本文整理汇总了Python中scilifelab.db.statusdb.SampleRunMetricsConnection类的典型用法代码示例。如果您正苦于以下问题:Python SampleRunMetricsConnection类的具体用法?Python SampleRunMetricsConnection怎么用?Python SampleRunMetricsConnection使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
在下文中一共展示了SampleRunMetricsConnection类的20个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Python代码示例。
示例1: test_dbcon
def test_dbcon(self):
"""Test database connection and that we get expected values."""
s_con = SampleRunMetricsConnection(dbname="samples-test", username="u", password="p")
samples = [s_con.get_entry(x) for x in s_con.name_view]
samples_d = {x["name"]: x for x in samples}
self.assertEqual(samples_d["1_120924_AC003CCCXX_TGACCA"]["date"], "120924")
self.assertEqual(samples_d["1_121015_BB002BBBXX_TGACCA"]["flowcell"], "BB002BBBXX")
self.assertEqual(samples_d["2_120924_AC003CCCXX_ACAGTG"]["entity_type"], "sample_run_metrics")
self.assertEqual(samples_d["3_120924_AC003CCCXX_ACAGTG"]["lane"], "3")
self.assertEqual(samples_d["4_120924_AC003CCCXX_CGTTAA"]["sequence"], "CGTTAA")
self.assertEqual(samples_d["2_121015_BB002BBBXX_TGACCA"]["project_id"], "P002")
fc_con = FlowcellRunMetricsConnection(dbname="flowcells-test", username="u", password="p")
flowcells = [fc_con.get_entry(x) for x in fc_con.name_view]
flowcells_d = {x["name"]: x for x in flowcells}
self.assertEqual(flowcells_d["120924_AC003CCCXX"]["name"], "120924_AC003CCCXX")
self.assertEqual(flowcells_d["121015_BB002BBBXX"]["name"], "121015_BB002BBBXX")
self.assertEqual(flowcells_d["120924_AC003CCCXX"]["entity_type"], "flowcell_run_metrics")
p_con = ProjectSummaryConnection(dbname="projects-test", username="u", password="p")
projects = [p_con.get_entry(x) for x in p_con.name_view]
projects_d = {x["project_name"]: x for x in projects}
self.assertEqual(projects_d["J.Doe_00_01"]["min_m_reads_per_sample_ordered"], 0.1)
self.assertEqual(projects_d["J.Doe_00_01"]["no_of_samples"], 2)
self.assertEqual(
set(projects_d["J.Doe_00_01"]["samples"].keys()), set(["P001_101_index3", "P001_102", "P001_103"])
)
self.assertEqual(projects_d["J.Doe_00_01"]["customer_reference"], "GnuGenome")
self.assertEqual(projects_d["J.Doe_00_02"]["min_m_reads_per_sample_ordered"], 0.2)
self.assertEqual(projects_d["J.Doe_00_03"]["samples"].keys(), ["3_index6"])
self.assertIn("A", projects_d["J.Doe_00_03"]["samples"]["3_index6"]["library_prep"])
开发者ID:pombredanne,项目名称:scilifelab,代码行数:29,代码来源:test_db.py
示例2: test_2_make_note
def test_2_make_note(self):
"""Make a note subset by example flowcell and project"""
s_con = SampleRunMetricsConnection(username=self.user, password=self.pw, url=self.url)
fc_con = FlowcellRunMetricsConnection(username=self.user, password=self.pw, url=self.url)
p_con = ProjectSummaryConnection(username=self.user, password=self.pw, url=self.url)
paragraphs = sample_note_paragraphs()
headers = sample_note_headers()
samples = s_con.get_samples(self.examples["flowcell"], self.examples["project"])
project = p_con.get_entry(self.examples["project"])
samples = p_con.map_srm_to_name(self.examples["project"], fc_id=self.examples["flowcell"], use_bc_map=True)
for k,v in samples.items():
s_param = parameters
s = s_con.get_entry(k)
s_param.update({key:s[srm_to_parameter[key]] for key in srm_to_parameter.keys()})
fc = "{}_{}".format(s["date"], s["flowcell"])
s_param["phix_error_rate"] = fc_con.get_phix_error_rate(str(fc), s["lane"])
s_param['avg_quality_score'] = s_con.calc_avg_qv(s["name"])
s_param['rounded_read_count'] = round(float(s_param['rounded_read_count'])/1e6,1) if s_param['rounded_read_count'] else None
s_param['customer_name'] = project['samples'][v["sample"]].get('customer_name', None)
if project:
s_param['ordered_amount'] = p_con.get_ordered_amount(self.examples["project"])
s_param['customer_reference'] = s_param.get('customer_reference', project['customer_reference'])
s_param['uppnex_project_id'] = s_param.get('uppnex_project_id', project['uppnex_id'])
s_param['success'] = sequencing_success(s_param, cutoffs)
s_param.update({k:"N/A" for k in s_param.keys() if s_param[k] is None})
make_note("{}.pdf".format(s["barcode_name"]), headers, paragraphs, **s_param)
开发者ID:hussius,项目名称:scilifelab,代码行数:27,代码来源:test_sample_delivery_note.py
示例3: test_4_get_samples
def test_4_get_samples(self):
"""Test getting samples given flowcell and sample_prj."""
