adding min-frequency option

This commit is contained in:
Ozbolt Menegatti 2019-02-19 14:57:48 +01:00
parent 93d7af3aea
commit de6c73980e

19
wani.py
View File

@ -856,7 +856,7 @@ class Writer:
return rows return rows
if len(rows[0]) <= self.sort_by: if len(rows[0]) <= self.sort_by:
print("Cannot sort by column #{}: Not enough columns!".format(len(rows[0])), file=sys.stderr) logging.warning("Cannot sort by column #{}: Not enough columns!".format(len(rows[0])))
return rows return rows
try: try:
@ -888,14 +888,15 @@ class Writer:
to_write.append("") # not yet implemented... to_write.append("") # not yet implemented...
if self.group: if self.group:
if colocation_ids.is_written(cid): if colocation_ids.should_write(cid):
continue
else:
to_write.append(colocation_ids.num(cid)) to_write.append(colocation_ids.num(cid))
colocation_ids.set_written(cid) colocation_ids.set_written(cid)
else:
continue
rows.append(to_write) rows.append(to_write)
if len(rows) > 0:
rows = self.sorted_rows(rows) rows = self.sorted_rows(rows)
file_handler.write("\n".join([", ".join(row) for row in rows]) + "\n") file_handler.write("\n".join([", ".join(row) for row in rows]) + "\n")
file_handler.flush() file_handler.flush()
@ -923,7 +924,6 @@ class Writer:
self.write_header(fp) self.write_header(fp)
sid_matches = matches[s.id] sid_matches = matches[s.id]
if len(sid_matches) > 0:
self.write_out_worker(fp, sid_matches, s.id, s.components, colocation_ids) self.write_out_worker(fp, sid_matches, s.id, s.components, colocation_ids)
if self.multiple_output: if self.multiple_output:
@ -936,6 +936,7 @@ class Writer:
class ColocationIds: class ColocationIds:
def __init__(self): def __init__(self):
self.data = {} self.data = {}
self.min_frequency = args.group
def add_match(self, key): def add_match(self, key):
if key in self.data: if key in self.data:
@ -946,8 +947,8 @@ class ColocationIds:
def get(self, key, n): def get(self, key, n):
return self.data[key][n] return self.data[key][n]
def is_written(self, key): def should_write(self, key):
return self.get(key, 2) return self.get(key, 1) >= self.min_frequency and not self.get(key, 2)
def num(self, key): def num(self, key):
return str(self.get(key, 1)) return str(self.get(key, 1))
@ -1048,8 +1049,8 @@ if __name__ == '__main__':
parser.add_argument('--skip-id-check', help='Skips checks for ids of <w> and <pc>, if they are in correct format', action='store_true') parser.add_argument('--skip-id-check', help='Skips checks for ids of <w> and <pc>, if they are in correct format', action='store_true')
parser.add_argument('--lemma-only', help='Will not write word ids, forms and msds in output', action='store_true') parser.add_argument('--lemma-only', help='Will not write word ids, forms and msds in output', action='store_true')
parser.add_argument('--without-rep', help='Will not write representtaions in output', action='store_true') parser.add_argument('--without-rep', help='Will not write representtaions in output', action='store_true')
parser.add_argument('--group', help='Group collocations with same collocation ID', action='store_true') parser.add_argument('--group', help='Group collocations with same collocation ID', type=int, default=0, const=1, nargs='?')
parser.add_argument('--verbose', help='Enable verbose output to stderr', choices=["warning", "info", "debug"], default="info") parser.add_argument('--verbose', help='Enable verbose output to stderr', choices=["warning", "info", "debug"], default="info", const="info", nargs='?')
parser.add_argument('--count-files', help="Count files: more verbose output", action='store_true') parser.add_argument('--count-files', help="Count files: more verbose output", action='store_true')
parser.add_argument('--multiple-output', help='Generate one output for each syntactic structure', action='store_true') parser.add_argument('--multiple-output', help='Generate one output for each syntactic structure', action='store_true')