def calcAndAppendStatValDiplo(alleleCounts, snpLocs, statName, subWinStart, subWinEnd, statVals, instanceIndex, subWinIndex, genosInSubWin, unmasked):
genosNAlt = genosInSubWin.to_n_alt()
if statName == "tajD":
statVals[statName][instanceIndex].append(allel.stats.diversity.tajima_d(
alleleCounts, pos=snpLocs, start=subWinStart, stop=subWinEnd))
elif statName == "pi":
statVals[statName][instanceIndex].append(allel.stats.diversity.sequence_diversity(
snpLocs, alleleCounts, start=subWinStart, stop=subWinEnd, is_accessible=unmasked))
elif statName == "thetaW":
statVals[statName][instanceIndex].append(allel.stats.diversity.watterson_theta(
snpLocs, alleleCounts, start=subWinStart, stop=subWinEnd, is_accessible=unmasked))
elif statName == "thetaH":
statVals[statName][instanceIndex].append(thetah(
snpLocs, alleleCounts, start=subWinStart, stop=subWinEnd, is_accessible=unmasked))
elif statName == "fayWuH":
statVals[statName][instanceIndex].append(
statVals["thetaH"][instanceIndex][subWinIndex]-statVals["pi"][instanceIndex][subWinIndex])
elif statName == "HapCount":
statVals[statName][instanceIndex].append(len(hapsInSubWin.distinct()))
elif statName == "nDiplos":
diplotypeCounts = shicstats.getHaplotypeFreqSpec(genosNAlt)
nDiplos = diplotypeCounts[genosNAlt.shape[1]]
statVals["nDiplos"][instanceIndex].append(nDiplos)
diplotypeCounts = diplotypeCounts[:-1]
dh1 = garudH1(diplotypeCounts)
dh2 = garudH2(diplotypeCounts)
dh12 = garudH12(diplotypeCounts)
if "diplo_H1" in statVals:
statVals["diplo_H1"][instanceIndex].append(dh1)
if "diplo_H12" in statVals:
statVals["diplo_H12"][instanceIndex].append(dh12)
if "diplo_H2/H1" in statVals:
statVals["diplo_H2/H1"][instanceIndex].append(dh2/dh1)
elif statName == "diplo_ZnS":
if genosNAlt.shape[0] == 1:
statVals["diplo_ZnS"][instanceIndex].append(0.0)
statVals["diplo_Omega"][instanceIndex].append(0.0)
else:
r2Matrix = allel.stats.ld.rogers_huff_r(genosNAlt)
statVals["diplo_ZnS"][instanceIndex].append(np.nanmean(r2Matrix))
r2Matrix2 = squareform(r2Matrix ** 2)
statVals["diplo_Omega"][instanceIndex].append(
shicstats.omega(r2Matrix2)[0])
elif statName == "distVar":
dists = shicstats.pairwiseDiffsDiplo(
genosNAlt)/float(unmasked[subWinStart-1:subWinEnd].count(True))
statVals["distVar"][instanceIndex].append(np.var(dists, ddof=1))
statVals["distSkew"][instanceIndex].append(scipy.stats.skew(dists))
statVals["distKurt"][instanceIndex].append(scipy.stats.kurtosis(dists))
elif statName in ["diplo_H12", "diplo_H123", "diplo_H2/H1", "distVar", "distSkew", "distKurt", "diplo_Omega"]:
if not len(statVals[statName][instanceIndex]) == subWinIndex+1:
print(statName, instanceIndex, subWinIndex+1)
print(statVals["diplo_H1"][instanceIndex],
statVals["diplo_H12"][instanceIndex])
sys.exit()
def calcAndAppendStatValForScan(alleleCounts, snpLocs, statName, subWinStart, subWinEnd, statVals, subWinIndex, hapsInSubWin, unmasked, precomputedStats):
if statName == "tajD":
statVals[statName].append(allel.stats.diversity.tajima_d(
alleleCounts, pos=snpLocs, start=subWinStart, stop=subWinEnd))
elif statName == "pi":
statVals[statName].append(allel.stats.diversity.sequence_diversity( # NOQA
