percobaan pembuatan grafik visualisasi bagian 2
Muhammad Fabian Reinhard Delano
2025-03-13
input data
library(ggplot2)
library(readxl)
fabian <- read_xlsx("/Users/M.Fabian.R.D/Desktop/SEMESTER 4/visualisasi data/data_excell_terbaru.xlsx")
fabian## # A tibble: 10 × 7
## id tahun_data kabupaten_kota jumlah_ibuhamil_dpt_…¹ jumlah_ibuhamil_dpt_…²
## <dbl> <dbl> <chr> <dbl> <dbl>
## 1 1 2023 Kab.Cilacap 27808 26614
## 2 2 2023 Kab.Banyumas 21336 21797
## 3 3 2023 Kab.Purbaling… 12607 12521
## 4 4 2023 Kab.Banjarneg… 12487 11369
## 5 5 2023 Kab.Kebumen 15593 16289
## 6 6 2023 Kab.Purworejo 7488 7312
## 7 7 2023 Kab.Wonosobo 9890 10245
## 8 8 2023 Kab.Magelang 15645 15182
## 9 9 2023 Kab.Boyolali 13307 12924
## 10 10 2023 Kab.Klaten 13449 12908
## # ℹ abbreviated names: ¹​jumlah_ibuhamil_dpt_pelayanan_k_satu,
## # ²​jumlah_ibuhamil_dpt_pelayanan_k_empat
## # ℹ 2 more variables: jumlah_ibuhamil_dpt_pelayanan_nifas <dbl>,
## # jumlah_ibu_yg_bersalin_di_fasyankes <dbl>histogram
perintah atau syntax untuk histogram sebagai berikut
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu))+
geom_histogram() #jika menggunakan geom_hist langsung melihat sebaran data dengan defaultnya 30 kelas ## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu))+
geom_histogram(bins = 90) #untuk melihat sebaran lebih banyak 
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu))+
geom_histogram(bins = 90, col = "skyblue") # menambahkan warna 
library(scales)
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu))+
geom_histogram(bins = 10, col = "black", fill = "lightgreen") +
scale_x_continuous(labels = comma)+
scale_y_continuous(labels = comma)+
labs(x = "jumlah ibu hamil mendapatkan pelayanan",
y = "frekuensi")
density plot
berikut ada beberapa cara untuk membuat data density
library(ggridges)
library(ggplot2)ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu, y = jumlah_ibuhamil_dpt_pelayanan_k_empat))+
geom_density_2d_filled()
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu))+
geom_density()
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu))+
geom_density(fill = "lightgreen", alpha = 0.7)+
scale_x_continuous(labels = comma)+
scale_y_continuous(labels = comma)+
labs(x = "jumlah ibu hamil dapat pelayanan",
y = "frekuensi")
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu, fill = kabupaten_kota, color = kabupaten_kota))+
geom_density(alpha = 0.3)+
scale_x_continuous(labels = comma)+
scale_y_continuous(labels = comma)+
labs(x = "jumlah ibu hamil dapat pelayanan")## Warning: Groups with fewer than two data points have been dropped.
## Groups with fewer than two data points have been dropped.
## Groups with fewer than two data points have been dropped.
## Groups with fewer than two data points have been dropped.
## Groups with fewer than two data points have been dropped.
## Groups with fewer than two data points have been dropped.
## Groups with fewer than two data points have been dropped.
## Groups with fewer than two data points have been dropped.
## Groups with fewer than two data points have been dropped.
## Groups with fewer than two data points have been dropped.## Warning in max(ids, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf
## Warning in max(ids, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf
## Warning in max(ids, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf
## Warning in max(ids, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf
## Warning in max(ids, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf
## Warning in max(ids, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf
## Warning in max(ids, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf
## Warning in max(ids, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf
## Warning in max(ids, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf
## Warning in max(ids, na.rm = TRUE): no non-missing arguments to max; returning
## -Inf
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu, fill = kabupaten_kota, y = kabupaten_kota))+
geom_density_ridges2()+
labs(x = "jumlah ibu hamil dapat pelayanan", y = "kabupaten/kota")## Picking joint bandwidth of NaN
boxplot
berikut adalah beberapa syntax untuk membuat boxplot
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu))+
geom_boxplot()
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu))+
geom_boxplot()+
coord_flip() # jikalau ingin vertikal 
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu, y = kabupaten_kota))+
geom_boxplot() #untuk membandingkan sebaran harga warna berlian #dan untuk mengelompokkan 
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu, y = kabupaten_kota, fill = kabupaten_kota))+
geom_boxplot() #untuk memberikan warna 
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu, y = kabupaten_kota, fill = kabupaten_kota))+
geom_boxplot() +
theme(legend.position = "none")
violin plot
berikut adalah beberapa syntax untuk violin plot
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu, y = "all"))+
geom_violin(fill = "black", alpha = 0.5)+
geom_boxplot(fill = "pink", width = 0.1)
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu, y = kabupaten_kota))+
geom_violin(fill = "black", alpha = 0.5)+
geom_boxplot(fill = "pink", width = 0.1) # untuk membuat banyak data terbagi menjadi beberapa grafik## Warning: Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
## Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
## Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
## Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
## Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
## Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
## Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
## Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
## Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.
