def test_store():
'It test the store for iterables'
item_list = [1, 3, 4]
storage = CachedArray(typecode='I')
storage.extend(item_list)
assert list(storage) == item_list
assert list(storage) == item_list
def create_maf_distribution(
seqs, distrib_fhand=None, plot_fhand=None, summary_fhand=None, groups=None, group_kind=None
):
"It creates the distribution of the maf (not takes in account ref allele)"
title = "maf"
if groups and group_kind:
title = "maf (%s: %s)" % (group_kind, ",".join(groups))
mafs = CachedArray("f")
for seq in seqs:
for snv in seq.get_features("snv"):
maf = calculate_maf_frequency(snv, groups=groups, group_kind=group_kind)
if maf:
mafs.append(maf)
if list(mafs):
create_distribution(
mafs,
labels={"title": title},
distrib_fhand=distrib_fhand,
bins=None,
plot_fhand=plot_fhand,
range_=None,
summary_fhand=summary_fhand,
calculate_freqs=False,
remove_outliers=False,
)
def create_het_distribution(
seqs, distrib_fhand=None, plot_fhand=None, summary_fhand=None, group_kind=None, groups=None, ploidy=2
):
"""It creates the distribution of the heterozygosity
(not takes in account ref allele)"""
title = "heterozygosity"
if groups and group_kind:
title = "heterozygosity (%s: %s)" % (group_kind, ",".join(groups))
hets = CachedArray("f")
for seq in seqs:
for snv in seq.get_features("snv"):
if not group_kind and "heterozygosity" in snv.qualifiers:
het = snv.qualifiers["heterozygosity"]
else:
het = calculate_heterozygosity(snv, ploidy, group_kind=group_kind, groups=groups)
if het is not None:
hets.append(het)
if list(hets):
create_distribution(
hets,
labels={"title": title},
distrib_fhand=distrib_fhand,
bins=None,
plot_fhand=plot_fhand,
range_=None,
summary_fhand=summary_fhand,
calculate_freqs=False,
remove_outliers=False,
)
def create_pic_distribution(
seqs, distrib_fhand=None, plot_fhand=None, summary_fhand=None, read_groups=None, group_kind=None, groups=None
):
"It creates the distribution of the pic (not takes in account ref allele)"
title = "pic"
if groups and group_kind:
title = "pic (%s: %s)" % (group_kind, ",".join(groups))
pics = CachedArray("f")
for seq in seqs:
for snv in seq.get_features("snv"):
if not group_kind and "pic" in snv.qualifiers:
pic = snv.qualifiers["pic"]
else:
pic = calculate_pic(snv, group_kind=group_kind, groups=groups)
if pic is not None:
pics.append(pic)
if list(pics):
create_distribution(
pics,
labels={"title": title},
distrib_fhand=distrib_fhand,
bins=None,
plot_fhand=plot_fhand,
range_=None,
summary_fhand=summary_fhand,
calculate_freqs=False,
remove_outliers=False,
)
def test_basic_statistics():
'It test the max, min avg, etc.'
item_list = [1, 2, 3]
storage = CachedArray(typecode='I')
storage.extend(item_list)
assert storage.max == max(item_list)
assert storage.min == min(item_list)
assert storage.average == 2
assert len(storage) == len(item_list)
def test_basic_distribution(self):
'It tests the distribution'
summary_fhand = StringIO()
distrib_fhand = StringIO()
numbers = CachedArray(typecode='I')
numbers.extend([1, 2, 3, 4, 5, 6, 7, 8, 9, 101, 2, 3, 4, 5, 6, 7, 8, 9])
create_distribution(numbers, distrib_fhand=distrib_fhand,
summary_fhand=summary_fhand)
result = '''Statistics for histogram
-------------------------
minimum: 1
maximum: 101
average: 10.5556
variance: 486.9136
sum: 190
items: 18'''
assert result in summary_fhand.getvalue()
def test_store_to_disk():
'It test the store for iterables saving to disk'
item_list = [1, 2, 3]
item_list2 = [4, 5, 6]
storage = CachedArray(typecode='I')
storage.extend(item_list)
storage.to_disk()
storage.extend(item_list2)
assert list(storage) == [1, 2, 3, 4, 5, 6]
def test_sample():
'It tests the random sample'
storage = CachedArray(typecode='I')
storage.extend([0] * 10000)
storage.extend([1] * 10000)
storage.extend([2] * 10000)
count = {}
for item in storage.sample:
try:
count[item] += 1
except KeyError:
count[item] = 1
len_sample = len(storage.sample)
assert len_sample == storage.sample_length
assert count[1] / (len_sample * 1.0) - 1/3.0 < 0.05
assert storage.get_sample_percentiles([5, 95]) == [0, 2]
