def _write_table(self, table, filename, region_names):
if not any(table["<NA>"][None][None][1:]):
table.pop("<NA>")
zeros = [0] * (_MAX_DEPTH + 1)
first = lambda pair: (pair[0] or "")
rows = [["Name", "Sample", "Library", "Contig", "Size", "MaxDepth"] + ["MD_%03i" % i for i in xrange(1, _MAX_DEPTH + 1)]]
for sample, libraries in sorted(table.iteritems(), key = first):
for library, regions in sorted(libraries.iteritems(), key = first):
for (region, size) in sorted(region_names.items(), key = first):
key = (self._target_name, sample, library, region)
row = [("*" if value is None else value) for value in key]
counts = regions.get(region, zeros)
row.append(size)
row.append(self._calc_max_depth(counts))
row.extend(self._calc_cumfrac(counts))
rows.append(row)
if (key[-1] is None) and self._max_contigs_reached:
row = list(row)
row[3] = "<Genome>"
rows.append(row)
rows.append("#")
rows.extend("#")
while rows and rows[-1] == "#":
rows.pop()
with open(filename, "w") as table_file:
table_file.write(_HEADER % datetime.datetime.now().isoformat())
for line in padded_table(rows):
table_file.write(line)
table_file.write("\n")
def finalize(self):
"""Called by the pipeline at the termination of a run. By default,
this function prints the location of the log-file if one was created
during the run (e.g. if there were errors), and a summary of all nodes.
"""
runtime = (self._end_time or 0) - (self._start_time or 0)
if self.states[self.ERROR]:
print_err("Done; but errors were detected ...")
else:
print_info("Done ...")
print_info()
rows = [(" Number of nodes:", sum(self.states)),
(" Number of done nodes:", self.states[self.DONE]),
(" Number of runable nodes:", self.states[self.RUNABLE]),
(" Number of queued nodes:", self.states[self.QUEUED]),
(" Number of outdated nodes:", self.states[self.OUTDATED]),
(" Number of failed nodes:", self.states[self.ERROR]),
(" Pipeline runtime:", _fmt_runtime(round(runtime)))]
for line in text.padded_table(rows):
print_info(line)
print_info()
print_info("Use --list-output-files to view status of output files.")
logfile = pypeline.logger.get_logfile()
if logfile:
print_debug("Log-file located at %r" % (logfile, ))
print_info()
def finalize(self):
"""Called by the pipeline at the termination of a run. By default,
this function prints the location of the log-file if one was created
during the run (e.g. if there were errors), and a summary of all nodes.
"""
runtime = (self._end_time or 0) - (self._start_time or 0)
if self.states[self.ERROR]:
print_err("Done; but errors were detected ...")
else:
print_info("Done ...")
print_info()
rows = [(" Number of nodes:", sum(self.states)),
(" Number of done nodes:", self.states[self.DONE]),
(" Number of runable nodes:", self.states[self.RUNABLE]),
(" Number of queued nodes:", self.states[self.QUEUED]),
(" Number of outdated nodes:", self.states[self.OUTDATED]),
(" Number of failed nodes:", self.states[self.ERROR]),
(" Pipeline runtime:", _fmt_runtime(round(runtime)))]
for line in text.padded_table(rows):
print_info(line)
print_info()
print_info("Use --list-output-files to view status of output files.")
logfile = pypeline.logger.get_logfile()
if logfile:
print_debug("Log-file located at %r" % (logfile,))
print_info()
def _write_tables(self, out, genomes):
rows = [[
"Target", "Sample", "Library", "Measure", "Value", "# Description"
]]
for (target, samples) in sorted(
self._read_tables(self._prefixes, genomes).iteritems()):
for (sample, libraries) in sorted(samples.iteritems()):
for (library, prefixes) in sorted(libraries.iteritems()):
ordered = [("reads", prefixes.pop("reads"))
] if "reads" in prefixes else []
ordered.extend(sorted(prefixes.items()))
for (prefix, table) in ordered:
table.pop("hits_unique_nts(%s)" % prefix, None)
for (key, (value,
comment)) in sorted(table.iteritems(),
key=_measure_ordering):
if isinstance(
value,
numbers.Number) and math.isnan(value):
value = "NA"
rows.append(
(target, sample, library, key, value, comment))
rows.append("")
rows.append("")
for line in text.padded_table(rows):
out.write("%s\n" % line)
def _write_table(table, filename):
_calculate_totals(table)
rows = _build_rows(table)
with open(filename, "w") as table_file:
table_file.write(_HEADER % datetime.datetime.now().isoformat())
for line in padded_table(rows):
table_file.write(line)
table_file.write("\n")
def _write_areas_of_interest(self, table, rois):
table.write("# Regions Of Interest:\n")
rows = [["Genome", "ROI", "Size", "NFeatures", "NIntervals", "Path"]]
for (_, roi) in sorted(rois.items()):
rows.append([roi[key] for key in ("Genome", "Name", "Size", "NFeatures", "NIntervals", "Path")])
for line in text.padded_table(rows):
table.write("# %s\n" % (line,))
def _write_areas_of_interest(self, table, rois):
table.write("# Regions Of Interest:\n")
