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: linha do tempo (top) + 5 barras (bottom grid)
layout(matrix(c(1, 1,
2, 3,
4, 5,
6, 6), nrow = 4, byrow = TRUE))
# --- Gráfico de linhas ---
par(mar = c(5, 5, 2, 2))
plot(clock, MRT_1F, type = "b", pch = 4, col = "black",
ylim = c(0, max(MRT_1F)),
xlab = "Time between Things requests (seconds)",
ylab = "Response Time (sec.)",
lwd = 1.5)
lines(clock, MRT_3F, type = "b", pch = 17, col = "orange", lwd = 1.5)
lines(clock, MRT_5F, type = "b", pch = 16, col = "red", lwd = 1.5)
lines(clock, MRT_10F, type = "b", pch = 24, col = "purple", lwd = 1.5)
lines(clock, MRT_15F, type = "b", pch = 25, col = "green", lwd = 1.5)
lines(clock, MRT_sem_F,type = "b", pch = 23, col = "cyan", lwd = 1.5)
legend("topright",
legend = c("1 Fog", "3 Fogs", "5 Fogs", "10 Fogs", "15 Fogs", "w/o Fog"),
col = c("black", "orange", "red", "purple", "green", "cyan"),
pch = c(4, 17, 16, 24, 25, 23),
lty = 1, lwd = 1.5, cex = 0.8)
# Função auxiliar para gráfico de barras
plot_bar <- function(fog_data, fog_label) {
mat <- rbind(MRT_sem_F, fog_data)
barplot(mat,
beside = TRUE,
names.arg = clock,
log = "y",
col = c("#E6E6E6", "#666666"),
xlab = "Time between Things requests",
ylab = "Response time (s)",
legend.text = c("w/o Fog", fog_label),
args.legend = list(x = "topright", cex = 0.7),
cex.names = 0.7)
}
plot_bar(MRT_1F, "1 Fog")
plot_bar(MRT_3F, "3 Fogs")
plot_bar(MRT_5F, "5 Fogs")
plot_bar(MRT_10F, "10 Fogs")
plot_bar(MRT_15F, "15 Fogs")
Questão 2
meal_data <- matrix(
c(53.8, 43.6, 2.6,
33.9, 54.2, 11.9,
2.6, 60.5, 36.8,
0.0, 21.4, 78.6),
nrow = 3, byrow = FALSE,
dimnames = list(
c("Good", "Very Good", "Excellent"),
c("$10-19", "$20-29", "$30-39", "$40-49")
)
)
cores <- c("#4E79A7", "#F28E2B", "#59A14F")
barplot(meal_data,
beside = FALSE,
col = cores,
main = "Qualidade de Refeição por Faixa de Preço",
xlab = "Faixa de Preço",
ylab = "Percentual (%)",
ylim = c(0, 110),
legend.text = rownames(meal_data),
args.legend = list(x = "topright", bty = "n"))
Questão 3
may_temps_f <- airquality$Temp[airquality$Month == 5]
may_temps_c <- (may_temps_f - 32) / 1.8
hist(may_temps_c,
main = "Histograma das Temperaturas de Maio",
xlab = "Temperatura (°C)",
ylab = "Frequência",
col = "steelblue",
border = "white",
freq = FALSE)
lines(density(may_temps_c), col = "red", lwd = 2)
Questão 4
sales <- read.table(
"https://training-course-material.com/images/8/8f/Sales.txt",
header = TRUE
)
# Identifica automaticamente a coluna de país (character) e a coluna numérica de vendas
col_char <- names(sales)[sapply(sales, is.character) | sapply(sales, is.factor)][1]
col_num <- names(sales)[sapply(sales, is.numeric)][1]
# Agrega total por país usando os nomes reais das colunas
formula_agg <- as.formula(paste(col_num, "~", col_char))
total_vendas <- aggregate(formula_agg, data = sales, FUN = sum)
names(total_vendas) <- c("Country", "Sales")
pct <- round(total_vendas$Sales / sum(total_vendas$Sales) * 100, 1)
labels_pct <- paste0(pct, "%")
cores_pizza <- rainbow(nrow(total_vendas))
pie(total_vendas$Sales,
labels = labels_pct,
col = cores_pizza,
main = "Total de Vendas por País")
legend("bottomleft",
legend = total_vendas$Country,
fill = cores_pizza,
cex = 0.75,
bty = "n")
Questão 5
boxplot(count ~ spray,
data = InsectSprays,
outline = FALSE,
col = "yellow",
main = "Contagem de Insetos por Inseticida",
xlab = "Tipo de Inseticida",
ylab = "Contagem de Insetos")
Questão 6
library(lubridate)
# Função para carregar e tratar os dados
carregar_dados <- function(caminho) {
df <- read.csv(caminho, stringsAsFactors = FALSE)
colnames(df) <- trimws(colnames(df))
# Converte currentTime para POSIXct
df$currentTime <- as.POSIXct(df$currentTime, format = "%Y-%m-%d %H:%M:%OS")
# Torna o tempo contínuo (horas a partir do início)
df$time_h <- as.numeric(difftime(df$currentTime, df$currentTime[1], units = "hours"))
# Converte usedMemory para MB
converter_mb <- function(x) {
