def summarize(path_stage1, path_stage2, path_stage3, wordlimit,
phraselimit):
print('Generating summary...')
#Calculate a significance weight for each sentence, using MinHash to approximate a Jaccard distance from key phrases determined by TextRank
kernel = pytextrank.rank_kernel(path_stage2)
try:
os.remove(path_stage3)
except OSError:
pass
with open(path_stage3, 'w') as f:
for s in pytextrank.top_sentences(kernel, path_stage1):
f.write(pytextrank.pretty_print(s._asdict()))
f.write("\n")
#print(pytextrank.pretty_print(s._asdict()))
#Summarize essay based on most significant sentences and key phrases
phrases = ", ".join(
set([
p
for p in pytextrank.limit_keyphrases(path_stage2,
phrase_limit=phraselimit)
]))
sent_iter = sorted(pytextrank.limit_sentences(path_stage3,
word_limit=wordlimit),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(pytextrank.make_sentence(sent_text))
graf_text = " ".join(s)
#print("**excerpts:** %s\n\n**keywords:** %s" % (graf_text, phrases,))
return graf_text, phrases
def get_key_phrases(path_stage2):
"""Get all found key phrases."""
phrases = set([
p for p in pytextrank.limit_keyphrases(
os.path.join(PATH_PREFIX, path_stage2), phrase_limit=3)
])
return phrases
def text_rank(json_request):
pattern = re.compile("TI - (.*?)\\r|AB - (.*?)\\r")
matches = re.findall(pattern, json_request['ris'])
all_inputs = []
for section in matches:
all_inputs.append((''.join([word + ' ' for word in section])).strip())
input_json = {}
input_json['id'] = "0"
input_json['text'] = '.'.join(all_inputs)
with open('ris_extracted.json', 'w') as output:
json.dump(input_json, output)
with open(path_stage1, 'w') as f:
for graf in pytextrank.parse_doc(pytextrank.json_iter('ris_extracted.json')):
f.write("%s\n" % pytextrank.pretty_print(graf._asdict()))
graph, ranks = pytextrank.text_rank(path_stage1)
with open(path_stage2, 'w') as f:
for rl in pytextrank.normalize_key_phrases(path_stage1, ranks):
f.write("%s\n" % pytextrank.pretty_print(rl._asdict()))
phrases = list([p for p in pytextrank.limit_keyphrases(path_stage2, phrase_limit=20)])
return phrases
def summarise_text(self, key_phrases_output, top_sentences_output):
"""
Summarise the text filtered by the top n sentences count.
Put summary sentences together along with the key phrases
which helped to determine the summary sentences.
Parameters
==========
key_phrases_output:
text file (JSON) into which key phrases are stored
top_sentences_output:
text file (JSON) into which top scored sentences are written
Return
======
Nothing, writes top n sentences into a text file (JSON)
by the name specified in top_sentences_output
"""
phrases = pytextrank.limit_keyphrases(key_phrases_output,
phrase_limit=12)
key_phrases = ", ".join([phrase for phrase in phrases])
sentence_iterator = sorted(pytextrank.limit_sentences( \
top_sentences_output, word_limit=150), key=lambda x: x[1])
sentences = []
for sentence_text in sentence_iterator:
sentences.append(pytextrank.make_sentence(sentence_text[0]))
return " ".join(sentences), key_phrases
def summarize(self, _id, content_text, word_limit):
self.logger.log("_id: " + _id)
self.logger.log("word_limit: " + str(word_limit))
# File names
path_stage0 = 'process/' + _id + '.json'
path_stage1 = 'process/' + _id + '_o1.json'
path_stage2 = 'process/' + _id + '_o2.json'
path_stage3 = 'process/' + _id + '_o3.json'
path_stage4 = 'process/' + _id + '_o4.json'
# Create input file
with open(path_stage0, 'w') as outfile:
json.dump({"id": "123", "text": content_text}, outfile)
# Statistical Parsing - Stage 1
# Perform statistical parsing/tagging on a document in JSON format
with open(path_stage1, 'w') as f:
