library(tidyr)
library(tidyverse)
library(dplyr)
library(readxl)
library(forecast)
library(kableExtra)
library(mFilter)

# Carga de los datos
Data_PIB <- read_excel("C:/Users/MovilDell/Downloads/datos_PIB_trim_CA (1).xlsx", skip = 5)
colnames(Data_PIB) <- c("Fecha", "Costa_Rica", "El_Salvador", "Guatemala", 
                        "Honduras", "Nicaragua", "RD", "Panama")
Data_PIB$Costa_Rica <- as.numeric(Data_PIB$Costa_Rica)
Data_PIB$El_Salvador<- as.numeric(Data_PIB$El_Salvador)
Data_PIB$Guatemala<- as.numeric(Data_PIB$Guatemala)
  Data_PIB$Honduras<- as.numeric(Data_PIB$Honduras)
  Data_PIB$Nicaragua<- as.numeric(Data_PIB$Nicaragua)
  Data_PIB$RD<- as.numeric(Data_PIB$RD)
  Data_PIB$Panama<- as.numeric(Data_PIB$Panama)
  
#  tabla estilizada e interactiva
Data_PIB %>% 
  kable(caption = "PIB por trimestres de los países de Centroamérica", align = "c", digits = 2) %>%  
  kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"), 
                full_width = FALSE, 
                position = "center") %>% 
  scroll_box(width = "100%", height = "400px") %>% 
  footnote(general = "Elaboración propia con datos de Secretaría Ejecutiva del Consejo Monetario Centroamericano    en Millones de Moneda Nacional",
           general_title = "Fuente:", 
           footnote_as_chunk = TRUE)

Data_PIB <- Data_PIB %>% filter(!is.na(Costa_Rica))
Costa_Rica_ts <- ts(Data_PIB$Costa_Rica, start = c(1991,1), frequency = 4)


hp_cr <- hpfilter(Costa_Rica_ts, freq = 1600)

# Extrae la tendencia y el componente cíclico
trend <- hp_cr$trend
cycle <- hp_cr$cycle

# grafico 

plot(Costa_Rica_ts, type = "l", main = "Filtro de Hodrick-Prescott Costa Rica  (trimestre I 1991 - trimestre II 2024)", ylab = "PIB en Millones", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2 )
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)

plot(hp_cr,ask = FALSE)

Data_PIB <- Data_PIB %>% filter(!is.na(El_Salvador))
El_Salvador_ts <- ts(Data_PIB$El_Salvador, start = c(1990,1), frequency = 4)


hp_sv <- hpfilter(El_Salvador_ts, freq = 1600)

# Extrae la tendencia y el componente cíclico
trend <- hp_sv$trend
cycle <- hp_sv$cycle

# gráfico 

plot(El_Salvador_ts, type = "l", main = "Filtro de Hodrick-Prescott El Salvador, (trimestre I 1990 - trimestre II 2024)", ylab = "PIB en Millones", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2 )
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)

plot(hp_sv,ask = FALSE)

Data_PIB <- Data_PIB %>% filter(!is.na(Guatemala))
Guatemala_ts <- ts(Data_PIB$Guatemala, start = c(2001,1), frequency = 4)


hp_gt <- hpfilter(Guatemala_ts, freq = 1600)

# Extrae la tendencia y el componente cíclico
trend <- hp_gt$trend
cycle <- hp_gt$cycle

# grafico 

plot(Guatemala_ts, type = "l", main = "Filtro de Hodrick-Prescott Guatemala, (trimestre I 2001 - trimestre II 2024)", ylab = "PIB en Millones", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2 )
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)

plot(hp_gt,ask = FALSE)

Data_PIB <- Data_PIB %>% filter(!is.na(Honduras))
Honduras_ts <- ts(Data_PIB$Honduras, start = c(1999,1), frequency = 4)


hp_hn <- hpfilter(Honduras_ts, freq = 1600)

# Extrae la tendencia y el componente cíclico
trend <- hp_hn$trend
cycle <- hp_hn$cycle

# grafico 

plot(Honduras_ts, type = "l", main = "Filtro de Hodrick-Prescott Honduras, (trimestre I 1999 - trimestre II 2024)", ylab = "PIB en Millones", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2 )
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)

plot(hp_hn,ask = FALSE)

Data_PIB <- Data_PIB %>% filter(!is.na(Nicaragua))
Nicaragua_ts <- ts(Data_PIB$Nicaragua, start = c(2006,1), frequency = 4)


hp_nic <- hpfilter(Nicaragua_ts, freq = 1600)

# Extrae la tendencia y el componente cíclico
trend <- hp_nic$trend
cycle <- hp_nic$cycle

# grafico 

plot(Nicaragua_ts, type = "l", main = "Filtro de Hodrick-Prescott Nicaragua, (trimestre I 2006 - trimestre II 2024)", ylab = "PIB en Millones", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2 )
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)

plot(hp_nic,ask = FALSE)

Data_PIB <- Data_PIB %>% filter(!is.na(RD))
RD_ts <- ts(Data_PIB$RD, start = c(1991,1), frequency = 4)


hp_RD <- hpfilter(RD_ts, freq = 1600)

# Extrae la tendencia y el componente cíclico
trend <- hp_RD$trend
cycle <- hp_RD$cycle

# grafico 

plot(RD_ts, type = "l", main = "Filtro de Hodrick-Prescott República Dominicana, (T I 1991 - T II 2024)", ylab = "PIB", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2 )
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)

plot(hp_RD,ask = FALSE)

Data_PIB <- Data_PIB %>% filter(!is.na(Panama))
Panama_ts <- ts(Data_PIB$Panama, start = c(1996,1), frequency = 4)


hp_Panama <- hpfilter(Panama_ts, freq = 1600)

# Extrae la tendencia y el componente cíclico
trend <- hp_Panama$trend
cycle <- hp_Panama$cycle

# grafico 

plot(Panama_ts, type = "l", main = "Filtro de Hodrick-Prescott Panama, (trimestre I 1996 - trimestre III 2022)", ylab = "PIB en Millones", xlab = "Tiempo")
lines(trend, col = "red", lwd = 2 )
legend("topleft", legend = c("PIB Original", "Tendencia (Filtro HP)"), col = c("black", "red"), lty = 1, lwd = 2)

plot(hp_Panama,ask = FALSE)