Questões
— 1. Definir os dados —
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)
# Gráfico 1
plot(clock, MRT_1F, type = "o", col = "black", pch = 4, ylim = c(0, max(MRT_1F)),
xlab = "Time between Things requests (seconds)",
ylab = "Response Time (sec.)",
main = "Tempo de Resposta vs Intervalo de Requisições")
lines(clock, MRT_3F, type = "o", col = "yellow", pch = 11)
lines(clock, MRT_5F, type = "o", col = "red", pch = 1)
lines(clock, MRT_10F, type = "o", col = "blue", pch = 2)
lines(clock, MRT_15F, type = "o", col = "purple", pch = 5)
lines(clock, MRT_sem_F, type = "o", col = "green", pch = 4)
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, 11, 1, 2, 5, 4),
lwd = 1)
# Gráfico 2
dados_1F <- matrix(c(MRT_sem_F, MRT_1F), nrow = 2, ncol = 7, byrow = TRUE)
dados_3F <- matrix(c(MRT_sem_F, MRT_3F), nrow = 2, ncol = 7, byrow = TRUE)
dados_5F <- matrix(c(MRT_sem_F, MRT_5F), nrow = 2, ncol = 7, byrow = TRUE)
dados_10F <- matrix(c(MRT_sem_F, MRT_10F), nrow = 2, ncol = 7, byrow = TRUE)
dados_15F <- matrix(c(MRT_sem_F, MRT_15F), nrow = 2, ncol = 7, byrow = TRUE)
par(mfrow = c(3, 2))
criar_barplot <- function(dados, titulo) {
barplot(dados, beside = TRUE, col = c("#E6E6E6", "#666666"),
names.arg = clock, log = "y",
xlab = "Time between Things requests (seconds)",
ylab = "Response time (s)")
legend("topright", legend = c("w/o Fog", titulo),
fill = c("#E6E6E6", "#666666"))
}
criar_barplot(dados_1F, "1 Fog")
criar_barplot(dados_3F, "3 Fogs")
criar_barplot(dados_5F, "5 Fogs")
criar_barplot(dados_10F, "10 Fogs")
criar_barplot(dados_15F, "15 Fogs")
# Restaurar layout padrão
par(mfrow = c(1, 1))
Questão 2
dados_q2 <- 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(dados_q2) <- c("Good", "Very Good", "Excellent")
colnames(dados_q2) <- c("$10-19", "$20-29", "$30-39", "$40-49")
cores_q2 <- c("#FDBF6F", "#B2DF8A", "#A6CEE3")
barplot(dados_q2,
main = "Qualidade da Refeição por Categoria de Preço",
xlab = "Categoria de Preço",
ylab = "Porcentagem (%)",
col = cores_q2,
legend.text = rownames(dados_q2),
args.legend = list(x = "bottomleft", bty = "n", inset = c(-0.12, -0.35))
)
Questão 3
data(airquality)
temp_f_maio <- airquality$Temp[airquality$Month == 5]
temp_c_maio <- (temp_f_maio - 32) / 1.8
hist(temp_c_maio,
main = "Histograma das Temperaturas em Maio",
xlab = "Temperatura (°C)",
ylab = "Frequência",
col = "lightblue",
prob = TRUE
)
lines(density(temp_c_maio, na.rm = TRUE), col = "red", lwd = 2)
Questão 4
# Leitura dos dados de vendas
Sales <- read.table("https://training-course-material.com/images/8/8f/Sales.txt", header = TRUE)
vendas_por_pais <- aggregate(SALES ~ COUNTRY, data = Sales, FUN = sum)
vendas_por_pais$Pct <- vendas_por_pais$SALES / sum(vendas_por_pais$SALES)
# formatar porcentagens (usa scales::percent)
if (!requireNamespace("scales", quietly = TRUE)) install.packages("scales")
library(scales)
pct_labels <- percent(vendas_por_pais$Pct, accuracy = 0.1)
pie_labels <- paste0(vendas_por_pais$COUNTRY, " (", pct_labels, ")")
cores_pie <- rainbow(length(vendas_por_pais$COUNTRY))
pie(vendas_por_pais$SALES,
labels = pie_labels,
col = cores_pie,
main = "Vendas Totais por País"
)
legend("topright",
legend = vendas_por_pais$COUNTRY,
fill = cores_pie,
cex = 0.8
)
Questão 5
data(InsectSprays)
boxplot(count ~ spray,
data = InsectSprays,
main = "Contagem de Insetos por Tipo de Inseticida",
xlab = "Tipo de Inseticida",
ylab = "Contagem de Insetos",
col = "yellow",
outline = FALSE
)
Questão 6
# Função para converter strings de memória para MB
convert_to_mb <- function(memory_str) {
value <- as.numeric(gsub("([0-9\\.]+).*", "\\1", memory_str))
if (grepl("TB", memory_str, ignore.case = TRUE)) {
return(value * 1000000) # 1 TB = 1000000 MB
} else if (grepl("GB", memory_str, ignore.case = TRUE)) {
return(value * 1024) # 1 GB = 1024 MB