rows = [["Genome", "ROI", "Size", "NFeatures", "NIntervals", "Path"]]
for (_, roi) in sorted(rois.items()):
rows.append([roi[key] for key in ("Genome", "Name", "Size", "NFeatures", "NIntervals", "Path")])
for line in text.padded_table(rows):
table.write("# %s\n" % (line,))
def _write_genomes(self, table, genomes):
table.write("# Genomes:\n")
rows = [["Name", "Label", "Contigs", "Size", "Prefix"]]
for (_, prefix) in sorted(self._prefixes.items()):
stats = genomes[prefix["Name"]]
rows.append((prefix["Name"], prefix.get("Label", "-"), stats["NContigs"], stats["Size"], prefix["Path"]))
for line in text.padded_table(rows):
table.write("# %s\n" % (line,))
def _write_genomes(self, table, genomes):
table.write("# Genomes:\n")
rows = [["Name", "Label", "Contigs", "Size", "Prefix"]]
for (_, prefix) in sorted(self._prefixes.items()):
stats = genomes[prefix["Name"]]
rows.append((prefix["Name"], prefix.get("Label", "-"), stats["NContigs"], stats["Size"], prefix["Path"]))
for line in text.padded_table(rows):
table.write("# %s\n" % (line,))
def print_table(handle, args, totals):
lengths = collect_references(args, handle)
if args.outfile == "-":
output_handle = sys.stdout
else:
output_handle = open(args.outfile, "w")
with output_handle:
rows = build_table(args.target_name, totals, lengths)
output_handle.write(_HEADER % datetime.datetime.now().isoformat())
output_handle.write("\n")
for line in padded_table(rows):
output_handle.write(line)
output_handle.write("\n")
def print_table(handle, args, totals):
lengths = collect_references(args, handle)
if args.outfile == "-":
output_handle = sys.stdout
else:
output_handle = open(args.outfile, "w")
with output_handle:
rows = build_table(args.target_name, totals, lengths)
output_handle.write(_HEADER % datetime.datetime.now().isoformat())
output_handle.write("\n")
for line in padded_table(rows):
output_handle.write(line)
output_handle.write("\n")
def write_table(table, filename):
table = calculate_totals(table)
rows = build_rows(table)
if filename == "-":
output_handle = sys.stdout
else:
output_handle = open(filename, "w")
try:
output_handle.write(TABLE_HEADER % datetime.datetime.now().isoformat())
for line in padded_table(rows):
output_handle.write(line)
output_handle.write("\n")
finally:
if output_handle is not sys.stdout:
output_handle.close()
def write_table(table, filename):
table = calculate_totals(table)
rows = build_rows(table)
if filename == "-":
output_handle = sys.stdout
else:
output_handle = open(filename, "w")
try:
output_handle.write(TABLE_HEADER % datetime.datetime.now().isoformat())
for line in padded_table(rows):
output_handle.write(line)
output_handle.write("\n")
finally:
if output_handle is not sys.stdout:
output_handle.close()
def _write_tables(self, out, genomes):
rows = [["Target", "Sample", "Library", "Measure", "Value", "# Description"]]
for (target, samples) in sorted(self._read_tables(self._prefixes, genomes).iteritems()):
for (sample, libraries) in sorted(samples.iteritems()):
for (library, prefixes) in sorted(libraries.iteritems()):
ordered = [("reads", prefixes.pop("reads"))] if "reads" in prefixes else []
ordered.extend(sorted(prefixes.items()))
for (prefix, table) in ordered:
table.pop("hits_unique_nts(%s)" % prefix, None)
for (key, (value, comment)) in sorted(table.iteritems(), key=_measure_ordering):
if isinstance(value, numbers.Number) and math.isnan(value):
value = "NA"
rows.append((target, sample, library, key, value, comment))
rows.append("")
rows.append("")
for line in text.padded_table(rows):
out.write("%s\n" % line)
def _write_table(self, table, filename, region_names):
if not any(table["<NA>"][None][None][1:]):
table.pop("<NA>")
zeros = [0] * (_MAX_DEPTH + 1)
first = lambda pair: (pair[0] or "")
rows = [["Name", "Sample", "Library", "Contig", "Size", "MaxDepth"] +
["MD_%03i" % i for i in xrange(1, _MAX_DEPTH + 1)]]
for sample, libraries in sorted(table.iteritems(), key=first):
for library, regions in sorted(libraries.iteritems(), key=first):
for (region, size) in sorted(region_names.items(), key=first):
key = (self._target_name, sample, library, region)
row = [("*" if value is None else value) for value in key]
counts = regions.get(region, zeros)
row.append(size)
row.append(self._calc_max_depth(counts))
row.extend(self._calc_cumfrac(counts))
rows.append(row)
if (key[-1] is None) and self._max_contigs_reached:
row = list(row)
row[3] = "<Genome>"
rows.append(row)
rows.append("#")
rows.extend("#")
while rows and rows[-1] == "#":
rows.pop()
with open(filename, "w") as table_file:
table_file.write(_HEADER % datetime.datetime.now().isoformat())
for line in padded_table(rows):
table_file.write(line)
table_file.write("\n")
def _padded_table(*args, **kwargs):
return list(padded_table(*args, **kwargs))
def _padded_table(*args, **kwargs):
return list(padded_table(*args, **kwargs))