sample_con = SampleRunMetricsConnection(username=self.user, password=self.pw, url=self.url)
samples = sample_con.get_samples(fc_id=self.examples["flowcell"])
print "Number of samples before subsetting: " + str(len(samples))
samples = sample_con.get_samples(fc_id=self.examples["flowcell"], sample_prj=self.examples["project"])
print "Number of samples after subsetting: " + str(len(samples))
开发者ID:hussius,项目名称:scilifelab,代码行数:7,代码来源:test_db.py
示例4: test_get_samples_wrong_info
def test_get_samples_wrong_info(self):
"""Test getting samples when either flowcell or project id information is wrong"""
sample_con = SampleRunMetricsConnection(dbname="samples-test", username=self.user, password=self.pw, url=self.url)
samples = sample_con.get_samples(sample_prj="bogusproject", fc_id=self.examples["flowcell"])
LOG.info("Selecting on bogus project, subsetting on flowcell: " + str(len(samples)))
self.assertEqual(len(samples), 0)
开发者ID:Galithil,项目名称:scilifelab,代码行数:7,代码来源:test_db.py
示例5: fastq_screen
def fastq_screen(project_name=None, flowcell=None,
username=None, password=None, url=None, dbname="samples", **kw):
"""Perform application specific qc on a project.
:param project_name: project name
:param flowcell: flowcell identifier
:param username: database username
:param password: database password
:param url: database url
:param dbname: samples database name
"""
LOG.debug("Running fastq screen summary on project {}, flowcell ".format(project_name, flowcell))
output_data = {'stdout':StringIO(), 'stderr':StringIO()}
s_con = SampleRunMetricsConnection(dbname=dbname, username=username, password=password, url=url)
samples = s_con.get_samples(fc_id=flowcell, sample_prj=project_name)
for s in samples:
LOG.debug("Checking fastq_screen data for sample {}, id {}, project {}".format(s.get("name", None), s.get("_id", None), s.get("sample_prj", None)))
fqscreen_data = s.get("fastq_scr", {})
output_data["stdout"].write(s["barcode_name"] + "\n")
if fqscreen_data:
header = [[x for x in v.keys()] for k, v in fqscreen_data.iteritems()]
output_data["stdout"].write("\t\t" + "".join("{:>27}".format(x) for x in header[0]) + "\n")
vals = ["{:>12}\t{}\n".format(k, "".join(["{:>27}".format(x) for x in v.values()])) for k, v in fqscreen_data.iteritems()]
for v in vals:
output_data["stdout"].write(v)
return output_data
开发者ID:Galithil,项目名称:scilifelab,代码行数:26,代码来源:qc.py
示例6: test_get_flowcell
def test_get_flowcell(self):
"""Test getting a flowcell for a given sample"""
sample_con = SampleRunMetricsConnection(
dbname="samples-test", username=self.user, password=self.pw, url=self.url
)
fc = sample_con.get_entry(self.examples["sample"], "flowcell")
self.assertEqual(str(fc), self.examples["flowcell"])
开发者ID:pombredanne,项目名称:scilifelab,代码行数:7,代码来源:test_db.py
示例7: test_4_srm_sample_map
def test_4_srm_sample_map(self):
"""Make sample map from sample run metrics"""
s_con = SampleRunMetricsConnection(username=self.user, password=self.pw, url=self.url)
samples = s_con.get_project_samples(self.examples["project"])
sample_names = {x["name"]:x["_id"] for x in samples}
print len(sample_names.keys())
print len(list(set(sample_names.keys())))
print sample_names
开发者ID:hussius,项目名称:scilifelab,代码行数:8,代码来源:test_project_status_note.py
示例8: test_get_sample_ids
def test_get_sample_ids(self):
"""Test getting sample ids given flowcell and sample_prj"""
sample_con = SampleRunMetricsConnection(dbname="samples-test", username=self.user, password=self.pw, url=self.url)
sample_ids = sample_con.get_sample_ids(fc_id=self.examples["flowcell"])
LOG.info("Number of samples before subsetting: " + str(len(sample_ids)))
self.assertEqual(len(sample_ids), 5)
sample_ids = sample_con.get_sample_ids(fc_id=self.examples["flowcell"], sample_prj=self.examples["project"])
LOG.info( "Number of samples after subsetting: " + str(len(sample_ids)))
self.assertEqual(len(sample_ids), 2)
开发者ID:Galithil,项目名称:scilifelab,代码行数:9,代码来源:test_db.py
示例9: test_get_project_sample_ids
def test_get_project_sample_ids(self):
