Questões
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", pch = 4, col = "black",
ylim = range(c(MRT_1F, MRT_3F, MRT_5F, MRT_10F, MRT_15F, MRT_sem_F)),
xlab = "Time between Things requests (seconds)",
ylab = "Response Time (sec.)")
lines(clock, MRT_3F, type = "b", pch = 16, col = "yellow")
lines(clock, MRT_5F, type = "b", pch = 1, col = "red")
lines(clock, MRT_10F, type = "b", pch = 17, col = "blue")
lines(clock, MRT_15F, type = "b", pch = 2, col = "purple")
lines(clock, MRT_sem_F, type = "b", pch = 4, col = "green")
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"),
pch = c(4, 16, 1, 17, 2, 4), lty = 1, cex = 0.8)
barplot(rbind(MRT_sem_F, MRT_1F), beside = TRUE, log = "y",
col = c("#E6E6E6", "#666666"), names.arg = clock,
xlab = "Time between Things requests", ylab = "Response time (s)")
legend("topright", legend = c("w/o 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,
xlab = "Time between Things requests", ylab = "Response time (s)")
legend("topright", legend = c("w/o 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,
xlab = "Time between Things requests", ylab = "Response time (s)")
legend("topright", legend = c("w/o 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,
xlab = "Time between Things requests", ylab = "Response time (s)")
legend("topright", legend = c("w/o 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,
xlab = "Time between Things requests", ylab = "Response time (s)")
legend("topright", legend = c("w/o Fog", "15 Fogs"),
fill = c("#E6E6E6", "#666666"), cex = 0.7)
Questão 2
meal <- 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(meal) <- c("Good", "Very Good", "Excellent")
colnames(meal) <- c("$10-19", "$20-29", "$30-39", "$40-49")
par(mar = c(5, 4, 4, 9))
barplot(meal, beside = FALSE, col = c("lightblue", "orange", "darkgreen"),
main = "Qualidade da refeição por preço",
xlab = "Faixa de preço", ylab = "Percentual (%)")
legend("topright", legend = rownames(meal),
fill = c("lightblue", "orange", "darkgreen"), bty = "n",
inset = c(-0.3, 0), xpd = TRUE, title = "Qualidade")
Questão 3
data(airquality)
mai <- subset(airquality, Month == 5)
mai$TempC <- (mai$Temp - 32) / 1.8
h <- hist(mai$TempC, plot = FALSE)
dens <- density(mai$TempC, na.rm = TRUE)
hist(mai$TempC, freq = FALSE, col = "skyblue", border = "white",
ylim = c(0, max(h$density, dens$y) * 1.05),
main = "Temperaturas de maio (convertidas para °C)",
xlab = "Temperatura (°C)", ylab = "Densidade")
lines(dens, col = "red", lwd = 2)
Questão 4
Questão 5
boxplot(count ~ spray, data = InsectSprays,
outline = FALSE, col = "yellow",
main = "Contagem de insetos por inseticida (sem outliers)",
xlab = "Inseticida", ylab = "Contagem")
Questão 6
ler_monitoramento <- function(nomes) {
arquivo <- nomes[file.exists(nomes)][1]
if (is.na(arquivo)) stop("Arquivo não encontrado: ", nomes[1])
df <- read.csv(arquivo, stringsAsFactors = FALSE)
partes <- str_match(df$currentTime,
"(\\d{4}-\\d{2}-\\d{2}) (\\d{2}:\\d{2}:\\d{2}\\.\\d+)$")
data_ini <- str_extract(df$currentTime, "^\\d{4}-\\d{2}-\\d{2}")
corrompido <- data_ini != partes[, 2]
t_fim <- as.POSIXct(paste(partes[, 2], partes[, 3]),
format = "%Y-%m-%d %H:%M:%OS", tz = "UTC")
t_ini <- as.POSIXct(paste(data_ini, partes[, 3]),
format = "%Y-%m-%d %H:%M:%OS", tz = "UTC")
tempo <- t_fim
for (i in which(corrompido)) {
if (i == 1) next
candidatos <- c(t_ini[i], t_fim[i])
dist <- abs(as.numeric(difftime(candidatos, tempo[i - 1], units = "secs")))
tempo[i] <- candidatos[which.min(dist)]
}
df$tempo <- tempo
df$horas <- as.numeric(difftime(df$tempo, min(df$tempo), units = "hours"))
