Tugas Analisis Eksplorasi Data
A. Tahapan Pra-Prosessing
Import Data Excell
library(readxl)## Warning: package 'readxl' was built under R version 4.1.2lembar1 <- read_xlsx("C:/SMT 4/Analisis Eksplorasi Data/3/Data untuk Eksplorasi (1).xlsx", sheet=1)
lembar3 <- read_xlsx("C:/SMT 4/Analisis Eksplorasi Data/3/Data untuk Eksplorasi (1).xlsx", sheet=3)## New names:
## * `` -> ...2
## * `` -> ...3
## * `` -> ...4
## * `` -> ...5
## * `` -> ...6
## * ...str(lembar1)## tibble [118 x 38] (S3: tbl_df/tbl/data.frame)
## $ Country: chr [1:118] "Country" "CH" "DE" "DK" ...
## $ X2 : chr [1:118] "GDP (USDbn)" "749.0176725" "3793.593164" "355.1840323" ...
## $ X3 : chr [1:118] "Real GDP growth ( avg last 5yrs%)" "1.88522" "1.62892" "2.68708" ...
## $ X4 : chr [1:118] "Real GDP growth (%)" "-2.7232" "-4.7654" "-2.7333" ...
## $ X5 : chr [1:118] "Consumer prices ( avg annual avg. % growth 5yrs)" "0.00116" "1.20768" "0.54" ...
## $ X6 : chr [1:118] "Consumer prices (annual avg. % growth)" "-0.0084" "0.3778" "0.3" ...
## $ X7 : chr [1:118] "Gross dom. inv. (% GDP avg 5yrs)" "24.41888" "20.71144" "22.06322" ...
## $ X8 : chr [1:118] "Gross dom. inv. (% GDP)" "24.5284" "20.2475" "23.1748" ...
## $ X9 : chr [1:118] "Gross dom. svg. (% GDP avg 5yrs)" "36.5367" "27.49714" "28.83828" ...
## $ X10 : chr [1:118] "Gross dom. svg. (% GDP)" "37.0514" "25.9843" "29.6644" ...
## $ X39 : chr [1:118] "Bank System Assets (% GDP avg 5yr)" "473.2558" "179.5237" "281.1473" ...
## $ X40 : chr [1:118] "Bank System Assets (% GDP)" "523.8202" "193.952499113789" "310.480386182536" ...
## $ X42 : chr [1:118] "Loan-deposit ratio (% avg 5yr)" "84.47336" "144.0191" "355.6127" ...
## $ X43 : chr [1:118] "Loan-deposit ratio (%)" "82.5" "138.357238793467" "359.138861033201" ...
## $ X44 : chr [1:118] "Capital adequacy ratio (% avg 5yr)" "17.92784" "18.782" "21.346" ...
## $ X45 : chr [1:118] "Capital adequacy ratio (%)" "19.3" "18.58" "22.6" ...
## $ X46 : chr [1:118] "Non-performing loans (% of gross loans avg 5yr)" "0.6909" "1.494" "2.52018" ...
## $ X47 : chr [1:118] "Non-performing loans (% of gross loans)" "0.75" NA "1.8" ...
## $ X60 : chr [1:118] "NXD (% GDP avg 5yr)" "-152.445" "-15.6481" "-5.59082" ...
## $ X61 : chr [1:118] "NXD (% GDP)" "-154.9536" "-19.0912" "-13.995" ...
## $ X66 : chr [1:118] "GXD (% GDP avg 5yr)" "275.6169" "165.293" "155.8403" ...
## $ X67 : chr [1:118] "GXD (% GDP)" "319.5953" "205.9636" "194.6712" ...
## $ X102 : chr [1:118] "GDP per cap. (USD)" "89770.8521" "50891.5812" "67565.6556" ...
## $ X103 : chr [1:118] "GDP per cap. (% US)" "129.49325180099" "73.4104242604391" "97.4625532568579" ...
## $ X104 : chr [1:118] "GNI per cap. (PPP)e (USD)" "71660" "57410" "62120" ...
