''' Purpose: for a user-specified dataset, dataset
                 a user-specified column label, label
                 a column value, key
             counts the number of rows whose column values equals key
'''

# get a hold of helpful web functions
import url

# specify base web folder for datasets
CSV_REPOSITORY = 'http://www.cs.virginia.edu/~cs1112/datasets/csv/'

# get dataset of interest
reply = input( 'Enter the name of a data set: ' )

name = reply.strip()

link = CSV_REPOSITORY + name

dataset = url.get_dataset( link )

# get label for the column of interest
reply = input( 'Enter column label for the data set: ' )

label = reply.strip()

# get key value for column of interest
# the value in the column label we want to find
# we also assume that the value is a string
reply = input( 'Enter the key: ' )

key = reply.strip()

print()

# identify header and data from the dataset
header = dataset[ 0 ]

table  = dataset[ 1 : ]

# get the index i of the dataset column of interest
# what is the index of the column that we want to look in
# the variable <label> holds the name of the column that we care about
# we want to find where this column is in the list <header> --> find the index of the label in this list <header>
i = header.index( label )   # use index() for lists
                            # tell me where the index of the string in <label> within the list <header>

print( i )  # here, we know which column we care about and where it is in the list header
# header = ['ID', 'State', 'GWDB', 'When']
# if we want to know which column contains the information for When president's day is,
# we use header.index( 'When' ) to find the index position within the header list --> this is where
# the column is for the rest of the data as well
# 'When' is stored in the variable <label>
# 'When' is at index 3 in the list header
# Therefore, for the rest of the data, info on President's day is in column 3 of every row

# get from dataset, a list of values for the column of interest
# since we know where the column is now (in <i>)
# we want to access the value at index <i> for EACH row
# then we want to build up a list of these values (list accumulation)
ith_column = []   # this list will store the values within the ith column in table

# for each row in the table, we get the value at the ith column
# ith column is where our column of interest is
# then we append the value to our list accumulator <ith_column>
for row in table:
    # row[i] == ith value in the row == the column value we're interested in
    cell = row[i]

    # for each row, we want to get the value at index i in the row
    # we can do indexing with row because row is a list in itself
    # if row = ['a', 'b', 'c'] and i = 2
    # cell = row[i] == row[2] == 'c'
    # then we append this cell into ith_column --> ith_column = ['c']
    # if next row = ['d', 'e', 'f'] and i = 2
    # cell = row[i] == row[2] == 'f'
    # then we append this cell into ith_column --> ith_column = ['c', 'f']
    # so on until we run out of rows

    # add this new cell to our list accumulator
    ith_column.append( cell )
    # ith_column.append( row[i] )  # same thing as line 78

print( 'ith_column =', ith_column )

# count from that list of values (ith_column), the number of values equalling the key (the key string we're
# interested in)
# some_list.count( something ) --> return how many times <something> appears in <some_list>
# <something> has to appear exactly in <some_list>
# now we have a list of the values from the column of interest, <ith_column>, we can use count() to find
# the key value
counted_values = ith_column.count( key )
# <key> is not in quotes because it is a variable --> we want the value in <key> not the string 'key'

# count( x ) works on strings and lists
#   if string, x must be a string/char --> counts how many times x appears in the string
#   if list, counts how many times x appears in the list as an element exactly as x appears
#       some_list = [ 'a', 'ab', 'abc' ]
#       count_a = some_list.count( 'a' ) --> count_a = 1 (not 3)


# print the total
print( 'Number of occurrences of', key, '=', counted_values )

# for value in i:     # i is a single number, not a sequence, so for loop will only execute once for value = i

# since we've gotten all the values within the ith column from table
# we can go through each value in that column in another for loop
# for whatever you need to do
for value in ith_column:
    # do something
    pass