-
Notifications
You must be signed in to change notification settings - Fork 0
/
RECICLADO2.Rmd
107 lines (79 loc) · 9.63 KB
/
RECICLADO2.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
---
title: "Proceso de clustering y análisis descriptivo"
author: "Diego Medina"
date: "21-03-2022"
output: rmdformats::readthedown
---
```{r,message=FALSE,warning=FALSE}
library(sf)
library(rgdal)
library(ggplot2)
library(cowplot)
```
```{r,message=FALSE,warning=FALSE,include=FALSE}
SANTIAGO <- st_read(dsn="outputs/ISMT/SANTIAGO/SANTIAGO_ISMT.shp",quiet=TRUE)
database <- as.data.frame(st_read(dsn="outputs/GEODATABASE/adultomayor.shp",quiet=TRUE) )
```
### Dendrograma general
![Clustering Jerárquico Santiago](outputs/Plots/HClust.png)
### Para 4 categorías
```{r,message=FALSE,warning=FALSE,include=FALSE}
# ------ CLUSTER k = 4 ------- #
PORC_ADM4 <- ggplot(SANTIAGO,aes(x = cluster4,y = PORC_ADM)) + geom_boxplot() + labs(title = "Porcentaje adultos mayores por zona" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PORC_ADM)),linetype="dotted",size=1.5,color="deeppink1")
PJHSEM4 <- ggplot(SANTIAGO,aes(x = cluster4,y = PJHSEM)) + geom_boxplot() + labs(title = "Porcentaje Jefes de Hogar sin ensenanza media" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PJHSEM)) ,linetype="dotted",size=1.5,color="deeppink1")
TIM4 <- ggplot(SANTIAGO,aes(x = cluster4,y = log(TIM))) + geom_boxplot() + labs(title = "Tasa de inmigración" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(log(database$TIM))),linetype="dotted",size=1.5,color="deeppink1")
EMP4 <- ggplot(SANTIAGO,aes(x = cluster4,y = EMP)) + geom_boxplot() + labs(title = "Porcentaje empleabilidad mayor a 15 anos" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$EMP)) ,linetype="dotted",size=1.5,color="deeppink1")
HAC4 <- ggplot(SANTIAGO,aes(x = cluster4,y = HAC)) + geom_boxplot() + labs(title = "Porcentaje hacinamiento por zona" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$HAC)) ,linetype="dotted",size=1.5,color="deeppink1")
PIMVZ4 <- ggplot(SANTIAGO,aes(x = cluster4,y = PIMVZ)) + geom_boxplot() + labs(title = "Materialidad de la vivienda" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PIMVZ)) ,linetype="dotted",size=1.5,color="deeppink1")
```
```{r,fig.width=12,fig.height=7}
plot_grid(PORC_ADM4,PJHSEM4,TIM4,EMP4,HAC4,PIMVZ4)
```
### Para 5 categorías
```{r,message=FALSE,warning=FALSE,include=FALSE}
PORC_ADM5 <- ggplot(SANTIAGO,aes(x = cluster5,y = PORC_ADM)) + geom_boxplot() + labs(title = "Porcentaje adultos mayores por zona" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PORC_ADM)),linetype="dotted",size=1.5,color="deeppink1")
PJHSEM5 <- ggplot(SANTIAGO,aes(x = cluster5,y = PJHSEM)) + geom_boxplot() + labs(title = "Porcentaje Jefes de Hogar sin ensenanza media" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PJHSEM)) ,linetype="dotted",size=1.5,color="deeppink1")
TIM5 <- ggplot(SANTIAGO,aes(x = cluster5,y = log(TIM))) + geom_boxplot() + labs(title = "Tasa de inmigración" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(log(database$TIM))),linetype="dotted",size=1.5,color="deeppink1")
EMP5 <- ggplot(SANTIAGO,aes(x = cluster5,y = EMP)) + geom_boxplot() + labs(title = "Porcentaje empleabilidad mayor a 15 anos" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$EMP)) ,linetype="dotted",size=1.5,color="deeppink1")
HAC5 <- ggplot(SANTIAGO,aes(x = cluster5,y = HAC)) + geom_boxplot() + labs(title = "Porcentaje hacinamiento por zona" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$HAC)) ,linetype="dotted",size=1.5,color="deeppink1")
PIMVZ5 <- ggplot(SANTIAGO,aes(x = cluster5,y = PIMVZ)) + geom_boxplot() + labs(title = "Materialidad de la vivienda" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PIMVZ)) ,linetype="dotted",size=1.5,color="deeppink1")
```
```{r,fig.width=12,fig.height=7}
plot_grid(PORC_ADM5,PJHSEM5,TIM5,EMP5,HAC5,PIMVZ5)
```
### Para 6 categorías
```{r,message=FALSE,warning=FALSE,include=FALSE}
PORC_ADM6 <- ggplot(SANTIAGO,aes(x = cluster6,y = PORC_ADM)) + geom_boxplot() + labs(title = "Porcentaje adultos mayores por zona" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PORC_ADM)),linetype="dotted",size=1.5,color="deeppink1")
PJHSEM6 <- ggplot(SANTIAGO,aes(x = cluster6,y = PJHSEM)) + geom_boxplot() + labs(title = "Porcentaje Jefes de Hogar sin ensenanza media" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PJHSEM)) ,linetype="dotted",size=1.5,color="deeppink1")
TIM6 <- ggplot(SANTIAGO,aes(x = cluster6,y = log(TIM))) + geom_boxplot() + labs(title = "Tasa de inmigración" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(log(database$TIM))),linetype="dotted",size=1.5,color="deeppink1")
EMP6 <- ggplot(SANTIAGO,aes(x = cluster6,y = EMP)) + geom_boxplot() + labs(title = "Porcentaje empleabilidad mayor a 15 anos" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$EMP)) ,linetype="dotted",size=1.5,color="deeppink1")
HAC6 <- ggplot(SANTIAGO,aes(x = cluster6,y = HAC)) + geom_boxplot() + labs(title = "Porcentaje hacinamiento por zona" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$HAC)) ,linetype="dotted",size=1.5,color="deeppink1")
PIMVZ6 <- ggplot(SANTIAGO,aes(x = cluster6,y = PIMVZ)) + geom_boxplot() + labs(title = "Materialidad de la vivienda" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PIMVZ)) ,linetype="dotted",size=1.5,color="deeppink1")
```
```{r,fig.width=12,fig.height=7}
plot_grid(PORC_ADM6,PJHSEM6,TIM6,EMP6,HAC6,PIMVZ6)
```
### Para 7 categorías
```{r,message=FALSE,warning=FALSE,include=FALSE}
PORC_ADM7 <- ggplot(SANTIAGO,aes(x = cluster7,y = PORC_ADM)) + geom_boxplot() + labs(title = "Porcentaje adultos mayores por zona" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PORC_ADM)),linetype="dotted",size=1.5,color="deeppink1")
PJHSEM7 <- ggplot(SANTIAGO,aes(x = cluster7,y = PJHSEM)) + geom_boxplot() + labs(title = "Porcentaje Jefes de Hogar sin ensenanza media" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PJHSEM)) ,linetype="dotted",size=1.5,color="deeppink1")
TIM7 <- ggplot(SANTIAGO,aes(x = cluster7,y = log(TIM))) + geom_boxplot() + labs(title = "Tasa de inmigración" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(log(database$TIM))),linetype="dotted",size=1.5,color="deeppink1")
EMP7 <- ggplot(SANTIAGO,aes(x = cluster7,y = EMP)) + geom_boxplot() + labs(title = "Porcentaje empleabilidad mayor a 15 anos" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$EMP)) ,linetype="dotted",size=1.5,color="deeppink1")
HAC7 <- ggplot(SANTIAGO,aes(x = cluster7,y = HAC)) + geom_boxplot() + labs(title = "Porcentaje hacinamiento por zona" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$HAC)) ,linetype="dotted",size=1.5,color="deeppink1")
PIMVZ7 <- ggplot(SANTIAGO,aes(x = cluster7,y = PIMVZ)) + geom_boxplot() + labs(title = "Materialidad de la vivienda" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PIMVZ)) ,linetype="dotted",size=1.5,color="deeppink1")
```
```{r,fig.width=12,fig.height=7}
plot_grid(PORC_ADM7,PJHSEM7,TIM7,EMP7,HAC7,PIMVZ7)
```
### Para 8 categorías
```{r,message=FALSE,warning=FALSE,include=FALSE}
PORC_ADM8 <- ggplot(SANTIAGO,aes(x = cluster8,y = PORC_ADM)) + geom_boxplot() + labs(title = "Porcentaje adultos mayores por zona" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PORC_ADM)),linetype="dotted",size=1.5,color="deeppink1")
PJHSEM8 <- ggplot(SANTIAGO,aes(x = cluster8,y = PJHSEM)) + geom_boxplot() + labs(title = "Porcentaje Jefes de Hogar sin ensenanza media" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PJHSEM)) ,linetype="dotted",size=1.5,color="deeppink1")
TIM8 <- ggplot(SANTIAGO,aes(x = cluster8,y = log(TIM))) + geom_boxplot() + labs(title = "Tasa de inmigración" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(log(database$TIM))),linetype="dotted",size=1.5,color="deeppink1")
EMP8 <- ggplot(SANTIAGO,aes(x = cluster8,y = EMP)) + geom_boxplot() + labs(title = "Porcentaje empleabilidad mayor a 15 anos" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$EMP)) ,linetype="dotted",size=1.5,color="deeppink1")
HAC8 <- ggplot(SANTIAGO,aes(x = cluster8,y = HAC)) + geom_boxplot() + labs(title = "Porcentaje hacinamiento por zona" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$HAC)) ,linetype="dotted",size=1.5,color="deeppink1")
PIMVZ8 <- ggplot(SANTIAGO,aes(x = cluster8,y = PIMVZ)) + geom_boxplot() + labs(title = "Materialidad de la vivienda" , x = "Cluster", y = "Porcentaje") + geom_hline(aes(yintercept = mean(database$PIMVZ)) ,linetype="dotted",size=1.5,color="deeppink1")
```
```{r,fig.width=12,fig.height=7}
plot_grid(PORC_ADM8,PJHSEM8,TIM8,EMP8,HAC8,PIMVZ8)
```