Languedoc Changeset - 3980aeb455b0

Changeset - 3980aeb455b0

Parent rev.

Child rev.

[Not reviewed]

default

0 1 0

Laman - 3 years ago 2022-09-28 22:56:06

sorted input files

1 file changed with 2 insertions and 3 deletions:

languedoc.py

0 comments (0 inline, 0 general)

languedoc.py

➞

Show inline comments

@@ @@ -116,13 +116,12 @@ def cross_validate(sample_sets): @@
 	models = [s.create_model() for s in sample_sets]
 	score = 0
 	max_score = 0
 	for s in sample_sets:
 		for (test_text, partial_model) in s.generate_tests():
 			partial_model.print_overview()
 			real_lang = partial_model.language
 			test_models = [partial_model] + [m for m in models if m.language != real_lang]
 			for k in TEST_LENS:
 				j = random.randrange(0, len(test_text)-k)
 				t = test_text[j:j+k]
@@ @@ -139,23 +138,23 @@ def identify(text, models): @@
 	sample = Sample(text=text)
 	return min(map(lambda m: (m.compare(sample), m.language), models))[1]
 DATA_DIR = os.path.join(os.path.dirname(__file__), "data")
 LANG_DIRS = [x.path for x in os.scandir(DATA_DIR)]
+LANG_DIRS = sorted([x.path for x in os.scandir(DATA_DIR)])
 if __name__ == "__main__":
 	samples = []
 	for d in LANG_DIRS:
 		lang = os.path.basename(d)
 		lang_samples = SampleSet(lang)
 		samples.append(lang_samples)
 		for file in os.scandir(d):
+		for file in sorted(os.scandir(d), key=lambda f: f.name):
 			with open(file) as f:
 				text = f.read()
 				text = preprocess(text)
 				print(f"{file.name} ({len(text)})")
 				print(text[:256])
 				print()

0 comments (0 inline, 0 general)