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, 2), nrow = 2, byrow = TRUE))
# Gráfico 1: Linhas
plot(clock, MRT_1F, type = "o", col = "red", pch = 16, ylim = c(0.1, max(MRT_1F)), log = "y", ylab = "Valores", xlab = "Clock")
lines(clock, MRT_3F, type = "o", col = "blue", pch = 16)
lines(clock, MRT_5F, type = "o", col = "green", pch = 16)
lines(clock, MRT_10F, type = "o", col = "purple", pch = 16)
lines(clock, MRT_15F, type = "o", col = "orange", pch = 16)
lines(clock, MRT_sem_F, type = "o", col = "black", pch = 16)
legend("topright", legend = c("1F", "3F", "5F", "10F", "15F", "Sem F"),
col = c("red", "blue", "green", "purple", "orange", "black"), lty = 1, pch = 16)
# Gráfico 2: Barras com escala logarítmica
data_matrix <- rbind(MRT_1F, MRT_3F, MRT_5F, MRT_10F, MRT_15F, MRT_sem_F)
barplot(data_matrix, beside = TRUE, col = c("#E6E6E6", "#666666"), log = "y",
names.arg = clock, legend.text = c("1F", "3F", "5F", "10F", "15F", "Sem F"),
args.legend = list(x = "topright"), ylab = "Valores", xlab = "Clock")
Questão 2
precos <- c("$10-19", "$20-29", "$30-39", "$40-49")
qualidade <- c("Good", "Very Good", "Excellent")
dados <- matrix(c(
53.8, 33.9, 2.6, 0.0, # Good
43.6, 54.2, 60.5, 21.4, # Very Good
2.6, 11.9, 36.8, 78.6 # Excellent
), nrow = 3, byrow = TRUE)
cores <- c("#E6E6E6", "#666666", "#2E86C1")
barplot(dados, beside = FALSE, col = cores, names.arg = precos,
main = "Qualidade da Refeição por Faixa de Preço",
xlab = "Faixa de Preço da Refeição", ylab = "Porcentagem (%)",
ylim = c(0, 100))
legend("topright", legend = qualidade, fill = cores, title = "Qualidade")
Questão 3
data(airquality)
temp_maio <- airquality$Temp[airquality$Month == 5]
temp_maio_celsius <- (temp_maio - 32) / 1.8
hist(temp_maio_celsius,
main = "Histograma das Temperaturas de Maio (°C)",
xlab = "Temperatura (°C)",
ylab = "Frequência",
col = "lightblue",
border = "black",
probability = TRUE)
lines(density(temp_maio_celsius), col = "red", lwd = 2)
Questão 4
sales <- read.table("https://training-course-material.com/images/8/8f/Sales.txt", header = TRUE)
total_sales <- sum(sales$SALES)
sales$Percentage <- (sales$SALES / total_sales) * 100
colors <- rainbow(nrow(sales))
pie(sales$SALES,
labels = paste0(round(sales$Percentage, 1), "%"),
col = colors,
main = "Porcentagem de Vendas por País")
legend("topright", legend = sales$COUNTRY, fill = colors, title = "Países")
Questão 5
data("InsectSprays")
boxplot(count ~ spray, data = InsectSprays,
main = "Contagem de Insetos por Tipo de Inseticida",
xlab = "Tipo de Inseticida",
ylab = "Contagem de Insetos",
col = "yellow",
outline = FALSE)
Questão 6
df_0.1 <- read.csv("monitoringCloudData_0.1.csv")
df_0.5 <- read.csv("monitoringCloudData_0.5.csv")
df_1 <- read.csv("monitoringCloudData_1.csv")
df_NONE <- read.csv("monitoringCloudData_NONE.csv")
convert_to_mb <- function(memory) {
if (grepl("TB", memory)) {
return(as.numeric(gsub("TB", "", memory)) * 1000000)
} else if (grepl("GB", memory)) {
return(as.numeric(gsub("GB", "", memory)) * 1024)
} else if (grepl("MB", memory)) {
return(as.numeric(gsub("MB", "", memory)))
} else {
return(NA)
}
}
adjust_data <- function(df) {
df$currentTime <- as.POSIXct(df$currentTime, format="%Y-%m-%d %H:%M:%S")
df$hours <- as.numeric(difftime(df$currentTime, df$currentTime[1], units = "hours"))
df$usedMemoryMB <- sapply(df$usedMemory, convert_to_mb)
return(df)
}
df_0.1 <- adjust_data(df_0.1)
df_0.5 <- adjust_data(df_0.5)
df_1 <- adjust_data(df_1)
df_NONE <- adjust_data(df_NONE)
plot_memory_usage <- function(df, title) {
plot(df$hours, df$usedMemoryMB, type = "l", xlab = "Tempo (horas)", ylab = "Memória Usada (MB)", main = title)
