final_solution.py

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Wed Jun 21 18:01:05 2017

@author: saliksyed
"""

import matplotlib.pyplot as plt; plt.rcdefaults()
import numpy as np
import matplotlib.pyplot as plt
 


# Open the file with all the airports and read every line
data = open("airports.dat", "r").readlines()

# make an array to store the final data
final_data = []

# go through each row and extract the airport country
for row in data:
	row_items = row.split(",") # split by the comma
	data_dict = {}
	data_dict["airport_country"] = row_items[3].decode('utf-8', 'ignore')
	final_data.append(data_dict)
  
# create a count dictionary to hold the results
counts = {} 

# loop through the data points
for data_point in final_data:
	country_name = data_point["airport_country"]
  # if the country is missing (hasn't been seen yet) then initialize it to 0
	if not country_name in counts:
		counts[country_name] = 0
  # add to the count
	counts[country_name] += 1



 # the categorical values (names)
countries = counts.iterkeys()

# the lengths of the bars
number_of_airports = counts.itervalues()

tmp = sorted(zip(countries, number_of_airports), key=lambda x : x[1], reverse=True)[:25]
countries = [x[0] for x in tmp]
number_of_airports = [x[1] for x in tmp]

# y_pos holds the position of the bars ... np.arange(N) just produces N evenly spaced ticks
y_pos = np.arange(len(countries)) 


# Plots the bar chart  
plt.barh(y_pos, number_of_airports, align='center', alpha=0.5)

# Adds the tick labels
plt.yticks(y_pos, countries)

# Sets the X label
plt.xlabel('Number of Airports')

# Sets the chart title
plt.title('Number of Airports by Country') 
 
plt.show()