Sprawozdanie 5

dane %>%
  filter(Languages=="Polish") %>%
ggplot(aes(x = IMDb.Score)) +
  geom_histogram(
    aes(fill = Series.or.Movie)
    ,bins = 10
    ,color = 'blue'
  ) +
  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') 

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'))

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))

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 = '')

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 = 'black'
    ,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 = 'purple'
    ,size = 1
  ) +
  theme(legend.position = 'none')

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')

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')

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

ggplot(germancredit, aes(x = credit.amount)) +
  geom_histogram(
    ,bins = 10
    ,fill = 'purple'
    ,colour = 'black'
  ) +
  labs(title = 'Wysokość kredytu')

ggplot(germancredit, aes(x = age.in.years, y=creditability)) +
  geom_boxplot(aes(fill = ) ,outlier.alpha = 0.25) +
  theme(axis.text.x = element_text('age.in.years'), axis.title.x = element_text('age.in.years')) +
  labs(title = 'Ryzyko kredytu według wieku', fill = 'Wiek')

ggplot(germancredit, aes(x = age.in.years, y = credit.amount)) +
  geom_point(aes(color = creditability)) +
geom_smooth(
    method = 'lm'
    ,se = FALSE
  ) +
  theme(legend.position = c(0.2, 0.8))

dane <- germancredit
Długość<- dane$duration.in.month
Powód<- dane$purpose
wysokosc.kredytu <- dane$credit.amount
zdolność.kredytowa <- dane$creditability

dane <- germancredit %>%
  group_by(creditability) %>%
  summarise(count = length(creditability), `duration.mean` = NA ,`credit.mean` = NA)

for (i in 1:nrow(dane)) {
 dane$duration.mean[i] <- germancredit %>% 
    filter(str_detect(zdolność.kredytowa, dane$creditability[i] %>%
                        as.character() %>% eval())) %>%
    select(duration.in.month) %>% unlist() %>% mean(na.rm = TRUE)
  
   dane$credit.mean[i] <- germancredit %>% 
    filter(str_detect(zdolność.kredytowa, dane$creditability[i] %>%
                        as.character() %>% eval())) %>%
    select(credit.amount) %>% unlist() %>% mean(na.rm = TRUE)
}

ggplot() +
  geom_point(aes(x=Powód, y=wysokosc.kredytu, color=Długość, label='zdolność.kredytowa')) +
  xlab("Powód zaciągnięcia kredytu") + ylab("Wysokość kredytu")+
  theme(axis.text.x = element_text(size = 10,angle = 45, vjust = 1, hjust = 1 ), axis.title = element_text(size = 13))+
  geom_text_repel()

data("germancredit")
ggplot(data=germancredit, aes(x=credit.amount, y=purpose, colour=creditability)) + geom_point() +
facet_grid(creditability ~ .) +
facet_wrap(vars(savings.account.and.bonds), nrow = 7, scales = 'free')