"""Test getting project sample ids"""
sample_con = SampleRunMetricsConnection(
dbname="samples-test", username=self.user, password=self.pw, url=self.url
)
sample_ids = sample_con.get_sample_ids(sample_prj=self.examples["project"])
sample_names = [sample_con.db.get(x)["name"] for x in sample_ids]
self.assertEqual(
set(sample_names),
set(["1_120924_AC003CCCXX_TGACCA", "2_120924_AC003CCCXX_ACAGTG", "1_121015_BB002BBBXX_TGACCA"]),
)
开发者ID:pombredanne,项目名称:scilifelab,代码行数:11,代码来源:test_db.py
示例10: test_get_samples
def test_get_samples(self):
"""Test getting samples given flowcell and sample_prj."""
sample_con = SampleRunMetricsConnection(dbname="samples-test", username=self.user, password=self.pw, url=self.url)
samples = sample_con.get_samples(fc_id=self.examples["flowcell"])
LOG.info("Selecting on flowcell: " + str(len(samples)))
self.assertEqual(len(samples), 5)
samples = sample_con.get_samples(fc_id=self.examples["flowcell"], sample_prj=self.examples["project"])
LOG.info("Selecting on flowcell, subsetting on project: " + str(len(samples)))
self.assertEqual(len(samples), 2)
samples = sample_con.get_samples(sample_prj=self.examples["project"])
LOG.info("Selecting on project: " + str(len(samples)))
self.assertEqual(len(samples), 3)
samples = sample_con.get_samples(sample_prj=self.examples["project"], fc_id=self.examples["flowcell"])
LOG.info("Selecting on project, subsetting on flowcell: " + str(len(samples)))
self.assertEqual(len(samples), 2)
开发者ID:Galithil,项目名称:scilifelab,代码行数:17,代码来源:test_db.py
示例11: setUp
def setUp(self):
self.app = self.make_app(
argv=["qc", "upload-qc", flowcells[0], "--mtime", "10000"],
extensions=["scilifelab.pm.ext.ext_qc", "scilifelab.pm.ext.ext_couchdb"],
)
self._run_app()
self.s_con = SampleRunMetricsConnection(dbname="samples-test", username="u", password="p")
self.p_con = ProjectSummaryConnection(dbname="projects-test", username="u", password="p")
self.fc_con = FlowcellRunMetricsConnection(dbname="flowcells-test", username="u", password="p")
开发者ID:pombredanne,项目名称:scilifelab,代码行数:9,代码来源:test_db.py
示例12: upload_qc
def upload_qc(self):
if not self._check_pargs(["flowcell"]):
return
url = self.pargs.url if self.pargs.url else self.app.config.get("db", "url")
if not url:
self.app.log.warn("Please provide a valid url: got {}".format(url))
return
if not validate_fc_directory_format(self.pargs.flowcell):
self.app.log.warn(
"Path '{}' does not conform to bcbio flowcell directory format; aborting".format(self.pargs.flowcell)
)
return
runinfo_csv = os.path.join(os.path.abspath(self.pargs.flowcell), "{}.csv".format(fc_id(self.pargs.flowcell)))
runinfo_yaml = os.path.join(os.path.abspath(self.pargs.flowcell), "run_info.yaml")
(fc_date, fc_name) = fc_parts(self.pargs.flowcell)
if int(fc_date) < 120815:
self.log.info("Assuming pre-casava based file structure for {}".format(fc_id(self.pargs.flowcell)))
qc_objects = self._collect_pre_casava_qc()
else:
self.log.info("Assuming casava based file structure for {}".format(fc_id(self.pargs.flowcell)))
qc_objects = self._collect_casava_qc()
if len(qc_objects) == 0:
self.log.info("No out-of-date qc objects for {}".format(fc_id(self.pargs.flowcell)))
return
else:
self.log.info("Retrieved {} updated qc objects".format(len(qc_objects)))
s_con = SampleRunMetricsConnection(dbname=self.app.config.get("db", "samples"), **vars(self.app.pargs))
fc_con = FlowcellRunMetricsConnection(dbname=self.app.config.get("db", "flowcells"), **vars(self.app.pargs))
p_con = ProjectSummaryConnection(dbname=self.app.config.get("db", "projects"), **vars(self.app.pargs))
for obj in qc_objects:
if self.app.pargs.debug:
self.log.debug("{}: {}".format(str(obj), obj["_id"]))
if isinstance(obj, FlowcellRunMetricsDocument):
dry("Saving object {}".format(repr(obj)), fc_con.save(obj))
if isinstance(obj, SampleRunMetricsDocument):
project_sample = p_con.get_project_sample(
obj.get("sample_prj", None), obj.get("barcode_name", None), self.pargs.extensive_matching
)
if project_sample:
obj["project_sample_name"] = project_sample["sample_name"]
