Last active
November 30, 2022 04:07
-
-
Save sscovil/a2ecff2b3b03eace7d7e052b017bb2a6 to your computer and use it in GitHub Desktop.
Python Keyphrase Extraction (PKE) AWS Lambda Docker Image (1/3)
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
#!/usr/bin/env python | |
import json | |
import pke | |
extractor = pke.unsupervised.TopicRank() | |
def lambda_handler(event, context): | |
body = event["body"] if "body" in event else event | |
if isinstance(body, str): | |
body = json.loads(event["body"]) | |
lang = "en" | |
count = 10 | |
if isinstance(body, str): | |
text = body | |
else: | |
text = body["text"] if "text" in body else body | |
lang = body["lang"] if "lang" in body else lang | |
count = body["count"] if "count" in body else count | |
extractor.load_document(input=text, language=lang) | |
extractor.candidate_selection() | |
extractor.candidate_weighting() | |
keywords = extractor.get_n_best(n=count) | |
tags = [keyword[0] for keyword in keywords] | |
return { | |
"statusCode": 200, | |
"tags": tags | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment