Search
Fig 2. Inference and uncertainty using the posterior

Figure 2:

The posterior distribution over s is plotted for the realistic scenario of $n_{a}$ = 47, $n_{b}$ = 32, and $n_{ab}$ = 20 [line; Eq (6)]. The $\hat{s}$ posterior mean provides our estimate of the true overlap open circle; Eq (7), and the interval accounting for at least 90% of the area under the posterior curve provides an equal-tailed 90% credible interval [shading; Eq (8)]. The $\overset{\circ}{S}$ estimate is shown for comparison [black cross; Eq (1)], and is typically less than or equal to $\hat{s}$ .

Link to the published figure: https://doi.org/10.1371/journal.pcbi.1006898.g002

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
from scipy.stats import hypergeom
from scipy.stats import binned_statistic as binsta
from scipy.special import logsumexp
from util import *
import palettable as pal
clrx = pal.cartocolors.qualitative.Prism_10.mpl_colors
clr = tuple(x for n,x in enumerate(clrx) if n in [1,2,4,5,6])
clr2 = pal.cartocolors.sequential.agSunset_7.mpl_colors
import matplotlib.gridspec as gridspec
import matplotlib.patches as patches
import plotly.graph_objects as go
import plotly.tools as tls
from plotly.offline import plot, iplot, init_notebook_mode
from IPython.core.display import display, HTML
init_notebook_mode(connected = True)
config={'showLink': False, 'displayModeBar': False}

# CCP, the Coupon Collector's Problem
def ccp_sample(c,pool=60):
    return len(set(np.random.choice(pool,c)))

# Draw overlap
def nab_sample(s,na,nb,pool=60):
    sa = np.random.hypergeometric(s,pool-s,na)
    nab = np.random.hypergeometric(sa,pool-sa,nb)
    return nab

# Overlap between two PCRs of depth c and overlap s
def pcr_sample(c,s):
    na = ccp_sample(c)
    nb = ccp_sample(c)
    return nab_sample(s,na,nb),na,nb

# Draw na and nb samples from two populations of size pool_a and pool_b, with true overlap s
# and return empirical overlap between na and nb
# note that this is basically the same as nab_sample, but with two different size pools!
def nab_sample_unequal(s,na,nb,pool_a,pool_b):
    sa = np.random.hypergeometric(s,pool_a-s,na)
    nab = np.random.hypergeometric(sa,pool_b-sa,nb)
    return nab


def p_ccp(c, pool=60):
    p = np.zeros([c+1,pool+1])
    p[0,0] = 1;
    for row in range(1,c+1):
        for k in range(1,np.min([row+2,pool+1])):
            p[row,k] = p[row-1,k]*k/pool + p[row-1,k-1]*(1-(k-1)/pool)
    return p[-1,:]

def p_overlap(na,nb,nab,pool=60):
    p_s = np.zeros(pool+1)
    # reference: hypergeom.pmf(outcome, Total, hits, Draws, loc=0)
    for s in np.arange(pool+1):
        # p_sa is the probability that we'd get sa from the overlap (s), just in na draws of a
        p_sa = hypergeom.pmf(np.arange(pool+1),pool,s,na)
        # p_nab_given_sa is the probability of getting that nab, given sa
        p_nab_given_sa = hypergeom.pmf(nab,pool,np.arange(pool+1),nb)
        p_s[s] = np.dot(p_sa,p_nab_given_sa)
    return p_s/np.sum(p_s)

def e_overlap(na,nb,nab,pool=60):
    p_s = p_overlap(na,nb,nab,pool=pool)
    return np.dot(np.arange(pool+1),p_s)


def credible_interval(na,nb,nab,pct=90,pool=60):
    p_s = p_overlap(na,nb,nab,pool=pool)
    cdf = np.cumsum(p_s)
    ccdf = np.flipud(np.cumsum(np.flipud(p_s)))
    # adjust for fractions vs percents; put everything as a fraction
    if pct > 1:
        pct = pct/100
    cutoff = (1-pct)/2
    # get the lower bound. 
    # it's the first index at which cdf ≥ cutoff
    try:
        lower = np.where(cdf >= cutoff)[0][0]
    except IndexError:
        lower = 0
    # get the upper bound
    # it's the first index at which ccdf ≥ 0.05
    try:
        upper = np.where(ccdf >= cutoff)[0][-1]
    except IndexError:
        upper=pool
    expectation = np.dot(np.arange(pool+1),p_s)
    # Sanity and indexing check: uncomment this line to see true tail probability ≤ 0.05
    # print([cdf[lower-1],(1-ccdf[upper+1])])
    return lower,expectation,upper


def p_nab_given_c(s,c,pool=60):
    pna = p_ccp(c)
    pnb = p_ccp(c)
    nas = np.arange(1,len(pna))
    nbs = np.arange(1,len(pnb))
    p_gen = np.zeros([pool+1,pool+1,pool+1])
    for na in nas:
        p_sa = hypergeom.pmf(np.arange(pool+1),pool,s,na)
        for nb in nbs:
            pna_pnb = pna[na] * pnb[nb]
            for nab in range(0,np.minimum(na,nb)):
                p_nab_given_sa = hypergeom.pmf(nab,pool,np.arange(pool+1),nb)
                p_nab_given_s = np.dot(p_sa,p_nab_given_sa)
                p_gen[na,nb,nab] = p_nab_given_s * pna_pnb
    return p_gen

def p_shat_given_sc(s,c,shat,pool=60):
    masses = p_nab_given_c(s,c,pool=pool)
    if np.sum(masses)<0.99:
        print('Swapping to Monte Carlo')
        return p_shat_given_sc_montecarlo(s,c,shat,pool=pool)
    hist = binsta(np.ravel(shat),np.ravel(masses),statistic='sum',bins=(np.arange(pool+2)-0.5))
    return hist

def p_shat_given_sc_montecarlo(s,c,shat,pool=60,n_mc=int(1e5)):
    masses = np.zeros([pool+1,pool+1,pool+1])
    for ii in range(n_mc):
        nab,na,nb = pcr_sample(c,s)
        masses[na,nb,nab] += 1
    hist = binsta(np.ravel(shat),np.ravel(masses/n_mc),statistic='sum',bins=(np.arange(pool+2)-0.5))
    return hist

def compute_all_estimates(pool=60):
    shat = np.zeros([pool+1,pool+1,pool+1])
    for na in range(1,pool+1):
        for nb in range(1,pool+1):
            for nab in range(0,np.minimum(na+1,nb+1)):
                shat[na,nb,nab] = e_overlap(na,nb,nab,pool=pool)
    return shat

def p_overlap_unequal(na,nb,nab,pool_a,pool_b):
    # all loops are in terms of pool_a, which is assumed to be ≤ pool_b. 
    p_s = np.zeros(pool_a+1)
    # reference: hypergeom.pmf(outcome, Total, hits, Draws, loc=0)
    for s in np.arange(pool_a+1):
        # p_sa is the probability that we'd get sa from the overlap (s), just in na draws of a
        p_sa = hypergeom.pmf(np.arange(pool_a+1),pool_a,s,na)
        # p_nab_given_sa is the probability of getting that nab, given sa
        p_nab_given_sa = hypergeom.pmf(nab,pool_b,np.arange(pool_a+1),nb)
        p_s[s] = np.dot(p_sa,p_nab_given_sa)
    return p_s/np.sum(p_s)

def e_overlap_unequal(na,nb,nab,pool_a,pool_b):
    # TODO. Code expects that pool_b > pool_a...
    p_s = p_overlap_unequal(na,nb,nab,pool_a,pool_b)
    return np.dot(np.arange(pool_a+1),p_s)

# shat = compute_all_estimates(pool=60)
# np.save('shat_60.npy',shat)
shat = np.load('shat_60.npy')

na = 47
nb = 32
nab = 20
pool = 60

pts = pool*2*nab/(na+nb)
ps = p_overlap(na,nb,nab,pool=pool)
lower,shat,upper = credible_interval(na,nb,nab,pool=pool)
x = np.arange(lower,upper+1)
y = np.copy(ps[x])
x = np.append(x,upper)
y = np.append(y,0)
x = np.insert(x,0,lower)
y =np.insert(y,0,0)
er =np.zeros([2,1])
er[0] = shat-lower
er[1] = upper-shat

fig = go.Figure()
fig.add_trace(go.Scatter(x = np.arange(pool+1), y = ps, 
                         mode = 'lines+markers',
                         line=dict(color='rgb(121, 178, 81)'),
                         name = "posterior distribuiton",
                         marker=dict(size=10)))
fig.add_trace(go.Scatter(x = x, y = y,
                         mode = "lines",
                         line=dict(color='rgba(121, 178, 81, 0.1)', width = 1),
                         fill = 'tozeroy',
                         name = "90% credible interval"))
fig.add_trace(go.Scatter(x = [shat], y = [0],
                         mode = 'markers',
                         name = "Bayesian estimate", 
                         marker=dict(size=15,
                                     color="rgb(255,255,255)",
                                     line=dict(width=3,
                                               color='rgb(121, 178, 81)'))))

fig.add_trace(go.Scatter(x = [pts], y = [0],
                         mode = 'markers',
                         marker_symbol = "x",
                         name = "Sorenson-Dice coefficient, S", 
                         marker=dict(size=15,
                                     color="rgb(1,1,1)",)))





fig.update_layout(plot_bgcolor='rgb(255,255,255)',xaxis_title="s",
    yaxis_title='Posterior probability P(s)', legend=dict(x=0.05, y=1))
fig.update_xaxes(ticks = 'outside', showline=True, linecolor='black')
fig.update_yaxes(ticks = 'outside', showline=True, linecolor='black')

# Plot figure
plot(fig, filename = 'plotly_figures/fig2.html', config = config)
display(HTML('plotly_figures/fig2.html'))