dry("Saving object {}".format(repr(obj)), s_con.save(obj))
开发者ID:vals,项目名称:scilifelab,代码行数:44,代码来源:ext_qc.py
示例13: test_2_make_project_note
def test_2_make_project_note(self):
"""Make a project note subset by flowcell and project"""
s_con = SampleRunMetricsConnection(username=self.user, password=self.pw, url=self.url)
fc_con = FlowcellRunMetricsConnection(username=self.user, password=self.pw, url=self.url)
p_con = ProjectSummaryConnection(username=self.user, password=self.pw, url=self.url)
paragraphs = project_note_paragraphs()
headers = project_note_headers()
param = parameters
project = p_con.get_entry(self.examples["project"])
if not project:
print "No project named {}".format(self.examples["project"])
return
if project:
ordered_amount = p_con.get_ordered_amount(self.examples["project"])
else:
return
ordered_amount = self.pargs.ordered_million_reads
## Start collecting the data
sample_table = []
sample_list = project['samples']
param.update({key:project.get(ps_to_parameter[key], None) for key in ps_to_parameter.keys()})
samples = p_con.map_name_to_srm(self.examples["project"], check_consistency=True, use_bc_map=True)
all_passed = True
for k,v in samples.items():
if k=="Unexpected":
continue
project_sample = sample_list[k]
vals = {x:project_sample.get(prjs_to_table[x], None) for x in prjs_to_table.keys()}
vals['MOrdered'] = ordered_amount
vals['BarcodeSeq'] = s_con.get_entry(v.keys()[0], "sequence")
## Set status
vals['Status'] = set_status(vals) if vals['Status'] is None else vals['Status']
vals.update({k:"N/A" for k in vals.keys() if vals[k] is None})
if vals['Status']=="N/A" or vals['Status']=="NP": all_passed = False
sample_table.append([vals[k] for k in table_keys])
if all_passed: param["finished"] = 'Project finished.'
sample_table.sort()
sample_table = list(sample_table for sample_table,_ in itertools.groupby(sample_table))
sample_table.insert(0, ['ScilifeID', 'CustomerID', 'BarcodeSeq', 'MSequenced', 'MOrdered', 'Status'])
paragraphs["Samples"]["tpl"] = make_sample_table(sample_table)
make_note("{}.pdf".format(self.examples["project"]), headers, paragraphs, **param)
开发者ID:hussius,项目名称:scilifelab,代码行数:43,代码来源:test_project_status_note.py
示例14: update
def update(self):
if not self._check_pargs(["sample_prj"]):
return
url = self.pargs.url if self.pargs.url else self.app.config.get("db", "url")
if not url:
self.app.log.warn("Please provide a valid url: got {}".format(url))
return
s_con = SampleRunMetricsConnection(dbname=self.app.config.get("db", "samples"), **vars(self.app.pargs))
samples = s_con.get_samples(sample_prj=self.pargs.sample_prj)
if self.pargs.project_id:
self.app.log.debug("Going to update 'project_id' to {} for sample runs with 'sample_prj' == {}".format(self.pargs.project_id, self.pargs.sample_prj))
for s in samples:
if not s.get("project_id", None) is None:
if not query_yes_no("'project_id':{} for sample {}; are you sure you want to overwrite?".format(s["project_id"], s["name"]), force=self.pargs.force):
continue
s["project_id"] = self.pargs.project_id
s_con.save(s)
if self.pargs.names:
self.app.log.debug("Going to update 'project_sample_name' for sample runs with 'sample_prj' == {}".format(self.pargs.sample_prj))
if os.path.exists(self.pargs.names):
with open(self.pargs.names) as fh:
names_d = json.load(fh)
else:
names_d= ast.literal_eval(self.pargs.names)
samples_sort = sorted(samples, key=lambda s:s["barcode_name"])
groups = {}
for k, g in itertools.groupby(samples_sort, key=lambda x:x["barcode_name"]):
groups[k] = list(g)
for barcode_name in names_d:
sample_list = groups.get(barcode_name, None)
if not sample_list:
continue
for s in sample_list:
if not s.get("project_sample_name", None) is None:
if not query_yes_no("'project_sample_name':{} for sample {}; are you sure you want to overwrite?".format(s["project_sample_name"], s["name"]), force=self.pargs.force):
continue
s["project_sample_name"] = names_d[barcode_name]
s_con.save(s)
else:
self.app.log.info("Trying to use extensive matching...")
