Exercício 12
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)
layout(matrix(c(1,1,2,3,4,5,6,0), nrow = 4, byrow = TRUE))
plot(clock, MRT_1F, type = "b", ylim = c(0, max(MRT_1F)),
xlab = "Time between Things requests (seconds)",
ylab = "Response Time (sec)",
main = "Response Time by Fog Configuration")
lines(clock, MRT_3F, type = "b", col = "red")
lines(clock, MRT_5F, type = "b", col = "blue")
lines(clock, MRT_10F, type = "b", col = "purple")
lines(clock, MRT_15F, type = "b", col = "green")
lines(clock, MRT_sem_F, type = "b", col = "darkgray")
legend("topright",
legend = c("1 Fog", "3 Fogs", "5 Fogs", "10 Fogs", "15 Fogs", "No Fog"),
col = c("black", "red", "blue", "purple", "green", "darkgray"),
lty = 1, pch = 1, cex = 0.7)
barplot(rbind(MRT_sem_F, MRT_1F),
beside = TRUE, log = "y",
col = c("#E6E6E6", "#666666"),
names.arg = clock,
main = "No Fog x 1 Fog",
xlab = "Time between Things requests",
ylab = "Response time (s)")
legend("topright", legend = c("No Fog", "1 Fog"),
fill = c("#E6E6E6", "#666666"), cex = 0.7)
barplot(rbind(MRT_sem_F, MRT_3F),
beside = TRUE, log = "y",
col = c("#E6E6E6", "#666666"),
names.arg = clock,
main = "No Fog x 3 Fogs",
xlab = "Time between Things requests",
ylab = "Response time (s)")
legend("topright", legend = c("No Fog", "3 Fogs"),
fill = c("#E6E6E6", "#666666"), cex = 0.7)
barplot(rbind(MRT_sem_F, MRT_5F),
beside = TRUE, log = "y",
col = c("#E6E6E6", "#666666"),
names.arg = clock,
main = "No Fog x 5 Fogs",
xlab = "Time between Things requests",
ylab = "Response time (s)")
legend("topright", legend = c("No Fog", "5 Fogs"),
fill = c("#E6E6E6", "#666666"), cex = 0.7)
barplot(rbind(MRT_sem_F, MRT_10F),
beside = TRUE, log = "y",
col = c("#E6E6E6", "#666666"),
names.arg = clock,
main = "No Fog x 10 Fogs",
xlab = "Time between Things requests",
ylab = "Response time (s)")
legend("topright", legend = c("No Fog", "10 Fogs"),
fill = c("#E6E6E6", "#666666"), cex = 0.7)
barplot(rbind(MRT_sem_F, MRT_15F),
beside = TRUE, log = "y",
col = c("#E6E6E6", "#666666"),
names.arg = clock,
main = "No Fog x 15 Fogs",
xlab = "Time between Things requests",
ylab = "Response time (s)")
legend("topright", legend = c("No Fog", "15 Fogs"),
fill = c("#E6E6E6", "#666666"), cex = 0.7)
Questão 2
tabela_refeicao <- matrix(
c(
53.8, 33.9, 2.6, 0.0,
43.6, 54.2, 60.5, 21.4,
2.6, 11.9, 36.8, 78.6
),
nrow = 3,
byrow = TRUE
)
rownames(tabela_refeicao) <- c("Good", "Very Good", "Excellent")
colnames(tabela_refeicao) <- c("$10-19", "$20-29", "$30-39", "$40-49")
barplot(
tabela_refeicao,
beside = FALSE,
col = c("lightblue", "orange", "lightgreen"),
main = "Qualidade da refeição por categoria de preço",
xlab = "Categoria de preço",
ylab = "Percentual (%)",
ylim = c(0, 100)
)
legend(
"topright",
legend = rownames(tabela_refeicao),
fill = c("lightblue", "orange", "lightgreen"),
title = "Quality Rating"
)
Questão 3
dados_maio <- airquality[airquality$Month == 5, ]
temperatura_celsius <- (dados_maio$Temp - 32) / 1.8
hist(
temperatura_celsius,
probability = TRUE,
col = "lightblue",
main = "Histograma das temperaturas de maio",
xlab = "Temperatura em graus Celsius",
ylab = "Densidade"
)
lines(
density(temperatura_celsius),
col = "red",
lwd = 2
)
Questão 4
sales <- read.table(
"https://training-course-material.com/images/8/8f/Sales.txt",
header = TRUE
)
total_pais <- aggregate(SALES ~ COUNTRY, data = sales, sum)
porcentagem <- round(100 * total_pais$SALES / sum(total_pais$SALES), 1)
rotulos <- paste(total_pais$COUNTRY, porcentagem, "%")
cores <- rainbow(length(total_pais$COUNTRY))
pie(
total_pais$SALES,
labels = rotulos,
col = cores,
main = "Porcentagem de vendas por país"
)
legend(
"topright",
legend = total_pais$COUNTRY,
fill = cores,
cex = 0.8
)
Questao 5
boxplot(
count ~ spray,
data = InsectSprays,
outline = FALSE,
col = "yellow",
main = "Contagem de insetos por tipo de inseticida",
