''' Purpose: for user-specified dataset, and two user-specified column labels
        column1 and column2:
            determines the minimum value min2 in column2 in the dataset
            determines min_label -- the column1 value whose column2 value equals min2
            prints labeled explanatory information about min2
'''

# get ahold 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_and_convert_csv_dataset( link )  # what is dataset?

# get the labels for the columns of interest
reply = input( 'Enter a column label for the data set: ' )
column1 = reply.strip()

reply = input( 'Enter a column label for the data set: ' )  # what happens when you enter different information here?
column2 = reply.strip()

print()

# header specifies column labels
header = dataset[ 0 ]  # which row does this represent?

data = dataset[ 1: ] # which rows does data represent? where is index 1?

# scan the column that the user indicated interest in
c1 = header.index( column1 )  # what does the index function do?
c2 = header.index( column2 )

cells = []  # a list to help us keep track of all the cells
for each_row in data:
    cell = each_row[ c2 ]  # what data type is this? what information does cell represent? what data type is this?
    cells.append( cell )

min_cells = min( cells )

# we have the actual minimum, but we want the column1 information related to min_cells
spot = cells.index( min_cells )  # what does spot represent? what does it tell us?

row_interested_in = data[ spot ] # get corresponding row from the dataset

label = row_interested_in[ c1 ]  # get the column1 cell (i.e. at index c1 )

print( "The min", column2, "for the dataset is", min_cells )
print( "It is in the row whose", column1, "value is", label )