project.Rmd

```{r}
library(scales)
library(tidyverse)
library(modelr)
library(ggplot2)

city <- read_csv(gzfile("data/city_day_agg_cleaned.csv.gz"))

country <- read_csv(gzfile("data/country_day_agg_cleaned.csv.gz"))

```

## plot the world map of NO2,O3, and PM2.5

```{r}
# year_2020<- country %>% 
#   filter(date > "2019-12-31") 
#   
# three_year<- country %>% 
#   filter(date < "2020-01-01") 


# separate by parameter
year_2020_pm25 <- year_2020 %>% 
  filter(parameter =="pm25") %>% 
  group_by(countryCode) %>%
  summarize(avg = mean(mean,na.rm = TRUE))

three_yr_pm25 <- three_year %>% 
  filter(parameter =="pm25") %>% 
  group_by(countryCode) %>%
  summarize(avg = mean(mean,na.rm = TRUE))


year_2020_pm25_by_city <- city %>%
  filter(date > as.Date("2019-12-31")) %>%
  filter(parameter == "pm25") %>%
  mutate(year = date) %>% 
  group_by(city_id, date) %>%
  summarize(avg = mean(mean, na.rm = TRUE)) 

three_year_pm25_by_city <- city %>% 
  filter(date < "2020-01-01") %>% 
  filter(parameter =="pm25") %>% 
  group_by(city_id) %>%
  summarize(avg = mean(mean,na.rm = TRUE)) 


# use the is_2020_factor to plot two 
pm25 <- inner_join(year_2020_pm25_by_city, three_year_pm25_by_city, by = 'city_id')

# then use the factor for plotting two plots
  
ggplot(year_2020_pm25_by_city, aes(x = avg), fill = "pink") +
    geom_density(fill = is_2020) +
    scale_x_log10(label = comma) +
    xlab('PM2.5') +
    ylab('Data Density')





     

world <- map_data("world")
ggplot() +
  geom_map(
    data = world, map = world,
    aes(long, lat, map_id = region),
    color = "black", fill = "grey", size = 0.1
  ) +
  

```