def getGenotypes(self,sample_idx=None,idx_start=None,idx_end=None,chrom=None,pos_start=None,pos_end=None,center=True,unit=True,impute_missing=False,snp_idx=None,windowsize=0):
"""load genotypes.
Optionally the indices for loading subgroups the genotypes for all people
based on position of cumulative position.
Positions can be given as (pos_start-pos_end on chrom)
If both of these are None (default), then all genotypes are returned
Args:
idx_start: genotype index based selection (start index)
idx_end: genotype index based selection (end index)
chrom: chromosome based selection (return whole chromosome)
pos_start: position based selection (start position) tuple of chrom, position
pos_end: position based selection (end position) tuple of chrom, position
impute_missing: Boolean indicator variable if missing values should be imputed
Returns:
X: scipy.array of genotype values
"""
#position based matching?
if (idx_start is None) and (idx_end is None) and ((pos_start is not None) & (pos_end is not None)):
idx_start,idx_end=self.getGenoIndex(chrom=chrom,pos_start=pos_start,pos_end=pos_end,windowsize=windowsize)
#index based matching?
if (idx_start is not None) & (idx_end is not None):
X = self.geno_matrix[:,idx_start:idx_end]
elif snp_idx is not None:
X = self.geno_matrix[:,snp_idx]
else:
X = self.geno_matrix[:,:]
if sample_idx is not None:
X=X[sample_idx]
if impute_missing:
X = du.imputeMissing(X,center=center,unit=unit)
return X
def getGenotypes(self,idx_start=None,idx_end=None,pos_start=None,pos_end=None,windowsize=0,chrom=None,center=True,unit=True,impute_missing=False,cast_float=True):
"""return genotypes.
Optionally the indices for loading subgroups the genotypes for all people
can be given in one out of three ways:
- 0-based indexing (idx_start-idx_end)
- position (pos_start-pos_end on chrom)
- cumulative position (pos_cum_start-pos_cum_end)
If all these are None (default), then all genotypes are returned
Args:
idx_start: genotype index based selection (start index)
idx_end: genotype index based selection (end index)
pos_start: position based selection (start position)
pos_end: position based selection (end position)
chrom: position based selection (chromosome)
pos_cum_start: cumulative position based selection (start position)
pos_cum_end: cumulative position based selection (end position)
impute_missing: Boolean indicator variable if missing values should be imputed
cast_float: Boolean indicator variable if output genotypes should be casted as float
Returns:
X: scipy.array of genotype values
"""
query_idx = self.range_query_geno(idx_start=idx_start, idx_end=idx_end, chrom=chrom, pos_start=pos_start,windowsize=windowsize)
X = self.geno_reader.getGenotypes(sample_idx= sp.array(self.sample_idx["geno"]),snp_idx=query_idx)
if impute_missing:
X = du.imputeMissing(X,center=center,unit=unit)
if cast_float:
if X.dtype!='float64':
X = sp.array(X,dtype='float64')
return X
def getGenotypes(self,
sample_idx=None,
idx_start=None,
idx_end=None,
pos_start=None,
pos_end=None,
chrom=None,
center=True,
unit=True,
pos_cum_start=None,
pos_cum_end=None,
impute_missing=False,
snp_idx=None):
"""load genotypes.
Optionally the indices for loading subgroups the genotypes for all people
can be given in one out of three ways:
- 0-based indexing (idx_start-idx_end)
- position (pos_start-pos_end on chrom)
- cumulative position (pos_cum_start-pos_cum_end)
If all these are None (default), then all genotypes are returned
Args:
idx_start: genotype index based selection (start index)
idx_end: genotype index based selection (end index)
pos_start: position based selection (start position)
pos_end: position based selection (end position)
chrom: position based selection (chromosome)
pos_cum_start: cumulative position based selection (start position)
pos_cum_end: cumulative position based selection (end position)
impute_missing: Boolean indicator variable if missing values should be imputed
Returns:
X: scipy.array of genotype values
"""
#position based matching?
