IMPORTAR DATAS
library(rio)
presicovid = import("dataOK_all.xlsx")## New names:
## • `` -> `...1`viviendas con agua por red pública
presicovid$agua_percent <- (presicovid$agua1_Red / presicovid$agua10_Total) * 100presicovid$tasa_covid <- (presicovid$countFallecidos / presicovid$countPositivos) * 1000presicovid$razon_presi <- presicovid$Keiko / presicovid$Castillooptions(repos = c(CRAN = "https://cran.rstudio.com/"))
# Instalar y cargar el paquete caret si aún no está instalado
install.packages("caret")## Installing package into 'C:/Users/Romina/AppData/Local/R/win-library/4.3'
## (as 'lib' is unspecified)## package 'caret' successfully unpacked and MD5 sums checked## Warning: cannot remove prior installation of package 'caret'## Warning in file.copy(savedcopy, lib, recursive = TRUE): problema al copiar
## C:\Users\Romina\AppData\Local\R\win-library\4.3\00LOCK\caret\libs\x64\caret.dll
## a C:\Users\Romina\AppData\Local\R\win-library\4.3\caret\libs\x64\caret.dll:
## Permission denied## Warning: restored 'caret'##
## The downloaded binary packages are in
## C:\Users\Romina\AppData\Local\Temp\RtmpW61mOT\downloaded_packageslibrary(caret)## Loading required package: ggplot2## Loading required package: lattice# Seleccionar las columnas que deseas estandarizar
columns_to_standardize <- presicovid[, 51:53]
# Crear el objeto de preprocesamiento con el método de estandarización
preProc <- preProcess(columns_to_standardize, method = c("center", "scale"))
# Aplicar la transformación para estandarizar las columnas
standardized_columns <- predict(preProc, columns_to_standardize)
