Tugas Praktikum Visdat UAS
Bulan Cahyani Suhaeri G1401221030
library(tidyverse) #Include beberapa packages termasuk ggplot## Warning: package 'tidyverse' was built under R version 4.3.2## Warning: package 'ggplot2' was built under R version 4.3.3## Warning: package 'tidyr' was built under R version 4.3.3## Warning: package 'stringr' was built under R version 4.3.3## Warning: package 'lubridate' was built under R version 4.3.2## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.0 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── 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 errorslibrary(dplyr)
library(reshape2)##
## Attaching package: 'reshape2'
##
## The following object is masked from 'package:tidyr':
##
## smithslibrary(ggforce)## Warning: package 'ggforce' was built under R version 4.3.3library(readxl)
library(ggplot2)
library(tidyverse)
library(plotly)## Warning: package 'plotly' was built under R version 4.3.2##
## 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':
##
## layoutlibrary(ggcorrplot)## Warning: package 'ggcorrplot' was built under R version 4.3.3library(gridExtra)## Warning: package 'gridExtra' was built under R version 4.3.3##
## Attaching package: 'gridExtra'
##
## The following object is masked from 'package:dplyr':
##
## combineinstall.packages("gridExtra")## Warning: package 'gridExtra' is in use and will not be installed#READ DATA
data <- read_excel("C:/Users/bulbu/Documents/Data Praktikum Visdat.xlsx")
data## # A tibble: 27 × 8
## Wilayah Y IK IP AMH PDRB UHH TP
## <chr> <dbl> <dbl> <dbl> <dbl> <chr> <dbl> <dbl>
## 1 Bogor 71.8 79.5 62.5 98.4 167 966,18 69.7 12.2
## 2 Sukabumi 68.5 79.3 57.7 99.5 50 388,72 69.5 9.51
## 3 Cianjur 66.6 77.8 57.4 99.2 34 556,40 68.6 9.32
## 4 Bandung 73.7 83.1 65.6 99.5 88 437,96 72.1 8.32
## 5 Garut 68.1 79.8 59.8 99.6 42 012,96 69.7 8.68
## 6 Tasikmalaya 67.8 76.8 60.7 99.0 26 361,66 68.0 6.16
## 7 Ciamis 72.0 80.5 66.3 98.6 23 918,89 70.4 5.06
## 8 Kuningan 70.7 83.1 60.3 98.0 18 450,34 72.2 11.7
## 9 Cirebon 71.0 80.7 58.8 94.8 35 523,78 70.5 10.4
## 10 Majalengka 69.1 78.1 59.0 98.2 24 300,77 68.8 5.71
## # ℹ 17 more rowsstr(data)## tibble [27 × 8] (S3: tbl_df/tbl/data.frame)
## $ Wilayah: chr [1:27] "Bogor" "Sukabumi" "Cianjur" "Bandung" ...
## $ Y : num [1:27] 71.8 68.5 66.5 73.7 68.1 ...
## $ IK : num [1:27] 79.5 79.3 77.8 83.1 79.8 ...
## $ IP : num [1:27] 62.5 57.7 57.4 65.6 59.9 ...
## $ AMH : num [1:27] 98.4 99.5 99.2 99.5 99.6 ...
## $ PDRB : chr [1:27] "167 966,18" "50 388,72" "34 556,40" "88 437,96" ...
## $ UHH : num [1:27] 69.7 69.5 68.6 72.1 69.7 ...
## $ TP : num [1:27] 12.22 9.51 9.32 8.32 8.68 ...#1. DATA PEUBAH NUMERIK
#Korelasi
plot_X1 <- ggplot(data, aes(x = IK, y = Y)) +
geom_point() +
labs(title = "Scatter Plot", x = "Indeks Kesehatan", y = "IPM") +
theme_classic()
plot_X2 <- ggplot(data, aes(x = IP, y = Y)) +
geom_point() +
labs(title = "Scatter Plot", x = "Indeks Pendidikan", y = "IPM") +
theme_classic()
plot_X3 <- ggplot(data, aes(x = AMH, y = Y)) +
geom_point() +
labs(title = "Scatter Plot", x = "Angka Melek Huruf", y = "IPM") +
theme_classic()
grid.arrange(plot_X1, plot_X2, plot_X3, nrow=1)
Dari hasil perwakilan visualisasi data diatas, terlihat bahwa Indeks Kesehatan, Indeks Pendidikan , dan Angka Melek Huruf menunjukkan hubungan linear positif. Yang menandakan bahwa semakin tinggi Indeks Kesehatan,Indeks Pendidikan dan Angka Melek Huruf. Maka, nilai Indeks Pembangunan Manusia cenderung meningkat.
