Wykresy zmiennej ilościowej

dane %>%
  filter(Languages=="Polish") %>%
ggplot(aes(x = IMDb.Score)) +
  geom_histogram(
    aes(fill = Series.or.Movie)
    ,bins = 10
    ,color = 'black'
  ) +
  labs(title = 'Polskie filmy i seriale')

ggplot(dane, aes(x=IMDb.Score, fill=Series.or.Movie)) +
  geom_density(alpha=.25) +
  labs(title = 'Gęstość rozkładu ocen') 

Wykresy zmiennej jakościowej

dane %>%
  filter(Runtime != '') %>%
  ggplot(aes(Runtime)) +
  geom_bar(aes(fill = Runtime))+
  scale_x_discrete(
    limits = c('< 30 minutes'
               ,'30-60 mins'
               ,'1-2 hour'
               ,'> 2 hrs')
    ,labels = function(x) str_wrap(x, width = 8)
  ) +
  theme(
    legend.position = 'none'
    ,axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1)
  ) +
  scale_fill_manual(values = brewer.pal(4, 'Accent'))

Wykresy dwóch zmiennych ilościowych

ggplot(dane, aes(x = IMDb.Score, y = IMDb.Votes)) +
  geom_point(aes(color = Series.or.Movie)) +
  geom_smooth(
    method = 'loess'
    ,se = FALSE
  ) +
  theme(legend.position = c(0.2, 0.8))

Wykresy dwóch zmiennych jakościowych

dane %>%
  filter(Runtime != '') %>%
  ggplot(aes(x = Series.or.Movie, y = Runtime)) +
  geom_jitter(aes(color = Runtime)) +
  theme(legend.position = 'none') +
  scale_y_discrete(
    limits = c('< 30 minutes'
               ,'30-60 mins'
               ,'1-2 hour'
               ,'> 2 hrs')
  ) +
  labs(x = '', y = '')

Wykresy zmiennej ilościowej vs zmiennej jakościowej

medians = dane %>%
  group_by(Series.or.Movie) %>%
  summarize(m = median(IMDb.Score, na.rm = TRUE))

ggplot(dane, aes(x = Series.or.Movie, y = IMDb.Score)) +
  geom_boxplot(
    aes(fill = Series.or.Movie)
    ,outlier.alpha = 0.25
  ) +
  geom_text(
    data = medians
    ,aes(x = Series.or.Movie, y = m, label = m)
    ,color = 'blue'
    ,hjust = 7
  ) +
  stat_boxplot(geom ='errorbar', position = 'dodge') +
  stat_summary(
    aes(ymax = ..y.., ymin = ..y..)
    ,fun = mean
    ,geom = 'errorbar'
    ,width = .75
    ,linetype = 'solid'
    ,position = 'dodge'
    ,color = 'white'
    ,size = 1
  ) +
  theme(legend.position = 'none')

Wykresy bąbelkowe

gatunki <- dane %>% 
  select(Genre) %>% 
  unlist() %>% 
  strsplit(',') %>%
  unlist() %>% 
  trimws() %>% 
  table() %>% 
  as.data.frame()

gatunki <- data.frame(
  Gatunek = gatunki$.
  ,`Count` = gatunki$Freq
  ,`IMDb Score Average` = NA
  ,`IMDb Votes Average` = NA
)

for (i in 1:nrow(gatunki)) {
  gatunki$IMDb.Score.Average[i] <- dane %>% 
    filter(str_detect(Genre, gatunki$Gatunek[i] %>%
                        as.character() %>% eval())) %>%
    select(IMDb.Score) %>% unlist() %>% mean(na.rm = TRUE)
  
  gatunki$IMDb.Votes.Average[i] <- dane %>% 
    filter(str_detect(Genre, gatunki$Gatunek[i] %>%
                        as.character() %>% eval())) %>%
    select(IMDb.Votes) %>% unlist() %>% mean(na.rm = TRUE)
}

ggplot(gatunki, aes(IMDb.Score.Average, IMDb.Votes.Average, label = Gatunek)) +
  geom_point(aes(color = Gatunek, size = Count)) +
  geom_text_repel() +
  theme(legend.position = 'none')

Kilka wykresów na jednym panelu

dane %>%
  filter(Runtime != '') %>%
  ggplot(aes(x = IMDb.Score)) +
  geom_histogram(
    aes(fill = Series.or.Movie)
    ,bins = 50
    ,color = 'black'
  ) +
  # facet_grid(.~ Series.or.Movie) +
  # facet_grid(Series.or.Movie ~ .) +
  # facet_grid(Runtime ~ Series.or.Movie, scales = 'free') +
  # facet_wrap(vars(Series.or.Movie), ncol = 2) +
   facet_wrap(vars(Series.or.Movie), nrow = 2) +
  # facet_wrap(vars(Series.or.Movie, Runtime), nrow = 2, scales = 'free') +
  theme(legend.position = 'none')

Zadanie domowe

Korzystając z paczki danych “germancredit” dotyczącą oceny kredytowej (creditability) wybranych klientów pewnego banku wykreśl zmienną ilościową (np. wysokość kredytu); zmienną jakościową (ryzyko); ilościową wg jakościowej (np. wiek wg ryzyka); 2 ilościowe (wiek wg wysokości kredytu) oraz wykres bąbelkowy wg własnego pomysłu + przedstaw kilka wykresów na 1 panelu.