for graf in pytextrank.parse_doc(
pytextrank.json_iter(path_stage0)):
f.write("%s\n" % pytextrank.pretty_print(graf._asdict()))
# Ranked Keyphrases - Stage 2
# Collect and normalize the key phrases from a parsed document
graph, ranks = pytextrank.text_rank(path_stage1)
pytextrank.render_ranks(graph, ranks)
with open(path_stage2, 'w') as f:
for rl in pytextrank.normalize_key_phrases(path_stage1, ranks):
f.write("%s\n" % pytextrank.pretty_print(rl._asdict()))
# Extractive Summarization - Stage 3
# Calculate a significance weight for each sentence, using MinHash to approximate a Jaccard distance from key phrases determined by TextRank
kernel = pytextrank.rank_kernel(path_stage2)
with open(path_stage3, 'w') as f:
for s in pytextrank.top_sentences(kernel, path_stage1):
f.write(pytextrank.pretty_print(s._asdict()))
f.write("\n")
# Final Output - Stage 4
# Summarize a document based on most significant sentences and key phrases
phrases = ", ".join(
set([
p for p in pytextrank.limit_keyphrases(path_stage2,
phrase_limit=12)
]))
sent_iter = sorted(pytextrank.limit_sentences(path_stage3,
word_limit=word_limit),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(pytextrank.make_sentence(sent_text))
graf_text = " ".join(s)
return {'excerpts': graf_text, 'keywords': phrases}
def pytrankSummarize(filename):
"""
This is another TextRank algorithm. It works in four stages, each feeding its output to the next
1. Part-of-Speech Tagging and lemmatization are performed for every sentence in the document.
2. Key phrases are extracted along with their counts, and are normalized.
3. Calculates a score for each sentence by approximating jaccard distance between the sentence and key phrases.
4. Summarizes the document based on most significant sentences and key phrases.
"""
import pytextrank
jsonText = createJSON(filename)
path_stage0 = jsonText
path_stage1 = "o1.json"
with open(path_stage1, 'w') as f:
for graf in pytextrank.parse_doc(pytextrank.json_iter(path_stage0)):
f.write("%s\n" % pytextrank.pretty_print(graf._asdict()))
path_stage2 = "o2.json"
graph, ranks = pytextrank.text_rank(path_stage1)
with open(path_stage2, 'w') as f:
for rl in pytextrank.normalize_key_phrases(path_stage1, ranks):
f.write("%s\n" % pytextrank.pretty_print(rl._asdict()))
path_stage3 = "o3.json"
kernel = pytextrank.rank_kernel(path_stage2)
with open(path_stage3, 'w') as f:
for s in pytextrank.top_sentences(kernel, path_stage1):
f.write(pytextrank.pretty_print(s._asdict()))
f.write("\n")
phrases = ", ".join(
set([
p
for p in pytextrank.limit_keyphrases(path_stage2, phrase_limit=12)
]))
sent_iter = sorted(pytextrank.limit_sentences(path_stage3, word_limit=50),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(pytextrank.make_sentence(sent_text))
graf_text = " ".join(s)
print("")
print("####### From PyTextRank #######")
print("**excerpts:** %s\n\n**keywords:** %s" % (
graf_text,
phrases,
))
def stage4(path_stage2, path_stage3, phrase_l, word_l):
#Stage 4
phrases = [
p for p in pytextrank.limit_keyphrases(path_stage2,
phrase_limit=int(phrase_l))
]
sent_iter = sorted(pytextrank.limit_sentences(path_stage3,
word_limit=int(word_l)),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(" ".join(sent_text))
return phrases, s
def summarise_text(self, key_phrases_output, top_sentences_output):
key_phrases = ", ".join(
set([
phrase
for phrase in pytextrank.limit_keyphrases(key_phrases_output,
phrase_limit=12)
]))
sentence_iterator = sorted(pytextrank.limit_sentences(
top_sentences_output, word_limit=150),
key=lambda x: x[1])
sentences = []
for sentence_text, idx in sentence_iterator:
sentences.append(pytextrank.make_sentence(sentence_text))