if (idx_start is None) and (idx_end is None) and (
(pos_start is not None) & (pos_end is not None) &
(chrom is not None)) or ((pos_cum_start is not None) &
(pos_cum_end is not None)):
idx_start, idx_end = self.getGenoIndex(pos_start=pos_start,
pos_end=pos_end,
chrom=chrom,
pos_cum_start=pos_cum_start,
pos_cum_end=pose_cum1)
#index based matching?
if (idx_start is not None) & (idx_end is not None):
X = self.geno_matrix[:, idx_start:idx_end]
elif snp_idx is not None:
X = self.geno_matrix[:, snp_idx]
else:
X = self.geno_matrix[:, :]
if sample_idx is not None:
X = X[sample_idx]
if impute_missing:
X = du.imputeMissing(X, center=center, unit=unit)
return X
def getGenotypes(self,
idx_start=None,
idx_end=None,
pos_start=None,
pos_end=None,
windowsize=0,
chrom=None,
center=True,
unit=True,
impute_missing=False,
cast_float=True):
"""return genotypes.
Optionally the indices for loading subgroups the genotypes for all people
can be given in one out of three ways:
- 0-based indexing (idx_start-idx_end)
- position (pos_start-pos_end on chrom)
- cumulative position (pos_cum_start-pos_cum_end)
If all these are None (default), then all genotypes are returned
Args:
idx_start: genotype index based selection (start index)
idx_end: genotype index based selection (end index)
pos_start: position based selection (start position)
pos_end: position based selection (end position)
chrom: position based selection (chromosome)
pos_cum_start: cumulative position based selection (start position)
pos_cum_end: cumulative position based selection (end position)
impute_missing: Boolean indicator variable if missing values should be imputed
cast_float: Boolean indicator variable if output genotypes should be casted as float
Returns:
X: scipy.array of genotype values
"""
query_idx = self.range_query_geno(idx_start=idx_start,
idx_end=idx_end,
chrom=chrom,
pos_start=pos_start,
windowsize=windowsize)
X = self.geno_reader.getGenotypes(sample_idx=sp.array(
self.sample_idx["geno"]),
snp_idx=query_idx)
if impute_missing:
X = du.imputeMissing(X, center=center, unit=unit)
if cast_float:
if X.dtype != 'float64':
X = sp.array(X, dtype='float64')
return X
def getGenotypes(self,sample_idx=None,idx_start=None,idx_end=None,pos_start=None,pos_end=None,chrom=None,center=True,unit=True,pos_cum_start=None,pos_cum_end=None,impute_missing=False,snp_idx=None):
"""load genotypes.
Optionally the indices for loading subgroups the genotypes for all people
can be given in one out of three ways:
- 0-based indexing (idx_start-idx_end)
- position (pos_start-pos_end on chrom)
- cumulative position (pos_cum_start-pos_cum_end)
If all these are None (default), then all genotypes are returned
Args:
idx_start: genotype index based selection (start index)
idx_end: genotype index based selection (end index)
pos_start: position based selection (start position)
pos_end: position based selection (end position)
chrom: position based selection (chromosome)
pos_cum_start: cumulative position based selection (start position)
pos_cum_end: cumulative position based selection (end position)
impute_missing: Boolean indicator variable if missing values should be imputed
Returns:
X: scipy.array of genotype values
"""
#position based matching?
if (idx_start is None) and (idx_end is None) and ((pos_start is not None) & (pos_end is not None) & (chrom is not None)) or ((pos_cum_start is not None) & (pos_cum_end is not None)):
idx_start,idx_end=self.getGenoIndex(pos_start=pos_start,pos_end=pos_end,chrom=chrom,pos_cum_start=pos_cum_start,pos_cum_end=pose_cum1)
#index based matching?
if (idx_start is not None) & (idx_end is not None):
X = self.geno_matrix[:,idx_start:idx_end]
elif snp_idx is not None:
X = self.geno_matrix[:,snp_idx]
else:
X = self.geno_matrix[:,:]
if sample_idx is not None:
X=X[sample_idx]
if impute_missing:
X = du.imputeMissing(X,center=center,unit=unit)
return X
