Exercicio 12

Abas

Questão 1

MRT_1F <-c(517.1468515630205, 85.13094142168089, 30.333207896694553, 12.694776264558937, 3.3041601673945418, 1.1823111717498882, 1.1892293502386786)

MRT_3F <-c(156.68929936163462, 11.540837783562276, 0.4512835621696538, 0.4509797929766453, 0.4502068233039181, 0.4496185276300172, 0.4543157082191288)

MRT_5F <-c(83.90319666471157, 0.3068151086494968, 0.30522314133037304, 0.3072588968084928, 0.30655265997285697, 0.3055812715727718, 0.3053297166713006)

MRT_10F <-c(29.55430642951759, 0.19832832665772515, 0.1971923924717474, 0.19796648905716516, 0.19615594370806338, 0.2034569237883263, 0.19617420889447737)

MRT_15F <-c(11.317736530583566, 0.167364215666193, 0.16172168266811013, 0.16701085329580515, 0.1598052657153692, 0.1645934043532696, 0.16216563797118075)

MRT_sem_F <-c(11.93430909937736, 0.6095414637034009, 0.6060645101029295, 0.612167181646899, 0.6146761002685637, 0.6096747087200697, 0.6125810476877268)


clock <- c(0.1, 0.5, 1, 1.5, 2, 2.5, 3)

par(mar = c(2, 2, 1, 1), cex = 0.8)

# Configurando o layout
layout(matrix(c(1, 1,
                2, 3,
                4, 5,
                6, 7), nrow=4, byrow=TRUE),
       heights = c(4, 3, 3, 3),
       widths = c(1, 1))  


# Gráfico 1: Ocupa toda a primeira linha
plot(clock,MRT_1F, type = "o",col="black", pch = 4, xlab="Time between Things requested (seconds)", ylab="Response Time")

legend("topright", legend = c("1 Fog", "3 Fogs", "5 Fogs", "10 Fogs", "15 Fogs", "w/o fog"),
       col = c("black", "yellow", "red", "blue", "purple", "green"), lty = 1, pch = c(4, 11, 1, 2, 5, 4))


lines(clock,MRT_3F,col="yellow",type="o" , pch = 11)
lines(clock,MRT_5F,col="red",type="o", pch = 1)
lines(clock,MRT_10F,col="blue",type="o", pch = 2)
lines(clock,MRT_15F,col="purple",type="o", pch = 5)
lines(clock,MRT_sem_F,col="green",type="o", pch = 4)

barplot(rbind(MRT_sem_F,MRT_1F), beside = TRUE,col = c("#E6E6E6", "#666666"), xlab="Time between Things requested (seconds)", ylab="Response Time",names.arg = clock,  log = "y")

legend("topright", c("w/o fog", "1 Fog"), fill = c("#E6E6E6", "#666666"))

barplot(rbind(MRT_sem_F,MRT_3F), beside = TRUE,col = c("#E6E6E6", "#666666"), xlab="Time between Things requested (seconds)", ylab="Response Time",names.arg = clock, log = "y")

legend("topright", c("w/o fog", "3 Fog"), fill = c("#E6E6E6", "#666666"))

barplot(rbind(MRT_sem_F,MRT_5F), beside = TRUE,col = c("#E6E6E6", "#666666"), xlab="Time between Things requested (seconds)", ylab="Response Time",names.arg = clock, log = "y")

legend("topright", c("w/o fog", "5 Fog"), fill = c("#E6E6E6", "#666666"))

barplot(rbind(MRT_sem_F,MRT_10F), beside = TRUE,col = c("#E6E6E6", "#666666"), xlab="Time between Things requested (seconds)", ylab="Response Time",names.arg = clock, log = "y")

legend("topright", c("w/o fog", "10 Fog"), fill = c("#E6E6E6", "#666666"))

barplot(rbind(MRT_sem_F,MRT_15F), beside = TRUE,col = c("#E6E6E6", "#666666"), xlab="Time between Things requested (seconds)", ylab="Response Time",names.arg = clock, log = "y")

legend("topright", c("w/o fog", "15 Fog"), fill = c("#E6E6E6", "#666666"))

Questão 2

Good = c(53.8,33.9,2.6,0)
VeryG = c(43.6,54.2,60.5,21.4)
Exc = c(2.6,11.9,36.8,78.6)
Names = c("$10-19","$20-29","$30-39","$40-49")
data = rbind(Good,VeryG,Exc)

colnames(data)= Names

par(mar = c(5, 4, 4, 8))
barplot(data, beside = FALSE, main="Meal Quality by Price Category", col=c("black", "gray", "gold"), xlab="Meal Price ($)", ylab="Quality Rating (%)",names.arg = Names)

legend(
  "topright",                             
  legend = c("Good", "Very Good", "Excellent"), 
  fill = c("black", "gray", "gold"),   
  xpd = TRUE,
  inset = c(-0.3, 0)                      
)

Questão 3

maio = subset(airquality,
              Month == 5)

c = ((maio$Temp -32)/1.8)

hist(c,                   
     main = "Distribuição da Temperatura",   
     xlab = "Temperatura(C)",                   
     ylab = "Dias do Mes",                
     col = "#B0C4DE",                    
     border = "black",
     probability = TRUE,
     freq = FALSE
     )                   

lines(density(c), col = "red")

Questão 4

sales <- read.table("https://training-course-material.com/images/8/8f/Sales.txt", header=TRUE)

porcent = round(sales$SALES/ sum(sales$SALES) *100)

rotulos= paste(sales$COUNTRY,"-", porcent, "%", sep=" ")

pie(sales$SALES,labels=rotulos,col=c("#1E90FF", "#00BFFF", "#87CEEB", "#4682B4", "#5F9EA0", "#6495ED"),main="Sales by country")

legend("topright",legend=sales$COUNTRY, fill=c("#1E90FF", "#00BFFF", "#87CEEB", "#4682B4", "#5F9EA0", "#6495ED"), title = "Categorias", xpd = TRUE,
  inset = c(-0.06, 0))

Questão 5

boxplot(count ~ spray,data = InsectSprays, main="Contagem de Insetos por Tipo de Inseticida",xlab="Tipo", ylab="Contagem de insetos", col = "yellow", outline = FALSE )

Questão 6

monitoringCloudData_0.1 <- read.csv("monitoringCloudData_0.1.csv")

monitoringCloudData_0.5 <- read.csv("monitoringCloudData_0.5.csv")

monitoringCloudData_1 <- read.csv("monitoringCloudData_1.csv")

monitoringCloudData_NONE <- read.csv("monitoringCloudData_NONE.csv")

timediff <- function(baseC) {
  
  first <- head(baseC$currentTime, 1)
  
  data_inicial <- as.POSIXct(first, format = "%Y-%m-%d %H:%M:%OS")
  
  baseC$currentTime <- sapply(baseC$currentTime, function(tempo) {
    
    data_referencia <- as.POSIXct(tempo, format = "%Y-%m-%d %H:%M:%OS")
    
    return(as.numeric(difftime(data_referencia, data_inicial, units = "hours")))
  })
  
  return(baseC)
}


mem <- function(memoria) {
  if (grepl("[:xdigit:]*.T", memoria)) {
    tera <- as.numeric(gsub("[:xdigit:]*.T", "", memoria))
    mb <- (tera * 1000000)
    return(paste0(round(mb, 3)))
  } 
  else if(grepl("[:xdigit:]*.GB", memoria)){
    gb <- as.numeric(gsub("[:xdigit:]*.GB", "", memoria))
    mb <- (gb * 1024)
    return(paste0(round(mb, 3)))
  }
  else {
    return(as.numeric(gsub("[:xdigit:]*.MB", "", memoria))) 
  }
}

monitoringCloudData_0.1$usedMemory <- sapply(monitoringCloudData_0.1$usedMemory, mem)
monitoringCloudData_0.1 = timediff(monitoringCloudData_0.1)

monitoringCloudData_0.5$usedMemory <- sapply(monitoringCloudData_0.5$usedMemory, mem)
monitoringCloudData_0.5 = timediff(monitoringCloudData_0.5)

monitoringCloudData_1$usedMemory <- sapply(monitoringCloudData_1$usedMemory, mem)
monitoringCloudData_1 = timediff(monitoringCloudData_1)

monitoringCloudData_NONE$usedMemory <- sapply(monitoringCloudData_NONE$usedMemory, mem)
monitoringCloudData_NONE = timediff(monitoringCloudData_NONE)

layout(matrix(c(1, 2,
                3, 4), nrow=2, byrow=TRUE),
       heights = c(2, 2),  
       widths = c(2, 2))  



plot(monitoringCloudData_NONE$currentTime,monitoringCloudData_NONE$usedMemory,main = "Memory Analysis (Workload of NONE)", type = "l",col="black", xlab="Time (hour)", ylab="Used Memory (Mb)")

plot(monitoringCloudData_0.1$currentTime,monitoringCloudData_0.1$usedMemory,main = "Memory Analysis (Workload of 0.1)", type = "l",col="black", xlab="Time (hour)", ylab="Used Memory (Mb)")

plot(monitoringCloudData_0.5$currentTime,monitoringCloudData_0.5$usedMemory,main = "Memory Analysis (Workload of 0.5)", type = "l",col="black", xlab="Time (hour)", ylab="Used Memory (Mb)")

plot(monitoringCloudData_1$currentTime,monitoringCloudData_1$usedMemory,main = "Memory Analysis (Workload of 1)", type = "l",col="black", xlab="Time (hour)", ylab="Used Memory (Mb)")

