df<-read.csv("nome_do_arquivo.csv", h = T)
head(df)
str(df)
df$Parametro
df$Valor<-as.numeric(df$Valor)
df$data<-as.Date(df$data,"%d/%m/%Y")
str(df)

library(dplyr)

df %>% count(Parametro, sort = TRUE)
df_group<-group_by(df, Parametro)
summarise(df_group, 
          mean = mean(Valor,na.rm=T),
          sd = sd(Valor,na.rm=T))



df<-dplyr::select(df, "data", "Parametro", "Valor")
head(df)
df_select<-dplyr::filter(df, Parametro %in%
                           c("Cl", "N_amonio", "N_total", "N_nitrato", "P_total", "T_agua", "T_ar", "tubidez", "dbo",  "od", "pH", "st", "tensoativo"))
head(df_select)
df_select %>% count(Parametro, sort = TRUE)

install.packages('tidyverse')
library(tidyverse)

df_wider<-pivot_wider(df_select,names_from = Parametro, 
                 values_from = Valor, 
                 values_fn = list) 
df_wider<-df_wider%>%unnest(cols = everything(),keep_empty = T)

head(df_wider)
df_wider<-as.data.frame(df_wider)
write.csv(df_wider, "cetesb_wider.csv")
df_wider<-read.csv("cetesb_wider.csv", header =T)

df_wider$od<-as.numeric(df_wider$od)

library(ggplot2)
ggplot(df_wider, aes(od)) + geom_histogram()
str(df_wider)
g_od<-ggplot(df_wider, aes(od)) + 
  geom_histogram(color = "black",fill= "blue",alpha=0.5, bins = 8, binwidth = 1) +
  scale_x_continuous(name = "OD (mg/L)") +
  scale_y_continuous(name = "Contagem") +
  theme(axis.line.x = element_line(size = 0.5, colour = "black"),
      axis.line.y = element_line(size = 0.5, colour = "black"),
      axis.line = element_line(size=1, colour = "black"),
      panel.grid.major = element_blank(),
      panel.grid.minor = element_blank(),
      panel.border = element_blank(),
      panel.background = element_blank(),
      axis.text.x=element_text(size=16, face="bold"),
      axis.text.y=element_text(size=14, face="bold"),
      axis.title.y=element_text(size=16, face = "bold"),
      axis.title.x = element_text (size = 16, face = "bold"), 
      legend.title = element_blank(),
      legend.text = element_text(size=11))
g_od

g_od_cum<-ggplot(df_wider, aes(od)) + 
  #geom_histogram(color = "black",fill= "gold",alpha=0.5, bins = 8, binwidth = 1) +
  stat_ecdf(geom = "step", color="purple", size = 1.5) +
  scale_x_continuous(name = "OD (mg/L)", breaks=seq(0,8,1), limits=c(0,8))+
  scale_y_continuous(name = "Proporção") +
  theme(axis.line.x = element_line(size = 0.5, colour = "black"),
        axis.line.y = element_line(size = 0.5, colour = "black"),
        axis.line = element_line(size=1, colour = "black"),
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        panel.border = element_blank(),
        panel.background = element_blank(),
        axis.text.x=element_text(size=16, face="bold"),
        axis.text.y=element_text(size=14, face="bold"),
        axis.title.y=element_text(size=16, face = "bold"),
        axis.title.x = element_text (size = 16, face = "bold"), 
        legend.title = element_blank(),
        legend.text = element_text(size=11))
g_od_cum

g_dbo_cum<-ggplot(df_wider, aes(dbo)) + 
  #geom_histogram(color = "black",fill= "gold",alpha=0.5, bins = 8, binwidth = 1) +
  stat_ecdf(geom = "step", color="purple", size = 1.5) +
  scale_x_continuous(name = "DBO (mg/L)", breaks=seq(0,8,1), limits=c(0,8))+
  scale_y_continuous(name = "Proporção") +
  theme(axis.line.x = element_line(size = 0.5, colour = "black"),
        axis.line.y = element_line(size = 0.5, colour = "black"),
        axis.line = element_line(size=1, colour = "black"),
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        panel.border = element_blank(),
        panel.background = element_blank(),
        axis.text.x=element_text(size=16, face="bold"),
        axis.text.y=element_text(size=14, face="bold"),
        axis.title.y=element_text(size=16, face = "bold"),
        axis.title.x = element_text (size = 16, face = "bold"), 
        legend.title = element_blank(),
        legend.text = element_text(size=11))
g_dbo_cum

df_wider$col = ifelse(df_wider$od < 5,'fora', 'dentro')

df_wider$col

df_wider$N_nitrato <- as.numeric(df_wider$N_nitrato)
od_nitrato<-ggplot(df_wider, aes(od,N_nitrato)) + 
  geom_point(aes(color = col, fill  = col), size = 3, alpha = 0.4) + 
  scale_x_continuous("OD (mg/L") +
  scale_y_continuous("N-nitrato (mg/L)")+
  scale_color_manual(values = c("green4", "red")) +
  scale_fill_manual(values = c("green4", "red")) +
  theme(axis.line.x = element_line(size = 0.5, colour = "black"),
        axis.line.y = element_line(size = 0.5, colour = "black"),
        axis.line = element_line(size=1, colour = "black"),
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        panel.border = element_blank(),
        panel.background = element_blank(),
        axis.text.x=element_text(size=16, face="bold"),
        axis.text.y=element_text(size=14, face="bold"),
        axis.title.y=element_text(size=16, face = "bold"),
        axis.title.x = element_text (size = 16, face = "bold"), 
        legend.title = element_blank(),
        legend.text = element_text(size=11))
od_nitrato

df_wider$data <- as.Date(df_wider$data,"%d/%m/%y" )

time<-ggplot() + 
  geom_line(df_wider,mapping = aes(data,od), color = "red", size = 1.0) + 
  #geom_line(df_wider, mapping = aes(data,dbo), color = "blue", size = 1.0) +
  geom_hline(yintercept=5, linetype = "dashed") +
  scale_x_date(date_breaks = "4 month", date_minor_breaks = "1 month", date_labels = "%b/%Y") + 
  scale_y_continuous("OD (mg/L)", breaks = seq(0,8,1), limits = c(0,8)) +
  theme(axis.line.x = element_line(size = 0.5, colour = "black"),
        axis.line.y = element_line(size = 0.5, colour = "black"),
        axis.line = element_line(size=1, colour = "black"),
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        panel.border = element_blank(),
        panel.background = element_blank(),
        axis.text.x=element_text(size=11, face="bold", angle = 45, hjust=1),
        axis.text.y=element_text(size=12, face="bold"),
        axis.title.y=element_text(size=14, face = "bold"),
        axis.title.x = element_text (size = 16, face = "bold"), 
        legend.title = element_blank(),
        legend.text = element_text(size=11))
time
ggsave("temporal_od.jpeg", units="cm", width=16, height=18, dpi=600)