Week 5 Python

# importing modules
import matplotlib.pyplot as plt;
import matplotlib.patches as mpatches;

# opens file and displays error message if file isn't able to be displayed
try:
        readFile = open("GBplaces.csv","r");

except:
        print("An error occured, the file 'GBplaces.csv' has failed to open.");

# these are the empty arrays - each variable corresponds to a column
# store data in these list variables 
# create empty lists (arrays) place, town/city, population, latitude, longitude, colour    
names=[]
town_city=[]
population=[]
latitude=[]
longitude=[]
colour=[]


# define initial to be false so as to skip header line
initial = False;

# for loop to read the file line by line and split the data into 5 different arrays - going by collumn
# read in the file line by line
for line in readFile:
    if initial:
        
# split the input line based on a comma (excel will be able to read this)
        organizer = line.split(',');
        
# store the values in the arrays
        names.append(organizer[0]);
        town_city.append(organizer[1]);
        population.append(int(organizer[2]));
        latitude.append(float(organizer[3]));
        longitude.append(float(organizer[4]));
    initial = True;

# close the file
readFile.close()

# this sorts the population but reverses them so largest populations shown first
sortedPopulation = sorted(population, reverse=True)

# setting thes size of the plotted points to reflect the population size of each city but dividing the sizes 
area = [ x/10000 for x in sortedPopulation]

# colour coding towns orange and cities red
for i in town_city:
    if i == 'Town':
        colour.append('orange')
    elif i == 'City':
        colour.append('red')

# plotting longitude against latitude
for i in range(0, len(sortedPopulation)):
    plt.scatter(longitude[population.index(sortedPopulation[i])],latitude[population.index(sortedPopulation[i])], s=area[i], alpha=0.5, color=colour[population.index(sortedPopulation[i])], label=str(colour[population.index(sortedPopulation[i])]))

# this is to have the colour key displaying town and city and indicating the colour red or orange
orange = mpatches.Patch(color='orange', alpha=0.5, label='Town')
red = mpatches.Patch(color='red', alpha=0.5, label='City')
plt.legend(handles=[orange, red], loc='upper right')

# labelling the axes and giving the plot a title
plt.xlabel("Longtitude");
plt.ylabel("Latitude");
plt.title("Visualization of GBPlaces - area of point proportional to population size");

# display the 10 most populated towns/cities from sorted list 
for i in range(0,10):
    plt.annotate(str(names[population.index(sortedPopulation[i])]), (longitude[population.index(sortedPopulation[i])],latitude[population.index(sortedPopulation[i])]))

# display the plot
plt.show()