mem <- str_match(df$usedMemory, "^\\s*([0-9.]+)\\s*([A-Za-z]+)\\s*$")
fatores <- c(B = 1 / 1024^2, KB = 1 / 1024, MB = 1,
GB = 1024, TB = 1000000)
df$usedMB <- as.numeric(mem[, 2]) * unname(fatores[toupper(mem[, 3])])
df
}
d01 <- ler_monitoramento(c("monitoringCloudData_0.1.csv", "monitoringCloudData_0_1.csv"))
d05 <- ler_monitoramento(c("monitoringCloudData_0.5.csv", "monitoringCloudData_0_5.csv"))
d1 <- ler_monitoramento("monitoringCloudData_1.csv")
dNone <- ler_monitoramento("monitoringCloudData_NONE.csv")
layout(matrix(c(1, 2, 3, 4), nrow = 2, byrow = TRUE))
plot(dNone$horas, dNone$usedMB, type = "l",
main = "Memory Analysis (None Workload)",
xlab = "Time (hour)", ylab = "Used Memory (MB)")
plot(d01$horas, d01$usedMB, type = "l",
main = "Memory Analysis (Workload of 0.1)",
xlab = "Time (hour)", ylab = "Used Memory (MB)")
plot(d05$horas, d05$usedMB, type = "l",
main = "Memory Analysis (Workload of 0.5)",
xlab = "Time (hour)", ylab = "Used Memory (MB)")
plot(d1$horas, d1$usedMB, 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)
um_pais <- netflix %>%
filter(!is.na(country), country != "", !grepl(",", country))
top10 <- um_pais %>%
count(country, sort = TRUE) %>%
slice_head(n = 10)
plot_ly(top10, labels = ~country, values = ~n, type = "pie") %>%
layout(title = "Top 10 países com mais conteúdos na Netflix")
Questão 8
tabela <- data.frame(
"País" = top10$country,
"Total de conteúdos" = top10$n,
check.names = FALSE
)
plot_ly(
type = "table",
header = list(
values = names(tabela),
fill = list(color = "gray"),
font = list(color = "white"),
align = "center"
),
cells = list(
values = list(tabela$`País`, tabela$`Total de conteúdos`),
align = "center"
)
)
Questão 9
contagem <- netflix %>%
filter(!is.na(release_year)) %>%
mutate(
decada = floor(release_year / 10) * 10,
tipo = case_when(type == "TV Show" ~ "TV Series",
type == "Movie" ~ "Movies")
) %>%
filter(!is.na(tipo)) %>%
count(decada, tipo)
grade <- expand.grid(
decada = seq(min(contagem$decada), max(contagem$decada), by = 10),
tipo = c("TV Series", "Movies"),
stringsAsFactors = FALSE
)
dados_q9 <- grade %>%
left_join(contagem, by = c("decada", "tipo")) %>%
mutate(n = ifelse(is.na(n), 0, n))
plot_ly(dados_q9, x = ~decada, y = ~n, color = ~tipo,
colors = c("TV Series" = "blue", "Movies" = "yellow"),
type = "scatter", mode = "lines+markers") %>%
layout(
title = "Quantidade de conteúdo por década",
xaxis = list(title = "Década"),
yaxis = list(title = "Qnd. Conteúdo")
)
Questão 10
# Usa só o primeiro gênero de cada filme
generos_pt <- c("Dramas" = "Drama",
"Action & Adventure" = "Ação e Aventura",
"Comedies" = "Comédia")
filmes <- netflix %>%
filter(type == "Movie", release_year >= 2000, release_year <= 2010) %>%
mutate(genero_principal = str_trim(str_split_fixed(listed_in, ",", 2)[, 1])) %>%
filter(genero_principal %in% names(generos_pt)) %>%
count(release_year, genero_principal)
grade10 <- expand.grid(
release_year = 2000:2010,
genero_principal = names(generos_pt),
stringsAsFactors = FALSE
)
dados_q10 <- grade10 %>%
left_join(filmes, by = c("release_year", "genero_principal")) %>%
mutate(
n = ifelse(is.na(n), 0, n),
genero = factor(unname(generos_pt[genero_principal]), levels = unname(generos_pt))
)
plot_ly(dados_q10, x = ~release_year, y = ~n, color = ~genero,
type = "bar",
colors = c("Drama" = "#1f77b4",
"Ação e Aventura" = "#ff7f0e",
"Comédia" = "#2ca02c")) %>%
layout(
barmode = "group",
title = "Filmes por gênero (2000–2010)",
xaxis = list(title = "Ano de Lançamento"),
yaxis = list(title = "Qnt. de Lançamentos")
)