# Asignar las columnas estandarizadas de nuevo al dataframe original
presicovid[, 51:53] <- standardized_columns
# Verificar el resultado
print(head(presicovid[, 51:53]))## agua_percent tasa_covid razon_presi
## 1 -0.35767647 -1.1425581 -0.38149003
## 2 0.38593873 -0.5361040 -0.03106791
## 3 1.09391603 -0.8001609 0.04925502
## 4 -2.18071172 -1.2606334 -0.92027166
## 5 0.05637991 -0.4987786 -0.03127341
## 6 0.20333970 1.1681410 0.08556784str(presicovid)## 'data.frame': 196 obs. of 53 variables:
## $ ...1 : num 1 2 3 4 5 6 7 8 9 10 ...
## $ key : chr "AMAZONAS+BAGUA" "AMAZONAS+BONGARA" "AMAZONAS+CHACHAPOYAS" "AMAZONAS+CONDORCANQUI" ...
## $ Código : num 102 103 101 104 105 106 107 202 203 204 ...
## $ pared1_Ladrillo : num 4633 1602 3782 291 430 ...
## $ pared2_Piedra : num 46 9 22 7 7 7 35 1 0 3 ...
## $ pared3_Adobe : num 6639 2729 5881 672 5217 ...
## $ pared4_Tapia : num 222 240 2476 8 6052 ...
## $ pared5_Quincha : num 2518 157 309 386 346 ...
## $ pared6_Piedra : num 127 36 168 7 54 28 518 65 7 6 ...
## $ pared7_Madera : num 4484 2505 1270 8145 606 ...
## $ pared8_Triplay : num 851 30 91 200 45 24 210 18 0 1 ...
## $ pared9_Otro : num 0 0 0 0 0 0 0 0 0 0 ...
## $ pared10_Total : num 19520 7308 13999 9716 12757 ...
## $ techo1_Concreto : num 2187 692 2262 56 187 ...
## $ techo2_Madera : num 294 75 160 188 43 48 340 57 12 8 ...
## $ techo3_Tejas : num 179 382 3393 177 3071 ...
## $ techo4_Planchas : num 13186 6084 8005 2036 9343 ...
## $ techo5_Caña : num 160 38 50 15 26 15 196 10 8 5 ...
## $ techo6_Triplay : num 106 5 14 10 12 5 62 17 4 3 ...
## $ techo7_Paja : num 3408 32 115 7234 75 ...
## $ techo8_Otro : num 0 0 0 0 0 0 0 0 0 0 ...
## $ techo9_Total : num 19520 7308 13999 9716 12757 ...
## $ piso1_Parquet : num 6 5 23 2 4 3 20 0 0 5 ...
## $ piso2_Láminas : num 19 2 36 0 0 4 32 0 0 1 ...
## $ piso3_Losetas : num 647 165 1077 20 46 ...
## $ piso4_Madera : num 157 132 240 1523 295 ...
## $ piso5_Cemento : num 7121 2917 6189 943 1911 ...
## $ piso6_Tierra : num 11569 4087 6434 7228 10501 ...
## $ piso7_Otro : num 1 0 0 0 0 0 0 0 0 0 ...
## $ piso8_Total : num 19520 7308 13999 9716 12757 ...
## $ agua1_Red : num 9429 4569 10647 1307 7172 ...
## $ agua2_Red_fueraVivienda: num 4392 1497 1619 867 3097 ...
## $ agua3_Pilón : num 793 215 184 1003 1112 ...
## $ agua4_Camión : num 59 0 49 2 0 0 117 0 0 0 ...
## $ agua5_Pozo : num 1792 474 876 2564 819 ...
## $ agua6_Manantial : num 270 67 92 431 132 211 471 121 61 27 ...
## $ agua7_Río : num 2648 388 488 3428 369 ...
## $ agua8_Otro : num 56 61 24 80 9 29 104 2 1 6 ...
## $ agua9_Vecino : num 81 37 20 34 47 8 177 9 4 6 ...
## $ agua10_Total : num 19520 7308 13999 9716 12757 ...
## $ elec1_Sí : num 13204 6025 12248 1792 10886 ...
## $ elec2_No : num 6316 1283 1751 7924 1871 ...
## $ elec3_Total : num 19520 7308 13999 9716 12757 ...
## $ departamento : chr "AMAZONAS" "AMAZONAS" "AMAZONAS" "AMAZONAS" ...
## $ provincia : chr "BAGUA" "BONGARA" "CHACHAPOYAS" "CONDORCANQUI" ...
