def test_merge(self):
EXPECTED_VALUES = {
"n_reads": 300,
"n_zmws": 60,
}
NAMES = {
"n_reads": "Number of reads",
"n_zmws": "Number of ZMWs"
}
chunks = [
Report("pbcommand_test",
attributes=[
Attribute(id_="n_reads", value=50, name="Number of reads"),
Attribute(id_="n_zmws", value=10, name="Number of ZMWs")],
dataset_uuids=["12345"]),
Report("pbcommand_test",
attributes=[
Attribute(id_="n_reads", value=250, name="Number of reads"),
Attribute(id_="n_zmws", value=50, name="Number of ZMWs")]),
]
r = Report.merge(chunks)
self.assertEqual([a.id for a in r.attributes], ["n_reads", "n_zmws"])
self.assertEqual(r._dataset_uuids, ["12345"])
for attr in r.attributes:
self.assertEqual(attr.value, EXPECTED_VALUES[attr.id])
self.assertEqual(attr.name, NAMES[attr.id])
for table in r.tables:
for column in table.columns:
self.assertEqual(column.header, NAMES[column.id])
def test_merge(self):
EXPECTED_VALUES = {
"n_reads": 300,
"n_zmws": 60,
}
NAMES = {"n_reads": "Number of reads", "n_zmws": "Number of ZMWs"}
chunks = [
Report("pbcommand_test",
attributes=[
Attribute(id_="n_reads",
value=50,
name="Number of reads"),
Attribute(id_="n_zmws", value=10, name="Number of ZMWs")
],
dataset_uuids=["12345"]),
Report("pbcommand_test",
attributes=[
Attribute(id_="n_reads",
value=250,
name="Number of reads"),
Attribute(id_="n_zmws", value=50, name="Number of ZMWs")
]),
]
r = Report.merge(chunks)
self.assertEqual([a.id for a in r.attributes], ["n_reads", "n_zmws"])
self.assertEqual(r._dataset_uuids, ["12345"])
for attr in r.attributes:
self.assertEqual(attr.value, EXPECTED_VALUES[attr.id])
self.assertEqual(attr.name, NAMES[attr.id])
for table in r.tables:
for column in table.columns:
self.assertEqual(column.header, NAMES[column.id])
def test_merge_tables(self):
names = ['laa_report1.json', 'laa_report2.json']
r = Report.merge([_to_report(names[0]), _to_report(names[1])])
table = r.tables[0]
self.assertEqual(len(table.columns), 7)
self.assertEqual([col.header for col in table.columns], [
'BarcodeName', 'FastaName', 'CoarseCluster', 'Phase',
'TotalCoverage', 'SequenceLength', 'PredictedAccuracy'
])
for col in table.columns:
self.assertEqual(len(col.values), 4)
if col.header == 'BarcodeName':
self.assertEqual(
col.values,
['Barcode1', 'Barcode2', 'Barcode4', 'Barcode3'])
elif col.header == 'FastaName':
self.assertEqual(col.values, [
'BarcodeFasta1', 'BarcodeFasta2', 'BarcodeFasta4',
'BarcodeFasta3'
])
else:
self.assertEqual(col.values, [1, 2, 4, 3])
column_list_d = table.to_columns_d()
self.assertEqual(len(column_list_d), 4)
def test_merge_tables(self):
names = ['laa_report1.json', 'laa_report2.json']
r = Report.merge([_to_report(names[0]), _to_report(names[1])])
table = r.tables[0]
assert len(table.columns) == 7
assert [col.header for col in table.columns] == [
'BarcodeName', 'FastaName', 'CoarseCluster', 'Phase',
'TotalCoverage', 'SequenceLength', 'PredictedAccuracy'
]
for col in table.columns:
assert len(col.values) == 4
if col.header == 'BarcodeName':
assert col.values == [
'Barcode1', 'Barcode2', 'Barcode4', 'Barcode3'
]
elif col.header == 'FastaName':
assert col.values == [
'BarcodeFasta1', 'BarcodeFasta2', 'BarcodeFasta4',
'BarcodeFasta3'
]
else:
assert col.values == [1, 2, 4, 3]
column_list_d = table.to_columns_d()
assert len(column_list_d) == 4
def test_merge_tables(self):
names = ["laa_report1.json", "laa_report2.json"]
r = Report.merge([_to_report(names[0]), _to_report(names[1])])
table = r.tables[0]
self.assertEqual(len(table.columns), 7)
self.assertEqual(
[col.header for col in table.columns],
[
"BarcodeName",
"FastaName",
"CoarseCluster",
"Phase",
"TotalCoverage",
"SequenceLength",
"PredictedAccuracy",
],
)
for col in table.columns:
self.assertEqual(len(col.values), 4)
if col.header == "BarcodeName":
self.assertEqual(col.values, ["Barcode1", "Barcode2", "Barcode4", "Barcode3"])
elif col.header == "FastaName":
self.assertEqual(col.values, ["BarcodeFasta1", "BarcodeFasta2", "BarcodeFasta4", "BarcodeFasta3"])
else:
self.assertEqual(col.values, [1, 2, 4, 3])
def gather_report(json_files, output_file):
"""
Combines statistics (usually raw counts) stored as JSON files.
Data models: pbcommand.models.report
"""
reports = [ load_report_from_json(fn) for fn in json_files ]
merged = Report.merge(reports)
with open(output_file, "w") as writer:
writer.write(merged.to_json())
return output_file
def gather_report(json_files, output_file):
"""
Combines statistics (usually raw counts) stored as JSON files.