## $ X105 : chr [1:118] "GNI per cap. (PPP)e (% US)" "108.444309927361" "86.8795399515738" "94.0072639225182" ...
## $ X106 : chr [1:118] "Real GDP per cap. (%, 5Y av. gr.)" "0.1733" "-0.1226" "1.3106" ...
## $ X107 : chr [1:118] "Population (%, 5Y av. gr.)" "0.8402" "0.4835" "0.3613" ...
## $ X108 : chr [1:118] "Unemployment (% labour force avg 5yr)" "2.88574" "3.73164" "5.5" ...
## $ X109 : chr [1:118] "Unemployment (% labour force)" "3.1728" "4.8177" "5.4" ...
## $ X111 : chr [1:118] "Pol. Stab." "94.7619018554687" "66.6666641235352" "83.8095245361328" ...
## $ X112 : chr [1:118] "Gov. Eff." "99.5192337036133" "93.2692337036133" "99.038459777832" ...
## $ X113 : chr [1:118] "Rule of Law" "99.038459777832" "92.3076934814453" "98.0769195556641" ...
## $ X114 : chr [1:118] "Ctrl. of Corr." "96.1538467407227" "95.1923065185547" "97.5961532592773" ...
## $ X115 : chr [1:118] "Reg. Qual." "94.711540222168" "96.1538467407227" "92.3076934814453" ...
## $ X116 : chr [1:118] "Voice & Acc-ty" "97.0443344116211" "95.0738906860352" "98.5221710205078" ...
## $ X117 : chr [1:118] "HDI" "98.9" "97.3" "95.2" ...
## $ X118 : chr [1:118] "Ease of DB (p-tile)f" "81.5" "88.9" "98.5" ...str(lembar3)## tibble [251 x 11] (S3: tbl_df/tbl/data.frame)
## $ source: https://raw.githubusercontent.com/lukes/ISO-3166-Countries-with-Regional-Codes/master/all/all.csv: chr [1:251] NA "name" "Afghanistan" "Ã…land Islands" ...
## $ ...2 : chr [1:251] NA "alpha-2" "AF" "AX" ...
## $ ...3 : chr [1:251] NA "alpha-3" "AFG" "ALA" ...
## $ ...4 : chr [1:251] NA "country-code" "4" "248" ...
## $ ...5 : chr [1:251] NA "iso_3166-2" "ISO 3166-2:AF" "ISO 3166-2:AX" ...
## $ ...6 : chr [1:251] NA "region" "Asia" "Europe" ...
## $ ...7 : chr [1:251] NA "sub-region" "Southern Asia" "Northern Europe" ...
## $ ...8 : chr [1:251] NA "intermediate-region" NA NA ...
## $ ...9 : chr [1:251] NA "region-code" "142" "150" ...
## $ ...10 : chr [1:251] NA "sub-region-code" "34" "154" ...
## $ ...11 : chr [1:251] NA "intermediate-region-code" NA NA ...Rename kolom lembar3
colnames(lembar3) <- c("Negara", "Alpha.2", "Alpha.3", "Kode_Negara", "Kode_ISO", "Region", "Sub_Region", "Intermediate_Region", "Kode_Region", "Kode_Sub.Region", "Intermediate_Kode.Region")Mengubah Tipe Data
lembar1['Country'] <- as.factor(lembar1[['Country']]) library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlembar1 <- lembar1 %>%
mutate(across(where(is.character), as.numeric))## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercion
## Warning in mask$eval_all_mutate(quo): NAs introduced by coercionlembar1['Country'] <- as.character(lembar1[['Country']]) #ubah lagi tipe data variabel country menjadi chr
str(lembar1)## tibble [118 x 38] (S3: tbl_df/tbl/data.frame)