return " ".join(sentences), key_phrases
def summarize_text(input_file):
# seriously f**k this API
path_stage0 = input_file
path_stage1 = 'stage1.txt'
with open(path_stage1, 'w') as f:
for graf in pytextrank.parse_doc(pytextrank.json_iter(path_stage0)):
f.write("%s\n" % pytextrank.pretty_print(graf._asdict()))
# to view output in this notebook
#print(pytextrank.pretty_print(graf))
graph, ranks = pytextrank.text_rank(path_stage1)
pytextrank.render_ranks(graph, ranks)
path_stage2 = 'stage2.txt'
with open(path_stage2, 'w') as f:
for rl in pytextrank.normalize_key_phrases(path_stage1, ranks):
f.write("%s\n" % pytextrank.pretty_print(rl._asdict()))
# to view output in this notebook
#print(pytextrank.pretty_print(rl))
path_stage3 = 'stage3.txt'
kernel = pytextrank.rank_kernel(path_stage2)
with open(path_stage3, 'w') as f:
for s in pytextrank.top_sentences(kernel, path_stage1):
f.write(pytextrank.pretty_print(s._asdict()))
f.write("\n")
# to view output in this notebook
#print(pytextrank.pretty_print(s._asdict()))
phrases = ", ".join(
set([
p
for p in pytextrank.limit_keyphrases(path_stage2, phrase_limit=12)
]))
sent_iter = sorted(pytextrank.limit_sentences(path_stage3, word_limit=120),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(pytextrank.make_sentence(sent_text))
graf_text = " ".join(s)
#print("**excerpts:** %s\n\n**keywords:** %s" % (graf_text, phrases,))
return ' '.join(s)
def summarise_text(self, key_phrases_output, top_sentences_output):
"""
Summarise the text filtered by the top n sentences count.
Put summary sentences together along with the key phrases
which helped to determine the summary sentences.
"""
key_phrases = ", ".join({
[
phrase for phrase in \
pytextrank.limit_keyphrases(key_phrases_output, phrase_limit=12)
]
})
sentence_iterator = sorted(pytextrank.limit_sentences( \
top_sentences_output, word_limit=150), key=lambda x: x[1])
sentences = []
for sentence_text in sentence_iterator:
sentences.append(pytextrank.make_sentence(sentence_text))
return " ".join(sentences), key_phrases
def stage_4():
cur_dir = os.path.dirname(__file__)
data_dir = stage_1_dir
ids = os.listdir(data_dir)
phrase_limit = 15
word_limit = 100
result_dir = stage_4_dir + '_limits_' + str(phrase_limit) + '_' + str(
word_limit)
if os.path.exists(result_dir):
shutil.rmtree(result_dir, ignore_errors=True)
os.mkdir(result_dir)
os.chdir(result_dir)
for cur_id in ids:
phrases = ", ".join(
set([
p for p in pytextrank.limit_keyphrases(
stage_2_dir + '\\' + cur_id, phrase_limit=phrase_limit)
]))
sent_iter = sorted(pytextrank.limit_sentences(stage_3_dir + '\\' +
cur_id,
word_limit=word_limit),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(pytextrank.make_sentence(sent_text))
graf_text = " ".join(s)
with codecs.open(cur_id[:-5] + '.txt', "w+", "utf_8_sig") as file:
file.write("**excerpts:** %s\n\n**keywords:** %s" % (
graf_text,
phrases,
))
os.chdir(cur_dir)
def extract_phrasesfrom_textrank(corpus):
record_data = pd.DataFrame({'sentences': corpus})
record_data = pd.DataFrame({
'id': record_data.index.tolist(),
'text': record_data['sentences'].tolist()
})
tweet_items = []
for jdict in record_data.to_dict(orient='records'):
tweet_items.append(jdict)
new_df_tweet = pd.DataFrame(columns=['text', 'keywords'])
path_stage1 = "celebrity1_tweet.json"
path_stage2 = "celebrity2_tweet.json"
path_stage3 = "celebrity3_tweet.json"
for item in tweet_items:
items_new = [item]
with open(path_stage1, 'w') as f:
for graf in pytextrank.parse_doc(items_new):
f.write("%s\n" % pytextrank.pretty_print(graf._asdict()))
graph, ranks = pytextrank.text_rank(path_stage1)
pytextrank.render_ranks(graph, ranks)
with open(path_stage2, 'w') as f:
for rl in pytextrank.normalize_key_phrases(path_stage1, ranks):
f.write("%s\n" % pytextrank.pretty_print(rl._asdict()))
kernel = pytextrank.rank_kernel(path_stage2)
with open(path_stage3, 'w') as f:
for s in pytextrank.top_sentences(kernel, path_stage1):
f.write(pytextrank.pretty_print(s._asdict()))
f.write("\n")
phrases = ", ".join(
set([
p for p in pytextrank.limit_keyphrases(path_stage2,
phrase_limit=5)
]))
sent_iter = sorted(pytextrank.limit_sentences(path_stage3,
word_limit=150),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(pytextrank.make_sentence(sent_text))
graf_text = " ".join(s)
new_df_tweet = new_df_tweet.append(
{
'text': item.get('text'),
'keywords': phrases
}, ignore_index=True)
celeb_list = [
'Bradley Cooper', 'Chris Kyle', 'Clint Eastwood', 'bradley cooper',
'bradley', 'cooper', 'chris kyle', 'chris', 'kyle', 'clint eastwood',
'clint', 'eastwood'
]
cleaned_df_tweet = pd.DataFrame(columns=['sentences', 'keywords'])
for index, row in new_df_tweet.iterrows():
if any(celeb in row['keywords'] for celeb in celeb_list):
cleaned_df_tweet = cleaned_df_tweet.append(
{
'sentences': row['text'],
'keywords': row['keywords']
},
ignore_index=True)
cleaned_df_tweet.to_csv(phrase_filepath,
sep=',',
encoding='utf-8',
index=False)
new_df_tweet.to_csv(all_phrasefile_path,
sep=',',
encoding='utf-8',
index=False)
return new_df_tweet, cleaned_df_tweet
sentences_fake_json = [] # stage 3 output
for s in pytextrank.top_sentences(kernel, fake_json_graph_dicts):
sentence_dict = s._asdict()
sentences_fake_json.append([sentence_dict])
print(pytextrank.pretty_print(sentence_dict))
stage_3_filename = "{publisher}_{version}_textRank.topSentences.".format(
version=version, publisher=publisher)
stage_3_out = os.path.join(directory, "Stage3Results",
"agglomerated", stage_3_filename)
pickle.dump(fake_json_graph_dicts, open(stage_3_out, 'wb'))
#stage 4: generate a summary of the entire set of books
phrases = ", ".join(
set([
p for p in pytextrank.limit_keyphrases(rl_fake_json,
phrase_limit=12)
]))
sent_iter = sorted(pytextrank.limit_sentences(sentences_fake_json,
word_limit=150),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(pytextrank.make_sentence(sent_text))
graf_text = " ".join(s)
print("**excerpts:** %s\n\n**keywords:** %s" % (
graf_text,
phrases,
))
import networkx as nx
# import pylab as plt
nx.draw(graph, with_labels=True)
# plt.show()
path_stage3 = "../tests/pytextrank_dat/o3.json"
kernel = ptr.rank_kernel(path_stage2)
with open(path_stage3, 'w') as f:
for s in ptr.top_sentences(kernel, path_stage1):
f.write(ptr.pretty_print(s._asdict()))
f.write("\n")
print(ptr.pretty_print(s._asdict()))
# Stage 4
phrases = ", ".join(
set([p for p in ptr.limit_keyphrases(path_stage2, phrase_limit=12)]))
sent_iter = sorted(ptr.limit_sentences(path_stage3, word_limit=150),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(ptr.make_sentence(sent_text))
graf_text = " ".join(s)
print("**excerpts:** %s\n\n**keywords:** %s" % (
graf_text,
phrases,
))
'minimal generating sets of solutions for all types of systems are given. ' + \
'These criteria and the corresponding algorithms for constructing a minimal ' + \
'supporting set of solutions can be used in solving all the considered types ' + \
'systems and systems of mixed types.'
someothertext = 'Amazon.com, Inc. is located in Seattle, WA and was founded July 5th, 1994 by Jeff Bezos, ' + \
'allowing customers to buy everything from books to blenders. Seattle is north of Portland and ' + \
'south of Vancouver, BC. Other notable Seattle - based companies are Starbucks and Boeing.'
