def tax_connect(feature, taxmap):
old = feature
feature, name, stratum = util.fsplit(feature)
if stratum is None or stratum == c_unclassified:
stratum2 = taxmap.get(feature, c_unclassified)
else:
stratum2 = taxmap.get(stratum, c_unclassified)
return util.fjoin(feature, name, stratum2)
def regroup(table, map_feature_groups, function, precision, ungrouped=False):
function = c_funcmap[function]
seen_before = {}
feature_counts = {}
# index of new group names to old table rows
mapping = {}
for i, rowhead in enumerate(table.rowheads):
feature, name, stratum = util.fsplit(rowhead)
if feature not in feature_counts:
feature_counts[feature] = 0
# decide which groups to use
if feature in map_feature_groups:
groups = map_feature_groups[feature]
elif ungrouped:
groups = [util.c_ungrouped]
else:
groups = []
# track grouping
for group in groups:
if feature not in seen_before and group != util.c_ungrouped:
feature_counts[feature] += 1
# account for stratified feature
groupname = group
if stratum is not None:
groupname = util.fjoin(groupname, stratum=stratum)
mapping.setdefault(groupname, []).append(i)
# we have processed an instance of this feature
seen_before[feature] = 1
# rebuild table
groupnames = util.fsort(mapping.keys())
groupdata = []
for groupname in groupnames:
oldrow_index = mapping[groupname]
newrow = [[] for j in range(len(table.colheads))]
for i in oldrow_index:
for j in range(len(table.colheads)):
newrow[j].append(float(table.data[i][j]))
# collapse groups
groupdata.append(
[round(function(block), precision) for block in newrow])
table.rowheads = groupnames
table.data = groupdata
# report
n = len(feature_counts)
ungrouped = list(feature_counts.values()).count(0)
grouped_total = n - ungrouped
grouped_multi = grouped_total - list(feature_counts.values()).count(1)
print( "Original Feature Count: %d; Grouped 1+ times: %d (%.1f%%); Grouped 2+ times: %d (%.1f%%)" % \
( n,
grouped_total,
100 * grouped_total / float( n ),
grouped_multi,
100 * grouped_multi / float( n ),
), file=sys.stderr )
def main():
args = get_args()
tbl = util.Table(args.input)
# build the taxmap
print("Building taxonomic map for input table", file=sys.stderr)
p_datafile = args.dev if args.dev is not None else databases[
args.resolution]
taxmap = build_taxmap(tbl.rowheads, args.level, p_datafile)
# refine the taxmap
counts = {}
for old, new in taxmap.items():
counts[new] = counts.get(new, 0) + 1
total = float(sum(counts.values()))
count = {k: v / total for k, v in counts.items()}
taxmap = {
old: new
for old, new in taxmap.items() if count[new] >= args.threshold
}
# reindex the table
print("Reindexing the input table", file=sys.stderr)
ticker = util.Ticker(tbl.rowheads)
index = {}
for i, rowhead in enumerate(tbl.rowheads):
ticker.tick()
feature, name, stratum = util.fsplit(rowhead)
new_rowhead = tax_connect(rowhead, taxmap)
# unmapped is never stratified
if feature == util.c_unmapped:
index.setdefault(rowhead, []).append(i)
# outside of unclassified mode, keep totals
elif stratum is None and args.mode != c_umode:
index.setdefault(rowhead, []).append(i)
# in totals mode, guess at taxonomy from uniref name
if args.mode == c_tmode:
index.setdefault(new_rowhead, []).append(i)
elif stratum == c_unclassified and args.mode == c_umode:
# in unclassified mode, make a new row for the total...
index.setdefault(util.fjoin(feature, name, None), []).append(i)
# ...then replace "unclassified" with inferred taxonomy
index.setdefault(new_rowhead, []).append(i)
elif stratum is not None and args.mode == c_smode:
index.setdefault(new_rowhead, []).append(i)
# rebuild the table
print("Rebuilding the input table", file=sys.stderr)
rowheads2, data2 = [], []
ticker = util.Ticker(index)
for rowhead in util.fsort(index):
ticker.tick()
rowheads2.append(rowhead)
newrow = [0 for k in tbl.colheads]
for i in index[rowhead]:
oldrow = map(float, tbl.data[i])
newrow = [a + b for a, b in zip(newrow, oldrow)]
data2.append(newrow)
tbl.rowheads = rowheads2
tbl.data = data2
# output
print("Writing new table", file=sys.stderr)
tbl.write(args.output, unfloat=True)
# report on performance
success, total = 0, 0
for rowhead in tbl.rowheads:
feature, name, stratum = util.fsplit(rowhead)
if stratum is not None:
total += 1
if stratum != c_unclassified:
success += 1
print(
"Summary: Of {TOTAL} stratifications, {SUCCESS} mapped at {TARGET} level ({PERCENT}%)"
.format(
TOTAL=total,
SUCCESS=success,
TARGET=args.level,
PERCENT=round(100 * success / float(total), 1),
),
file=sys.stderr,
)