library(rio)
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, union#LIMPIEZA DE LA PRIMERA BASE DE DATOS: LIMA2022
data_denuncias=import("Lima2022.xlsx")## New names:
## • `` -> `...2`data_denuncias= data_denuncias[,-c(2)] print(names(data_denuncias))## [1] "Distrito" "2022"library(dplyr)data_denuncias <- data_denuncias %>% rename(DENUNCIAS_2022 = `2022`)#LIMPIEZA DE LA SEGUNDA BASE DE DATOS: RESIDUOS PERU
datos_residuos= import("residuosPeru.xlsx")## New names:
## • `` -> `...2`
## • `` -> `...3`
## • `` -> `...4`
## • `` -> `...5`
## • `` -> `...6`
## • `` -> `...7`
## • `` -> `...8`
## • `` -> `...9`
## • `` -> `...10`
## • `` -> `...11`
## • `` -> `...12`
## • `` -> `...13`
## • `` -> `...14`
## • `` -> `...15`residuos_lima <- datos_residuos %>%
filter(...6 == "LIMA")%>%
slice(1:43)print(names(residuos_lima))## [1] "Residuos municipales generados anualmente"
## [2] "...2"
## [3] "...3"
## [4] "...4"
## [5] "...5"
## [6] "...6"
## [7] "...7"
## [8] "...8"
## [9] "...9"
## [10] "...10"
## [11] "...11"
## [12] "...12"
## [13] "...13"
## [14] "...14"
## [15] "...15"residuos_lima <- residuos_lima %>%
rename(
FECHA_CORTE = `Residuos municipales generados anualmente`,
N_SEC = '...2',
UBIGEO = '...3',
REG_NAT = '...4',
DEPARTAMENTO= '...5',
PROVINCIA ='...6',
DISTRITO1 = '...7',
POB_TOTAL = '...8',
POB_URBANA = '...9',
POB_RURAL = '...10',
GPC_DOM = '...11',
QRESIDUOS_DOM = '...12',
QRESIDUOS_NO_DOM = '...13',
QRESIDUOS_MUN = '...14',
PERIODO = '...15')print(names(residuos_lima))## [1] "FECHA_CORTE" "N_SEC" "UBIGEO" "REG_NAT"
## [5] "DEPARTAMENTO" "PROVINCIA" "DISTRITO1" "POB_TOTAL"
## [9] "POB_URBANA" "POB_RURAL" "GPC_DOM" "QRESIDUOS_DOM"
## [13] "QRESIDUOS_NO_DOM" "QRESIDUOS_MUN" "PERIODO"#TERCERA BASE DE DATOS
data_votos= import("datos_votos.xlsx")print(names(data_votos))## [1] "Column1" "Column2" "Column3" "Column4" "Column5" "Column6"
## [7] "Column7" "Column8" "Column9" "Column10" "Column11" "Column12"
## [13] "Column13" "Column14" "Column15" "Column16" "Column17"data_votos <- data_votos %>%
rename(
DISTRITOVOTO = `Column1`,
VOTOS_RP = `Column2`,
PORC_RP = `Column3`,
VOTOS_PP = `Column4`,
PORC_PP = `Column5`,
VOTOS_SP = `Column6`,
PORC_SP = `Column7`,
VOTOS_FE = `Column8`,
PORC_FE = `Column9`,
VOTOS_APP = `Column10`,
PORC_APP = `Column11`,
VOTOS_JP = `Column12`,
PORC_JP = `Column13`,
VOTOS_AVP = `Column14`,
PORC_AVP = `Column15`,
VOTOS_PL = `Column16`,
PORC_PL = `Column17`)print(names(data_votos))## [1] "DISTRITOVOTO" "VOTOS_RP" "PORC_RP" "VOTOS_PP" "PORC_PP"
