''' Purpose: determine a rough estimate of the geocenter of the
        continental USA


    Strategy1: Average the latitude and the longitude
    Strategy2 (Median Strategy): Put them in order and find the one in the middle (sort them and find the "median" value)
    Strategy3 (Average of the Min/Max Strategy): Average the Min and Max latitudes and longitudes
'''

# get access to web-based data support
import url

# specify dataset web location
CSV_WEB_FOLDER = 'http://www.cs.virginia.edu/~cs1112/datasets/csv/'

USA_DATASET    = CSV_WEB_FOLDER + 'continental-usa.csv'

# get the dataset of interest
dataset = url.get_dataset( USA_DATASET )

# determine webfile header and location data
header    = dataset[ 0 ] # ['Zipcode', 'Town','State', 'Latitude','Longitude']
locations = dataset[ 1 : ]

# determine geocenter

# Accumulators
list_latitudes = [] # Add all the latitudes from each entry into this list
list_longitudes = [] # Add all the longitudes from each entry into this list

# a loop that might be helpful for solving the problem
for entry in locations : # We are looking at each row (list) after the header
    zipcode, town, state, latitude, longitude = entry # Get the values in each entry and store them in variables
    # Ex. one entry is [99362, 'Walla Walla', 'OR', 45.986775, -118.07919]
    # So the variables are assigned the values from the list so that
    # zipcode is 99362, town is 'Walla Walla', state is 'OR', latitude is 45.986775, longitude is -118.07919
    list_latitudes.append( latitude ) # For the entry we're on, put it's latitude into our list_latitudes
    list_longitudes.append( longitude ) # For each entry we're on, put it's longitude into our list_longitudes

print( list_latitudes )
print( list_longitudes)

# Get Average of Min and Max Latitude and Longitude

min_latitude = min( list_latitudes )
max_latitude = max( list_latitudes )

min_longitude = min( list_longitudes )
max_longitude = max( list_longitudes )

average_latitude_1 = (min_latitude + max_latitude ) / 2
average_longitude_1 = (min_longitude + max_longitude) / 2

print('Guess 1: ', average_latitude_1, average_longitude_1  ) # 36.954868499999996 -95.81564449999999

# Get Average of All Latitudes and All Longitudes
number_locations = len( list_latitudes ) # How many latitudes and longitudes do we have (how many locations)
# Average = sum / total # of things
average_latitude_2 = sum( list_latitudes ) / number_locations
average_longitude_2 = sum( list_longitudes ) / number_locations

print('Guess 2: ', average_latitude_2, average_longitude_2 ) # 38.52071282671683 -90.43203752861102

# Get the median of the latitudes and longitudes (middle value)
# The sorted() function takes in a list and hands back a sorted version of that list
sorted_latitudes = sorted( list_latitudes )
sorted_longitudes = sorted( list_longitudes )

middle_index = number_locations // 2 # index of the middle location
# Use index to get the latitude and longitude at that index position middle_index
middle_latitude = sorted_latitudes[middle_index]
middle_longitude = sorted_longitudes[middle_index]
print( 'Guess 3:', middle_latitude, middle_longitude ) # 39.143979 -87.76815