## $ Country: chr [1:118] "Country" "CH" "DE" "DK" ...
## $ X2 : num [1:118] NA 749 3793.6 355.2 73.1 ...
## $ X3 : num [1:118] NA 1.89 1.63 2.69 3.23 ...
## $ X4 : num [1:118] NA -2.72 -4.77 -2.73 -1.31 ...
## $ X5 : num [1:118] NA 0.00116 1.20768 0.54 1.17428 ...
## $ X6 : num [1:118] NA -0.0084 0.3778 0.3 0.4 ...
## $ X7 : num [1:118] NA 24.4 20.7 22.1 18.4 ...
## $ X8 : num [1:118] NA 24.5 20.2 23.2 15.7 ...
## $ X9 : num [1:118] NA 36.5 27.5 28.8 53.7 ...
## $ X10 : num [1:118] NA 37.1 26 29.7 54.5 ...
## $ X39 : num [1:118] NA 473 180 281 1618 ...
## $ X40 : num [1:118] NA 524 194 310 1660 ...
## $ X42 : num [1:118] NA 84.5 144 355.6 46.3 ...
## $ X43 : num [1:118] NA 82.5 138.4 359.1 42.7 ...
## $ X44 : num [1:118] NA 17.9 18.8 21.3 23.3 ...
## $ X45 : num [1:118] NA 19.3 18.6 22.6 23.9 ...
## $ X46 : num [1:118] NA 0.691 1.494 2.52 NA ...
## $ X47 : num [1:118] NA 0.75 NA 1.8 1.03 ...
## $ X60 : num [1:118] NA -152.44 -15.65 -5.59 -1955.72 ...
## $ X61 : num [1:118] NA -155 -19.1 -14 -2807.2 ...
## $ X66 : num [1:118] NA 276 165 156 6908 ...
## $ X67 : num [1:118] NA 320 206 195 5946 ...
## $ X102 : num [1:118] NA 89771 50892 67566 124340 ...
## $ X103 : num [1:118] NA 129.5 73.4 97.5 179.4 ...
## $ X104 : num [1:118] NA 71660 57410 62120 77350 ...
## $ X105 : num [1:118] NA 108.4 86.9 94 117.1 ...
## $ X106 : num [1:118] NA 0.1733 -0.1226 1.3106 0.0792 ...
## $ X107 : num [1:118] NA 0.84 0.483 0.361 2.022 ...
## $ X108 : num [1:118] NA 2.89 3.73 5.5 5.97 ...
## $ X109 : num [1:118] NA 3.17 4.82 5.4 6.8 ...
## $ X111 : num [1:118] NA 94.8 66.7 83.8 95.7 ...
## $ X112 : num [1:118] NA 99.5 93.3 99 95.7 ...
## $ X113 : num [1:118] NA 99 92.3 98.1 95.7 ...
## $ X114 : num [1:118] NA 96.2 95.2 97.6 98.1 ...
## $ X115 : num [1:118] NA 94.7 96.2 92.3 95.2 ...
## $ X116 : num [1:118] NA 97 95.1 98.5 96.6 ...
## $ X117 : num [1:118] NA 98.9 97.3 95.2 87.7 95.7 100 96.8 91.4 95.7 ...
## $ X118 : num [1:118] NA 81.5 88.9 98.5 62.5 78.4 95.8 95.3 97.4 93.2 ...Penggabungan sheet1 dan sheet3 berdasarkan kode negara Alpha.2
data_merge <- merge(lembar1, lembar3, by.x=1, by.y=2, all=FALSE)Save Data
library(writexl)## Warning: package 'writexl' was built under R version 4.1.2write_xlsx(data_merge, 'Datafix (1).xlsx')B. Proses Awal
IMPORT DATA
library(readxl)
TugasAED<-read_xlsx("C:/SMT 4/Analisis Eksplorasi Data/3/Datafix.xlsx")
head(TugasAED)## # A tibble: 6 x 48
## Country X2 X3 X4 X5 X6 X7 X8 X9 X10 X39 X40
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AD 2.86 1.79 -11.8 0.68 0.3 NA NA NA NA 564. 605.
## 2 AE 353. 2.66 -7.51 1.77 -2.07 24.9 23.8 50.1 47.8 176. 226.
## 3 AM 12.6 4.75 -7.6 1.44 1.2 19.4 17.2 7.93 8.58 81.0 109.
## 4 AO 62.5 -0.878 -3.98 22.4 21.8 NA NA 32.0 31.3 47.3 44.7
## 5 AR 375. -0.237 -9.91 36.7 42.7 16.7 13.8 17.1 20.2 NA NA
## 6 AT 430. 1.88 -6.26 1.52 1.39 24.8 25.2 28.2 28.7 177. 183.
## # ... with 36 more variables: X42 <dbl>, X43 <dbl>, X44 <dbl>, X45 <dbl>,
## # X46 <dbl>, X47 <dbl>, X60 <dbl>, X61 <dbl>, X66 <dbl>, X67 <dbl>,
## # X102 <dbl>, X103 <dbl>, X104 <dbl>, X105 <dbl>, X106 <dbl>, X107 <dbl>,
## # X108 <dbl>, X109 <dbl>, X111 <dbl>, X112 <dbl>, X113 <dbl>, X114 <dbl>,
## # X115 <dbl>, X116 <dbl>, X117 <dbl>, X118 <dbl>, Negara <chr>,
## # Alpha.3 <chr>, Kode_Negara <dbl>, Kode_ISO <chr>, Region <chr>,
## # Sub_Region <chr>, Intermediate_Region <chr>, Kode_Region <dbl>, ...str(TugasAED)## tibble [115 x 48] (S3: tbl_df/tbl/data.frame)
