Tugas 3 Sains Data
Syaza
7/9/2021
Soal no 1.a
library(tidyverse)## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.3 v dplyr 1.0.7
## v tidyr 1.1.3 v stringr 1.4.0
## v readr 2.0.1 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(RSQLite)
library(DBI)
DBI::dbConnect(RSQLite::SQLite(), path = ":dbname:")## <SQLiteConnection>
## Path:
## Extensions: TRUENorthwind<-DBI::dbConnect(RSQLite::SQLite(), "C:/sqlite/db/Northwind_large.sqlite")
class(Northwind)## [1] "SQLiteConnection"
## attr(,"package")
## [1] "RSQLite"listtabel<-RSQLite::dbListTables(Northwind)
product<-dplyr::tbl(Northwind,"Product")
supplier<-dplyr::tbl(Northwind,"Supplier")
customer<-dplyr::tbl(Northwind,"Customer")
category<-dplyr::tbl(Northwind,"category")
region<-dplyr::tbl(Northwind,"Region")
employee<-dplyr::tbl(Northwind,"Employee")
employeeterritory<-dplyr::tbl(Northwind,"EmployeeTerritory")
fulljoin<- full_join(product, supplier, by = c("SupplierId" = "Id"))
tabel1<- data.frame(fulljoin)
innerjoin<- inner_join(product, supplier, by = c("SupplierId" = "Id"))
tabel2<- data.frame(innerjoin)
leftjoin<- left_join(product, category, by = c("CategoryId" = "Id"))
tabel3<- data.frame(leftjoin)
rightjoin<- right_join(supplier, region, by = c("Region" = "RegionDescription"))
tabel4<- data.frame(rightjoin)
semijoin<- semi_join(employee, employeeterritory, by = c("Id"="EmployeeId"))
tabel5<- data.frame(semijoin)
antijoin<- anti_join(product, supplier, by = c("SupplierId"="Id"))
tabel6<- data.frame(antijoin)Soal Nomor 1b view total negara
library(sf)## Linking to GEOS 3.9.0, GDAL 3.2.1, PROJ 7.2.1library(ggplot2)
library(tigris)## To enable
## caching of data, set `options(tigris_use_cache = TRUE)` in your R script or .Rprofile.library(dplyr)
library(readxl)
Admin2Kabupaten<-"D:/Magister IPB/Sains Data-STA581/Shape Data/Admin Kabupaten/idn_admbnda_adm2_bps_20200401.shp"
glimpse(Admin2Kabupaten)## chr "D:/Magister IPB/Sains Data-STA581/Shape Data/Admin Kabupaten/idn_admbnda_adm2_bps_20200401.shp"admin2<-st_read(Admin2Kabupaten)## Reading layer `idn_admbnda_adm2_bps_20200401' from data source
## `D:\Magister IPB\Sains Data-STA581\Shape Data\Admin Kabupaten\idn_admbnda_adm2_bps_20200401.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 522 features and 14 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: 95.01079 ymin: -11.00762 xmax: 141.0194 ymax: 6.07693
## Geodetic CRS: WGS 84glimpse(admin2)## Rows: 522
## Columns: 15
## $ Shape_Leng <dbl> 2.360029, 1.963994, 4.590182, 3.287754, 4.448584, 4.907219,~
## $ Shape_Area <dbl> 0.22896809, 0.15413587, 0.23639581, 0.31616114, 0.34303826,~
## $ ADM2_EN <chr> "Aceh Barat", "Aceh Barat Daya", "Aceh Besar", "Aceh Jaya",~
## $ ADM2_PCODE <chr> "ID1107", "ID1112", "ID1108", "ID1116", "ID1103", "ID1102",~
## $ ADM2_REF <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM2ALT1EN <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM2ALT2EN <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM1_EN <chr> "Aceh", "Aceh", "Aceh", "Aceh", "Aceh", "Aceh", "Aceh", "Ac~
## $ ADM1_PCODE <chr> "ID11", "ID11", "ID11", "ID11", "ID11", "ID11", "ID11", "ID~
## $ ADM0_EN <chr> "Indonesia", "Indonesia", "Indonesia", "Indonesia", "Indone~
## $ ADM0_PCODE <chr> "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID",~
## $ date <date> 2019-12-20, 2019-12-20, 2019-12-20, 2019-12-20, 2019-12-20~
## $ validOn <date> 2020-04-01, 2020-04-01, 2020-04-01, 2020-04-01, 2020-04-01~
## $ validTo <date> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA~
## $ geometry <MULTIPOLYGON [°]> MULTIPOLYGON (((96.26836 4...., MULTIPOLYGON (~SumbarLpg<-read_excel(path = "D:/Magister IPB/Sains Data-STA581/Shape Data/datamaster.xlsx")
merged_SumbarLpg <- geo_join(spatial_data=admin2, data_frame=SumbarLpg, by_sp="ADM2_PCODE", by_df="ADM2_PCODE", how = "inner")## Warning: We recommend using the dplyr::*_join() family of functions instead.mycol <- c("green", "yellow", "red", "red4")
GraphDATA<-ggplot()+
geom_sf(data=merged_SumbarLpg,aes(fill=DATA))+
scale_fill_gradientn(colours=mycol)+
labs(title="Data Simulasi Sebaran Covid-19 di Sumbar dan Lampung")
GraphDATA
Soal Nomor 1b view total pulau sumatera
library(sf)
library(ggplot2)
library(tigris)
library(dplyr)
library(readxl)
Admin2Kabupaten<-"D:/Magister IPB/Sains Data-STA581/Shape Data/Admin Kabupaten/idn_admbnda_adm2_bps_20200401.shp"
glimpse(Admin2Kabupaten)## chr "D:/Magister IPB/Sains Data-STA581/Shape Data/Admin Kabupaten/idn_admbnda_adm2_bps_20200401.shp"admin2<-st_read(Admin2Kabupaten)## Reading layer `idn_admbnda_adm2_bps_20200401' from data source
## `D:\Magister IPB\Sains Data-STA581\Shape Data\Admin Kabupaten\idn_admbnda_adm2_bps_20200401.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 522 features and 14 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: 95.01079 ymin: -11.00762 xmax: 141.0194 ymax: 6.07693
## Geodetic CRS: WGS 84glimpse(admin2)## Rows: 522
## Columns: 15
## $ Shape_Leng <dbl> 2.360029, 1.963994, 4.590182, 3.287754, 4.448584, 4.907219,~
## $ Shape_Area <dbl> 0.22896809, 0.15413587, 0.23639581, 0.31616114, 0.34303826,~
## $ ADM2_EN <chr> "Aceh Barat", "Aceh Barat Daya", "Aceh Besar", "Aceh Jaya",~
## $ ADM2_PCODE <chr> "ID1107", "ID1112", "ID1108", "ID1116", "ID1103", "ID1102",~
## $ ADM2_REF <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM2ALT1EN <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM2ALT2EN <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM1_EN <chr> "Aceh", "Aceh", "Aceh", "Aceh", "Aceh", "Aceh", "Aceh", "Ac~
## $ ADM1_PCODE <chr> "ID11", "ID11", "ID11", "ID11", "ID11", "ID11", "ID11", "ID~
## $ ADM0_EN <chr> "Indonesia", "Indonesia", "Indonesia", "Indonesia", "Indone~
## $ ADM0_PCODE <chr> "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID",~
## $ date <date> 2019-12-20, 2019-12-20, 2019-12-20, 2019-12-20, 2019-12-20~
## $ validOn <date> 2020-04-01, 2020-04-01, 2020-04-01, 2020-04-01, 2020-04-01~
## $ validTo <date> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA~
## $ geometry <MULTIPOLYGON [°]> MULTIPOLYGON (((96.26836 4...., MULTIPOLYGON (~SumbarLpg<-read_excel(path = "D:/Magister IPB/Sains Data-STA581/Shape Data/datamaster2.xlsx")
merged_SumbarLpg <- geo_join(spatial_data=admin2, data_frame=SumbarLpg, by_sp="ADM2_PCODE", by_df="ADM2_PCODE", how = "inner")## Warning: We recommend using the dplyr::*_join() family of functions instead.mycol <- c("green", "yellow", "red", "red4")
GraphDATA<-ggplot()+
geom_sf(data=merged_SumbarLpg,aes(fill=DATA))+
scale_fill_gradientn(colours=mycol)+
labs(title="Data Simulasi Sebaran Covid-19 di Sumbar dan Lampung")
GraphDATA
Soal Nomor 1b view total Provinsi Sumbar
library(sf)
library(ggplot2)
library(tigris)
library(dplyr)
library(readxl)
Admin2Kecamatan<-"D:/Magister IPB/Sains Data-STA581/Shape Data/Admin Kecamatan/idn_admbnda_adm3_bps_20200401.shp"
glimpse(Admin2Kecamatan)## chr "D:/Magister IPB/Sains Data-STA581/Shape Data/Admin Kecamatan/idn_admbnda_adm3_bps_20200401.shp"admin3<-st_read(Admin2Kecamatan)## Reading layer `idn_admbnda_adm3_bps_20200401' from data source
## `D:\Magister IPB\Sains Data-STA581\Shape Data\Admin Kecamatan\idn_admbnda_adm3_bps_20200401.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 7069 features and 16 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: 95.01079 ymin: -11.00762 xmax: 141.0194 ymax: 6.07693
## Geodetic CRS: WGS 84glimpse(admin3)## Rows: 7,069
## Columns: 17
## $ Shape_Leng <dbl> 0.2798656, 0.7514001, 0.6900061, 0.6483629, 0.2437073, 1.35~
## $ Shape_Area <dbl> 0.003107633, 0.016925540, 0.024636382, 0.010761277, 0.00116~
## $ ADM3_EN <chr> "2 X 11 Enam Lingkung", "2 X 11 Kayu Tanam", "Abab", "Abang~
## $ ADM3_PCODE <chr> "ID1306050", "ID1306052", "ID1612030", "ID5107050", "ID7471~
## $ ADM3_REF <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM3ALT1EN <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM3ALT2EN <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM2_EN <chr> "Padang Pariaman", "Padang Pariaman", "Penukal Abab Lematan~
## $ ADM2_PCODE <chr> "ID1306", "ID1306", "ID1612", "ID5107", "ID7471", "ID9432",~
## $ ADM1_EN <chr> "Sumatera Barat", "Sumatera Barat", "Sumatera Selatan", "Ba~
## $ ADM1_PCODE <chr> "ID13", "ID13", "ID16", "ID51", "ID74", "ID94", "ID94", "ID~
## $ ADM0_EN <chr> "Indonesia", "Indonesia", "Indonesia", "Indonesia", "Indone~
## $ ADM0_PCODE <chr> "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID",~
## $ date <date> 2019-12-20, 2019-12-20, 2019-12-20, 2019-12-20, 2019-12-20~
## $ validOn <date> 2020-04-01, 2020-04-01, 2020-04-01, 2020-04-01, 2020-04-01~
## $ validTo <date> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA~
## $ geometry <MULTIPOLYGON [°]> MULTIPOLYGON (((100.2811 -0..., MULTIPOLYGON (~Sumbar<-read_excel(path = "D:/Magister IPB/Sains Data-STA581/Shape Data/datamaster4.xlsx")
merged_Sumbar <- geo_join(spatial_data=admin3, data_frame=Sumbar, by_sp="ADM3_PCODE", by_df="ADM3_PCODE", how = "inner")## Warning: We recommend using the dplyr::*_join() family of functions instead.mycol <- c("green", "yellow", "red", "red4")