#Matrix Plot
data_numerik <- select_if(data, is.numeric)
str(data_numerik)## tibble [27 × 6] (S3: tbl_df/tbl/data.frame)
## $ Y : num [1:27] 71.8 68.5 66.5 73.7 68.1 ...
## $ IK : num [1:27] 79.5 79.3 77.8 83.1 79.8 ...
## $ IP : num [1:27] 62.5 57.7 57.4 65.6 59.9 ...
## $ AMH: num [1:27] 98.4 99.5 99.2 99.5 99.6 ...
## $ UHH: num [1:27] 69.7 69.5 68.6 72.1 69.7 ...
## $ TP : num [1:27] 12.22 9.51 9.32 8.32 8.68 ...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)
library(ggcorrplot)
ggcorrplot(data_corrl)
ggcorrplot(data_corrl, method = "circle")
Piecewise Constant (Fungsi Tangga)
mod = lm(Y ~ cut(IK,3),data=data)
summary(mod)##
## Call:
## lm(formula = Y ~ cut(IK, 3), data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -7.5275 -2.3900 -0.3975 2.4087 4.7925
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 69.840 1.265 55.230 <2e-16 ***
## cut(IK, 3)(79.7,82.5] 2.062 1.591 1.296 0.207
## cut(IK, 3)(82.5,85.4] 8.407 1.732 4.856 6e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.346 on 24 degrees of freedom
## Multiple R-squared: 0.53, Adjusted R-squared: 0.4909
## F-statistic: 13.53 on 2 and 24 DF, p-value: 0.0001161ggplot(data,aes(x=IK, y= Y)) +
geom_point(alpha=0.55, color="black") +
stat_smooth(method = "lm",
formula = y~cut(x,3),
lty = 1, col = "red",se = F)+
theme_bw()
#2. DATA TIME SERIES
data2 <- read_excel ("C:/Users/bulbu/Documents/Data2.xlsx")
data2## # A tibble: 1,259 × 7
## Date Open High Low Close `Adj Close` Volume
## <dttm> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2019-05-14 00:00:00 134210007 135240005 131009995 1.34e8 133580002 1.13e6
## 2 2019-05-15 00:00:00 132149994 136649994 131330002 1.36e8 136429993 9.06e5
## 3 2019-05-16 00:00:00 136429993 138160004 135050003 1.35e8 135429993 1.03e6
## 4 2019-05-17 00:00:00 133729996 135000000 131990005 1.33e8 132759995 9.91e5
## 5 2019-05-20 00:00:00 131500000 133440002 130985001 1.32e8 131520004 1.06e6
## 6 2019-05-21 00:00:00 132750000 134850006 132080002 1.32e8 132240005 9.04e5
## 7 2019-05-22 00:00:00 132050003 132660004 126610001 1.27e8 127089996 2.02e6
## 8 2019-05-23 00:00:00 124550003 124809998 120050003 1.22e8 121580002 2.10e6
## 9 2019-05-24 00:00:00 122900002 125570000 122320000 1.25e8 124650002 1.23e6
## 10 2019-05-28 00:00:00 124339996 125779999 123690002 1.24e8 124360001 6.78e5
## # ℹ 1,249 more rowsstr(data2)## tibble [1,259 × 7] (S3: tbl_df/tbl/data.frame)
## $ Date : POSIXct[1:1259], format: "2019-05-14" "2019-05-15" ...
## $ Open : num [1:1259] 1.34e+08 1.32e+08 1.36e+08 1.34e+08 1.32e+08 ...
## $ High : num [1:1259] 1.35e+08 1.37e+08 1.38e+08 1.35e+08 1.33e+08 ...
## $ Low : num [1:1259] 1.31e+08 1.31e+08 1.35e+08 1.32e+08 1.31e+08 ...
## $ Close : num [1:1259] 1.34e+08 1.36e+08 1.35e+08 1.33e+08 1.32e+08 ...
## $ Adj Close: num [1:1259] 1.34e+08 1.36e+08 1.35e+08 1.33e+08 1.32e+08 ...
## $ Volume : num [1:1259] 1130600 906100 1032300 991300 1057000 ...ggplot(data2, aes(x = Date, y = Close)) +
geom_point() + # Add points
geom_line() + # Connect points with lines
labs(title = "Scatter Plot with Connected Lines",
x = "Date",
y = "Volume")
#3. VISUALISASI SPASIAL
library("ggplot2")
library("sf")## Warning: package 'sf' was built under R version 4.3.3## Linking to GEOS 3.11.2, GDAL 3.8.2, PROJ 9.3.1; sf_use_s2() is TRUElibrary("ggplot2")
library("sf")
library("rnaturalearth")## Warning: package 'rnaturalearth' was built under R version 4.3.3library("rnaturalearthdata")## Warning: package 'rnaturalearthdata' was built under R version 4.3.3##
## Attaching package: 'rnaturalearthdata'## The following object is masked from 'package:rnaturalearth':
##
## countries110library(dplyr)
library(ggmap)## Warning: package 'ggmap' was built under R version 4.3.3## ℹ Google's Terms of Service: <https://mapsplatform.google.com>