}
par(mfrow=c(2, 2))
plot_memory_usage(df_0.1, "Memória Usada (0.1)")
plot_memory_usage(df_0.5, "Memória Usada (0.5)")
plot_memory_usage(df_1, "Memória Usada (1)")
plot_memory_usage(df_NONE, "Memória Usada (NONE)")
Questão 7
library(dplyr)
library(plotly)
netflix_data <- read.csv("netflix_titles.csv")
netflix_data <- netflix_data %>%
filter(!is.na(country) & !grepl(",", country))
country_counts <- netflix_data %>%
group_by(country) %>%
summarise(count = n()) %>%
arrange(desc(count))
top_10_countries <- head(country_counts, 10)
plot_ly(top_10_countries, labels = ~country, values = ~count, type = 'pie') %>%
layout(title = "Top 10 Países com Mais Conteúdos na Netflix (2019)",
showlegend = TRUE)
Questão 8
library(dplyr)
library(plotly)
netflix_data <- read.csv("netflix_titles.csv")
netflix_data <- netflix_data %>%
filter(!is.na(country) & !grepl(",", country))
country_counts <- netflix_data %>%
group_by(country) %>%
summarise(count = n(), .groups = 'drop') %>%
arrange(desc(count))
top_10_countries <- head(country_counts, 10)
colnames(top_10_countries) <- c("País", "Total de Conteúdos")
tabela <- plot_ly(
type = "table",
header = list(
values = c("<b>País</b>", "<b>Total de Conteúdos</b>"),
align = c("center", "center"),
fill = list(color = "gray"),
font = list(color = "white", size = 14)
),
cells = list(
values = rbind(top_10_countries$País, top_10_countries$`Total de Conteúdos`),
align = c("center", "center"),
font = list(size = 12)
)
)
tabela
Questão 9
library(dplyr)
library(plotly)
netflix_data <- read.csv("netflix_titles.csv")
netflix_data <- netflix_data %>%
mutate(decade = floor(release_year / 10) * 10)
netflix_data <- netflix_data %>%
filter(!is.na(release_year))
content_by_decade <- netflix_data %>%
group_by(decade, type) %>%
summarise(count = n(), .groups = 'drop')
series_data <- content_by_decade %>% filter(type == "TV Show")
movies_data <- content_by_decade %>% filter(type == "Movie")
grafico <- plot_ly() %>%
add_trace(
x = ~series_data$decade,
y = ~series_data$count,
type = 'scatter',
mode = 'lines+markers',
name = 'Séries',
line = list(color = 'blue'),
marker = list(color = 'blue')
) %>%
add_trace(
x = ~movies_data$decade,
y = ~movies_data$count,
type = 'scatter',
mode = 'lines+markers',
name = 'Filmes',
line = list(color = 'yellow'),
marker = list(color = 'yellow')
) %>%
layout(
title = "Quantidade de Conteúdo por Década na Netflix",
xaxis = list(title = "Década"),
yaxis = list(title = "Quantidade de Conteúdo"),
hovermode = "x unified"
)
grafico
Questão 10
library(dplyr)
library(plotly)
library(stringr)
netflix_data <- read.csv("netflix_titles.csv")
filmes_2000_2010 <- netflix_data %>%
filter(type == "Movie" & release_year >= 2000 & release_year <= 2010)
filmes_2000_2010 <- filmes_2000_2010 %>%
mutate(primeiro_genero = str_split(listed_in, ",", simplify = TRUE)[, 1])
generos_interesse <- c("Dramas", "Action & Adventure", "Comedies")
filmes_2000_2010 <- filmes_2000_2010 %>%
filter(primeiro_genero %in% generos_interesse)
filmes_por_ano_genero <- filmes_2000_2010 %>%
group_by(release_year, primeiro_genero) %>%
summarise(quantidade = n(), .groups = 'drop')
grafico <- plot_ly(
data = filmes_por_ano_genero,
x = ~release_year,
y = ~quantidade,
color = ~primeiro_genero,
type = "bar",
colors = c("Dramas" = "blue", "Action & Adventure" = "red", "Comedies" = "green")
) %>%
layout(
title = "Quantidade de Filmes Lançados por Gênero (2000-2010)",
xaxis = list(title = "Ano"),
yaxis = list(title = "Quantidade de Filmes"),
barmode = "group" # Barras lado a lado
)
grafico