Brute Force Ancestral Monte Carlo I used for project planning when writing my PhD thesis

thesis-planning.py

# renders a MAP estimate of the PhD thesis timeline along with estimate of the
# 50%, 90% and 99% chance of thesis being complete
import numpy as np
import time
import datetime
from datetime import timedelta

def main():
    # model the PhD as a sequence of events of random length.

    # would like to be recursively evaluated

    # (name,                n,                                p)
    # (str,  days to complete, probability of succesful workday)
    to_complete = [#("Resouce-Efficient",                   1, 2), DONE
                   #("Moonshine",                           5, 0.8), DONE
                   #("Lit Review",                          2,  0.9), DONE
                   ("Low-Rank",                            1, 0.8),
                   ("Intro & Conclusion",                  2,  0.8),
                   ("Editing",                             2,  0.8)]

    # sample a lot
    rng = np.random.RandomState(42)
    n_samples = 100000
    samples = [(n,rng.geometric(p, size=(n_samples,d)).sum(1)) for n, d, p in to_complete]

    # would be nice to take into account weekends, but probably not going to happen

    # combine the samples to get no. of days to completion
    sum_events = np.concatenate([s.reshape(1,-1) for n, s in samples],0)
    sum_events = sum_events.sum(0)

    today = datetime.date.fromtimestamp(time.time())
    if False:
        ######################
        # The NIPS condition #
        ######################
        # if any of these exceed the 2nd of December, add a week for NIPS
        December2 = datetime.date(2018, 12, 2)
        days_until = (December2 - today).days
        exceeding = (sum_events > days_until).astype(int)
        sum_events = sum_events + exceeding*7 # add a week where we hit NIPS

    # sort scenarios
    sum_events.sort()
    p = lambda x: int(round(sum_events[x*n_samples//100]))
    print("50 percent chance to be done by: " + str(today + timedelta(days=p(50))))
    print("90 percent chance to be done by: " + str(today + timedelta(days=p(90))))
    print("99 percent chance to be done by: " + str(today + timedelta(days=p(99))))

    return None
    # draw timeline
    days = 0
    current_month = today.month
    to_complete = []
    for i, (n,m,s) in enumerate(to_complete):
        sum_events = np.concatenate([s.reshape(1,-1) for n, s in samples[:i+1]],0)
        sum_events = sum_events.sum(0)
        sum_events.sort()
        p = lambda x: int(round(sum_events[x*n_samples//100]))
        to_complete.append((n[0], p(90)))
    timeline = ""
    total_days = p(90)
    while days < total_days:
        if days > days_until and days < days_until + 7:
            timeline += "N"
            to_complete = [(n,m+1) for n,m in to_complete]
            total_days += 1
        else:
            timeline += "-"
        days += 1
        # see if we've changed month
        now = today + timedelta(days)
        if now.month > current_month:
            current_month = now.month
            timeline += "|%i|"%current_month
        # to add in when stuff should be completed
        past = [n for n,m in to_complete if days-m == 0]
        if len(past) > 0:
            to_complete.pop(0)
            timeline += "|%s|"%past[0]

    print(timeline)

if __name__ == '__main__':
    main()