docs = [{'text': sometext, 'id': 777}]
grafs = [{'graf': graf.graf} for graf in pytextrank.parse_doc(docs)]
graph, ranks = pytextrank.text_rank(grafs)
rank_list = [
rl._asdict()
for rl in pytextrank.normalize_key_phrases(grafs, ranks, skip_ner=False)
]
kernel = pytextrank.rank_kernel(rank_list)
sents = [s._asdict() for s in pytextrank.top_sentences(kernel, grafs)]
phrases = [
p[0] for p in pytextrank.limit_keyphrases(rank_list, phrase_limit=6)
]
sent_iter = sorted(pytextrank.limit_sentences(sents, word_limit=150),
key=lambda x: x[1])
sents = [pytextrank.make_sentence(sent_text) for sent_text, idx in sent_iter]
graf_text = ' '.join(sents)
print("\n**excerpts:** %s\n\n**keywords:** %s" % (
graf_text,
phrases,
))
path_stage2 = "o2.json"
path_stage3 = "o3.json"
kernel = pytextrank.rank_kernel(path_stage2)
with open(path_stage3, 'w') as f:
for s in pytextrank.top_sentences(kernel, path_stage1):
f.write(pytextrank.pretty_print(s._asdict()))
f.write("\n")
# to view output in this notebook
print(pytextrank.pretty_print(s._asdict()))
path_stage2 = "o2.json"
path_stage3 = "o3.json"
phrases = ", ".join(
set([p
for p in pytextrank.limit_keyphrases(path_stage2, phrase_limit=20)]))
sent_iter = sorted(pytextrank.limit_sentences(path_stage3, word_limit=500),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(pytextrank.make_sentence(sent_text))
graf_text = " ".join(s)
print("**excerpts:** %s\n\n**keywords:** %s" % (
graf_text,
phrases,
))
with open(path_stage2, 'w') as f:
for rl in pytextrank.normalize_key_phrases(path_stage1, ranks):
f.write("%s\n" % pytextrank.pretty_print(rl._asdict()))
#print(pytextrank.pretty_print(rl))
path_stage1 = "o1.json"
path_stage2 = "o2.json"
path_stage3 = "o3.json"
kernel = pytextrank.rank_kernel(path_stage2)
with open(path_stage3, 'w') as f:
for s in pytextrank.top_sentences(kernel, path_stage1):
f.write(pytextrank.pretty_print(s._asdict()))
f.write("\n")
# to view output in this notebook
print(pytextrank.pretty_print(s._asdict()))
path_stage2 = "o2.json"
path_stage3 = "o3.json"
phrases = ", ".join(set([p for p in pytextrank.limit_keyphrases(path_stage2)]))
sent_iter = sorted(pytextrank.limit_sentences(path_stage3, word_limit=200), key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(pytextrank.make_sentence(sent_text))
graf_text = " ".join(s)
print("**excerpts:** %s\n\n**keywords:** %s" % (graf_text, phrases,))
if os.path.exists(OUTOUT_DIRECTORY):
shutil.rmtree(OUTOUT_DIRECTORY)
os.makedirs(OUTOUT_DIRECTORY)
print('Saving tweets to json...')
with open(TWEETS_JSON, 'w', encoding='utf8') as outfile:
json.dump({'id': '777', 'text': '. '.join(user_tweets)}, outfile, ensure_ascii=False)
print('Saving tweets to json - Done')
print('Performing statistical parsing/tagging on tweets...')
with open(STATISTICAL_PARSING_OUTPUT, 'w') as f:
for graf in pytextrank.parse_doc(pytextrank.json_iter(TWEETS_JSON)):
f.write("%s\n" % pytextrank.pretty_print(graf._asdict()))
print('Performing statistical parsing/tagging on tweets... - Done')
print('Collect and normalizing the key phrases from the parsed document...')
graph, ranks = pytextrank.text_rank(STATISTICAL_PARSING_OUTPUT)
pytextrank.render_ranks(graph, ranks)
with open(KEY_PHRASES_NORMALIZATION_OUTPUT, 'w') as f:
for rl in pytextrank.normalize_key_phrases(STATISTICAL_PARSING_OUTPUT, ranks):
f.write("%s\n" % pytextrank.pretty_print(rl._asdict()))
print('Collect and normalizing the key phrases from the parsed document... - Done')
print("Summarizing tweets based on key phrases...")
phrases = ", ".join(set([p for p in pytextrank.limit_keyphrases(KEY_PHRASES_NORMALIZATION_OUTPUT, phrase_limit=MAX_SUBJECTS_TO_SHOW)]))
print("**Top-10 subjects:** %s" % phrases)
def get_key_phrases(path_stage2):
phrases = set([p for p in pytextrank.limit_keyphrases(os.path.join(PATH_PREFIX, path_stage2), phrase_limit=4)])
print("**keywords:** %s" % (phrases))
return phrases
def insert_key_phrases_into_db(list_of_doc_dicts, doctype, collection):
'''
Takes in list of doc dictionaries and a doctype ('comment' or 'post'),
processes each doc with PyTextRank, obtains key phrases and
inserts key phrases into document in Mongodb as 'key_phrases' field.
