kj7rrv/gptc
1
0
Fork 0
Code Issues 2 Pull Requests Projects Releases 12 Wiki Activity

Include file name of output in arguments

Browse Source
This commit is contained in:
Samuel Sloniker 2022-12-24 12:17:44 -08:00
parent f8dbc78b82
commit ec7f4116fc
Signed by: kj7rrv
GPG Key ID: 1BB4029E66285A62
2 changed files with 19 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -27,9 +27,10 @@ argument, and it treats the input as a single token or ngram.
### Compiling models ### Compiling models
gptc compile [-n <max_ngram_length>] [-c <min_count>] <raw model file> gptc compile [-n <max_ngram_length>] [-c <min_count>] <raw model file> <compiled model file>
This will print the compiled model encoded in binary format to stdout. This will write the compiled model encoded in binary format to `<compiled model
file>`.
If `-c` is specified, words and ngrams used less than `min_count` times will be If `-c` is specified, words and ngrams used less than `min_count` times will be
excluded from the compiled model. excluded from the compiled model.

21
gptc/__main__.py
View File

@ -13,8 +13,13 @@ def main() -> None:
) )
subparsers = parser.add_subparsers(dest="subparser_name", required=True) subparsers = parser.add_subparsers(dest="subparser_name", required=True)
compile_parser = subparsers.add_parser("compile", help="compile a raw model") compile_parser = subparsers.add_parser(
"compile", help="compile a raw model"
)
compile_parser.add_argument("model", help="raw model to compile") compile_parser.add_argument("model", help="raw model to compile")
compile_parser.add_argument(
"out", help="name of file to write compiled model to"
)
compile_parser.add_argument( compile_parser.add_argument(
"--max-ngram-length", "--max-ngram-length",
"-n", "-n",
@ -53,11 +58,15 @@ def main() -> None:
action="store_true", action="store_true",
) )
check_parser = subparsers.add_parser("check", help="check one word or ngram in model") check_parser = subparsers.add_parser(
"check", help="check one word or ngram in model"
)
check_parser.add_argument("model", help="compiled model to use") check_parser.add_argument("model", help="compiled model to use")
check_parser.add_argument("token", help="token or ngram to check") check_parser.add_argument("token", help="token or ngram to check")
pack_parser = subparsers.add_parser("pack", help="pack a model from a directory") pack_parser = subparsers.add_parser(
"pack", help="pack a model from a directory"
)
pack_parser.add_argument("model", help="directory containing model") pack_parser.add_argument("model", help="directory containing model")
args = parser.parse_args() args = parser.parse_args()
@ -66,7 +75,10 @@ def main() -> None:
with open(args.model, "r") as f: with open(args.model, "r") as f:
model = json.load(f) model = json.load(f)
gptc.compile(model, args.max_ngram_length, args.min_count).serialize(sys.stdout.buffer) with open(args.out, "wb+") as f:
gptc.compile(
model, args.max_ngram_length, args.min_count
).serialize(f)
elif args.subparser_name == "classify": elif args.subparser_name == "classify":
with open(args.model, "rb") as f: with open(args.model, "rb") as f:
model = gptc.deserialize(f) model = gptc.deserialize(f)
@ -76,7 +88,6 @@ def main() -> None:
else: else:
text = sys.stdin.read() text = sys.stdin.read()
if args.category: if args.category:
classifier = gptc.Classifier(model, args.max_ngram_length) classifier = gptc.Classifier(model, args.max_ngram_length)
print(classifier.classify(text)) print(classifier.classify(text))