This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
@app.route("/tag", methods=['GET', 'POST']) | |
def tag(): | |
content = request.get_json(silent=True) | |
if len(content) > 50: | |
return abort(400) | |
tokens = map(nltk.word_tokenize, content) | |
tagged_tokens = map(nltk.pos_tag, tokens) | |
for_feature = pre_feature(tagged_tokens) | |
with_feature = map(feature_extractor, for_feature) | |
flattened_with_feature = [item for sublist in with_feature for item in sublist] | |
xseq = to_crfsuite(flattened_with_feature) | |
yseq = tagger.tag(xseq) | |
tags = [] | |
for y in yseq: | |
tags.append(y) | |
tags = list(reversed(tags)) | |
result = [] | |
for feature in with_feature: | |
tagged_token = [] | |
for token in feature: | |
tagged_token.append({"token": token['w'], "tag": tags.pop()}) | |
result.append(tagged_token) | |
return jsonify(tagged_tokens=result) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment