def mkmodel(config):
this_dir = os.path.dirname(os.path.abspath(__file__))
root_dir = os.path.dirname(os.path.dirname(this_dir))
name = config["name"]
features = [isinstance(f, str) and [f] or f for f in config["features"]]
features.sort(key=lambda fs: ftrs.FEATURE_JOIN_STRING.join(fs).encode("UTF-8"))
with open(os.path.join(CORPORA_DIR, name + ".tok")) as fp:
ctxs = context.read_contexts(fp)
with open(os.path.join(root_dir, "models", name + ".mdl"), "w") as fp:
version = dump_model(name, features, ctxs, fp)
with open(os.path.join(root_dir, "src", name + ".cm"), "w") as fp:
dump_code(name, version, features, fp)
def mkmodel(config):
this_dir = os.path.dirname(os.path.abspath(__file__))
root_dir = os.path.dirname(os.path.dirname(this_dir))
name = config["name"]
features = [isinstance(f, str) and [f] or f for f in config["features"]]
features.sort(
key=lambda fs: ftrs.FEATURE_JOIN_STRING.join(fs).encode("UTF-8"))
with open(os.path.join(CORPORA_DIR, name + ".tok")) as fp:
ctxs = context.read_contexts(fp)
with open(os.path.join(root_dir, "models", name + ".mdl"), "w") as fp:
version = dump_model(name, features, ctxs, fp)
with open(os.path.join(root_dir, "src", name + ".cm"), "w") as fp:
dump_code(name, version, features, fp)
#!/usr/bin/env python3
"""
Reads a corpus from the standard input (see context.py for the expected format),
extracts features from it, and output a dataset file for use with bayes_fss.
"""
import sys, features, context
ctxs = context.read_contexts(sys.stdin, allow_empty_features=False)
fns = sorted(features.EXTRACTORS.items())
print("\t" + "\t".join(name for name, _ in fns))
for ctx, label in ctxs:
fields = [fn(ctx) for _, fn in fns]
print("%s\t%s" % (label, "\t".join(fields)))
#!/usr/bin/env python3
"""
Reads a corpus from the standard input (see context.py for the expected format),
extracts features from it, and output a dataset file for use with bayes_fss.
"""
import sys, features, context
ctxs = context.read_contexts(sys.stdin, allow_empty_features=False)
fns = sorted(features.EXTRACTORS.items())
print("\t" + "\t".join(name for name, _ in fns))
for ctx, label in ctxs:
fields = [fn(ctx) for _, fn in fns]
print("%s\t%s" % (label, "\t".join(fields)))