## $ Country : chr [1:115] "AD" "AE" "AM" "AO" ...
## $ X2 : num [1:115] 2.86 352.91 12.65 62.49 375.19 ...
## $ X3 : num [1:115] 1.786 2.659 4.748 -0.878 -0.237 ...
## $ X4 : num [1:115] -11.81 -7.51 -7.6 -3.98 -9.91 ...
## $ X5 : num [1:115] 0.68 1.77 1.44 22.36 36.7 ...
## $ X6 : num [1:115] 0.3 -2.07 1.2 21.83 42.68 ...
## $ X7 : num [1:115] NA 24.9 19.4 NA 16.7 ...
## $ X8 : num [1:115] NA 23.8 17.2 NA 13.8 ...
## $ X9 : num [1:115] NA 50.12 7.93 32.02 17.11 ...
## $ X10 : num [1:115] NA 47.81 8.58 31.33 20.22 ...
## $ X39 : num [1:115] 564.5 176.3 81 47.3 NA ...
## $ X40 : num [1:115] 604.9 226.1 109.4 44.7 NA ...
## $ X42 : num [1:115] NA 112 143 54 NA ...
## $ X43 : num [1:115] 55 102.5 166.8 34.8 NA ...
## $ X44 : num [1:115] 21.5 18.1 15.1 21.3 15.8 ...
## $ X45 : num [1:115] 17.5 18.2 14 NA 23.3 ...
## $ X46 : num [1:115] 7.3 5.49 6.07 NA NA ...
## $ X47 : num [1:115] 8 8.15 6.6 NA NA ...
## $ X60 : num [1:115] NA -13.6 47.27 15.45 -5.01 ...
## $ X61 : num [1:115] NA 4.64 58.3 43.91 -11.5 ...
## $ X66 : num [1:115] 172.8 103.5 89.6 57.1 43.3 ...
## $ X67 : num [1:115] 199.2 134.7 102.3 109.3 73.1 ...
## $ X102 : num [1:115] 38675 40105 4251 2034 9203 ...
## $ X103 : num [1:115] 55.79 57.85 6.13 2.93 13.28 ...
## $ X104 : num [1:115] NA 70430 14500 6380 22120 ...
## $ X105 : num [1:115] NA 106.58 21.94 9.65 33.47 ...
## $ X106 : num [1:115] -2.084 -0.725 2.332 -5.203 -3.73 ...
## $ X107 : num [1:115] 1.221 0.87 0.256 3.342 0.966 ...
## $ X108 : num [1:115] 2.17 1.83 18.31 8.89 9.55 ...
## $ X109 : num [1:115] 3 2.45 18.5 10.5 11.05 ...
## $ X111 : num [1:115] 98.6 69.5 27.6 35.2 43.3 ...
## $ X112 : num [1:115] 98.1 88.9 50 13 49 ...
## $ X113 : num [1:115] 90.9 77.9 49 13.5 37 ...
## $ X114 : num [1:115] 87.5 83.7 50 13.9 53.4 ...
## $ X115 : num [1:115] 86.1 78.4 63.5 16.3 33.7 ...
## $ X116 : num [1:115] 87.2 17.7 47.8 25.6 66.5 ...
## $ X117 : num [1:115] 81.3 84 57.4 21.8 76 90.9 95.7 NA 53.1 29.7 ...
## $ X118 : num [1:115] NA 92.1 75.7 6.9 33.9 ...
## $ Negara : chr [1:115] "Andorra" "United Arab Emirates" "Armenia" "Angola" ...
## $ Alpha.3 : chr [1:115] "AND" "ARE" "ARM" "AGO" ...
## $ Kode_Negara : num [1:115] 20 784 51 24 32 40 36 533 31 50 ...
## $ Kode_ISO : chr [1:115] "ISO 3166-2:AD" "ISO 3166-2:AE" "ISO 3166-2:AM" "ISO 3166-2:AO" ...
## $ Region : chr [1:115] "Europe" "Asia" "Asia" "Africa" ...
## $ Sub_Region : chr [1:115] "Southern Europe" "Western Asia" "Western Asia" "Sub-Saharan Africa" ...
## $ Intermediate_Region : chr [1:115] NA NA NA "Middle Africa" ...
## $ Kode_Region : num [1:115] 150 142 142 2 19 150 9 19 142 142 ...
## $ Kode_Sub.Region : num [1:115] 39 145 145 202 419 155 53 419 145 34 ...
## $ Intermediate_Kode.Region: num [1:115] NA NA NA 17 5 NA NA 29 NA NA ...ggplot2
library(ggplot2)## Warning: package 'ggplot2' was built under R version 4.1.2library(dplyr)cek missing value
is.na(TugasAED$Region)## [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [25] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [37] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [49] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [73] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [85] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [97] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [109] FALSE FALSE FALSE FALSE FALSE FALSE FALSEis.na(TugasAED$X2)## [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [25] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [37] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [49] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [73] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [85] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [97] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [109] FALSE FALSE FALSE FALSE FALSE FALSE FALSEC. Histogram