## Stadia Maps' Terms of Service: <https://stadiamaps.com/terms-of-service/>
## OpenStreetMap's Tile Usage Policy: <https://operations.osmfoundation.org/policies/tiles/>
## ℹ Please cite ggmap if you use it! Use `citation("ggmap")` for details.
##
## Attaching package: 'ggmap'
##
##
## The following object is masked from 'package:plotly':
##
## windlibrary(tidygeocoder)## Warning: package 'tidygeocoder' was built under R version 4.3.3##
## Attaching package: 'tidygeocoder'
##
## The following object is masked from 'package:ggmap':
##
## geocodeBACA DATA
library ("sf")
library("readxl")
my_sf <- read_sf("C:/Users/bulbu/Downloads/BATAS PROVINSI DESEMBER 2019 DUKCAPIL/BATAS PROVINSI DESEMBER 2019 DUKCAPIL/BATAS_PROVINSI_DESEMBER_2019_DUKCAPIL.shp")
data3 <- read_excel("C:/Users/bulbu/Downloads/Tingkat Pengangguran Terbuka Menurut Provinsi, 2024.xlsx")
data3## # A tibble: 39 × 2
## Provinsi Persentase
## <chr> <dbl>
## 1 ACEH 5.56
## 2 SUMATERA UTARA 5.1
## 3 SUMATERA BARAT 5.79
## 4 RIAU 3.85
## 5 JAMBI 4.45
## 6 SUMATERA SELATAN 3.97
## 7 BENGKULU 3.17
## 8 LAMPUNG 4.12
## 9 KEP. BANGKA BELITUNG 3.85
## 10 KEP. RIAU 6.94
## # ℹ 29 more rowsmy_sf## Simple feature collection with 34 features and 4 fields
## Geometry type: MULTIPOLYGON
## Dimension: XYZ
## Bounding box: xmin: 95.01079 ymin: -11.00762 xmax: 141.0194 ymax: 6.07693
## z_range: zmin: 2.65e-05 zmax: 2.65e-05
## Geodetic CRS: WGS 84
## # A tibble: 34 × 5
## OBJECTID PROVINSI Shape_Leng Shape_Area geometry
## <dbl> <chr> <dbl> <dbl> <MULTIPOLYGON [°]>
## 1 1 ACEH 27.5 4.63 Z (((97.39178 2.037481 2…
## 2 2 BALI 6.03 0.459 Z (((115.1251 -8.847606 …
## 3 3 BANTEN 9.28 0.765 Z (((105.5498 -6.995661 …
## 4 4 BENGKULU 11.7 1.63 Z (((102.3862 -5.471439 …
## 5 5 DAERAH ISTIMEWA YOG… 3.34 0.260 Z (((110.8198 -8.203577 …
## 6 6 DKI JAKARTA 3.12 0.0534 Z (((106.8768 -6.1003 2.…
## 7 7 GORONTALO 11.0 0.978 Z (((121.4254 0.4124347 …
## 8 8 JAMBI 11.8 3.98 Z (((104.4071 -0.863707 …
## 9 9 JAWA BARAT 11.6 3.03 Z (((108.685 -6.769898 2…
## 10 10 JAWA TENGAH 15.5 2.82 Z (((108.8835 -7.748463 …
## # ℹ 24 more rowslibrary(ggforce)
library(quantmod)## Warning: package 'quantmod' was built under R version 4.3.3## Loading required package: xts## Warning: package 'xts' was built under R version 4.3.3## Loading required package: zoo## Warning: package 'zoo' was built under R version 4.3.3##
## Attaching package: 'zoo'## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric##
## ######################### Warning from 'xts' package ##########################
## # #
## # The dplyr lag() function breaks how base R's lag() function is supposed to #
## # work, which breaks lag(my_xts). Calls to lag(my_xts) that you type or #
## # source() into this session won't work correctly. #
## # #
## # Use stats::lag() to make sure you're not using dplyr::lag(), or you can add #
## # conflictRules('dplyr', exclude = 'lag') to your .Rprofile to stop #
## # dplyr from breaking base R's lag() function. #
## # #
## # Code in packages is not affected. It's protected by R's namespace mechanism #
## # Set `options(xts.warn_dplyr_breaks_lag = FALSE)` to suppress this warning. #
## # #
## #################################################################################
## Attaching package: 'xts'## The following objects are masked from 'package:dplyr':
##
## first, last## Loading required package: TTR## Warning: package 'TTR' was built under R version 4.3.3## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoolibrary(maps)## Warning: package 'maps' was built under R version 4.3.3##
## Attaching package: 'maps'## The following object is masked from 'package:purrr':
##
## maplibrary(ggmap)
library(ggthemes)## Warning: package 'ggthemes' was built under R version 4.3.3library(sf)
library(ggrepel)## Warning: package 'ggrepel' was built under R version 4.3.3data3$PROVINSI <- toupper(data3$Provinsi)
Persen.Geo <- merge(x=my_sf, y=data3, by="PROVINSI",all.x = TRUE, all.y=TRUE)
ggplot(Persen.Geo) +
geom_sf(aes(fill= Persentase)
, color = "#69b3a2") +
scale_fill_gradient(low="green", high="red") +
theme_void()
Hasil Visualisasi dari Visualisasi Spasial diatas adalah, diberikan data
persebaran dengan tingkat pengangguran tertinggi di indonesia. Dapat
dilihat dari Persentase bahwa tingkat pengangguran tertinggi di berikan
dengan level tinggi warna merah sampai tingkat pengangguran terendah
dengan warna hijau