YiLi225

###### Process data and subset on countries
# sort(unique(series_df$Country.Region))
selected_countries = c('China', 'Italy', 'US', 'Iran')

## sum group by country by status 
date_col_idx = which(grepl('X', colnames(series_df)))

country_data = series_df %>%
  filter(Country.Region %in% selected_countries) %>%
  select(c(Country.Region, Status, colnames(.)[date_col_idx])) %>%

YiLi225

### check whether the column names of 3 datasets match up 
columns = sapply(series_data_, colnames)

### !!! The code below certainly works for datasets with small numbers of columns, 
### However, what if we have 1000 columns to do pair-wise checking, 
### or additional columns being added to the datasource? 
all(columns[, 1] == columns[, 2])
all(columns[, 2] == columns[, 3])
all(columns[, 1] == columns[, 3])

YiLi225

#### Append a list of datasets into one single data frame 
series_df = do.call(rbind, series_data_)

##### (optional) Recode the values 
series_df[which(series_df$Country.Region == 'United Kingdom'), 'Country.Region'] = 'UK'
series_df[which(series_df$Country.Region == 'Korea, South'), 'Country.Region'] = 'Korea S'

YiLi225

#### helper function for trajectory line chart:
#### note: there is global variable in this function!!!
helper_vis_continuous <- function(dat = country_data, country = 'US') {
  ## vertical structure for ggplot
  current_dat = dat %>%
    filter(Country.Region == country) %>%
    reshape2::melt(.) %>%
    set_colnames(c('Country', 'Status', 'Date', 'Total'))

  ## starts with the date when 1st case was confirmed for this country 

YiLi225

#### Select the countries for plotting, and convert wide format to long
current_dat = country_data %>%
  filter(Country.Region %in% selected_countries) %>%
  reshape2::melt(.) %>%
  set_colnames(c('Country', 'Status', 'Date', 'Total'))

## starts with the date when 1st case confirmed
find_case1_onwards <- function(country_name) {
  case1_idx = which(current_dat[current_dat$Country == country_name, 'Total'] > 0)[1]
  

YiLi225

#### Plotly with ggplot facet_wrap
country_plot = ggplot(dat = current_dat,
                      aes_string(x = 'Date', y = 'Total', color = 'Status', group = 'Status', linetype = 'Status')) +
  geom_line(lwd = 1.2) +
  
  facet_wrap(~ Country, scales = "free") +
  
  labs(title = sprintf('Trajectories of the Status of Coronavirus \n')) +
  xlab('Date') + ylab('Total Numbers') +
  theme_bw() +

YiLi225

####### Heatmap from 2/22 to 3/28
library(gplots)
my_palette <- colorRampPalette(c("light blue", "black", "red"))(n = 1000)

heatmap_dat = country_data %>%
  filter(Status == 'confirmed')
  
## subset: after Feb 22nd
col_idx = which(colnames(heatmap_dat) == '2_22_20')
heatmap_dat = heatmap_dat[, c(1, 2, col_idx:ncol(heatmap_dat))]

YiLi225

#####======= static and animated plots
total_text_y = 0.87*(max(confirmed_formatted$Total))
panel_size_y = max(confirmed_formatted$Total) * 1.15  
vline_original_y = seq(floor(max(confirmed_formatted$Total)/8), 
                       max(confirmed_formatted$Total), by = floor(max(confirmed_formatted$Total)/8))

country_font_size = 10
bar_end_num_size = 11

staticplot = ggplot(confirmed_formatted, 

YiLi225

#### Specify the transition length and ease_aes to give it a smoother transition 
current_state_len = 0 
current_transition_len = 3  

anim = staticplot + 
  transition_states(Date, transition_length = current_transition_len, state_length = current_state_len) + 
  ease_aes('cubic-in-out') +   
  view_follow(fixed_x = TRUE, fixed_y = c(-10, NA))  + 
  labs(title = 'Spead of Confirmed Cases per day: {closest_state}',
       subtitle = 'Top 10 Countries/Regions',

YiLi225

######## Point to your data directory 
series_all_files = list.files(series_data_dir)
series_data_files = series_all_files[grepl('.csv', series_all_files)]

print(sprintf('Total data files = %s', length(series_data_files)))

series_data_ = lapply(series_data_files, 
                      function(i) {
                        dat = read.csv(paste0(series_data_dir, '/', i), stringsAsFactors = FALSE)
                        file_ = gsub('.csv', '', i)