data("germancredit")
attach(germancredit)
# http://archive.ics.uci.edu/ml/datasets/Statlog+(German+Credit+Data)

Wykres 1 zmiennej ilościowej -

dane2 <- germancredit
attach(dane2)

## Następujące obiekty zostały zakryte z germancredit:
## 
##     age.in.years, credit.amount, credit.history, creditability,
##     duration.in.month, foreign.worker, housing,
##     installment.rate.in.percentage.of.disposable.income, job,
##     number.of.existing.credits.at.this.bank,
##     number.of.people.being.liable.to.provide.maintenance.for,
##     other.debtors.or.guarantors, other.installment.plans,
##     personal.status.and.sex, present.employment.since,
##     present.residence.since, property, purpose,
##     savings.account.and.bonds, status.of.existing.checking.account,
##     telephone

dane2 %>%
ggplot(aes(x = credit.amount)) +
  geom_histogram(color = 'red') +
  labs(title = 'WYSOKOŚĆ KREDYTÓW')

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

dane2 %>%
  ggplot(aes(creditability)) +
  geom_bar(aes(fill = creditability))+
  scale_x_discrete(
    limits = c('good'
               ,'bad')
    ,labels = function(x) str_wrap(x, width = 4)
  ) +
  theme(
    legend.position = 'none'
    ,axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1)
  ) +
  scale_fill_manual(values = brewer.pal(4, 'Accent'))+
  labs(title = 'ZDOLNOŚĆ KREDYTOWA') 

medians = dane2 %>%
  group_by(creditability) %>%
  summarize(m = median(age.in.years, na.rm = TRUE))

ggplot(dane2, aes(x = creditability , y = age.in.years)) +
  geom_boxplot(
    aes(fill = creditability)
    ,outlier.alpha = 0.25
  ) +
  geom_text(
    data = medians
    ,aes(x = creditability, y = m, label = m)
    ,color = 'green'
    ,hjust = 7
  ) +
  stat_boxplot(geom ='errorbar', position = 'dodge') +
  stat_summary(
    aes(ymax = ..y.., ymin = ..y..)
    ,fun = mean
    ,geom = 'errorbar'
    ,width = .75
    ,linetype = 'solid'
    ,position = 'dodge'
    ,color = 'red'
    ,size = 1
  ) +
  theme(legend.position = 'none')+
  labs(title = 'Zdolność kredyowa a wiek') 

ggplot(dane2, aes(x = age.in.years, y = credit.amount)) +
  geom_point()+
  geom_smooth(
    method = 'lm'
    ,se = FALSE
  ) +
  theme(legend.position = c(0.2, 0.8))+
  labs(title = 'Wysokość kredytu a wiek') 

## `geom_smooth()` using formula = 'y ~ x'

cel <- dane2$purpose %>%
  unlist() %>%
  table() %>%
  as.data.frame()


cel <- data.frame(
  Purpose = cel$.
  ,`Count` = cel$Freq
  ,`Credit amount average` = NA
  ,`Age in years average` = NA
)

for (i in 1:nrow(cel)) {
  cel$Credit.amount.average[i] <- dane2 %>% 
    filter(str_detect(purpose, cel$Purpose[i] %>%
                        as.character() %>% eval())) %>%
    select(credit.amount) %>% unlist() %>% mean(na.rm = TRUE)
  
  cel$Age.in.years.average[i] <- dane2 %>% 
    filter(str_detect(purpose, cel$Purpose[i] %>%
                        as.character() %>% eval())) %>%
    select(age.in.years) %>% unlist() %>% mean(na.rm = TRUE)
}  

ggplot(cel, aes(Age.in.years.average, Credit.amount.average, label = Purpose)) +
  geom_point(aes(color = Purpose, size = Count)) +
  geom_text_repel() +
  theme(legend.position = 'none')+
  labs(title = 'Wiek kredytobiorców względem wysokości kredytu i jego przeznaczenia') 

## Warning: Removed 2 rows containing missing values (`geom_point()`).

## Warning: Removed 2 rows containing missing values (`geom_text_repel()`).

dane2 %>%
  filter(credit.amount != '') %>%
  ggplot(aes(x = credit.amount)) +
  geom_histogram(
    aes(fill = credit.amount)
    ,bins = 50
    ,color = 'red'
  ) +
  facet_wrap(vars(purpose), ncol = 2) +
  theme(legend.position = 'none')+
  labs(title = 'WYSOKOŚĆ KREDYTU WZGLĘDEM JEGO PRZEZNACZENIA') 

## Warning: The following aesthetics were dropped during statistical transformation: fill
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
##   the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
##   variable into a factor?
## The following aesthetics were dropped during statistical transformation: fill
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
##   the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
##   variable into a factor?
## The following aesthetics were dropped during statistical transformation: fill
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
##   the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
##   variable into a factor?
## The following aesthetics were dropped during statistical transformation: fill
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
##   the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
##   variable into a factor?
## The following aesthetics were dropped during statistical transformation: fill
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
##   the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
##   variable into a factor?
## The following aesthetics were dropped during statistical transformation: fill
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
##   the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
##   variable into a factor?
## The following aesthetics were dropped during statistical transformation: fill
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
##   the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
##   variable into a factor?
## The following aesthetics were dropped during statistical transformation: fill
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
##   the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
##   variable into a factor?
## The following aesthetics were dropped during statistical transformation: fill
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
##   the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
##   variable into a factor?
## The following aesthetics were dropped during statistical transformation: fill
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
##   the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
##   variable into a factor?