df<-read.csv("mario.csv", h = T)
head(df)
str(df)
df$data_coleta<-as.Date(df$data_coleta,"%m/%d/%Y")
str(df)
df <-df %>% 
  rename("od" = "oxigenio_dissolvido", "N_nitrato" = "nitrogenio_nitrato", "data" = "data_coleta")
str(df)

summary(df)


g_od<-ggplot(df, aes(od)) + 
  geom_histogram(color = "black",fill= "gold",alpha=0.5, bins = 20) +
  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, 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, 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$col = ifelse(df$od < 5,'fora', 'dentro')

df$col




od_nitrato<-ggplot(df, 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

install.packages("tidyquant")
library(tidyquant)

od_time<-ggplot() + 
  #geom_line(df,mapping = aes(data,od), color = "red", size = 1.0) + 
  #geom_line(df, mapping = aes(data, dbo), color = "blue", size = 1.0)+
  geom_point(df, mapping = aes(data, od), color = "red", fill = "red")+
  #geom_point(df, mapping = aes(data, dbo), color = "blue", fill = "blue")+
  #geom_line(df, mapping = aes(data,dbo), color = "blue", size = 1.0) +
  #geom_smooth(df,mapping = aes(data,od), color = "blue", size = 1.0) +
  geom_ma(df, mapping  = aes(data, od), ma_fun = SMA, n = 5, color = "blue", linetype = "solid")+
  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(0,9.5,1), limits = c(0,9.5)) +
  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=6, face="bold", color = "black", 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))
od_time
ggsave("temporal_od.jpeg", units="cm", width=16, height=18, dpi=600)

dbo_time<-ggplot() + 
  #geom_line(df,mapping = aes(data,od), color = "red", size = 1.0) + 
  geom_line(df, mapping = aes(data, dbo), color = "blue", size = 1.0)+
  #geom_point(df, mapping = aes(data, od), color = "red", fill = "red")+
  geom_point(df, mapping = aes(data, dbo), color = "blue", fill = "blue")+
  #geom_line(df, 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("DBO (mg/L)") +
  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=6, face="bold", color = "black", 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))
dbo_time

cond_time<-ggplot() + 
  #geom_line(df,mapping = aes(data,condutividade), color = "red", size = 1.0) + 
  geom_point(df, mapping = aes(data, condutividade), color = "red", fill = "red")+
  #geom_smooth(df,mapping = aes(data,condutividade), color = "blue", size = 1.0) +
  geom_ma(df, mapping  = aes(data, condutividade), ma_fun = SMA, n = 5, color = "blue", linetype = "solid")+
  #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("condutividade (mS/L)") +
  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=6, face="bold", color = "black", 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))
cond_time
ggsave("temporal_od.jpeg", units="cm", width=16, height=18, dpi=600)

turbidez_time<-ggplot() + 
  #geom_line(df,mapping = aes(data,turbidez), color = "red", size = 1.0) + 
  geom_point(df, mapping = aes(data, turbidez), color = "red", fill = "red")+
  #geom_smooth(df,mapping = aes(data,turbidez), color = "blue", size = 1.0) +
  geom_ma(df, mapping  = aes(data, turbidez), ma_fun = SMA, n = 5, color = "blue", linetype = "solid")+
  #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("condutividade (mS/L)") +
  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=6, face="bold", color = "black", 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))
turbidez_time
ggsave("temporal_od.jpeg", units="cm", width=16, height=18, dpi=600)


ggplot() + geom_point(df, mapping = aes(turbidez, condutividade))


df_dbo<-filter(df, dbo<15)

df %>%
  gather(-data, -al_dissolvido, -al_total, -alcalinidade_total, -ba_total, -cd_total, -cod, -col,-dureza,-hg_total, -zn_total, -sulfato_total, -cr_total, -cu_total, -cu_dissolvido, -dqo, -fe_dissolvido, -fe_total, -feofitina_a,
         -fluoreto_total, -mg_total, -mn_total, -ni_total, -pb_total, -clorofila_a,-coliformes_termotolerantes, -cot, -escherichia_coli, -n_total, -nitrogenio_nitrito,
         -temperatura_ar, -subst_tensoat_reagem_com_azul_metileno, -solido_dissolvido_total, -solido_total, key = "var", value = "value") %>% 
  ggplot(aes(x = data, y = value )) +
  geom_point() +
  geom_smooth(method=lm) +
  facet_wrap(~ var, scales = "free") +
  theme_bw()

df_dbo %>%
  gather(-data, -al_dissolvido, -al_total, -alcalinidade_total, -ba_total, -cd_total, -cod, -col,-dureza,-hg_total, -zn_total, -sulfato_total, -cr_total, -cu_total, -cu_dissolvido, -dqo, -fe_dissolvido, -fe_total, -feofitina_a,
         -fluoreto_total, -mg_total, -mn_total, -ni_total, -pb_total, -clorofila_a,-coliformes_termotolerantes, -cot, -escherichia_coli, -n_total, -nitrogenio_nitrito,
         -temperatura_ar, -subst_tensoat_reagem_com_azul_metileno, -solido_dissolvido_total, -solido_total, key = "var", value = "value") %>% 
  ggplot(aes(x = data, y = value )) +
  geom_point() +
  geom_smooth(method=lm) +
  facet_wrap(~ var, scales = "free") +
  theme_bw()

m<-lm(nitrogenio_amoniacal~od,df)
summary(m)

df_select<-select(df, ca_total, cloreto_total, condutividade, dbo, N_nitrato, fosforo_total, k, nitrogenio_amoniacal, od, sodio, turbidez)
head(df_select)
install.packages("ggcorrplot")
library(ggcorrplot)
corr <- round(cor(df_select), 1)
corr
ggcorrplot(corr, lab = TRUE)
ggcorrplot(corr, method = "circle", lab = TRUE)

install.packages("wql")
library(wql)
help(wql)
sfb <- wqData(df, site.order = TRUE,
              type = "wide", time.format = "%Y/%m/%d")
head(sfb)
plot(df, vars = c('od', 'dbo'))

library(dplyr)

df10<-df %>%
  as_tibble %>%
  mutate(month = lubridate::month(data)) %>%
  group_by(month)
#summarise(od_month = mean(od), cond_month = mean(condutividade), turbidez_month = mean(turbidez))


df10

plot(df10$month, df10$od)

df10$month<-as.factor(df10$month)

ggplot(mapping = aes(month,condutividade), df10) + geom_boxplot() + geom_jitter()