#abrir sua pasta, e colocar como 'working directory'

#vamos abrir o conjunto de dados MeanAmp

meanAmp <- read.csv("MeanAmp_300_500_ROI.csv", stringsAsFactors = TRUE, header=TRUE, sep=";", dec=",")
str(meanAmp)
#vamos consertar a interpretação do primeiro cabeçalho
names(meanAmp)[names(meanAmp) == "ï..File"] <- "suj" 

#vamos abrir os dados, e vemos que eles não estão organizados da forma mais prático
#para a análise que vamos fazer. vamos transformar a organização wide para long
#install.packages("tidyr")
library(tidyr)
library(ggplot2)
library("plotrix")
library(dplyr)
library("writexl")

# The arguments to gather():
# - data: Data object
# - key: Name of new key column (made from names of data columns)
# - value: Name of new value column
# - ...: Names of source columns that contain values
# - factor_key: Treat the new key column as a factor (instead of character vector)
meanAmp_long <- gather(meanAmp,Data, meanamp, mid_FC_FC:rig_PO_FIC, factor_key=TRUE)

library("writexl")
write_xlsx(meanAmp_long,"meanAmp_long.xlsx")

meanAmp_long <- read.csv("MeanAmp_long.csv", stringsAsFactors = TRUE, header=TRUE, sep=";", dec=",")
str(meanAmp_long)

meanAmp_long$meanamp <- as.numeric(as.character(meanAmp_long$meanamp))
str(meanAmp_long)

names(meanAmp_long)[names(meanAmp_long) == "ï..suj"] <- "suj" 

meanAmp_long <- meanAmp_long %>%
  filter(suj!="suj19_sentences")%>%
  droplevels()

#install.packages("plotrix")
library("plotrix")  
library(tidyr)
library(dplyr)

 
meanAmp_stats <- meanAmp_long %>%
  group_by(cond, ROI)%>%
  summarise(media=mean(meanamp),
            sdev=sd(meanamp),
            quantidade = n(),
            se=std.error(meanamp),
            CImin=(media -(1.96*sdev/sqrt(quantidade))),
            CImax=(media +(1.96*sdev/sqrt(quantidade))))

ggplot(meanAmp_stats , aes(ROI,media,fill=cond)) + 
  geom_bar(stat="identity", color="black", 
           position=position_dodge()) +
  geom_errorbar(aes(ymin=CImin, ymax=CImax), width=.2,
                position=position_dodge(.9)) +
  scale_y_reverse()

#install.packages("rstatix")
#https://www.datanovia.com/en/lessons/mauchlys-test-of-sphericity-in-r/

anova_meanAmp <- aov(meanamp~ROI*lat*cond,data=meanAmp_long)
anova_meanAmp
summary(anova_meanAmp)

library(lmerTest)
library(lme4)

mod.INCONGR <- lmer(meanamp~ROI*lat*cond + (1|suj), data=meanAmp_long, REML = FALSE)
mod.INCONGR2 <- lmer(meanamp~cond + (1|suj), data=meanAmp_long, REML = FALSE)
mod.INCONGR3 <- lmer(meanamp~cond*ROI + (1|suj), data=meanAmp_long, REML = FALSE)
mod.INCONGR_nulo <- lmer(meanamp~1 + (1|suj), data=meanAmp_long, REML = FALSE)
anova(mod.INCONGR_nulo, mod.INCONGR)

summary(mod.INCONGR)
summary(mod.INCONGR2)
summary(mod.INCONGR3)

##########

meanAmp <- read.csv("MeanAmp_300_500_ROI.csv", stringsAsFactors = TRUE, header=TRUE, sep=";", dec=",")
str(meanAmp)
#vamos consertar a interpretação do primeiro cabeçalho
names(meanAmp)[names(meanAmp) == "ï..File"] <- "suj" 

#vamos abrir os dados, e vemos que eles não estão organizados da forma mais prático
#para a análise que vamos fazer. vamos transformar a organização wide para long
#install.packages("tidyr")
library(tidyr)
library(ggplot2)
library("plotrix")
library(dplyr)
library("writexl")

# The arguments to gather():
# - data: Data object
# - key: Name of new key column (made from names of data columns)
# - value: Name of new value column
# - ...: Names of source columns that contain values
# - factor_key: Treat the new key column as a factor (instead of character vector)
meanAmp_long <- gather(meanAmp,Data, meanamp, mid_FC_FC:rig_PO_FIC, factor_key=TRUE)

library("writexl")
write_xlsx(meanAmp_long,"meanAmp_long.xlsx")

meanAmp_long <- read.csv("MeanAmp_long.csv", stringsAsFactors = TRUE, header=TRUE, sep=";", dec=",")
str(meanAmp_long)

meanAmp_long$meanamp <- as.numeric(as.character(meanAmp_long$meanamp))
str(meanAmp_long)

names(meanAmp_long)[names(meanAmp_long) == "ï..suj"] <- "suj" 

meanAmp_long <- meanAmp_long %>%
  filter(suj!="suj19_sentences")%>%
  droplevels()

#install.packages("plotrix")
library("plotrix")  
library(tidyr)
library(dplyr)


meanAmp_stats <- meanAmp_long %>%
  group_by(cond, ROI)%>%
  summarise(media=mean(meanamp),
            sdev=sd(meanamp),
            quantidade = n(),
            se=std.error(meanamp),
            CImin=(media -(1.96*sdev/sqrt(quantidade))),
            CImax=(media +(1.96*sdev/sqrt(quantidade))))

ggplot(meanAmp_stats , aes(ROI,media,fill=cond)) + 
  geom_bar(stat="identity", color="black", 
           position=position_dodge()) +
  geom_errorbar(aes(ymin=CImin, ymax=CImax), width=.2,
                position=position_dodge(.9)) +
  scale_y_reverse()

#install.packages("rstatix")
#https://www.datanovia.com/en/lessons/mauchlys-test-of-sphericity-in-r/

anova_meanAmp <- aov(meanamp~ROI*lat*cond,data=meanAmp_long)
anova_meanAmp
summary(anova_meanAmp)