exercicio 12
hudo
2024-08-26
EXERCICIO 12
Carregando bibliotecas que usarei
library(ggplot2)
library(plotly)## Warning: package 'plotly' was built under R version 4.3.3library(dplyr)
library(readr)
library(tidyr)Questões
Questao 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)
plot(clock, MRT_1F, type = "o", col = "black", pch = 16, lty = 1, xlab = "Time between requests (seconds)", ylab = "Response Time (sec)")
lines(clock, MRT_3F, type = "o", col = "yellow", pch = 17, lty = 2)
lines(clock, MRT_5F, type = "o", col = "red", pch = 18, lty = 3)
lines(clock, MRT_10F, type = "o", col = "blue", pch = 19, lty = 4)
lines(clock, MRT_15F, type = "o", col = "purple", pch = 15, lty = 5)
lines(clock, MRT_sem_F, type = "o", col = "green", pch = 8, lty = 6)
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(16, 17, 18, 19, 15, 8),
lty = 1:6, # Tipos de linha diferentes
title = "Categorias")
layout(matrix(c(1, 2, 3, 4, 5, 6), nrow = 3, ncol = 2, byrow = TRUE))
barplot(
height = rbind(MRT_sem_F, MRT_1F),
beside = TRUE,
col = c("#E6E6E6", "#666666"),
log = "y",
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 = 0.8)
barplot(
height = rbind(MRT_sem_F, MRT_3F),
beside = TRUE,
col = c("#E6E6E6", "#666666"),
log = "y",
names.arg = clock,
xlab = "Time between things requests",
ylab = "Response time (s)"
)
legend("topright",
legend = c("w/o Fog", "3 Fog"),
fill = c("#E6E6E6", "#666666"),
cex = 0.8)
barplot(
height = rbind(MRT_sem_F, MRT_5F),
beside = TRUE,
col = c("#E6E6E6", "#666666"),
log = "y",
names.arg = clock,
xlab = "Time between things requests",
ylab = "Response time (s)"
)
legend("topright",
legend = c("w/o Fog", "5 Fog"),
fill = c("#E6E6E6", "#666666"),
cex = 0.8)
barplot(
height = rbind(MRT_sem_F, MRT_10F),
beside = TRUE,
col = c("#E6E6E6", "#666666"),
log = "y",
names.arg = clock,
xlab = "Time between things requests",
ylab = "Response time (s)"
)
legend("topright",
legend = c("w/o Fog", "10 Fog"),
fill = c("#E6E6E6", "#666666"),
cex = 0.8)
barplot(
height = rbind(MRT_sem_F, MRT_15F),
beside = TRUE,
col = c("#E6E6E6", "#666666"),
log = "y",
names.arg = clock,
xlab = "Time between things requests",
ylab = "Response time (s)"
)
legend("topright",
legend = c("w/o Fog", "15 Fog"),
fill = c("#E6E6E6", "#666666"),
cex = 0.8)
Questao 2
dados <- data.frame(
Quality_Rating = c("Good", "Very Good", "Excellent"),
`10_19` = c(53.8, 43.6, 2.6),
`20_29` = c(33.9, 54.2, 11.9),
`30_39` = c(2.6, 60.5, 36.8),
`40_49` = c(0.0, 21.4, 78.6)
)
barplot(as.matrix(dados[, -1]),
col = c("skyblue", "orange", "green"),
names.arg = c("10-19", "20-29", "30-39", "40-49"),
main = "Classificação da Qualidade da Refeição por Faixa de Preço",
xlab = "Faixa de Preço (USD)",
ylab = "Porcentagem")
legend("topright", legend = dados$Quality_Rating,
fill = c("skyblue", "orange", "green"), title = "Qualidade")
Questao 3
data(airquality)
maio <-subset(airquality,Month==5)
maio$TempCelsius <- (maio$Temp-32)/1.8
hist(maio$TempCelsius,main = "Histograma das Temperaturas em Maio",
xlab="Temperatura (Celsisus)",ylab="Frequencia",col="lightblue")
hist(maio$TempCelsius,main = "Histograma das Temperaturas em Maio com Curava de Densidade",
xlab="Temperatura (Celsisus)",ylab="Frequencia",col="lightblue",probability=TRUE)
lines(density(maio$TempCelsius),col = "red")
Questao 4
sales <- read.table("https://training-course-material.com/images/8/8f/Sales.txt",header=TRUE)
cores <- rainbow(nrow(sales))
total_sales <- sum(sales$SALES)
sales$PERCENTAGE <- round(sales$SALES / total_sales * 100, 1)
sales## COUNTRY SALES PERCENTAGE
## 1 US 340 11.9
## 2 UK 290 10.1
## 3 France 510 17.8
## 4 Poland 820 28.7
## 5 Japan 120 4.2
## 6 China 780 27.3pie(sales$SALES,
labels = sales$PERCENTAGE,
col = cores,
main = "Distribuição de Vendas por País")
legend("topright",
legend = sales$COUNTRY,
fill = cores,
cex = 0.8)
Questao 5
data(InsectSprays)
boxplot(count ~ spray,
data = InsectSprays,
outline = FALSE, # Remove os outliers
col = "yellow",
main = "Contagem de Insetos por Tipo de Inseticida",
xlab = "Tipo de Inseticida",
ylab = "Contagem de Insetos")
Questao 6
Aqui vai o conteúdo da Questão 6.