x <- trimws(x)
valor <- as.numeric(gsub("[^0-9.]", "", x))
unidade <- gsub("[0-9. ]", "", x)
dplyr::case_when(
grepl("TB", unidade, ignore.case = TRUE) ~ valor * 1e6,
grepl("GB", unidade, ignore.case = TRUE) ~ valor * 1024,
grepl("MB", unidade, ignore.case = TRUE) ~ valor,
grepl("KB", unidade, ignore.case = TRUE) ~ valor / 1024,
TRUE ~ valor
)
}
df$usedMemory_MB <- converter_mb(df$usedMemory)
df
}
d01 <- carregar_dados("monitoringCloudData_0.1.csv")
d05 <- carregar_dados("monitoringCloudData_0.5.csv")
d1 <- carregar_dados("monitoringCloudData_1.csv")
dnone <- carregar_dados("monitoringCloudData_NONE.csv")
layout(matrix(c(1, 2, 3, 4), nrow = 2, byrow = TRUE))
plot_mem <- function(df, titulo) {
plot(df$time_h, df$usedMemory_MB,
type = "l", lwd = 0.8,
main = titulo,
xlab = "Time (hour)",
ylab = "Used Memory (MB)")
}
plot_mem(dnone, "Memory Analysis (None Workload)")
plot_mem(d01, "Memory Analysis (Workload of 0.1)")
plot_mem(d05, "Memory Analysis (Workload of 0.5)")
plot_mem(d1, "Memory Analysis (Workload of 1.0)")
Questão 7
library(plotly)
library(dplyr)
netflix <- read.csv("netflix_titles.csv", stringsAsFactors = FALSE)
# Apenas conteúdos com UM único país
netflix_1pais <- netflix %>%
filter(!is.na(country) & country != "" & !grepl(",", country))
top10 <- netflix_1pais %>%
count(country, name = "total") %>%
arrange(desc(total)) %>%
slice(1:10)
plot_ly(top10,
labels = ~country,
values = ~total,
type = "pie",
textinfo = "label+percent") %>%
layout(title = "Top 10 Países com Mais Conteúdo na Netflix")
Questão 8
top10_tabela <- top10 %>%
rename(País = country, `Total de Conteúdos` = total)
plot_ly(
type = "table",
header = list(
values = c("<b>País</b>", "<b>Total de Conteúdos</b>"),
fill = list(color = "gray"),
font = list(color = "white", size = 13),
align = "center"
),
cells = list(
values = list(top10_tabela$País, top10_tabela$`Total de Conteúdos`),
align = "center"
)
) %>%
layout(title = "Top 10 Países - Tabela de Conteúdos")
Questão 9
netflix_decadas <- netflix %>%
filter(!is.na(release_year)) %>%
mutate(decada = floor(release_year / 10) * 10)
series <- netflix_decadas %>%
filter(type == "TV Show") %>%
count(decada, name = "total")
filmes <- netflix_decadas %>%
filter(type == "Movie") %>%
count(decada, name = "total")
plot_ly() %>%
add_trace(data = series, x = ~decada, y = ~total,
type = "scatter", mode = "lines+markers",
name = "TV Series",
line = list(color = "blue"),
marker = list(color = "blue")) %>%
add_trace(data = filmes, x = ~decada, y = ~total,
type = "scatter", mode = "lines+markers",
name = "Movies",
line = list(color = "orange"),
marker = list(color = "orange")) %>%
layout(title = "Quantidade de Conteúdo por Década na Netflix",
xaxis = list(title = "Década"),
yaxis = list(title = "Qnd. Conteúdo"))
Questão 10
generos_alvo <- c("Dramas", "Action & Adventure", "Comedies")
filmes_genero <- netflix %>%
filter(type == "Movie",
release_year >= 2000,
release_year <= 2010) %>%
mutate(genero_principal = trimws(sub(",.*", "", listed_in))) %>%
filter(genero_principal %in% generos_alvo) %>%
count(release_year, genero_principal, name = "total")
cores_genero <- c("Dramas" = "blue",
"Action & Adventure" = "orange",
"Comedies" = "green")
plot_ly() %>%
add_trace(
data = filter(filmes_genero, genero_principal == "Dramas"),
x = ~release_year, y = ~total,
type = "bar", name = "Drama",
marker = list(color = "blue")
) %>%
add_trace(
data = filter(filmes_genero, genero_principal == "Action & Adventure"),
x = ~release_year, y = ~total,
type = "bar", name = "Ação e Aventura",
marker = list(color = "orange")
) %>%
add_trace(
data = filter(filmes_genero, genero_principal == "Comedies"),
x = ~release_year, y = ~total,
type = "bar", name = "Comédia",
marker = list(color = "green")
) %>%
layout(barmode = "group",
title = "Filmes por Gênero (2000–2010)",
xaxis = list(title = "Ano de Lançamento", dtick = 1),
yaxis = list(title = "Qnt. de Lançamentos"))