Questão 7

netflixData <- read.csv("https://www.dropbox.com/scl/fi/vjlgt50835d6snk03add2/netflix_titles.csv?rlkey=rzrveurxlom9cjp51nbv4w1gw&e=1&dl=1")

netflix = netflixData

netflix$country <- sapply(strsplit(as.character(netflix$country), ","), `[`, 1)

contagem <- table(netflix$country)

df_contagem <- as.data.frame(contagem)

colnames(df_contagem) <- c("Paises", "Frequencia")

ordem = order(df_contagem$Frequencia, decreasing = TRUE, na.last = TRUE)

df_contagem = df_contagem[ordem,]

df_contagem = head(df_contagem, 10)


fig <- plot_ly(labels = ~df_contagem$Paises, values = ~df_contagem$Frequencia, type = 'pie')

fig <- fig %>%
  layout(title = '10 paises com mais conteudos - solo ')


fig

Questão 8

fig <- plot_ly(
  type = 'table',
  header = list(
    values = c("País","Total de Conteudos"),
    align = 'center',
    fill = list(color = "grey"),
    font = list(size = 12, color = 'white')
  ),
  cells = list(
    values = t(df_contagem),
    align = 'center',
    fill = list(color = 'white'),
    font = list(size = 11, color = 'black')
  )
)

fig

Questão 9

#Filmes
movie = subset(netflixData, netflixData$type== "Movie")
tipoAno1 <- table(movie$release_year)

df_Movie <- as.data.frame(tipoAno1)

colnames(df_Movie) <- c("Ano", "Frequencia")

df_Movie$Ano <- as.character(df_Movie$Ano)

df_Movie$Ano <- as.numeric(df_Movie$Ano)

# Criando uma nova coluna para agrupar os anos em intervalos de 10 anos
df_Movie$decada <- cut(df_Movie$Ano, breaks = seq(1920, 2030, by = 10), right = FALSE, labels = seq(1920, 2020, by = 10))

resultM <- aggregate(Frequencia ~ decada, data = df_Movie, FUN = sum)

#Séries
serie = subset(netflixData, netflixData$type == "TV Show")
tipoAno2 <- table(serie$release_year)

df_Serie <- as.data.frame(tipoAno2)
colnames(df_Serie) <- c("Ano", "Frequencia")

df_Serie$Ano <- as.character(df_Serie$Ano)

df_Serie$Ano <- as.numeric(df_Serie$Ano)

# Criando uma nova coluna para agrupar os anos em intervalos de 10 anos
df_Serie$decada <- cut(df_Serie$Ano, breaks = seq(1920, 2030, by = 10), right = FALSE, labels = seq(1920, 2020, by = 10))

resultS <- aggregate(Frequencia ~ decada, data = df_Serie, FUN = sum)


fig <- plot_ly(x = ~resultS$decada, y = ~resultS$Frequencia, type = 'scatter', mode = 'lines+markers', name='TV Show') %>%

add_trace(x = ~resultM$decada, y = ~resultM$Frequencia, type = 'scatter', mode = 'lines+markers',name='Movies') 

fig <- fig %>%
  layout(title = 'Frequencia de filmes e series durantes os anos - Netflix',
         yaxis=list(title = 'Qnd. Conteúdo'),
         xaxis=list(title = 'Década'))

fig

Questão 10

netflixGen = netflixData

netflixGen$listed_in <- sapply(strsplit(as.character(netflixGen$listed_in), ","), `[`, 1)

netflixGen$release_year <- as.character(netflixGen$release_year)

netflixGen$release_year <- as.numeric(netflixGen$release_year)

Drama = subset(netflixGen, listed_in =="Dramas" & release_year >= 2000 & release_year <= 2010)
Action = subset(netflixGen, listed_in =="Action & Adventure" & release_year >= 2000 & release_year <= 2010)
Comedia = subset(netflixGen, listed_in =="Comedies" & release_year >= 2000 & release_year <= 2010)


df_count1 <- Drama %>%
  group_by(release_year) %>%
  summarise(count = n()) %>%
  ungroup()


df_count2 <- Action %>%
  group_by(release_year) %>%
  summarise(count = n()) %>%
  ungroup()


df_count3 <- Comedia %>%
  group_by(release_year) %>%
  summarise(count = n()) %>%
  ungroup()


fig <- plot_ly(
  x = ~df_count1$release_year,
  y = ~df_count1$count,
  type = 'bar',
  name = 'Dramas',
  marker = list(color = 'blue')
)

fig <- fig %>% add_trace(
  y = ~df_count2$count,
  name = 'Action & Adventure',
  marker = list(color = 'orange')
)


fig <- fig %>% add_trace(
  y = ~df_count3$count,
  name = 'Comedies',
  marker = list(color = 'green')
)

fig <- fig %>% layout(
  barmode = 'group',
  title = "Quantidade de Filmes por Gênero (2000-2010)",
  xaxis = list(title = "Ano"),
  yaxis = list(title = "Quantidade de filmes"),
  showlegend = TRUE,
  legend = list(title = list(text = 'Gênero'))
)


fig