snpLocs, alleleCounts, start=subWinStart, stop=subWinEnd, is_accessible=unmasked)) # NOQA
elif statName == "thetaW":
statVals[statName].append(allel.stats.diversity.watterson_theta(
snpLocs, alleleCounts, start=subWinStart, stop=subWinEnd, is_accessible=unmasked)) # NOQA
elif statName == "thetaH":
statVals[statName].append(thetah(
snpLocs, alleleCounts, start=subWinStart, stop=subWinEnd, is_accessible=unmasked)) # NOQA
elif statName == "fayWuH":
statVals[statName].append(
statVals["thetaH"][subWinIndex]-statVals["pi"][subWinIndex])
elif statName == "maxFDA":
# AK: undefined variables
statVals[statName].append(maxFDA(
snpLocs, alleleCounts, start=subWinStart, stop=subWinEnd, is_accessible=unmasked))
elif statName == "HapCount":
statVals[statName].append(len(hapsInSubWin.distinct()))
elif statName == "H1":
h1, h12, h123, h21 = allel.stats.selection.garud_h(hapsInSubWin)
statVals["H1"].append(h1)
if "H12" in statVals:
statVals["H12"].append(h12)
if "H123" in statVals:
statVals["H123"].append(h123)
if "H2/H1" in statVals:
statVals["H2/H1"].append(h21)
elif statName == "ZnS":
r2Matrix = shicstats.computeR2Matrix(hapsInSubWin)
statVals["ZnS"].append(shicstats.ZnS(r2Matrix)[0])
statVals["Omega"].append(shicstats.omega(r2Matrix)[0])
elif statName == "RH":
rMatrixFlat = allel.stats.ld.rogers_huff_r(
hapsInSubWin.to_genotypes(ploidy=2).to_n_alt())
rhAvg = rMatrixFlat.mean()
statVals["RH"].append(rhAvg)
r2Matrix = squareform(rMatrixFlat ** 2)
statVals["Omega"].append(shicstats.omega(r2Matrix)[0])
elif statName == "iHSMean":
vals = [x for x in precomputedStats["iHS"][subWinIndex]
if not (math.isnan(x) or math.isinf(x))]
if len(vals) == 0:
statVals["iHSMean"].append(0.0)
else:
statVals["iHSMean"].append(sum(vals)/float(len(vals)))
elif statName == "nSLMean":
vals = [x for x in precomputedStats["nSL"][subWinIndex]
if not (math.isnan(x) or math.isnan(x))]
if len(vals) == 0:
statVals["nSLMean"].append(0.0)
else:
statVals["nSLMean"].append(sum(vals)/float(len(vals)))
elif statName == "iHSMax":
vals = [x for x in precomputedStats["iHS"][subWinIndex]
if not (math.isnan(x) or math.isinf(x))]
if len(vals) == 0:
maxVal = 0.0
else:
maxVal = max(vals)
statVals["iHSMax"].append(maxVal)
elif statName == "nSLMax":
vals = [x for x in precomputedStats["nSL"][subWinIndex]
if not (math.isnan(x) or math.isnan(x))]
if len(vals) == 0:
maxVal = 0.0
else:
maxVal = max(vals)
statVals["nSLMax"].append(maxVal)
elif statName == "iHSOutFrac":
statVals["iHSOutFrac"].append(getOutlierFrac(
precomputedStats["iHS"][subWinIndex]))
elif statName == "nSLOutFrac":
statVals["nSLOutFrac"].append(getOutlierFrac(
precomputedStats["nSL"][subWinIndex]))
elif statName == "distVar":
dists = shicstats.pairwiseDiffs(
hapsInSubWin)/float(unmasked[subWinStart-1:subWinEnd].count(True))
statVals["distVar"].append(np.var(dists, ddof=1))
statVals["distSkew"].append(scipy.stats.skew(dists))
statVals["distKurt"].append(scipy.stats.kurtosis(dists))
elif statName in ["H12", "H123", "H2/H1",
"Omega", "distVar", "distSkew", "distKurt"]:
assert len(statVals[statName]) == subWinIndex+1