Histogram Data X3
ggplot(TugasAED, aes(x= X3))+
geom_histogram( fill="red", color="black", alpha=0.3)+
ggtitle("Sebaran X3")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Histogram Data X106
ggplot(TugasAED, aes(x= X106))+
geom_histogram( fill="yellow", color="black", alpha=0.3)+
ggtitle("Sebaran X106")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Histogram Data X107
ggplot(TugasAED, aes(x= X107))+
geom_histogram( fill="green", color="black", alpha=0.3)+
ggtitle("Sebaran X107")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
X3 by Region
ggplot(data=TugasAED, aes(x= X3))+
geom_histogram(aes(fill=Region))+
facet_wrap(~Region, ncol=1)+
xlab("Sebaran X3")+
ylab("frekuensi")+
theme_light()+
ggtitle("X3 by Region")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
X106 by Region
ggplot(data=TugasAED, aes(x= X106))+
geom_histogram(aes(fill=Region))+
facet_wrap(~Region, ncol=1)+
xlab("Sebaran X106")+
ylab("frekuensi")+
theme_light()+
ggtitle("X106 by Region")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
X107 by Region
ggplot(data=TugasAED, aes(x= X107))+
geom_histogram(aes(fill=Region))+
facet_wrap(~Region, ncol=1)+
xlab("Sebaran Warga Negara")+
ylab("frekuensi")+
theme_light()+
ggtitle("X107 by Region")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
D. Boxplot
Boxplot Data X3 dan Region
ggplot(data = TugasAED, mapping=aes(x=reorder(Region, X3, median), y=X3, fill=Region))+
geom_boxplot(width = 0.5, alpha=1)+
theme(legend.position="none")+
ggtitle ("Rata-Rata Pertumbuhan GDP Real 5 tahun terakhir Berdasarkan Region")+
scale_fill_manual(values=c("red", "green", "yellow", "blue", "purple"))+
labs(
x = "Region",
y = "Pertumbuhan GDP Real(%)"
)
Boxplot Data X106 dan Region
ggplot(data = TugasAED, mapping=aes(x=reorder(Region, X106, median), y=X106, fill=Region))+
geom_boxplot(width = 0.7, alpha=1)+
theme(legend.position="none")+
ggtitle ("Rata-Rata GDP Per Kapita 5 tahun terakhir Berdasarkan Region")+
scale_fill_manual(values=c("red", "green", "yellow", "blue", "purple"))+
labs(
x = "Region",
y = "GDP Per Kapita(%)"
)
E. QQ PLOT
Normal QQ-Plot Data X3
IMPORT DATA
library(readxl)
setwd("C:/SMT 4/Analisis Eksplorasi Data/3")
MydataX <- read_excel("Datafix.xlsx",sheet = "DataX3")
var.name <- read_excel ("Datafix.xlsx",sheet = "DataX3",
n_max = 0 )
names(var.name)## [1] "X3" "Region"colnames(MydataX) <- names(var.name)
head(MydataX)## # A tibble: 6 x 2
## X3 Region
## <dbl> <chr>
## 1 1.79 Europe
## 2 2.66 Asia
## 3 4.75 Asia
## 4 -0.878 Africa
## 5 -0.237 Americas
## 6 1.88 Europelibrary(ggplot2)
varX<-MydataX$X3
length(varX) ## [1] 115hist(varX, breaks=15)
Normal QQ-Plot
set.seed(42)
qqnorm(varX, cex = .5)
set.seed(42)
qqline(varX, distribution = qnorm, col = "red", lty = "dashed", lwd = .1)
Normal QQ-Plot Data X106
Import Data
library(readxl)
setwd("C:/SMT 4/Analisis Eksplorasi Data/3")
MydataY <- read_excel("Datafix.xlsx",sheet = "DataX106")
var.name <- read_excel ("Datafix.xlsx",sheet = "DataX106",
n_max = 0 )
names(var.name)## [1] "X106"colnames(MydataY) <- names(var.name)
head(MydataY)## # A tibble: 6 x 1
## X106
## <dbl>
## 1 -2.08
## 2 -0.725
## 3 2.33
## 4 -5.20
## 5 -3.73
## 6 -0.300library(ggplot2)
varY<-MydataY$X106
length(varY) ## [1] 115hist(varY, breaks=15)
#Normal QQ-Plot
set.seed(42)
qqnorm(varY, cex = .5)
set.seed(42)
qqline(varY, distribution = qnorm, col = "red", lty = "dashed", lwd = .1)