'''
    DS2500
    Spring 2025
    Sample code from class - 1/31/25

    On Tuesday, we debugged the code so we know there are no errors
    On Friday, we wrote unit tests for filter_age and convert_time
    to make sure we're doing our computations correctly

    End result is a histogram showing the distribution of marathon
    finish times for master's runners in the 2023 boston marathon (top 1000)
'''

import matplotlib.pyplot as plt
from utils import read_csv, lst_to_dct

FILENAME = "boston_marathon_2023.csv"
BIB_HEADER = "BibNumber"
AGE_HEADER = "AgeOnRaceDay"
RANK_HEADER = "RankOverall"
GENDER_HEADER = "Gender"
TIME_HEADER = "OfficialTime"


def filter_age(target_age, ages, times):
    ''' given a target age, a list of ages, and a list of times,
        filter and return a list of times for runners who are the given
        age OR OLDER
    '''
    filtered_times = []
    for i in range(len(ages)):
        if ages[i] >= target_age:
            filtered_times.append(times[i])
    return filtered_times

def convert_time(str_time):
    ''' given a string with a time in HH:MM:SS format,
        compute and return an int, the total number of minutes
    '''
    lst = str_time.split(":")
    hours = int(lst[0])
    mins = int(lst[1])
    return hours * 60 + mins

def plot_finish_times(times, title):
    ''' given a list of finish times, create a histogram showing their distribution '''
    plt.hist(times, color = "fuchsia")
    plt.title(title)
    plt.xlabel("Finish time (minutes)")
    plt.ylabel("Number of runners")
    plt.show()

def main():
    # Gather data - read in the MBTA speed restrictions as a 2d list
    # and then convert to a dictionary where keys come from the header
    data = read_csv(FILENAME, skip = 0)
    dct = lst_to_dct(data)

    # pull out a list of ages
    ages = dct[AGE_HEADER]
    for i in range(len(ages)):
        ages[i] = int(ages[i])
    print(f"Ages of runners in 2023: {ages}")

    # filter to keep everyone older than me, and convert to int
    master_times = filter_age(45, ages, dct[TIME_HEADER])
    master_times = [convert_time(time) for time in master_times]

    # plot the distribution of finish times
    plot_finish_times(master_times, "Boston Marathon 2023 Master's Runners (Top 1000)")

if __name__ == "__main__":
    main()