## $ Castillo : num 25629 8374 15671 13154 12606 ...
## $ Keiko : num 10770 5209 10473 1446 7840 ...
## $ ganaCastillo : num 1 1 1 1 1 1 1 1 1 1 ...
## $ countPositivos : num 8126 389 2174 3481 456 ...
## $ countFallecidos : num 462 72 281 111 88 60 336 26 31 21 ...
## $ agua_percent : num -0.3577 0.3859 1.0939 -2.1807 0.0564 ...
## $ tasa_covid : num -1.143 -0.536 -0.8 -1.261 -0.499 ...
## $ razon_presi : num -0.3815 -0.0311 0.0493 -0.9203 -0.0313 ...chaolima <- subset(presicovid, provincia != "LIMA")dataClus=chaolima[,c(51:53)]
row.names(dataClus)=chaolima$provincialibrary(cluster)
g.dist = daisy(dataClus, metric="gower")library(ggplot2)
library(factoextra)## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBaPAM - PARTICIÓN
library(factoextra)
fviz_nbclust(dataClus, pam,diss=g.dist,method = "gap_stat",k.max = 10,verbose = F)
library(kableExtra)
set.seed(123)
res.pam=pam(g.dist,5,cluster.only = F)
#nueva columna
dataClus$pam=res.pam$cluster
# ver
head(dataClus,15)%>%kbl()%>%kable_styling()| agua_percent | tasa_covid | razon_presi | pam | |
|---|---|---|---|---|
| BAGUA | -0.3576765 | -1.1425581 | -0.3814900 | 1 |
| BONGARA | 0.3859387 | -0.5361040 | -0.0310679 | 1 |
| CHACHAPOYAS | 1.0939160 | -0.8001609 | 0.0492550 | 2 |
| CONDORCANQUI | -2.1807117 | -1.2606334 | -0.9202717 | 3 |
| LUYA | 0.0563799 | -0.4987786 | -0.0312734 | 1 |
| RODRÍGUEZ DE MENDOZA | 0.2033397 | 1.1681410 | 0.0855678 | 1 |
| UTCUBAMBA | -0.3364349 | -0.9875844 | -0.1977399 | 1 |
| AIJA | 1.0259083 | 0.1450176 | -0.0559018 | 2 |
| ANTONIO RAYMONDI | 1.5768436 | 1.3034891 | -0.8405290 | 2 |
| ASUNCIÓN | 0.8467027 | 0.2718473 | -0.6090647 | 2 |
| BOLOGNESI | 0.8979283 | 0.4646200 | -0.2093348 | 2 |
| CARHUAZ | 0.9380403 | -0.0149440 | -0.3169852 | 2 |
| CARLOS FERMÍN FITZCARRALD | 0.5809679 | 1.4598788 | -0.6551620 | 2 |
| CASMA | 0.2768715 | 0.3663202 | 1.2717154 | 4 |
| CORONGO | 1.0471040 | 1.0170847 | 0.0549304 | 2 |
fviz_silhouette(res.pam,print.summary = F)
silPAM=data.frame(res.pam$silinfo$widths)
silPAM$country=row.names(silPAM)
poorPAM=silPAM[silPAM$sil_width<0,'country']%>%sort()
poorPAM## [1] "ACOBAMBA" "AMBO" "ANDAHUAYLAS"
## [4] "AYMARAES" "CANGALLO" "CARAVELÍ"
## [7] "CASTROVIRREYNA" "CAYLLOMA" "CORONEL PORTILLO"
## [10] "DATEM DEL MARAÑÓN" "HUAMALÍES" "HUANCAVELICA"
## [13] "HUANTA" "JAUJA" "OCROS"
## [16] "OXAPAMPA" "PUERTO INCA" "SAN MIGUEL"
## [19] "SANTA CRUZ" "TARMA" "UCAYALI"
## [22] "VILCAS HUAMÁN" "YAUYOS"AGNES - JERÁRQUICA AGLOMERATIVA
fviz_nbclust(dataClus, hcut,diss=g.dist,method = "gap_stat",k.max = 10,verbose = F,hc_func = "agnes")
set.seed(123)
library(factoextra)
res.agnes<- hcut(g.dist, k = 5,hc_func='agnes',hc_method = "ward.D")
dataClus$agnes=res.agnes$cluster
# ver
head(dataClus,15)%>%kbl()%>%kable_styling()| agua_percent | tasa_covid | razon_presi | pam | agnes | |
|---|---|---|---|---|---|
| BAGUA | -0.3576765 | -1.1425581 | -0.3814900 | 1 | 1 |
