def pyrange_apply_single(function, self, strand, kwargs):
if strand:
assert self.stranded, \
"Can only do stranded operation when PyRange contains strand info"
results = []
if strand:
for (c, s), df in self.items():
kwargs["chromosome"] = c
_strand = s
kwargs["strand"] = _strand
df = make_unary_sparse(kwargs, df)
result = call_f_single(function, df, kwargs)
results.append(result)
keys = self.keys()
elif not self.stranded:
keys = []
for c, df in self.items():
kwargs["chromosome"] = c
df = make_unary_sparse(kwargs, df)
result = call_f_single(function, df, kwargs)
results.append(result)
keys.append(c)
else:
keys = []
for c in self.chromosomes:
kwargs["chromosome"] = c
dfs = self[c]
if len(dfs.keys()) == 2:
df1, df2 = dfs.values()
# merge strands
df1 = merge_dfs.remote(df1, df2)
else:
df1 = dfs.values()[0]
df1 = make_unary_sparse(kwargs, df1)
result = call_f_single(function, df1, kwargs)
results.append(result)
keys.append(c)
results = ray.get(results)
results = process_results(results, keys)
return results
def pyrange_apply(function, self, other, **kwargs):
strandedness = kwargs["strandedness"]
other_strand = {"+": "-", "-": "+"}
same_strand = {"+": "+", "-": "-"}
if strandedness == "opposite":
strand_dict = other_strand
else:
strand_dict = same_strand
assert strandedness in ["same", "opposite", False, None]
if strandedness:
assert self.stranded and other.stranded, \
"Can only do stranded operations when both PyRanges contain strand info"
results = []
items = natsorted(self.dfs.items())
keys = natsorted(self.dfs.keys())
if strandedness:
for (c, s), df in items:
os = strand_dict[s]
if not (c, os) in other.keys() or len(other[c, os].values()) == 0:
odf = pd.DataFrame(columns="Chromosome Start End".split())
else:
odf = other[c, os].values()[0]
df, odf = make_binary_sparse(kwargs, df, odf)
result = call_f(function, df, odf, kwargs)
results.append(result)
else:
if self.stranded and not other.stranded:
for (c, s), df in items:
if not c in other.chromosomes:
odf = pd.DataFrame(columns="Chromosome Start End".split())
else:
odf = other.dfs[c]
df, odf = make_binary_sparse(kwargs, df, odf)
result = call_f(function, df, odf, kwargs)
results.append(result)
elif not self.stranded and other.stranded:
for c, df in items:
if not c in other.chromosomes:
odf = pd.DataFrame(columns="Chromosome Start End".split())
else:
odf1 = other[c, "+"]
odf2 = other[c, "-"]
odf = merge_dfs.remote(odf1, odf2)
df, odf = make_binary_sparse(kwargs, df, odf)
result = call_f(function, df, odf, kwargs)
results.append(result)
elif self.stranded and other.stranded:
for (c, s), df in self.items():
if not c in other.chromosomes:
odfs = pr.PyRanges(
pd.DataFrame(columns="Chromosome Start End".split()))
else:
odfs = other[c].values()
# from pydbg import dbg
# dbg(odfs)
if len(odfs) == 2:
odf = merge_dfs.remote(*odfs, kwargs)
elif len(odfs) == 1:
odf = odfs[0]
else:
odf = pd.DataFrame(columns="Chromosome Start End".split())
df, odf = make_binary_sparse(kwargs, df, odf)
# dbg(df)
# dbg(odf)
result = call_f(function, df, odf, kwargs)
results.append(result)
else:
for c, df in items:
if not c in other.chromosomes:
odf = pd.DataFrame(columns="Chromosome Start End".split())
else:
odf = other.dfs[c]
df, odf = make_binary_sparse(kwargs, df, odf)
result = call_f(function, df, odf, kwargs)
results.append(result)
results = ray.get(results)
results = process_results(results, keys)
return results