## [6] "VOTOS_SP" "PORC_SP" "VOTOS_FE" "PORC_FE" "VOTOS_APP"
## [11] "PORC_APP" "VOTOS_JP" "PORC_JP" "VOTOS_AVP" "PORC_AVP"
## [16] "VOTOS_PL" "PORC_PL"data_votos <- data_votos %>%
mutate_at(vars(2:ncol(data_votos)), ~ as.numeric(gsub(",", ".", .)))data_votos <- rbind(data_votos[15, ], data_votos[-15, ])temp <- data_votos[24, ]data_votos[24, ] <- data_votos[23, ]data_votos[23, ] <- data_votos[22, ]data_votos[22, ] <- data_votos[21, ]data_votos[21, ] <- temp#ANALISIS DE LA DATA
data_unida <- bind_cols(data_denuncias,residuos_lima, data_votos)data_unida <- data_unida[, -c(7, 8)]print(data_unida[, c(1, 7, 16)])## Distrito DISTRITO1 DISTRITOVOTO
## 1 LIMA LIMA Lima
## 2 ANCON ANCON Ancón
## 3 ATE ATE Ate
## 4 BARRANCO BARRANCO Barranco
## 5 BREс BREÑA Breña
## 6 CARABAYLLO CARABAYLLO Carabayllo
## 7 CHACLACAYO CHACLACAYO Chaclacayo
## 8 CHORRILLOS CHORRILLOS Chorrillos
## 9 CIENEGUILLA CIENEGUILLA Cieneguilla
## 10 COMAS COMAS Comas
## 11 EL AGUSTINO EL AGUSTINO El Agustino
## 12 INDEPENDENCIA INDEPENDENCIA Independencia
## 13 JESUS MARIA JESUS MARIA Jesús María
## 14 LA MOLINA LA MOLINA La Molina
## 15 LA VICTORIA LA VICTORIA La Victoria
## 16 LINCE LINCE Lince
## 17 LOS OLIVOS LOS OLIVOS Los Olivos
## 18 LURIGANCHO LURIGANCHO Lurigancho-Chosica
## 19 LURIN LURIN Lurín
## 20 MAGDALENA DEL MAR MAGDALENA DEL MAR Magdalena del Mar
## 21 PUEBLO LIBRE MAGDALENA VIEJA Pueblo Libre
## 22 MIRAFLORES MIRAFLORES Miraflores
## 23 PACHACAMAC PACHACAMAC Pachacámac
## 24 PUCUSANA PUCUSANA Pucusana
## 25 PUENTE PIEDRA PUENTE PIEDRA Puente Piedra
## 26 PUNTA HERMOSA PUNTA HERMOSA Punta Hermosa
## 27 PUNTA NEGRA PUNTA NEGRA Punta Negra
## 28 RIMAC RIMAC Rímac
## 29 SAN BARTOLO SAN BARTOLO San Bartolo
## 30 SAN BORJA SAN BORJA San Borja
## 31 SAN ISIDRO SAN ISIDRO San Isidro
## 32 SAN JUAN DE LURIGANCHO SAN JUAN DE LURIGANCHO San Juan de Lurigancho
## 33 SAN JUAN DE MIRAFLORES SAN JUAN DE MIRAFLORES San Juan de Miraflores
## 34 SAN LUIS SAN LUIS San Luis
## 35 SAN MARTIN DE PORRES SAN MARTIN DE PORRES San Martín de Porres
## 36 SAN MIGUEL SAN MIGUEL San Miguel
## 37 SANTA ANITA SANTA ANITA Santa Anita
## 38 SANTA MARIA DEL MAR SANTA MARIA DEL MAR Santa María del Mar
## 39 SANTA ROSA SANTA ROSA Santa Rosa
## 40 SANTIAGO DE SURCO SANTIAGO DE SURCO Santiago de Surco
## 41 SURQUILLO SURQUILLO Surquillo
## 42 VILLA EL SALVADOR VILLA EL SALVADOR Villa El Salvador
## 43 VILLA MARIA DEL TRIUNFO VILLA MARIA DEL TRIUNFO Villa María del Triunfodata_unida <- data_unida[, -c(7,16)]str(data_unida)## 'data.frame': 43 obs. of 30 variables:
## $ Distrito : chr "LIMA" "ANCON" "ATE" "BARRANCO" ...
## $ DENUNCIAS_2022 : num 643 114 101 554 219 ...
## $ FECHA_CORTE : chr "20230614" "20230614" "20230614" "20230614" ...
## $ N_SEC : chr "1262" "1263" "1264" "1265" ...
## $ UBIGEO : chr "150101" "150102" "150103" "150104" ...
## $ REG_NAT : chr "COSTA" "COSTA" "COSTA" "COSTA" ...
## $ POB_TOTAL : chr "276857" "38482" "611082" "30641" ...
## $ POB_URBANA : chr "276857" "38482" "611082" "30641" ...
## $ POB_RURAL : chr "0" "0" "0" "0" ...
## $ GPC_DOM : chr "1.59" "0.51" "0.56999999999999995" "1.25" ...
## $ QRESIDUOS_DOM : chr "161045.5" "7223.3" "127750" "13999.3" ...
## $ QRESIDUOS_NO_DOM: chr "69019.5" "3095.7" "54750" "5999.7" ...
## $ QRESIDUOS_MUN : chr "230065" "10319" "182500" "19999" ...
## $ PERIODO : chr "2014" "2014" "2014" "2014" ...
## $ VOTOS_RP : num 62.33 3.73 57.37 11.6 22.72 ...
## $ PORC_RP : num 29.2 13.3 17.5 36.9 31.1 ...
## $ VOTOS_PP : num 52.98 9.33 98.37 5.77 18.68 ...
## $ PORC_PP : num 24.9 33.3 30 18.3 25.6 ...
## $ VOTOS_SP : num 43.61 5.99 52.07 6.4 14.02 ...
## $ PORC_SP : num 20.5 21.4 15.9 20.4 19.2 ...
## $ VOTOS_FE : num 25.79 2.04 27.91 2.77 8.24 ...
## $ PORC_FE : num 12.1 7.28 8.51 8.82 11.3 ...
## $ VOTOS_APP : num 7.68 3.59 26.14 2.19 2.47 ...
## $ PORC_APP : num 3.6 12.79 7.97 6.98 3.39 ...
## $ VOTOS_JP : num 13.13 1.68 25.11 1.63 3.81 ...
## $ PORC_JP : num 6.16 5.99 7.66 5.18 5.23 7.37 6.07 5.61 6.8 7.17 ...
## $ VOTOS_AVP : num 4.51 1.23 32.85 845 2.44 ...
## $ PORC_AVP : num 2.12 4.38 10.01 2.69 3.34 ...
## $ VOTOS_PL : num 3.1 465 8.19 223 552 ...
## $ PORC_PL : num 1.46 1.67 2.5 0.71 0.76 2.3 3 1.09 1.62 1.44 ...#PREGUNTA UNO
set.seed(2019)data_unida$RP_GANA <- ifelse(data_unida$PORC_RP > data_unida$PORC_PP & data_unida$PORC_RP > data_unida$PORC_SP, 1, 0)data_unida$RP_GANA## [1] 1 0 0 1 1 0 1 1 0 0 0 0 1 1 1 1 0 0 0 1 1 1 0 0 0 1 1 0 0 1 1 0 0 1 0 1 0 1
## [39] 0 1 1 0 0#caso de exito es 1 y el caso de no exito es 0
data_unida$QRESIDUOS_NO_DOM <- as.numeric(data_unida$QRESIDUOS_NO_DOM)h1=formula(RP_GANA~QRESIDUOS_NO_DOM+DENUNCIAS_2022)rlog1=glm(h1, data=data_unida,family = binomial)modelrl=list('RP_gana (I)'=rlog1)library(modelsummary)## Version 2.0.0 of `modelsummary`, to be released soon, will introduce a
## breaking change: The default table-drawing package will be `tinytable`
## instead of `kableExtra`. All currently supported table-drawing packages
## will continue to be supported for the foreseeable future, including
## `kableExtra`, `gt`, `huxtable`, `flextable, and `DT`.
##
## You can always call the `config_modelsummary()` function to change the
## default table-drawing package in persistent fashion. To try `tinytable`
## now:
##
## config_modelsummary(factory_default = 'tinytable')
##
## To set the default back to `kableExtra`:
##
## config_modelsummary(factory_default = 'kableExtra')modelsummary(modelrl,
title = "Regresión Logística",
stars = TRUE,
output = "kableExtra")| RP_gana (I) | |
|---|---|
| (Intercept) | -1.789+ |
| (1.041) | |
| QRESIDUOS_NO_DOM | 0.000+ |
| (0.000) | |
| DENUNCIAS_2022 | 0.015* |
| (0.006) | |
| Num.Obs. | 43 |
| AIC | 50.6 |
| BIC | 55.9 |
| Log.Lik. | -22.318 |
| F | 3.674 |
| RMSE | 0.42 |
| + p < 0.1, * p < 0.05, ** p < 0.01, *** p < 0.001 |
#PREGUNTA2
modelo2=formula(PORC_RP~QRESIDUOS_NO_DOM+DENUNCIAS_2022)modelo2## PORC_RP ~ QRESIDUOS_NO_DOM + DENUNCIAS_2022reg2=lm(modelo2,data=data_unida)
summary(reg2)##
## Call:
## lm(formula = modelo2, data = data_unida)
##
## Residuals:
## Min 1Q Median 3Q Max
## -19.274 -6.968 -3.174 4.480 32.712
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.533e+01 3.427e+00 7.390 5.4e-09 ***
## QRESIDUOS_NO_DOM -1.124e-04 9.947e-05 -1.130 0.2650
## DENUNCIAS_2022 2.861e-02 1.188e-02 2.409 0.0207 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 12.01 on 40 degrees of freedom
## Multiple R-squared: 0.139, Adjusted R-squared: 0.09595
## F-statistic: 3.229 on 2 and 40 DF, p-value: 0.05013library(modelsummary)
model2=list('Porcentaje Renovacion Popular (Ii)'=reg2)
modelsummary(model2, title = "Regresion: modelo 2",
stars = TRUE,
output = "kableExtra")| Porcentaje Renovacion Popular (Ii) | |
|---|---|
| (Intercept) | 25.327*** |
| (3.427) | |
| QRESIDUOS_NO_DOM | 0.000 |
| (0.000) | |
| DENUNCIAS_2022 | 0.029* |
| (0.012) | |
| Num.Obs. | 43 |
| R2 | 0.139 |
| R2 Adj. | 0.096 |
| AIC | 340.7 |
| BIC | 347.8 |
| Log.Lik. | -166.361 |
| F | 3.229 |
| RMSE | 11.59 |
| + p < 0.1, * p < 0.05, ** p < 0.01, *** p < 0.001 |
library(lmtest)## Loading required package: zoo##
## Attaching package: 'zoo'## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numericlibrary(kableExtra)##
## Attaching package: 'kableExtra'## The following object is masked from 'package:dplyr':
##
## group_rowsresBP=bptest(reg2)
data.frame(list('BP'=resBP$statistic,
'df'=resBP$parameter,
"p-value"=resBP$p.value))%>%
kable(caption = resBP$method)%>%kable_styling(full_width = F)| BP | df | p.value | |
|---|---|---|---|
| BP | 1.217374 | 2 | 0.5440648 |
library(DescTools)##
## Attaching package: 'DescTools'## The following objects are masked from 'package:modelsummary':
##
## Format, Mean, Median, N, SD, VarVIF(reg2) %>%kable(col.names = "VIF",caption ="Evaluando Multicolinealidad usando VIF (Variance Inflation Factors)" )%>%kable_styling(full_width = F)| VIF | |
|---|---|
| QRESIDUOS_NO_DOM | 1.018987 |
| DENUNCIAS_2022 | 1.018987 |