'''
    Honors Series - Data Science
    Mini-Assignment #3 sample solutions
'''

import matplotlib.pyplot as plt
import csv
import random

SEX = 6
NAME = 1
ATTACK = 11
AGE = 5

def main():

    # 1A - Plot a simple line chart, where the numbers come from foreclosure data
    fores = [11, 10, 6, 8, 4, 13, 11, 8, 6, 10, 3, 4, 10, 10, 6, 2,
      	    6, 8, 10, 11, 14, 6, 10, 6]
    plt.plot(fores)
    plt.xlabel('Month')
    plt.ylabel('Number of Foreclosures')
    plt.title('Foreclosures in Boston 2018-2019')
    plt.show()

    # 1B - Plot a line chart of randomly-generated values, with labels
    pets = [44, 50, 6, 14, 12, 14, 14, 19, 11, 19, 15, 15, 13, 10, 
              20, 32, 31, 16, 41, 34, 33, 37, 36, 40]
    plt.plot(fores, color = 'blue', marker = 'x', label = 'foreclosures')
    plt.plot(pets, color = 'orange', marker = 'o', label = 'petitions')
    plt.title('Petitions vs Foreclosures')
    plt.legend()
    plt.show()

    # 1C - Same values, but now combine them by quarter and show a bar chart
    fore_qtr = []
    pet_qtr = []
    total_f = 0
    total_p = 0
    for i in range(len(fores)):
        total_f += fores[i]
        total_p += pets[i]
        if (i + 1) % 3 == 0:
            fore_qtr.append(total_f)
            pet_qtr.append(total_p)
            total_f = 0
            total_p = 0
    print(fore_qtr)
    print(pet_qtr)
    pos = [i for i in range(len(fores) // 3)]
    plt.bar(pos, pet_qtr, color = 'purple', width = .35, label = 'petitions')

    pos2 = [i + .35 for i in range(len(pets) // 3)]
    plt.bar(pos2, fore_qtr, color = 'orange', width = .35, label = 'foreclosures')

    plt.xticks(pos, ['Q1-18', 'Q2-18', 'Q3-18', 'Q4-18', 'Q1-19', 'Q2-19',
                     'Q3-19', 'Q4-19'])

    plt.legend()
    plt.show()
    
    # Part 2 - Read from a CSV file into a nested list.
    # Then, get the min/max/average ages like last time
    data = []
    with open('police_data.csv') as csvfile:
        reader = csv.reader(csvfile, delimiter = ',')
        next(reader)
        for row in reader:
            data.append(row)

    ages = []
    for row in data:
        if row[AGE] != '':
            ages.append(int(row[AGE]))
    print('Youngest:', min(ages))
    print('Oldest:', max(ages))
    print('Average age:', sum(ages) / len(ages))
                    
    # Part 3A - Plot Under 18 vs 18 and Over
    age_groups = [0, 0]
    for age in ages:
        if age < 18:
            age_groups[0] += 1
        else:
            age_groups[1] += 1
    pos = [0, 1]
    plt.bar(pos, age_groups, color = ['blue', 'red'], width = .5)
    plt.xticks(pos, ['Under 18', '18 and Up'])
    plt.show()

    # Part 3B - Plot all the age categories
    age_groups = [0] * 6
    pos = [0, 1, 2, 3, 4, 5]
    group_names = ['Under 18', '18-24', '25-34', '35-44', '45-54', '55+']
    for age in ages:
        if age < 18:
            age_groups[0] += 1
        elif age < 25:
            age_groups[1] += 1
        elif age < 35:
            age_groups[2] += 1
        elif age < 45:
            age_groups[3] += 1
        elif age < 55:
            age_groups[4] += 1
        else:
            age_groups[5] += 1
    plt.bar(pos, age_groups, color = ['gray', 'gray', 'orange',
                                      'orange', 'gray', 'gray'])
    plt.xticks(pos, group_names)
    plt.title('Incidents by Age Range')
    plt.show()


        
main()