''' Purpose: dataset nuance introduction
'''

best_sellers = [ # outer list (each inner list is a row)
    [ "Name",                             "Author",           "Language", "Date", "Sales" ],
    [ "Don Quixote",                      "de Cervantes",     "Spanish",  1605,   500000000 ],
    [ "A Tale of Two Cities",             "Dickens",          "English",  1859,   200000000 ],
    [ "The Lord of the Rings",            "Tolkien",          "English",  1954,   150000000 ],
    [ "The Little Prince",                "de Saint-Exupery", "French",   1943,   140000000 ],
    [ "Harry Potter",                     "Rowling",          "English",  1997,   120000000 ],
    [ "The Hobbit",                       "Tolkien",          "English",  1937,   100000000 ],
    [ "And Then There Were None",         "Christie",         "English",  1939,   100000000 ],
    [ "Dream of the Red Chamber",         "Xueqin",           "Chinese",  1754,   100000000 ],
    [ "Alice's Adventures in Wonderland", "Carroll",          "English",  1865,   100000000 ],
] # ending bracket of the outer list (table)

# print the dataset
for row in best_sellers :
    print( row ) # print each inner list one by one

print()

# separate out dataset elements
# best_sellers is the name of our table (our list of lists)
header = best_sellers[ 0 ] # the very first row is table[0]
books = best_sellers[ 1 : ] # every row after the first row (row[0])
# This is another way of slicing!
# Remember we can get multiple indexes from sequences.
# list1 = [[1,2],[3,4],[5,6]]
#            0      1    2
# list[0] is [1,2]
# list1[1: ] says give me index 1 all the way to the end! [[3,4],[5,6]]

# Python will know the types of values in your lists and data even
# it it's not displayed explicitly in the console when you print it.

# determine Sales column
sales_column = header.index( 'Sales' )

print( 'sales column:', sales_column )

print()

# determine total book solds amongs the top best sellers of all time
total = 0 # accumulator (start off with 0 and build up the total by
# adding the sales value to this total so that we sum up the
# sales value for all the books in our dataset)
for book in books : # loop through each row
    sold = book[ sales_column ] # get the column in our row (sales column)
    # book[sales_column] will look into column 4 (index of 'Sales') and get the
    # sales value within the row
    total = total + sold # add the sales value from the column in each
    # row to our total

billions_of_books = total / 1000000000

print( 'Total sold:', billions_of_books, 'billion' )