library(ggplot2)
library(ggQC)
library(qcc)

####### Graficos de controle por variáveis
dados <- read.csv("https://raw.githubusercontent.com/cibelerusso/Gestao-da-qualidade/main/Dados/Cozimento.csv", header=TRUE, sep=';', dec=',')

X <- c(cbind(dados$x1, dados$x2, dados$x3, dados$x4, dados$x5))
n_amostra <- rep(dados$Amostra, 5)
amostra <- c(rep(1,45), rep(2,45), rep(3,45), rep(4,45), rep(5,45))

df <- data.frame(n_amostra=n_amostra, amostra = amostra, X = X)
View(df)

# Usando o qcc

# Todas as observações
qcc(dados[,2:6], type='xbar')
qcc(dados[,2:6], type='R')


# Pacote ggQC: https://cran.r-project.org/web/packages/ggQC/ggQC.pdf
### Gráfico de Xbarra e R

XbarraeR <- ggplot(df, aes(x = n_amostra, y = X)) +
  stat_summary(fun.y = "mean", color = "blue", geom = c("point")) +
  stat_summary(fun.y = "mean", color = "blue", geom = c("line")) +
  stat_QC(method = "xBar.rBar") + stat_QC(method = "rBar") 
XbarraeR


# Uses the same data as previous example. 

QC_Violations <- 
  ggplot(df, aes(x = n_amostra, y = X)) + #init ggplot
  stat_qc_violations(method = "xBar.rBar" 
                     #show.facets = 4 #if you just want facet 4
  )
QC_Violations


# Uses the same data as the first example
CapabilityAnaylsis <- 
  ggplot(df, aes(x = X)) + #init ggplot
  geom_histogram(binwidth = .02, color="purple") + #make the histogram
  stat_QC_Capability(
    LSL=1, USL=2,                    #Specify LSL and USL
    show.cap.summary = c("Cp", "Cpk"), #selected summary
    digits = 2,                        #report two digits
    method="XmR") +                    #Use the XmR method
  scale_x_continuous(expand =  expansion(mult = c(0.15,.65))) #pad the X-axis 

#plot the graph
CapabilityAnaylsis



##
## Grouped-data
##

# Gráfico de controle para a soma cumulativa: https://www.rdocumentation.org/packages/qcc/versions/2.6/topics/cusum

# install.packages('qcc')

library(qcc)


# CUSUM tabular para os dados do cozimento

df2 <- qcc.groups(X, n_amostra)
cusum(df2, decision.interval = 3, se.shift = 1)


# Máscara V
# https://rdrr.io/cran/vMask/man/vMask-package.html

# https://www.itl.nist.gov/div898/handbook/pmc/section3/pmc323.htm

# https://www.pure.ed.ac.uk/ws/portalfiles/portal/11028324/Cusum_Charts.pdf


# Pacote vMask - Instalar manualmente utilizando https://cran.r-project.org/src/contrib/Archive/vMask/
# install.packages("vMask")
# install.packages("~/Downloads/vMask_1.0.tar.gz", repos = NULL, type = "source")

library(vMask)

### Example 1:  V-Mask CUSUM chart with vectored data based on the real data from:
#   https://www.itl.nist.gov/div898/handbook/pmc/section3/pmc323.htm

# In this applied example We are going to quickly detect a shift in mean as large as one 
# sigma by CUSUM chart.

Data = dados$Xbarra

n = 5
mean(Data)
sd(Data)
sd(Data)/sqrt(n)

vMask.method3(data=Data, mu0=1.5, k=1, alpha=.0027, beta=.01, s="PressEnter" )



### Example 2:  V-Mask CUSUM chart based on a data matrix.
# A wood products company manufactures charcoal briquettes for barbecues. It packages these 
# briquettes in bags of various sizes, the largest of which is supposed to contain 40 lbs.
# The weights of bags from 16 different samples, each of size n=4 are given in below. 


n = 5
m = 45
mu0 = 1.5
sigma = .14

Data = dados[,2:6] 

M = Data
M

# X.bar Control Chart: 
( LCL = mu0 - 3*sigma/sqrt(n) )
( UCL = mu0 + 3*sigma/sqrt(n) )
plot(1:45, rowMeans(M), col=3, pch=16, ylim=c(LCL-.2,UCL+.2))
abline(h=c(mu0, LCL, UCL), col=2, lty=c(3,1,1))

# Three different strategies for putting v-mask on CUSUM Control Chart:
M <- cumsum(apply(Data,1,mean)-mu0)

vMask.method2(M, mu0=0, d=0.5, h=0.4, sl="PressEnter" )
vMask.method6( data=M, mu0=0, mu1=0.3, sigma=.5, h=1, w=2, sl="PressEnter" )
vMask.method5( data=M, mu0=0, mu1=0.3, alpha=.1, beta=.01, sl="PressEnter")