p_con = ProjectSummaryConnection(dbname=self.app.config.get("db", "projects"), **vars(self.app.pargs))
project_name = self.pargs.sample_prj
if self.pargs.project_alias:
project_name = self.pargs.project_alias
for s in samples:
project_sample = p_con.get_project_sample(project_name, s["barcode_name"], extensive_matching=True)
if project_sample:
self.app.log.info("using mapping '{} : {}'...".format(s["barcode_name"], project_sample["sample_name"]))
s["project_sample_name"] = project_sample["sample_name"]
s_con.save(s)
开发者ID:emmser,项目名称:scilifelab,代码行数:52,代码来源:ext_qc.py
示例15: setUp
def setUp(self):
"""FIXME: All other tests depend on data being uploaded, so
these are not real unit tests. The setup to TestQCUpload has to
be run prior to other tests, else unexpected failures will
occur."""
self.app = self.make_app(argv = ['qc', 'upload-qc', flowcells[0], '--mtime', '10000'], extensions=['scilifelab.pm.ext.ext_qc', 'scilifelab.pm.ext.ext_couchdb'])
self._run_app()
self.app = self.make_app(argv = ['qc', 'upload-qc', flowcells[1], '--mtime', '10000'], extensions=['scilifelab.pm.ext.ext_qc', 'scilifelab.pm.ext.ext_couchdb'])
self._run_app()
self.s_con = SampleRunMetricsConnection(dbname="samples-test", username="u", password="p")
self.p_con = ProjectSummaryConnection(dbname="projects-test", username="u", password="p")
self.fc_con = FlowcellRunMetricsConnection(dbname="flowcells-test", username="u", password="p")
开发者ID:Galithil,项目名称:scilifelab,代码行数:12,代码来源:test_db.py
示例16: _project_status_note_table
def _project_status_note_table(project_name=None, username=None, password=None, url=None,
use_ps_map=True, use_bc_map=False, check_consistency=False,
ordered_million_reads=None, uppnex_id=None, customer_reference=None,
exclude_sample_ids={}, project_alias=None, sample_aliases={},
projectdb="projects", samplesdb="samples", flowcelldb="flowcells",
include_all_samples=False, param={}, **kw):
# mapping project_summary to parameter keys
ps_to_parameter = {"scilife_name":"scilife_name", "customer_name":"customer_name", "project_name":"project_name"}
# mapping project sample to table
table_keys = ['ScilifeID', 'SubmittedID', 'BarcodeSeq', 'MSequenced', 'MOrdered']
output_data = {'stdout':StringIO(), 'stderr':StringIO(), 'debug':StringIO()}
# Connect and run
s_con = SampleRunMetricsConnection(dbname=samplesdb, username=username, password=password, url=url)
fc_con = FlowcellRunMetricsConnection(dbname=flowcelldb, username=username, password=password, url=url)
p_con = ProjectSummaryConnection(dbname=projectdb, username=username, password=password, url=url)
#Get the information source for this project
source = p_con.get_info_source(project_name)
# Get project summary from project database
sample_aliases = _literal_eval_option(sample_aliases, default={})
prj_summary = p_con.get_entry(project_name)
if not prj_summary:
LOG.warn("No such project '{}'".format(project_name))
return
LOG.debug("Working on project '{}'.".format(project_name))
# Determine if project is finished by getting all samples sequenced date
try:
all_samples_sequenced = prj_summary['project_summary']['all_samples_sequenced']
except (TypeError,KeyError):
all_samples_sequenced = False
# Get sample run list and loop samples to make mapping sample -> {sampleruns}
sample_run_list = _set_sample_run_list(project_name, flowcell=None, project_alias=project_alias, s_con=s_con)
samples = {}
for s in sample_run_list:
prj_sample = p_con.get_project_sample(project_name, s.get("project_sample_name", None))
if prj_sample:
sample_name = prj_sample['project_sample'].get("scilife_name", None)
s_d = {s["name"] : {'sample':sample_name, 'id':s["_id"]}}
samples.update(s_d)
else:
if s["barcode_name"] in sample_aliases:
s_d = {sample_aliases[s["barcode_name"]] : {'sample':sample_aliases[s["barcode_name"]], 'id':s["_id"]}}
samples.update(s_d)
else:
s_d = {s["name"]:{'sample':s["name"], 'id':s["_id"], 'barcode_name':s["barcode_name"]}}
LOG.warn("No mapping found for sample run:\n '{}'".format(s_d))
# Convert to mapping from desired sample name to list of aliases
# Less important for the moment; one solution is to update the
# Google docs summary table to use the P names
sample_dict = prj_summary['samples']
param.update({key:prj_summary.get(ps_to_parameter[key], None) for key in ps_to_parameter.keys()})
param["ordered_amount"] = param.get("ordered_amount", p_con.get_ordered_amount(project_name, samples=sample_dict))
if not param.get('customer_reference') :
try:
param['customer_reference'] = prj_summary['details']['customer_project_reference']
except (TypeError,KeyError):
param['customer_reference'] = prj_summary.get('customer_reference')
param['uppnex_project_id'] = param.get('uppnex_project_id', prj_summary.get('uppnex_id'))
# Override database values if options passed at command line
if uppnex_id:
param["uppnex_project_id"] = uppnex_id
if customer_reference:
param["customer_reference"] = customer_reference
# Process options
ordered_million_reads = _literal_eval_option(ordered_million_reads)
exclude_sample_ids = _literal_eval_option(exclude_sample_ids, default={})
## Start collecting the data
sample_table = []
samples_excluded = []
last_library_preps = p_con.get_latest_library_prep(project_name)
last_library_preps_srm = [x for l in last_library_preps.values() for x in l]
LOG.debug("Looping through sample map that maps project sample names to sample run metrics ids")
for k,v in samples.items():
LOG.debug("project sample '{}' maps to '{}'".format(k, v))
if not include_all_samples:
if v['sample'] not in last_library_preps.keys():
LOG.info("No library prep information for sample {}; keeping in report".format(v['sample']))
else:
if k not in last_library_preps_srm:
LOG.info("Sample run {} ('{}') is not latest library prep ({}) for project sample {}: excluding from report".format(k, v["id"], ",".join(list(set(last_library_preps[v['sample']].values()))), v['sample']))
continue
else:
pass
if re.search("Unexpected", k):
continue
barcode_seq = s_con.get_entry(k, "sequence")
# Exclude sample id?
if _exclude_sample_id(exclude_sample_ids, v['sample'], barcode_seq):
samples_excluded.append(v['sample'])
#.........这里部分代码省略.........
开发者ID:guillermo-carrasco,项目名称:scilifelab,代码行数:101,代码来源:delivery_notes.py
示例17: data_delivery_note
def data_delivery_note(**kw):
"""Create an easily parseable information file with information about the data delivery
"""
output_data = {'stdout':StringIO(), 'stderr':StringIO(), 'debug':StringIO()}
project_name = kw.get('project_name',None)
flowcell = kw.get('flowcell',None)
LOG.debug("Generating data delivery note for project {}{}.".format(project_name,' and flowcell {}'.format(flowcell if flowcell else '')))
# Get a connection to the project and sample databases
p_con = ProjectSummaryConnection(**kw)
assert p_con, "Could not connect to project database"
s_con = SampleRunMetricsConnection(**kw)
assert s_con, "Could not connect to sample database"
# Get the entry for the project and samples from the database
LOG.debug("Fetching samples from sample database")
samples = s_con.get_samples(sample_prj=project_name, fc_id=flowcell)
LOG.debug("Got {} samples from database".format(len(samples)))
# Get the customer sample names from the project database
LOG.debug("Fetching samples from project database")
project_samples = p_con.get_entry(project_name, "samples")
customer_names = {sample_name:sample.get('customer_name','N/A') for sample_name, sample in project_samples.items()}
data = [['SciLifeLab ID','Submitted ID','Flowcell','Lane','Barcode','Read','Path','MD5','Size (bytes)','Timestamp']]
for sample in samples:
sname = sample.get('project_sample_name','N/A')
cname = customer_names.get(sname,'N/A')
fc = sample.get('flowcell','N/A')
lane = sample.get('lane','N/A')
barcode = sample.get('sequence','N/A')
if 'raw_data_delivery' not in sample:
data.append([sname,cname,'','','','','','','',''])
continue
delivery = sample['raw_data_delivery']
tstamp = delivery.get('timestamp','N/A')
for read, file in delivery.get('files',{}).items():
data.append([sname,
cname,
fc,
lane,
barcode,
read,
file.get('path','N/A'),
file.get('md5','N/A'),
file.get('size_in_bytes','N/A'),
tstamp,])
# Write the data to a csv file
outfile = "{}{}_data_delivery.csv".format(project_name,'_{}'.format(flowcell) if flowcell else '')
LOG.debug("Writing delivery data to {}".format(outfile))
with open(outfile,"w") as outh:
csvw = csv.writer(outh)
for row in data:
csvw.writerow(row)
# Write Texttable formatted output to stdout
tt = texttable.Texttable(180)
tt.add_rows(data)
output_data['stdout'].write(tt.draw())
return output_data
开发者ID:guillermo-carrasco,项目名称:scilifelab,代码行数:63,代码来源:delivery_notes.py
示例18: TestQCUpload
class TestQCUpload(PmFullTest):
def setUp(self):
"""FIXME: All other tests depend on data being uploaded, so
these are not real unit tests. The setup to TestQCUpload has to
be run prior to other tests, else unexpected failures will
occur."""
self.app = self.make_app(argv = ['qc', 'upload-qc', flowcells[0], '--mtime', '10000'], extensions=['scilifelab.pm.ext.ext_qc', 'scilifelab.pm.ext.ext_couchdb'])
self._run_app()
self.app = self.make_app(argv = ['qc', 'upload-qc', flowcells[1], '--mtime', '10000'], extensions=['scilifelab.pm.ext.ext_qc', 'scilifelab.pm.ext.ext_couchdb'])
self._run_app()
self.s_con = SampleRunMetricsConnection(dbname="samples-test", username="u", password="p")
self.p_con = ProjectSummaryConnection(dbname="projects-test", username="u", password="p")
self.fc_con = FlowcellRunMetricsConnection(dbname="flowcells-test", username="u", password="p")
def test_samplesheet(self):
"""Test samplesheet upload"""
fc = self.fc_con.get_entry("120924_AC003CCCXX")
self.assertEqual(fc["samplesheet_csv"][0]["Index"], "TGACCA")
self.assertEqual(fc["samplesheet_csv"][0]["Description"], "J__Doe_00_01")
self.assertEqual(fc["samplesheet_csv"][0]["FCID"], "C003CCCXX")
self.assertEqual(fc["samplesheet_csv"][1]["SampleRef"], "hg19")
self.assertEqual(fc["samplesheet_csv"][2]["SampleID"], "P002_101_index3")
def test_qc_upload(self):
"""Test running qc upload to server. Slightly circular testing
here - I setup the module with qc update so by definition the
test must 'work'"""