'''
path_stage0 = 'stage0.json'
path_stage1 = 'stage1.json'
path_stage2 = 'stage2.json'
path_stage3 = 'stage3.json'
total_docs = len(list_of_doc_dicts)
failed_ids = []
for i, doc_dict in enumerate(list_of_doc_dicts):
if i % 50 == 0:
print(f'processing {i} of {total_docs} documents')
doc_dict['text'] = doc_dict['text'].split('\n_____\n\n')[0]
try:
with open(path_stage0, 'w') as f:
json.dump(doc_dict, f)
# Stage 1
with open(path_stage1, 'w') as f:
for graf in pytextrank.parse_doc(
pytextrank.json_iter(path_stage0)):
f.write("%s\n" % pytextrank.pretty_print(graf._asdict()))
# print(pytextrank.pretty_print(graf))
# Stage 2
graph, ranks = pytextrank.text_rank(path_stage1)
pytextrank.render_ranks(graph, ranks)
with open(path_stage2, 'w') as f:
for rl in pytextrank.normalize_key_phrases(path_stage1, ranks):
f.write("%s\n" % pytextrank.pretty_print(rl._asdict()))
# to view output in this notebook
# print(pytextrank.pretty_print(rl))
# Stage 3
kernel = pytextrank.rank_kernel(path_stage2)
with open(path_stage3, 'w') as f:
for s in pytextrank.top_sentences(kernel, path_stage1):
f.write(pytextrank.pretty_print(s._asdict()))
f.write("\n")
# to view output in this notebook
# print(pytextrank.pretty_print(s._asdict()))
# Stage 4
phrase_list = list(
set([
p for p in pytextrank.limit_keyphrases(path_stage2,
phrase_limit=15)
]))
phrases = ", ".join(phrase_list)
sent_iter = sorted(pytextrank.limit_sentences(path_stage3,
word_limit=150),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(pytextrank.make_sentence(sent_text))
graf_text = " ".join(s)
collection.update_one({f'{doctype}_id': {
'$eq': doc_dict['id']
}}, {'$set': {
'key_phrases': phrase_list
}})
except:
failed_ids.append(doc_dict['id'])
print('failed on ', doc_dict['id'])
continue
from pytextrank import limit_keyphrases, limit_sentences, make_sentence
import sys
import json
## Stage 4:
## * summarize a document based on most significant sentences and key phrases
##
## INPUTS: <stage2> <stage3>
## OUTPUT: Markdown format
if __name__ == "__main__":
path_stage2 = sys.argv[1]
path_stage3 = sys.argv[2]
phrases = ", ".join(set([p for p in limit_keyphrases(path_stage2, phrase_limit=30)]))
sent_iter = sorted(limit_sentences(path_stage3, word_limit=500), key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append(make_sentence(sent_text))
data = {'sentences' : s}
with open('output.json', 'w') as file:
json.dump(data, file)
#!/usr/bin/env python
# encoding: utf-8
from pytextrank import limit_keyphrases, limit_sentences, make_sentence
import sys
## Stage 4:
## * summarize a document based on most significant sentences and key phrases
##
## INPUTS: <stage2> <stage3>
## OUTPUT: Markdown format
if __name__ == "__main__":
path_stage2 = sys.argv[1]
path_stage3 = sys.argv[2]
phrases = ", ".join(
[p for p in limit_keyphrases(path_stage2, phrase_limit=12)])
sent_iter = sorted(limit_sentences(path_stage3, word_limit=150),
key=lambda x: x[1])
s = []
for sent_text, idx in sent_iter:
s.append((make_sentence([w for w in sent_text])))
graf_text = " ".join(s)
print("**excerpts:** %s\n\n**keywords:** %s" % (
graf_text,
phrases,
))