Questao 7
netflix_data <- read.csv("netflix_titles.csv")
single_country_data <- netflix_data %>%
filter(!grepl(",", country)) %>%
filter(!is.na(country) & country != "") %>%
count(country) %>%
arrange(desc(n)) %>%
slice_max(order_by = n, n = 10)
fig <- plot_ly(single_country_data,
labels = ~country,
values = ~n,
type = 'pie',
textinfo = 'label+percent',
insidetextorientation = 'radial')
fig <- fig %>% layout(title = 'Top 10 países com mais conteúdos na plataforma')
figForam mostrados 11 países pois tem um empate
Questao 8
fig_table <- 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 = rbind(single_country_data$country, single_country_data$n),
align = "center"
)
)
fig_tableQuestao 9
netflix_data2 <- netflix_data %>%
mutate(decade = (release_year %/% 10) * 10)
# pegando dados de filmes
movies_data <- netflix_data2 %>%
filter(type == "Movie") %>%
count(decade)
# pegnado dads de series de tv
series_data <- netflix_data2 %>%
filter(type == "TV Show") %>%
count(decade)
fig <- plot_ly() %>%
add_trace(data = movies_data,
x = ~decade,
y = ~n,
type = 'scatter',
mode = 'lines+markers',
name = 'Movies',
line = list(color = 'orange')) %>%
add_trace(data = series_data,
x = ~decade,
y = ~n,
type = 'scatter',
mode = 'lines+markers',
name = 'TV Series',
line = list(color = 'blue')) %>%
layout(title = 'Quantidade de Conteúdo por Década no Netflix',
xaxis = list(title = 'Década'),
yaxis = list(title = 'Qtd. de Conteúdo'))
figQuestao 10
netflix_data3 <- netflix_data %>%
filter(release_year >= 2000 & release_year <= 2010)
# Extract the first genre listed
netflix_data3$first_genre <- sapply(strsplit(netflix_data3$listed_in, ","), `[`, 1)
# Filter relevant genres
genres <- c("Dramas", "Action & Adventure", "Comedies")
netflix_data3 <- netflix_data3 %>%
filter(first_genre %in% genres)
# Group by year and genre, then count occurrences
data <- netflix_data3 %>%
group_by(release_year, first_genre) %>%
summarize(count = n(), .groups = 'drop') %>%
pivot_wider(names_from = first_genre, values_from = count, values_fill = 0)
# Create the plotly bar chart
fig <- plot_ly(data, x = ~release_year, y = ~Dramas, type = 'bar', name = 'Dramas')
fig <- fig %>% add_trace(y = ~`Action & Adventure`, name = 'Action & Adventure')
fig <- fig %>% add_trace(y = ~Comedies, name = 'Comedies')
# Layout adjustments
fig <- fig %>% layout(
barmode = 'group',
xaxis = list(title = "Ano de Lançamento"),
yaxis = list(title = "Qnt. de Lançamentos"),
title = "Quantidade de Filmes Lançados por Gênero (2000-2010)"
)
# Show the plot
fig