Twitter Data Visualization using ggplot2

twitter_data_viz_barplot_tweet_activities_part_one.R

# BARPLOT OF TWEETS - JOKO WIDODO
data.jokowi.df$created = ymd_hms(data.jokowi.df$created,
                                 tz = 'Asia/Jakarta')
# Another way to make 'Date' and 'Hour' variables
data.jokowi.df$date = date(data.jokowi.df$created)
data.jokowi.df$hour = hour(data.jokowi.df$created)
# Date 2019-05-29
data.jokowi.date1 = subset(x = data.jokowi.df,
                           date == '2019-05-29')
data.hour.date1 = data.frame(table(data.jokowi.date1$hour))
colnames(data.hour.date1) = c('Hour','Total.Tweets')

# Create data viz
ggplot(data.hour.date1)+
  geom_bar(aes(x = Hour,
               y = Total.Tweets,
               fill = I('blue')),
           stat = 'identity',
           alpha = 0.75,
           show.legend = FALSE)+
  geom_hline(yintercept = mean(data.hour.date1$Total.Tweets),
             col = I('black'),
             size = 1)+
  geom_text(aes(fontface = 'italic',
                label = paste('Average:',
                              ceiling(mean(data.hour.date1$Total.Tweets)),
                              'Tweets per hour'),
                x = 8,
                y = mean(data.hour.date1$Total.Tweets)+20),
            hjust = 'left',
            size = 4)+
  labs(title = 'Total Tweets per Hours - Joko Widodo',
       subtitle = '28 May 2019',
       caption = 'Twitter Crawling 28 - 29 May 2019')+
  xlab('Time of Day')+
  ylab('Total Tweets')+
  scale_fill_brewer(palette = 'Dark2')+
  theme_bw()

# BARPLOT OF TWEETS - PRABOWO SUBIANTO
data.prabowo.df$created = ymd_hms(data.prabowo.df$created,
                                  tz = 'Asia/Jakarta')
# Another way to make 'Date' and 'Hour' variables
data.prabowo.df$date = date(data.prabowo.df$created)
data.prabowo.df$hour = hour(data.prabowo.df$created)
# Date 2019-05-28
data.prabowo.date1 = subset(x = data.prabowo.df,
                            date == '2019-05-28')
data.hour.date1 = data.frame(table(data.prabowo.date1$hour))
colnames(data.hour.date1) = c('Hour','Total.Tweets')
# Date 2019-05-29
data.prabowo.date2 = subset(x = data.prabowo.df,
                            date == '2019-05-29')
data.hour.date2 = data.frame(table(data.prabowo.date2$hour))
colnames(data.hour.date2) = c('Hour','Total.Tweets')
data.hour.date3 = rbind(data.hour.date1,data.hour.date2)
data.hour.date3$Date = c(rep(x = '2019-05-28',
                             len = nrow(data.hour.date1)),
                         rep(x = '2019-05-29',
                             len = nrow(data.hour.date2)))
data.hour.date3$Labels = c(letters,'A','B')
data.hour.date3$Hour = as.character(data.hour.date3$Hour)
data.hour.date3$Hour = as.numeric(data.hour.date3$Hour)
# Data pre-processing
for (i in 1:nrow(data.hour.date3)) {
  if (i%%2 == 0) {
    data.hour.date3[i,'Hour'] = ''
  }
  if (i%%2 == 1) {
    data.hour.date3[i,'Hour'] = data.hour.date3[i,'Hour']
  }
}
data.hour.date3$Hour = as.factor(data.hour.date3$Hour)

# Data viz
ggplot(data.hour.date3)+
  geom_bar(aes(x = Labels,
               y = Total.Tweets,
               fill = Date),
           stat = 'identity',
           alpha = 0.75,
           show.legend = TRUE)+
  geom_hline(yintercept = mean(data.hour.date3$Total.Tweets),
             col = I('black'),
             size = 1)+
  geom_text(aes(fontface = 'italic',
                label = paste('Average:',
                              ceiling(mean(data.hour.date3$Total.Tweets)),
                              'Tweets per hour'),
                x = 5,
                y = mean(data.hour.date3$Total.Tweets)+6),
            hjust = 'left',
            size = 3.8)+
  scale_x_discrete(limits = data.hour.date3$Labels,
                   labels = data.hour.date3$Hour)+
  labs(title = 'Total Tweets per Hours - Prabowo Subianto',
       subtitle = '28 - 29 May 2019',
       caption = 'Twitter Crawling 28 - 29 May 2019')+
  xlab('Time of Day')+
  ylab('Total Tweets')+
  ylim(c(0,100))+
  theme_bw()+
  theme(legend.position = 'bottom',
        legend.title = element_blank())+
  scale_fill_brewer(palette = 'Dark2')