xlab = "Tipo de inseticida",
ylab = "Contagem de insetos"
)
Questão 6
converter_memoria <- function(memoria) {
memoria <- as.character(memoria)
valor <- as.numeric(str_extract(memoria, "[0-9.]+"))
unidade <- str_extract(memoria, "[A-Za-z]+")
memoria_mb <- ifelse(
unidade %in% c("TB", "T"),
valor * 1000000,
ifelse(
unidade %in% c("GB", "G"),
valor * 1024,
ifelse(
unidade %in% c("KB", "K"),
valor / 1024,
ifelse(
unidade %in% c("B"),
valor / (1024 * 1024),
valor
)
)
)
)
return(memoria_mb)
}
preparar_monitoramento <- function(arquivo) {
dados <- read.csv(arquivo, stringsAsFactors = FALSE)
dados$currentTime <- as.POSIXct(dados$currentTime)
dados$tempo_hora <- as.numeric(
difftime(dados$currentTime, min(dados$currentTime), units = "hours")
)
dados$memoria_mb <- converter_memoria(dados$usedMemory)
return(dados)
}
dados_none <- preparar_monitoramento("monitoringCloudData_NONE.csv")
dados_01 <- preparar_monitoramento("monitoringCloudData_0.1.csv")
dados_05 <- preparar_monitoramento("monitoringCloudData_0.5.csv")
dados_1 <- preparar_monitoramento("monitoringCloudData_1.csv")
layout(matrix(c(1, 2, 3, 4), nrow = 2, byrow = TRUE))
plot(
dados_none$tempo_hora,
dados_none$memoria_mb,
type = "l",
main = "Memory Analysis (None Workload)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)"
)
plot(
dados_01$tempo_hora,
dados_01$memoria_mb,
type = "l",
main = "Memory Analysis (Workload of 0.1)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)"
)
plot(
dados_05$tempo_hora,
dados_05$memoria_mb,
type = "l",
main = "Memory Analysis (Workload of 0.5)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)"
)
plot(
dados_1$tempo_hora,
dados_1$memoria_mb,
type = "l",
main = "Memory Analysis (Workload of 1.0)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)"
)
Questão 7
netflix <- read.csv("netflix_titles.csv", stringsAsFactors = FALSE)
netflix_um_pais <- netflix %>%
filter(!is.na(country), country != "") %>%
filter(!str_detect(country, ","))
top10_paises <- netflix_um_pais %>%
count(country, sort = TRUE) %>%
slice_head(n = 10)
plot_ly(
data = top10_paises,
labels = ~country,
values = ~n,
type = "pie"
) %>%
layout(
title = "Top 10 países com mais conteúdos na Netflix"
)
Questão 8
tabela_paises <- top10_paises %>%
rename(
País = country,
`Total de conteúdos` = n
)
plot_ly(
type = "table",
header = list(
values = c("País", "Total de conteúdos"),
fill = list(color = "gray"),
font = list(color = "white"),
align = "center"
),
cells = list(
values = list(
tabela_paises$País,
tabela_paises$`Total de conteúdos`
),
align = "center"
)
)
Questão 9
netflix_decada <- netflix %>%
filter(!is.na(release_year), !is.na(type)) %>%
filter(type %in% c("Movie", "TV Show")) %>%
mutate(decada = floor(release_year / 10) * 10) %>%
count(decada, type)
plot_ly() %>%
add_lines(
data = netflix_decada %>% filter(type == "TV Show"),
x = ~decada,
y = ~n,
name = "TV Series",
line = list(color = "blue")
) %>%
add_lines(
data = netflix_decada %>% filter(type == "Movie"),
x = ~decada,
y = ~n,
name = "Movies",
line = list(color = "yellow")
) %>%
layout(
title = "Quantidade de conteúdos da Netflix por década",
xaxis = list(title = "Década"),
yaxis = list(title = "Qtd. Conteúdo")
)
Questão 10
generos_interesse <- c("Dramas", "Action & Adventure", "Comedies")
netflix_generos <- netflix %>%
filter(type == "Movie") %>%
filter(release_year >= 2000, release_year <= 2010) %>%
mutate(
genero_principal = str_trim(str_extract(listed_in, "^[^,]+"))
) %>%
filter(genero_principal %in% generos_interesse) %>%
count(release_year, genero_principal)
plot_ly(
data = netflix_generos,
x = ~release_year,
y = ~n,
color = ~genero_principal,
type = "bar"
) %>%
layout(
title = "Quantidade de filmes por gênero entre 2000 e 2010",
xaxis = list(title = "Ano de lançamento"),
yaxis = list(title = "Qtd. de lançamentos"),
barmode = "group"
)