Tugas Praktikum Visdat UAS
Lusi Oktaviani
2024-05-14
Data Peubah Numerik
library(readxl)
data <- read_xlsx("C:\\Users\\Lusi Oktaviani\\OneDrive\\Statistics and Data Science\\Semester 4\\Analisis Regresi\\Anregkel4.xlsx")
y<-data$Y
xpadi<-data$Xpadi
xpdrb<-data$Xpdrb
xpmiskin<-data$Xpmiskin
xpenduduk<-data$Xpenduduk
xpengeluaran<-data$Xpengeluaran
xkpm<-data$Xkpm
xuhh<-data$Xuhh
xtpt<-data$Xtpt
xair<-data$Xair
data<-data.frame(cbind(y,xpadi,xpdrb,xpmiskin,xpenduduk,xpengeluaran,xkpm,xuhh,xtpt,xair))
head(data)## y xpadi xpdrb xpmiskin xpenduduk xpengeluaran xkpm xuhh xtpt
## 1 10.98 3.588756 1.505006 14.64 95 668.481 2.8157456 70.18 6.17
## 2 7.72 3.914361 2.134922 4.57 790 609.855 0.9123802 72.60 4.80
## 3 2.46 3.426600 2.344226 6.16 1310 830.111 2.7333565 70.39 3.59
## 4 11.66 3.183043 1.681262 14.62 102 626.209 0.7933535 69.69 3.59
## 5 13.48 3.271550 1.692906 11.34 1186 628.845 1.9257433 75.08 4.06
## 6 3.42 3.164308 11.467806 4.69 16158 953.321 1.2906114 73.32 7.18
## xair
## 1 41.12
## 2 43.87
## 3 37.04
## 4 49.31
## 5 71.88
## 6 30.28Scatter Plot
plot(xpadi,y)
plot(xpdrb,y)
plot(xpmiskin,y)
plot(xpenduduk,y)
plot(xpengeluaran,y)
plot(xkpm,y)
plot(xuhh,y)
plot(xtpt,y)
plot(xair,y)
### Korelasi
library(GGally)## Warning: package 'GGally' was built under R version 4.3.2## Loading required package: ggplot2## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2library(ggplot2)
ggpairs(data,
upper = list(continuous = wrap('cor', size = 2)),
title = "Matriks Scatterplot Data",
cardinality_threshold = 40)
Terlihat bahwa terdapat korelasi antara variabel peubah xpmiskin dan
xpadi terhadap y (tingkat kecukupan pangan)
Matrix Plot
library(corrplot)## Warning: package 'corrplot' was built under R version 4.3.2## corrplot 0.92 loadeddatacor = cor(data[1:8])
corrplot(datacor, method = "number")
Visualisasi time series
library(fpp2) # An older forecasting framework## Warning: package 'fpp2' was built under R version 4.3.3## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo## ── Attaching packages ────────────────────────────────────────────── fpp2 2.5 ──## ✔ forecast 8.22.0 ✔ expsmooth 2.3
## ✔ fma 2.5## Warning: package 'forecast' was built under R version 4.3.3## Warning: package 'fma' was built under R version 4.3.3## Warning: package 'expsmooth' was built under R version 4.3.3## library(fpp3) # A newer tidy forecasting framework## Warning: package 'fpp3' was built under R version 4.3.3## ── Attaching packages ────────────────────────────────────────────── fpp3 0.5 ──## ✔ tibble 3.2.1 ✔ tsibbledata 0.4.1
## ✔ dplyr 1.1.4 ✔ feasts 0.3.2
## ✔ tidyr 1.3.0 ✔ fable 0.3.4
## ✔ lubridate 1.9.3 ✔ fabletools 0.4.2
## ✔ tsibble 1.1.4## Warning: package 'dplyr' was built under R version 4.3.2## Warning: package 'lubridate' was built under R version 4.3.2## Warning: package 'tsibble' was built under R version 4.3.3## Warning: package 'tsibbledata' was built under R version 4.3.3## Warning: package 'feasts' was built under R version 4.3.3## Warning: package 'fabletools' was built under R version 4.3.3## Warning: package 'fable' was built under R version 4.3.3## ── Conflicts ───────────────────────────────────────────────── fpp3_conflicts ──
## ✖ lubridate::date() masks base::date()
## ✖ dplyr::filter() masks stats::filter()
## ✖ tsibble::intersect() masks base::intersect()
## ✖ tsibble::interval() masks lubridate::interval()
## ✖ dplyr::lag() masks stats::lag()
## ✖ tsibble::setdiff() masks base::setdiff()
## ✖ tsibble::union() masks base::union()##
## Attaching package: 'fpp3'## The following object is masked from 'package:fpp2':
##
## insurancelibrary(timetk) # An even newer tidy forecasting framework## Warning: package 'timetk' was built under R version 4.3.3library(tidyverse) # Collection of data manipulation tools## Warning: package 'tidyverse' was built under R version 4.3.2## Warning: package 'stringr' was built under R version 4.3.2## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ readr 2.1.4
## ✔ purrr 1.0.2 ✔ stringr 1.5.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ tsibble::interval() masks lubridate::interval()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(tidyquant) # Business Science ggplot theme## Warning: package 'tidyquant' was built under R version 4.3.3## Loading required package: PerformanceAnalytics## Warning: package 'PerformanceAnalytics' 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 4.3.2##
## Attaching package: 'zoo'
##
## The following object is masked from 'package:tsibble':
##
## index
##
## 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
##
##
## Attaching package: 'PerformanceAnalytics'
##
## The following object is masked from 'package:fpp3':
##
## prices
##
## The following object is masked from 'package:graphics':
##
## legend
##
## Loading required package: quantmod## Warning: package 'quantmod' was built under R version 4.3.3## Loading required package: TTR## Warning: package 'TTR' was built under R version 4.3.3##
## Attaching package: 'tidyquant'
##
## The following object is masked from 'package:fable':
##
## VARlibrary(cowplot) # A ggplot add-on for arranging plots##
## Attaching package: 'cowplot'
##
## The following object is masked from 'package:lubridate':
##
## stamp# Data produksi triwulanan Australia sebagai tibble
aus <- tsibbledata::aus_production %>% as_tibble()
# Check structure
aus %>% str()## tibble [218 × 7] (S3: tbl_df/tbl/data.frame)
