R covid 19 data analytics projects part 2

R covid 19 data analytics projects part 1

R covid 19 data analytics projects part 2

#  And the rest of the world?

# Filter confirmed_cases_china_vs_world for not China

not_china <- confirmed_cases_china_vs_world %>%

  filter(is_china == "Not China")

# Using not_china, draw a line plot cum_cases vs. date

# Add a smooth trend line using linear regression, no error bars

plt_not_china_trend_lin <- ggplot(not_china, aes(date, cum_cases)) +

  geom_line() +

  geom_smooth(method = "lm", se = FALSE) +

  ylab("Cumulative confirmed cases")

# See the result

plt_not_china_trend_lin  

# Adding a logarithmic scale

# Modify the plot to use a logarithmic scale on the y-axis

plt_not_china_trend_lin + 

  scale_y_log10()

#   Which countries outside of China have been hit hardest?

# Run this to get the data for each country

confirmed_cases_by_country <- read_csv("confirmed_cases_by_country.csv")

glimpse(confirmed_cases_by_country)

# Group by country, summarize to calculate total cases, find the top 7

top_countries_by_total_cases <- confirmed_cases_by_country %>%

  group_by(country) %>%

  summarize(total_cases = max(cum_cases)) %>%

  top_n(7, total_cases)

# See the result

top_countries_by_total_cases

Output

 A tibble: 7 x 2

  country      total_cases

  <chr>              <dbl>

1 France              7699

2 Germany             9257

3 Iran               16169

4 Italy              31506

5 Korea, South        8320

6 Spain              11748

7 US                  6421

# Plotting hardest hit countries as of Mid-March 2020

# Read in the dataset from datasets/confirmed_cases_top7_outside_china.csv

confirmed_cases_top7_outside_china <- read_csv("confirmed_cases_top7_outside_china.csv")

# Glimpse the contents of confirmed_cases_top7_outside_china

glimpse(confirmed_cases_top7_outside_china)

# Using confirmed_cases_top7_outside_china, draw a line plot of

# cum_cases vs. date, grouped and colored by country

ggplot(confirmed_cases_top7_outside_china, aes(date, cum_cases, color = country, group = country)) +

  geom_line() +

  ylab("Cumulative confirmed cases")