle" = "steelblue", "Bellevue" = "darkorange")) +
  theme_minimal()

LATIHAN

data("quakes")
quakes <- tibble::as.tibble(quakes)
## Warning: `as.tibble()` was deprecated in tibble 2.0.0.
## ℹ Please use `as_tibble()` instead.
## ℹ The signature and semantics have changed, see `?as_tibble`.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
glimpse(quakes)
## Rows: 1,000
## Columns: 5
## $ lat      <dbl> -20.42, -20.62, -26.00, -17.97, -20.42, -19.68, -11.70, -28.1…
## $ long     <dbl> 181.62, 181.03, 184.10, 181.66, 181.96, 184.31, 166.10, 181.9…
## $ depth    <int> 562, 650, 42, 626, 649, 195, 82, 194, 211, 622, 583, 249, 554…
## $ mag      <dbl> 4.8, 4.2, 5.4, 4.1, 4.0, 4.0, 4.8, 4.4, 4.7, 4.3, 4.4, 4.6, 4…
## $ stations <int> 41, 15, 43, 19, 11, 12, 43, 15, 35, 19, 13, 16, 19, 10, 94, 1…
head(quakes)
## # A tibble: 6 × 5
##     lat  long depth   mag stations
##   <dbl> <dbl> <int> <dbl>    <int>
## 1 -20.4  182.   562   4.8       41
## 2 -20.6  181.   650   4.2       15
## 3 -26    184.    42   5.4       43
## 4 -18.0  182.   626   4.1       19
## 5 -20.4  182.   649   4         11
## 6 -19.7  184.   195   4         12
data_stacked <- quakes %>%
  filter(stations %in% c("11", "12","15")) %>%
  filter(mag %in% c(4.0, 4.2, 4.8))

ggplot(data_stacked, aes(x = as.factor(mag), y = depth, fill = as.factor(stations))) +
  geom_bar(stat = "identity", position = "dodge", width = 0.7, color = "white") +
  labs(fill = "Station") +
  ggtitle("Total Kedalaman gempa dan Magnitude") +
  xlab("Magnitude") +
  ylab("Kedalaman Gempa") +
  scale_fill_manual(values = c("11" = "steelblue", "12" = "darkorange","15" = "aquamarine")) +
  theme_minimal()

quakes %>%
  count(stations) %>%
  slice_max(n = 10, order_by = n) %>% 
  arrange(desc(n)) %>% # gunakan arrange(n) untuk mengurutkan sebaliknya
  ggplot() +
  geom_segment(aes(x = fct_reorder(as.factor(stations), n), xend = fct_reorder(as.factor(stations), n), y = 0, yend = n), color = "coral") +
  geom_point(aes(x = fct_reorder(as.factor(stations), n), y = n), color = "red", size = 2) +
  scale_y_continuous(expand = c(0, 0)) +
  coord_flip() +
  ggtitle("Jumlah Gempa pada Setiap Stations") +
  xlab("") +
  ylab("Intensitas Gempa") +
  theme_light() +
  theme(plot.title = element_text(hjust = 0.5))