Spaces:
Running
Running
File size: 1,968 Bytes
46193fd 97f7d3e 6fadf04 46193fd 907c0be 46193fd 47639e3 46193fd 47639e3 46193fd 47639e3 46193fd 47639e3 46193fd f7a1fef 907c0be f7a1fef |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.text_rank import TextRankSummarizer
from sumy.summarizers.lsa import LsaSummarizer
from sumy.summarizers.lex_rank import LexRankSummarizer
import nltk
nltk.download('punkt')
def summarize_with_textrank(text, sentences_count=10):
"""
Summarizes the provided text using TextRank algorithm.
Args:
text (str): Text to summarize.
sentences_count (int): Number of sentences for the summary.
Returns:
str: Summarized text.
"""
# Check if the text is not empty
if not text.strip():
return "Provided text is empty."
# Create a parser for the provided text
parser = PlaintextParser.from_string(text, Tokenizer("english"))
# Use TextRank for summarization
text_rank_summarizer = TextRankSummarizer()
text_rank_summary = text_rank_summarizer(parser.document, sentences_count=sentences_count)
# Compile summary into a single string
summary_text = "\n".join(str(sentence) for sentence in text_rank_summary)
return summary_text
# Define LSA summarization function
def summarize_with_lsa(text, sentences_count=10):
"""
Summarizes the provided text using LSA (Latent Semantic Analysis) algorithm.
Args:
text (str): Text to summarize.
sentences_count (int): Number of sentences for the summary.
Returns:
str: Summarized text.
"""
# Check if the text is not empty
if not text.strip():
return "Provided text is empty."
# Create a parser for the provided text
parser = PlaintextParser.from_string(text, Tokenizer("english"))
# Use LSA for summarization
lsa_summarizer = LsaSummarizer()
lsa_summary = lsa_summarizer(parser.document, sentences_count=sentences_count)
# Compile summary into a single string
summary_text = "\n".join(str(sentence) for sentence in lsa_summary)
return summary_text |