GraphDATA<-ggplot()+
geom_sf(data=merged_Sumbar,aes(fill=DATA))+
scale_fill_gradientn(colours=mycol)+
labs(title="Data Simulasi Sebaran Covid-19 di Sumbar")
GraphDATA
Soal Nomor 1b view total Provinsi Sumbar kota Solok
library(sf)
library(ggplot2)
library(tigris)
library(dplyr)
library(readxl)
Admin2Kecamatan<-"D:/Magister IPB/Sains Data-STA581/Shape Data/Admin Kecamatan/idn_admbnda_adm3_bps_20200401.shp"
glimpse(Admin2Kecamatan)## chr "D:/Magister IPB/Sains Data-STA581/Shape Data/Admin Kecamatan/idn_admbnda_adm3_bps_20200401.shp"admin3<-st_read(Admin2Kecamatan)## Reading layer `idn_admbnda_adm3_bps_20200401' from data source
## `D:\Magister IPB\Sains Data-STA581\Shape Data\Admin Kecamatan\idn_admbnda_adm3_bps_20200401.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 7069 features and 16 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: 95.01079 ymin: -11.00762 xmax: 141.0194 ymax: 6.07693
## Geodetic CRS: WGS 84glimpse(admin3)## Rows: 7,069
## Columns: 17
## $ Shape_Leng <dbl> 0.2798656, 0.7514001, 0.6900061, 0.6483629, 0.2437073, 1.35~
## $ Shape_Area <dbl> 0.003107633, 0.016925540, 0.024636382, 0.010761277, 0.00116~
## $ ADM3_EN <chr> "2 X 11 Enam Lingkung", "2 X 11 Kayu Tanam", "Abab", "Abang~
## $ ADM3_PCODE <chr> "ID1306050", "ID1306052", "ID1612030", "ID5107050", "ID7471~
## $ ADM3_REF <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM3ALT1EN <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM3ALT2EN <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,~
## $ ADM2_EN <chr> "Padang Pariaman", "Padang Pariaman", "Penukal Abab Lematan~
## $ ADM2_PCODE <chr> "ID1306", "ID1306", "ID1612", "ID5107", "ID7471", "ID9432",~
## $ ADM1_EN <chr> "Sumatera Barat", "Sumatera Barat", "Sumatera Selatan", "Ba~
## $ ADM1_PCODE <chr> "ID13", "ID13", "ID16", "ID51", "ID74", "ID94", "ID94", "ID~
## $ ADM0_EN <chr> "Indonesia", "Indonesia", "Indonesia", "Indonesia", "Indone~
## $ ADM0_PCODE <chr> "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID", "ID",~
## $ date <date> 2019-12-20, 2019-12-20, 2019-12-20, 2019-12-20, 2019-12-20~
## $ validOn <date> 2020-04-01, 2020-04-01, 2020-04-01, 2020-04-01, 2020-04-01~
## $ validTo <date> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA~
## $ geometry <MULTIPOLYGON [°]> MULTIPOLYGON (((100.2811 -0..., MULTIPOLYGON (~Sumbar<-read_excel(path = "D:/Magister IPB/Sains Data-STA581/Shape Data/datamaster6.xlsx")
merged_Sumbar <- geo_join(spatial_data=admin3, data_frame=Sumbar, by_sp="ADM3_PCODE", by_df="ADM3_PCODE", how = "inner")## Warning: We recommend using the dplyr::*_join() family of functions instead.mycol <- c("green", "yellow", "red", "red4")
GraphDATA<-ggplot()+
geom_sf(data=merged_Sumbar,aes(fill=DATA))+
scale_fill_gradientn(colours=mycol)+
labs(title="Data Simulasi Sebaran Covid-19 di Kota Solok-Sumbar")
GraphDATA