# load the starbucks nutrition data into the variable starbucks
starbucks <- read_csv("starbucks-menu-nutrition-drinks.csv", na = "-")

# rename some of the columns
starbucks <- starbucks %>% 
  rename(
    drink = X1,
    fat = 'Fat (g)',
    carb = 'Carb. (g)',
    fiber = 'Fiber (g)'
  )

# remove all rows with any missing (NA) value
starbucks <- na.omit(starbucks)

# read in the babies data (used importer with delimiter set to whitespaces
# to get this line)
babies <- read_table2("babies.csv")

# histogram of the mothers' ages
hist(babies$age)

# Are some motheres very old?  No, 99 was used to indicate the mother's age was
# missing.  You could either get rid of this row or replace 99 with the mean or 
# median age.

# To replace all values of 99 in the age column with the median of the age column:
# Store the median age in a variable
age_median <- median(babies$age)

# Replace any 99 in the age column with this median
babies$age[babies$age == 99] <- age_median

# Compute the probability of getting 6 successes out of 10 trails, 
# where the probability of success is 0.75
dbinom(x = 6, size = 10, prob = 0.75)