self.app = self.make_app(argv = ['qc', 'upload-qc', flowcells[1], '--mtime', '100'], extensions=['scilifelab.pm.ext.ext_qc', 'scilifelab.pm.ext.ext_couchdb'])
self._run_app()
s = self.s_con.get_entry("4_120924_AC003CCCXX_CGTTAA")
self.assertIsNone(s["project_sample_name"])
self.assertEqual(s["project_id"], "P003")
def test_qc_update(self):
"""Test running qc update of a project id"""
s = self.s_con.get_entry("4_120924_AC003CCCXX_CGTTAA")
s["project_id"]= None
self.assertIsNone(s["project_id"])
self.s_con.save(s)
self.app = self.make_app(argv = ['qc', 'update', '--sample_prj', projects[2], '--project_id', 'P003', '--debug', '--force'], extensions=['scilifelab.pm.ext.ext_qc', 'scilifelab.pm.ext.ext_couchdb'])
self._run_app()
s = self.s_con.get_entry("4_120924_AC003CCCXX_CGTTAA")
self.assertEqual(s["project_id"], "P003")
def test_qc_update_sample_names(self):
"""Test running qc update of project sample names"""
s1 = self.s_con.get_entry("1_120924_AC003CCCXX_TGACCA")
s2 = self.s_con.get_entry("2_120924_AC003CCCXX_ACAGTG")
s1["project_sample_name"] = None
s2["project_sample_name"] = None
self.assertIsNone(s1["project_sample_name"])
self.assertIsNone(s2["project_sample_name"])
self.s_con.save(s1)
self.s_con.save(s2)
sample_map = {'P001_101_index3': 'P001_101_index3', 'P001_102_index6':'P001_102'}
self.app = self.make_app(argv = ['qc', 'update', '--sample_prj', projects[0], '--names', "{}".format(sample_map), '--debug', '--force'], extensions=['scilifelab.pm.ext.ext_qc', 'scilifelab.pm.ext.ext_couchdb'])
self._run_app()
s1 = self.s_con.get_entry("1_120924_AC003CCCXX_TGACCA")
s2 = self.s_con.get_entry("2_120924_AC003CCCXX_ACAGTG")
self.assertEqual(s1["project_sample_name"], "P001_101_index3")
self.assertEqual(s2["project_sample_name"], "P001_102")
开发者ID:Galithil,项目名称:scilifelab,代码行数:61,代码来源:test_db.py
示例19: TestQCUpload
class TestQCUpload(PmFullTest):
def setUp(self):
self.app = self.make_app(
argv=["qc", "upload-qc", flowcells[0], "--mtime", "10000"],
extensions=["scilifelab.pm.ext.ext_qc", "scilifelab.pm.ext.ext_couchdb"],
)
self._run_app()
self.s_con = SampleRunMetricsConnection(dbname="samples-test", username="u", password="p")
self.p_con = ProjectSummaryConnection(dbname="projects-test", username="u", password="p")
self.fc_con = FlowcellRunMetricsConnection(dbname="flowcells-test", username="u", password="p")
def test_samplesheet(self):
"""Test samplesheet upload"""
fc = self.fc_con.get_entry("120924_AC003CCCXX")
self.assertEqual(fc["samplesheet_csv"][0]["Index"], "TGACCA")
self.assertEqual(fc["samplesheet_csv"][0]["Description"], "J__Doe_00_01")
self.assertEqual(fc["samplesheet_csv"][0]["FCID"], "C003CCCXX")
self.assertEqual(fc["samplesheet_csv"][1]["SampleRef"], "hg19")
self.assertEqual(fc["samplesheet_csv"][2]["SampleID"], "P001_101_index3")
def test_qc_upload(self):
"""Test running qc upload to server"""
self.app = self.make_app(
argv=["qc", "upload-qc", flowcells[1], "--mtime", "100"],
extensions=["scilifelab.pm.ext.ext_qc", "scilifelab.pm.ext.ext_couchdb"],
)
self._run_app()
s = self.s_con.get_entry("4_120924_AC003CCCXX_CGTTAA")
self.assertIsNone(s["project_sample_name"])
self.assertEqual(s["project_id"], "P003")
def test_qc_update(self):
"""Test running qc update of a project id"""
s = self.s_con.get_entry("4_120924_AC003CCCXX_CGTTAA")
s["project_id"] = None
self.assertIsNone(s["project_id"])
self.s_con.save(s)
self.app = self.make_app(
argv=["qc", "update", "--sample_prj", projects[2], "--project_id", "P003", "--debug", "--force"],
extensions=["scilifelab.pm.ext.ext_qc", "scilifelab.pm.ext.ext_couchdb"],
)
self._run_app()
s = self.s_con.get_entry("4_120924_AC003CCCXX_CGTTAA")
self.assertEqual(s["project_id"], "P003")
def test_qc_update_sample_names(self):
"""Test running qc update of project sample names"""
s1 = self.s_con.get_entry("1_120924_AC003CCCXX_TGACCA")
s2 = self.s_con.get_entry("2_120924_AC003CCCXX_ACAGTG")
s1["project_sample_name"] = None
s2["project_sample_name"] = None
self.assertIsNone(s1["project_sample_name"])
self.assertIsNone(s2["project_sample_name"])
self.s_con.save(s1)
self.s_con.save(s2)
sample_map = {"P001_101_index3": "P001_101_index3&quo
|
请发表评论