} else if (grepl("KB", memory_str, ignore.case = TRUE)) {
return(value / 1024) # KB -> MB
} else {
return(value) # assume MB
}
}
process_data <- function(filepath) {
df <- read.csv(filepath)
df$usedMemory_MB <- sapply(df$usedMemory, convert_to_mb)
df$currentTime <- as.POSIXct(df$currentTime, format = "%Y-%m-%d %H:%M:%OS")
start_time <- min(df$currentTime, na.rm = TRUE)
df$Time_hour <- as.numeric(difftime(df$currentTime, start_time, units = "hours"))
return(df)
}
df_none <- process_data("monitoringCloudData_NONE.csv")
df_0.1 <- process_data("monitoringCloudData_0.1.csv")
df_0.5 <- process_data("monitoringCloudData_0.5.csv")
df_1.0 <- process_data("monitoringCloudData_1.csv")
layout(matrix(c(1,2,3,4), nrow = 2, ncol = 2, byrow = TRUE))
par(mar = c(4.1, 4.1, 3.1, 1.1))
plot(df_none$Time_hour, df_none$usedMemory_MB,
type = "l",
main = "Memory Analysis (None Workload)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)",
ylim = c(96, 106)
)
plot(df_0.1$Time_hour, df_0.1$usedMemory_MB,
type = "l",
main = "Memory Analysis (Workload of 0.1)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)",
ylim = c(0, 3500)
)
plot(df_0.5$Time_hour, df_0.5$usedMemory_MB,
type = "l",
main = "Memory Analysis (Workload of 0.5)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)",
ylim = c(400, 1200)
)
plot(df_1.0$Time_hour, df_1.0$usedMemory_MB,
type = "l",
main = "Memory Analysis (Workload of 1.0)",
xlab = "Time (hour)",
ylab = "Used Memory (MB)",
ylim = c(242, 254)
)
par(mfrow = c(1, 1), mar = c(5.1, 4.1, 4.1, 2.1))
Questão 7
library(dplyr)
library(plotly)
df_netflix <- read.csv("netflix_titles.csv", na.strings = c("", NA), stringsAsFactors = FALSE)
top_10_countries <- df_netflix %>%
filter(!is.na(country)) %>%
filter(!grepl(",", country)) %>%
group_by(country) %>%
summarise(Total = n()) %>%
arrange(desc(Total)) %>%
slice_head(n = 10)
plot_ly(top_10_countries,
labels = ~country,
values = ~Total,
type = 'pie',
textinfo = 'percent+label',
insidetextorientation = 'radial') %>%
layout(title = "Top 10 Países com Mais Conteúdo na Netflix (País Único)",
margin = list(l = 90, r = 90, b = 90, t = 60)
)
Questão 8
tabela_data <- top_10_countries %>%
rename(País = country, "Total de conteúdos" = Total)
plot_ly(
type = 'table',
header = list(
values = colnames(tabela_data),
align = "center",
fill = list(color = "grey"),
font = list(color = "white", size = 12)
),
cells = list(
values = unname(as.list(tabela_data)),
align = "center",
fill = list(color = "#F5F5F5")
)
)
Questão 9
content_by_decade <- df_netflix %>%
filter(!is.na(release_year)) %>%
mutate(Decada = floor(release_year / 10) * 10) %>%
filter(Decada >= 1940) %>%
group_by(Decada, type) %>%
summarise(Quantidade = n(), .groups = 'drop')
plot_ly(content_by_decade,
x = ~Decada,
y = ~Quantidade,
color = ~type,
colors = c("Movie" = "orange", "TV Show" = "blue"),
type = 'scatter',
mode = 'lines+markers') %>%
layout(title = "Quantidade de Conteúdo por Década",
xaxis = list(title = "Década"),
yaxis = list(title = "Quantidade de Conteúdo"),
legend = list(title = list(text = 'Tipo')))
Questão 10
generos_interesse <- c("Dramas", "Action & Adventure", "Comedies")
movie_genres_by_year <- df_netflix %>%
filter(type == "Movie" & release_year >= 2000 & release_year <= 2010) %>%
mutate(Primeiro_Genero = sub(",.*", "", listed_in)) %>%
filter(Primeiro_Genero %in% generos_interesse) %>%
group_by(release_year, Primeiro_Genero) %>%
summarise(Quantidade = n(), .groups = 'drop')
plot_ly(movie_genres_by_year,
x = ~release_year,
y = ~Quantidade,
color = ~Primeiro_Genero,
type = 'bar') %>%
layout(title = "Filmes Lançados por Gênero (2000-2010)",
xaxis = list(title = "Ano de Lançamento"),
yaxis = list(title = "Quantidade de Lançamentos"),
barmode = 'group',
legend = list(title = list(text = 'Gênero')))