Data models: pbcommand.models.report
"""
reports = [load_report_from_json(fn) for fn in json_files]
merged = Report.merge(reports)
with open(output_file, "w") as writer:
writer.write(merged.to_json())
return output_file
def test_merge(self):
r = Report.merge([
Report.from_simple_dict("pbcommand_test",
{"n_reads": 50, "n_zmws": 10},
"pbcommand"),
Report.from_simple_dict("pbcommand_test",
{"n_reads": 250, "n_zmws": 50},
"pbcommand")])
attr = {a.id: a.value for a in r.attributes}
self.assertEqual(attr['pbcommand_n_reads'], 300)
self.assertEqual(attr['pbcommand_n_zmws'], 60)
def gather_report(json_files, output_file, dataset_xml=None):
"""
Combines statistics (usually raw counts) stored as JSON files.
Data models: pbcommand.models.report
"""
reports = [load_report_from_json(fn) for fn in json_files]
merged = Report.merge(reports)
if dataset_xml is not None:
ds_md = get_dataset_metadata(dataset_xml)
merged._dataset_uuids = [ds_md.uuid]
with open(output_file, "w") as writer:
writer.write(merged.to_json())
return output_file
def test_merge(self):
EXPECTED_VALUES = {
"n_reads": 300,
"n_zmws": 60,
"sample": "Person1,Person2"
}
NAMES = {
"n_reads": "Number of reads",
"n_zmws": "Number of ZMWs",
"sample": "Sample"
}
chunks = [
Report("pbcommand_test",
attributes=[
Attribute(id_="n_reads",
value=50,
name="Number of reads"),
Attribute(id_="n_zmws", value=10,
name="Number of ZMWs"),
Attribute(id_="sample", value="Person1", name="Sample")
],
dataset_uuids=["12345"]),
Report("pbcommand_test",
attributes=[
Attribute(id_="n_reads",
value=250,
name="Number of reads"),
Attribute(id_="n_zmws", value=50,
name="Number of ZMWs"),
Attribute(id_="sample", value="Person2", name="Sample")
]),
]
r = Report.merge(chunks)
assert [a.id for a in r.attributes] == ["n_reads", "n_zmws", "sample"]
assert r._dataset_uuids == ["12345"]
for attr in r.attributes:
assert attr.value == EXPECTED_VALUES[attr.id]
assert attr.name == NAMES[attr.id]
for table in r.tables:
for column in table.columns:
assert column.header == NAMES[column.id]
def test_merge_tables(self):
names = ['laa_report1.json', 'laa_report2.json']
r = Report.merge([_to_report(names[0]), _to_report(names[1])])
table = r.tables[0]
self.assertEqual(len(table.columns), 7)
self.assertEqual(
[col.header for col in table.columns],
['BarcodeName', 'FastaName', 'CoarseCluster', 'Phase',
'TotalCoverage', 'SequenceLength', 'PredictedAccuracy'])
for col in table.columns:
self.assertEqual(len(col.values), 4)
if col.header == 'BarcodeName':
self.assertEqual(
col.values,
['Barcode1', 'Barcode2', 'Barcode4', 'Barcode3'])
elif col.header == 'FastaName':
self.assertEqual(
col.values,
['BarcodeFasta1', 'BarcodeFasta2', 'BarcodeFasta4',
'BarcodeFasta3'])
else:
self.assertEqual(col.values, [1, 2, 4, 3])
def gather_report(json_files, output_file):
"""
Combines statistics (usually raw counts) stored as JSON files.
Data models: pbcommand.models.report
"""
reports = [ load_report_from_json(fn) for fn in json_files ]
merged = Report.merge(reports)
total_num_flnc_bases = 0
total_num_flnc = 0
for r in reports:
attrs = {a.id:a.value for a in r.attributes}
num_flnc = attrs["num_flnc"]
num_flnc_bases = attrs["num_flnc_bases"]
total_num_flnc += num_flnc
total_num_flnc_bases += num_flnc_bases
if total_num_flnc > 0:
for a in merged.attributes:
if a.id == "avg_flnc_len":
# mimicking pbtranscript.io.Summary
a._value = int(total_num_flnc_bases / total_num_flnc)
log.info("Setting avg_flnc_len = {v}".format(v=a.value))
with open(output_file, "w") as writer:
writer.write(merged.to_json())
return output_file
def gather_report(json_files, output_file):
"""
Combines statistics (usually raw counts) stored as JSON files.
Data models: pbcommand.models.report
"""
reports = [load_report_from_json(fn) for fn in json_files]
merged = Report.merge(reports)
total_num_flnc_bases = 0
total_num_flnc = 0
for r in reports:
attrs = {a.id: a.value for a in r.attributes}
num_flnc = attrs["num_flnc"]
num_flnc_bases = attrs["num_flnc_bases"]
total_num_flnc += num_flnc
total_num_flnc_bases += num_flnc_bases
if total_num_flnc > 0:
for a in merged.attributes:
if a.id == "avg_flnc_len":
# mimicking pbtranscript.io.Summary
a._value = int(total_num_flnc_bases / total_num_flnc)
log.info("Setting avg_flnc_len = {v}".format(v=a.value))
with open(output_file, "w") as writer:
writer.write(merged.to_json())
return output_file
