---
title: "04_Exploratory_Data_Analysis"
author: "Camille"
date: "4/11/2023"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

Generates Figure 2

```{r Load data}
library(ggplot2)
library(ggpubr)

master_full_dat <- read.csv("DataKeep/MasterSheet_full.csv")
master_full_dat <- master_full_dat[master_full_dat$Year>1999,]
master_full_dat$PercentDeforest <- master_full_dat$PercentDeforest *100
master_full_dat$Tourism <- master_full_dat$Tourism /1000
master_full_dat$Area <- "Inside PA"
master_full <- master_full_dat %>% dplyr::select(Name, Year, PercentDeforest, Area)

master_commune <- read.csv("DataKeep/MasterSheet_commune.csv")
master_commune$Tourism <- master_commune$Tourism/1000
master_commune$PercentDeforest <- master_commune$PercentDeforest*100
master_commune <- master_commune %>% filter(Year >= 2001)
master_commune$Area <- "Inside PA Commune"
master_commune <- master_commune %>% dplyr::select(Name, Year, PercentDeforest, Area)

master_buffer <- read.csv("DataKeep/Forest_buffer_3km_Deforestation.csv")
master_buffer$Area <- "3km Buffer"
master_buffer <- master_buffer%>% dplyr::select(Name, Year, PercentDeforest, Area)
master_buffer_commune <- read.csv("DataKeep/Forest_Buffer_Commune_Deforestation.csv")
master_buffer_commune$Area <- "3km Buffer Commune"
master_buffer_commune <- master_buffer_commune%>% dplyr::select(Name, Year, PercentDeforest, Area)

master_total <- rbind(master_full, master_commune, master_buffer, master_buffer_commune)
master_total <- master_total %>% filter(Year>2000)

```

```{r Summary Plot of Tourism and Deforestation}
#Set up data for plotting
master_full_dat_summary <- master_total %>% group_by(Year, Area) %>%drop_na(PercentDeforest)%>% summarise(PercentDeforest= mean(PercentDeforest))
master_full_dat_summary2 <- master_full_dat %>% group_by(Year, Area) %>%drop_na(Tourism)%>% summarise(Tourism= mean(Tourism))
master_full_dat_summary3 <- full_join(master_full_dat_summary2, master_full_dat_summary, by=c("Year", "Area"))
master_full_dat_summary3 <- master_full_dat_summary3 %>% filter(Year>2000)
scale = 5
master_full_dat_summary3$Area[master_full_dat_summary3$Area=="Inside PA Commune"] <- "Entrance, Inside PA"
master_full_dat_summary3$Area[master_full_dat_summary3$Area=="3km Buffer Commune"] <- "Entrance, 3km Buffer PA"
master_full_dat_summary3$Area[master_full_dat_summary3$Area=="Inside PA"] <- "Total, Inside PA"
master_full_dat_summary3$Area[master_full_dat_summary3$Area=="3km Buffer"] <- "Total, 3km Buffer PA"
master_full_dat_summary3$Location <- factor(master_full_dat_summary3$Area, levels = c("Total, Inside PA", "Entrance, Inside PA", "Total, 3km Buffer PA", "Entrance, 3km Buffer PA"))

#Forest loss plots
forest_loss_plot <- ggplot(data=master_full_dat_summary3, aes(x=Year, y=PercentDeforest))+
    theme_classic()+
      geom_line(aes(color=Location, linetype= Location))+
  geom_point(aes(color=Location, shape=Location), size=2)+
  labs(x="Year", y="Mean Percent Forest Loss")+
  scale_color_manual(values = c("magenta4", "plum", "magenta4", "plum"))+
  scale_shape_manual(values = c(19,17,19,17))+
  scale_linetype_manual(values = c( "solid", "solid", "dashed", "dashed"))+
  theme(legend.position = "top")

#Tourism plot
tourism_plot <- ggplot(data=master_full_dat_summary3[!is.na(master_full_dat_summary3$Tourism),], aes(x=Year, y=Tourism*40))+
    theme_classic()+
    geom_line()+
  geom_point()+
  labs(x="Year", y="Total Tourism (1,000s of Visits)")

#Combine
summary_plot <- ggarrange(forest_loss_plot, tourism_plot, labels=c("a", "b"), ncol=1, nrow=2)

```