# -*- coding: utf-8 -*-
"""
Created on Mon Aug 22 00:01:16 2016

@author: benedictusyoga
"""

import pandas
import numpy

data = pandas.read_csv("../gapminder.csv", low_memory = False)

print(len(data)) #number of observations (rows)
print(len(data.columns))  # number of variables (columns)

# gapminder columns country,incomeperperson,alcconsumption,armedforcesrate,breastcancerper100th,co2emissions,femaleemployrate,hivrate,internetuserate,lifeexpectancy,oilperperson,polityscore,relectricperperson,suicideper100th,employrate,urbanrate

def dist_freq(aux_data, ranges):
    cut_data = pandas.cut(aux_data, ranges)
    count = cut_data.value_counts(sort = False, dropna = False)
    percent = cut_data.value_counts(sort = False, dropna = False, normalize = True)

    print("Category\t\tFrequency\tPercentage")
    max_idx = len(count)
    for i in range(max_idx):
        if i == max_idx - 1:
            print("Missing Data", "\t\t", count[max_idx-1], "\t\t", percent[max_idx-1]*100, "%")
        else:
            print("(",ranges[i], "-",ranges[i+1],")", "\t", count[i], "\t\t", percent[i]*100, "%")

print("Income per person in countries")
aux_incomeperperson = pandas.to_numeric(data["incomeperperson"], errors = "coerce")
ranges_incomeperperson = [0, 2000, 5000, 10000, 20000, 35000, 50000, numpy.Inf]
dist_freq(aux_incomeperperson, ranges_incomeperperson)


print("Internet use rate in countries")
aux_internetuserate = pandas.to_numeric(data["internetuserate"], errors = "coerce")
ranges_internetuserate = [0, 5, 15, 45, 90, numpy.Inf]
dist_freq(aux_internetuserate, ranges_internetuserate)

print("Urban rate in countries")
aux_urbanrate = pandas.to_numeric(data["urbanrate"], errors = "coerce")
ranges_urbanrate = [0, 5, 15, 45, 90, numpy.Inf]
dist_freq(aux_urbanrate, ranges_urbanrate)