## Groups with fewer than two datapoints have been dropped.
## ℹ Set `drop = FALSE` to consider such groups for position adjustment purposes.## Warning in max(data$density, na.rm = TRUE): no non-missing arguments to max;
## returning -Inf## Warning: Computation failed in `stat_ydensity()`.
## Caused by error in `$<-.data.frame`:
## ! replacement has 1 row, data has 0
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu, y = "all"))+
geom_violin(fill = "black", alpha = 0.5)+
geom_boxplot(fill = "pink", width = 0.1)+
scale_x_continuous(labels = comma)
QQ-PLOT
ggplot(data = fabian, aes(sample = jumlah_ibuhamil_dpt_pelayanan_k_satu))+
stat_qq(col = "green", cex = 2)+
stat_qq_line(col = "red", lwd = 0.6)
scatter plot
ggplot(data = fabian, mapping = aes(x = jumlah_ibuhamil_dpt_pelayanan_k_satu, y = jumlah_ibuhamil_dpt_pelayanan_k_empat , color = jumlah_ibuhamil_dpt_pelayanan_nifas))+
geom_point()
Line chart Dasar
library(readxl)
library(ggplot2)
alibaba <- read_xlsx("//Users/M.Fabian.R.D/Desktop/SEMESTER 4/visualisasi data/Ali_Baba_Stock_Data.xlsx")
alibaba$Date <- as.Date(alibaba$Date)
head(alibaba)## # A tibble: 6 × 7
## Date `Adj Close` Close High Low Open Volume
## <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2014-09-19 90.7 93.9 99.7 89.9 92.7 271879400
## 2 2014-09-22 86.8 89.9 92.9 89.5 92.7 66657800
## 3 2014-09-23 84.2 87.2 90.5 86.6 88.9 39009800
## 4 2014-09-24 87.5 90.6 90.6 87.2 88.5 32088000
## 5 2014-09-25 85.9 88.9 91.5 88.5 91.1 28598000
## 6 2014-09-26 87.4 90.5 90.5 88.7 89.7 18340000str(alibaba)## tibble [2,617 × 7] (S3: tbl_df/tbl/data.frame)
## $ Date : Date[1:2617], format: "2014-09-19" "2014-09-22" ...
## $ Adj Close: num [1:2617] 90.7 86.8 84.2 87.5 85.9 ...
## $ Close : num [1:2617] 93.9 89.9 87.2 90.6 88.9 ...
## $ High : num [1:2617] 99.7 92.9 90.5 90.6 91.5 ...
## $ Low : num [1:2617] 89.9 89.5 86.6 87.2 88.5 ...
## $ Open : num [1:2617] 92.7 92.7 88.9 88.5 91.1 ...
## $ Volume : num [1:2617] 2.72e+08 6.67e+07 3.90e+07 3.21e+07 2.86e+07 ...colnames(alibaba)## [1] "Date" "Adj Close" "Close" "High" "Low" "Open"
## [7] "Volume"ggplot(data = alibaba, mapping = aes(x = Date, y = Close)) +
geom_line() +
labs(x = "tanggal", y = "banyaknya kasus harian")
Area Plot
- Untuk menambah estetika dapat dilakukan dengan mengarsir daerah di bawah plot deret waktu. Plot seperti ini disebut Area Plot. Hasilnya sebagai berikut.
ggplot(data = alibaba, aes(x=Date,y=Close)) +
geom_line(lwd=1.2, col="darkgreen") +
geom_area(fill="green", alpha=0.3)
labs(x="tanggal", x="banyaknya kasus harian")## $x
## [1] "tanggal"
##
## attr(,"class")
## [1] "labels"Multiple Line Chart
- Pada plot ini dapat digunakan untuk membandingkan trend data deret waktu pada beberapa wilayah/kelompok.
ggplot(data = alibaba, aes(x=Date)) +
geom_line(aes(y=Close), lwd=1.2, col="blue") +
geom_line(aes(y=Open), lwd=1.2, col="red") +
labs(x="tanggal", y="banyaknya kasus harian") 
- Untuk menambahkan nama kelompok digunakan perintah berikut.
ggplot(data = alibaba, aes(x=Date)) +
geom_line(aes(y=Close), lwd=1.2, col="pink") +
geom_line(aes(y=Low), lwd=0.1, col="blue") +
xlim(min(alibaba$Date),max(alibaba$Date)+100) +
geom_text(x=max(alibaba$Date),y=tail(alibaba$Close,1)+30,
label="Close alibaba", size = 5,
color="black", hjust=1) +
geom_text(x=max(alibaba$Date),y=tail(alibaba$Open,1)+30,
label="Open alibaba", size = 5,
color="chocolate", hjust= 2) +
labs(x="tanggal", x="banyaknya kasus harian")