Plotting Daily New COVID19 Cases in the US

daily_cases_us.R

# Plotting COVID19 daily new cases in the US
# Using the following libraries:
# coronavirus for data
# plotly for dataviz
# dplyr for data manipulation
library(coronavirus)
library(plotly)
library(dplyr)

df <- refresh_coronavirus_jhu()

head(df)

max(df$date)


# Filter the data for US confirmed cases
df_us <- df %>% filter(location == "US",
                              data_type == "cases_new") %>%
  select(date, cases = value) %>%
  arrange(date)

# Creating lags for moving average
d <- lapply(0:6, function(i){
  d <- df_us %>% select(date, cases) %>%
    mutate(cases_lag = lag(cases, n = i),
                  lag = i)
  
  return(d)
}) %>%
  dplyr::bind_rows() %>%
  dplyr::group_by(date) %>%
  dplyr::summarise(cases = mean(cases), 
                   cases_ma = mean(cases_lag, na.rm = TRUE))
  
head(d)

# Plot setting
mv_color <- "red"
bg_color <- "#fdfffc"

# Plotting the cases

plot_ly(data = d,
                x = ~ date,
                y = ~ cases,
                type = "scatter",
                mode = "markers",
                name = "Daily New Cases") %>%
  add_lines(x = ~ date, y = ~ cases_ma,
                    line = list(color = mv_color, width = 3),
                    name = "7 Days Moving Average") %>%
  layout(title = "US Daily New COVID-19 Cases",
                 yaxis = list(title = "Cases",
                              showgrid = TRUE),
                 xaxis = list(title = "Source: Johns Hopkins University Center for Systems Science and Engineering",
                              showgrid = FALSE),
                 legend = list(x = 0.1, y = 0.9),
                 paper_bgcolor= bg_color,
                 plot_bgcolor= bg_color,
                 margin = list(b = 65, t = 45, r = 40, l = 40))