def __init__(self, g_orig, haplotype, num_errors):
'''Initialize phasing statistics object for the original genotype g/and haplotype set problem.haplotype.'''
h = haplotype.data
r_orig = recode.recode_single_genotype(g_orig)
r = recode.recode_single_genotype(h)
# Sizes
self.time = 0
self.num_snps = haplotype.num_snps
self.num_samples = haplotype.num_samples
self.num_genotypes = haplotype.num_data / 2
self.num_haplotypes = haplotype.num_data
# Arrays
self.fill = np.array([haplotype.fill_fraction(sample=x) for x in xrange(haplotype.num_samples)])
# Fields
# A Field factory method
field = lambda index: StatsField(self, h, index)
self.called_orig = field(recode.where_called(r_orig))
self.imputed = field(recode.where_full_imputed(r, r_orig))
self.imputed_partial = field(recode.where_partial_imputed(r, r_orig))
self.errors = field(recode.where_error(r, r_orig))
self.errors_partial = field(recode.where_partial_error(r, r_orig))
self.called = field(recode.where_called(r))
self.partial_called = field(recode.where_partial_called(r))
self.still_missing = field(recode.where_still_missing(r, r_orig))
# Scalars
self.num_filled_haplotypes = haplotype.num_filled
self.num_errors = num_errors # Redundant
def __init__(self, g_orig, haplotype, num_errors):
'''Initialize phasing statistics object for the original genotype g/and haplotype set problem.haplotype.'''
h = haplotype.data
r_orig = recode.recode_single_genotype(g_orig)
r = recode.recode_single_genotype(h)
# Sizes
self.time = 0
self.num_snps = haplotype.num_snps
self.num_samples = haplotype.num_samples
self.num_genotypes = haplotype.num_data / 2
self.num_haplotypes = haplotype.num_data
# Arrays
self.fill = np.array([
haplotype.fill_fraction(sample=x)
for x in xrange(haplotype.num_samples)
])
# Fields
# A Field factory method
field = lambda index: StatsField(self, h, index)
self.called_orig = field(recode.where_called(r_orig))
self.imputed = field(recode.where_full_imputed(r, r_orig))
self.imputed_partial = field(recode.where_partial_imputed(r, r_orig))
self.errors = field(recode.where_error(r, r_orig))
self.errors_partial = field(recode.where_partial_error(r, r_orig))
self.called = field(recode.where_called(r))
self.partial_called = field(recode.where_partial_called(r))
self.still_missing = field(recode.where_still_missing(r, r_orig))
# Scalars
self.num_filled_haplotypes = haplotype.num_filled
self.num_errors = num_errors # Redundant
def total_partial_called(self):
'''Return the number of genotypes in which one alleles was called.'''
# Positive entries of r = called entries
return len(recode.where_partial_called(self.recoded_genotype)[0])
def __remove_partial_calls(self):
'''Set partially-imputed genotypes to missing. A prerequisite for loading into PLINK, for instance
(but not PLINK-SEQ).'''
self.h[recode.where_partial_called(
recode.recode_single_genotype(self.h)), :] = MISSING
def total_partial_called(self):
'''Return the number of genotypes in which one alleles was called.'''
# Positive entries of r = called entries
return len(recode.where_partial_called(self.recoded_genotype)[0])
def __remove_partial_calls(self):
'''Set partially-imputed genotypes to missing. A prerequisite for loading into PLINK, for instance
(but not PLINK-SEQ).'''
self.h[recode.where_partial_called(recode.recode_single_genotype(self.h)), :] = MISSING