| BONGARA | 0.3859387 | -0.5361040 | -0.0310679 | 1 | 2 |
| CHACHAPOYAS | 1.0939160 | -0.8001609 | 0.0492550 | 2 | 2 |
| CONDORCANQUI | -2.1807117 | -1.2606334 | -0.9202717 | 3 | 3 |
| LUYA | 0.0563799 | -0.4987786 | -0.0312734 | 1 | 2 |
| RODRÍGUEZ DE MENDOZA | 0.2033397 | 1.1681410 | 0.0855678 | 1 | 2 |
| UTCUBAMBA | -0.3364349 | -0.9875844 | -0.1977399 | 1 | 1 |
| AIJA | 1.0259083 | 0.1450176 | -0.0559018 | 2 | 2 |
| ANTONIO RAYMONDI | 1.5768436 | 1.3034891 | -0.8405290 | 2 | 2 |
| ASUNCIÓN | 0.8467027 | 0.2718473 | -0.6090647 | 2 | 2 |
| BOLOGNESI | 0.8979283 | 0.4646200 | -0.2093348 | 2 | 2 |
| CARHUAZ | 0.9380403 | -0.0149440 | -0.3169852 | 2 | 2 |
| CARLOS FERMÍN FITZCARRALD | 0.5809679 | 1.4598788 | -0.6551620 | 2 | 2 |
| CASMA | 0.2768715 | 0.3663202 | 1.2717154 | 4 | 4 |
| CORONGO | 1.0471040 | 1.0170847 | 0.0549304 | 2 | 2 |
fviz_silhouette(res.agnes,print.summary = F)
silAGNES=data.frame(res.agnes$silinfo$widths)
silAGNES$country=row.names(silAGNES)
poorAGNES=silAGNES[silAGNES$sil_width<0,'country']%>%sort()
poorAGNES## [1] "CAJABAMBA" "CAJATAMBO" "CARAVELÍ"
## [4] "CHINCHEROS" "CORONEL PORTILLO" "HUÁNUCO"
## [7] "HUAYTARÁ" "JAÉN" "JAUJA"
## [10] "LA UNIÓN" "LEONCIO PRADO" "LORETO"
## [13] "LUYA" "MANU" "NAZCA"
## [16] "OCROS" "OTUZCO" "OXAPAMPA"
## [19] "PACHITEA" "SÁNCHEZ CARRIÓN" "SANTIAGO DE CHUCO"
## [22] "SUCRE" "TARATA" "TARMA"DIANA
fviz_nbclust(dataClus, hcut,diss=g.dist,method = "gap_stat",k.max = 10,verbose = F,hc_func = "diana")
set.seed(123)
res.diana <- hcut(g.dist, k = 5,hc_func='diana')
dataClus$diana=res.diana$cluster
# veamos
head(dataClus,15)%>%kbl%>%kable_styling()| agua_percent | tasa_covid | razon_presi | pam | agnes | diana | |
|---|---|---|---|---|---|---|
| BAGUA | -0.3576765 | -1.1425581 | -0.3814900 | 1 | 1 | 1 |
| BONGARA | 0.3859387 | -0.5361040 | -0.0310679 | 1 | 2 | 2 |
| CHACHAPOYAS | 1.0939160 | -0.8001609 | 0.0492550 | 2 | 2 | 2 |
| CONDORCANQUI | -2.1807117 | -1.2606334 | -0.9202717 | 3 | 3 | 1 |
| LUYA | 0.0563799 | -0.4987786 | -0.0312734 | 1 | 2 | 2 |
| RODRÍGUEZ DE MENDOZA | 0.2033397 | 1.1681410 | 0.0855678 | 1 | 2 | 2 |
| UTCUBAMBA | -0.3364349 | -0.9875844 | -0.1977399 | 1 | 1 | 1 |
| AIJA | 1.0259083 | 0.1450176 | -0.0559018 | 2 | 2 | 2 |
| ANTONIO RAYMONDI | 1.5768436 | 1.3034891 | -0.8405290 | 2 | 2 | 2 |
| ASUNCIÓN | 0.8467027 | 0.2718473 | -0.6090647 | 2 | 2 | 2 |
| BOLOGNESI | 0.8979283 | 0.4646200 | -0.2093348 | 2 | 2 | 2 |
| CARHUAZ | 0.9380403 | -0.0149440 | -0.3169852 | 2 | 2 | 2 |
| CARLOS FERMÍN FITZCARRALD | 0.5809679 | 1.4598788 | -0.6551620 | 2 | 2 | 2 |
| CASMA | 0.2768715 | 0.3663202 | 1.2717154 | 4 | 4 | 2 |
| CORONGO | 1.0471040 | 1.0170847 | 0.0549304 | 2 | 2 | 2 |
silDIANA=data.frame(res.diana$silinfo$widths)
silDIANA$country=row.names(silDIANA)
poorDIANA=silDIANA[silDIANA$sil_width<0,'country']%>%sort()
poorDIANA## [1] "ASCOPE" "CHICLAYO" "HUACAYBAMBA" "LA MAR"
## [5] "LEONCIO PRADO" "PAITA" "PASCO" "SECHURA"fviz_silhouette(res.diana,print.summary = F)