## $ Quarter : qtr [1:218] 1956 Q1, 1956 Q2, 1956 Q3, 1956 Q4, 1957 Q1, 1957 Q2, 1957...
## $ Beer : num [1:218] 284 213 227 308 262 228 236 320 272 233 ...
## $ Tobacco : num [1:218] 5225 5178 5297 5681 5577 ...
## $ Bricks : num [1:218] 189 204 208 197 187 214 227 222 199 229 ...
## $ Cement : num [1:218] 465 532 561 570 529 604 603 582 554 620 ...
## $ Electricity: num [1:218] 3923 4436 4806 4418 4339 ...
## $ Gas : num [1:218] 5 6 7 6 5 7 7 6 5 7 ...# Convert tibble to time series object
aus_prod_ts <- ts(aus[, 2:7], #
start = c(1956, 1),
end = c(2010, 2),
frequency = 4)
aus_prod_ts %>% tail()## Beer Tobacco Bricks Cement Electricity Gas
## 2009 Q1 415 NA NA 1963 58368 196
## 2009 Q2 398 NA NA 2160 57471 238
## 2009 Q3 419 NA NA 2325 58394 252
## 2009 Q4 488 NA NA 2273 57336 210
## 2010 Q1 414 NA NA 1904 58309 205
## 2010 Q2 374 NA NA 2401 58041 236aus_long <- aus %>%
rename(date = Quarter) %>%
pivot_longer(
cols = c("Beer","Tobacco","Bricks",
"Cement","Electricity","Gas"))
aus_prod_tbl_long <- aus_prod_ts %>%
as_tsibble(index = "index",
pivot_longer = TRUE)# Using ggplot
aus_long %>%
ggplot(aes(date, value, group = name, color = name)) +
geom_line()## Warning: Removed 44 rows containing missing values or values outside the scale range
## (`geom_line()`).
Terlihat bahwa produksi listrik naik pada triwulan pertama.
# Using fpp3
aus_prod_tbl_long %>%
ggplot(aes(x = index, y = value, group = key)) +
geom_line() +
facet_grid(vars(key), scales = "free_y") # With facetting## Warning: Removed 44 rows containing missing values or values outside the scale range
## (`geom_line()`).
Data Spasial
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(indonesia)
library(dplyr)
library(readxl)
library(ggplot2)indonesia_kota <- id_map("indonesia", "kota")
indonesia_kota_jabar <- indonesia_kota %>%
filter(nama_provinsi == "Jawa Barat")## old-style crs object detected; please recreate object with a recent sf::st_crs()indonesia_kota_jabar$nama_kota## [1] Bandung Banjar Bekasi Bogor
## [5] Ciamis Cianjur Cimahi Cirebon
## [9] Depok Garut Indramayu Karawang
## [13] Kota Bandung Kota Bekasi Kota Bogor Kota Cirebon
## [17] Kota Sukabumi Kota Tasikmalaya Kuningan Majalengka
## [21] Purwakarta Subang Sukabumi Sumedang
## [25] Tasikmalaya
## 432 Levels: Aceh Barat Aceh Barat Daya Aceh Besar Aceh Jaya ... Yogyakartadata <- read_excel("C:\\Users\\Lusi Oktaviani\\OneDrive\\Statistics and Data Science\\data kerkom.xlsx")
data## # A tibble: 25 × 2
## Kota Jumlah
## <chr> <dbl>
## 1 Bandung 2796
## 2 Banjar 1263
## 3 Bekasi 2901
## 4 Bogor 3162
## 5 Ciamis 1818
## 6 Cianjur 2016
## 7 Kota Cimahi 2123
## 8 Cirebon 2198
## 9 Kota Depok 3156
## 10 Garut 2227
## # ℹ 15 more rowsggplot() + geom_sf(data = indonesia_kota_jabar, fill = "white", color = "black") +
geom_sf(data = indonesia_kota_jabar, aes(fill = data$Jumlah), color = "black") +
scale_fill_viridis_c(option = "viridis", direction = -1) + theme_void() + theme(legend.position = "right") + ggtitle("Sebaran Pengguna Internet di Provinsi Jawa barat") + theme(plot.title = element_text(face = "bold", hjust = 0.5))
Terlihat bahwa pada warna ungu di peta daerah bekasi, bogor, dan depok
memiliki pengguna internet lebih dari 3000 responden.