%
# VARIABLE FOR AGE OF GAME
mutate(release_year = substring(release_date, 8, 12), # EXTRACT YEAR
release_year = as.numeric(str_trim(release_year)),
release_year = case_when(release_year == 5 ~ 2015, # INCORRECT DATA POINT
TRUE ~ release_year),
age = 2019 - release_year) %>%
# VARIABLE FOR MIN/MAX NUMBER OF OWNERS
mutate(max_owners = str_trim(word(owners, 2, sep = "\\..")),
max_owners = as.numeric(str_replace_all(max_owners, ",", "")),
min_owners = str_trim(word(owners, 1, sep = "\\..")),
min_owners = as.numeric(str_replace_all(min_owners, ",", ""))) %>%
# REMOVE VALUES WITH INCONSISTENT RELEASE_DATE FORMAT (n=37)
filter(age < 15) %>%
# FILTER OUT STUDIO SOFTWARE
filter(price < 150)
Visualize data
Question: how many people still play games that are X years old (on Steam) ?" />
