Created
April 6, 2019 10:30
-
-
Save svenski/a433a823511a0f9a0941deba93fa0d2f to your computer and use it in GitHub Desktop.
NLP dojo on finding characters in Emma
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
| import spacy | |
| import nltk | |
| from nltk.corpus import gutenberg | |
| #nlp = spacy.load('en') | |
| nlp = spacy.load('en_core_web_sm') | |
| import random | |
| import pandas as pd | |
| import matplotlib.pyplot as plt | |
| import re | |
| def main(): | |
| emma = gutenberg.raw('austen-emma.txt') | |
| #TODO: replace -- with space | |
| emma = emma.replace('--', ' ') | |
| parsed_emma = nlp(emma) | |
| my_sample = list(parsed_emma.sents) | |
| sample=[] | |
| for sent in my_sample: | |
| sent = re.sub("\s+"," ",sent.text) # clean up the whitespace | |
| sample.append(sent) | |
| entities=[] | |
| type_entity=[] | |
| sentences=[] | |
| for sent in sample: | |
| parsed_sentence=nlp(sent) | |
| for ent in parsed_sentence.ents: | |
| entities.append(ent.text) | |
| sentences.append(sent) | |
| type_entity.append(ent.label_) | |
| ents=pd.DataFrame({'Sentence':sentences,'Entity':entities,'Entity_type':type_entity}) | |
| people = ents[ents.Entity_type=='PERSON'] | |
| people_in_sent = people.groupby('Sentence')['Entity'].agg({set}).reset_index() | |
| people_in_sent['num_person'] = people_in_sent.set.apply(lambda x : len(x)) | |
| mult = people_in_sent[people_in_sent.num_person == 2] | |
| mult['pp'] = mult.set.apply(lambda x: tuple(list(x))) | |
| tt = mult.groupby('pp').size().to_frame('count').sort_values('count', ascending = False).head(n = 10).reset_index() | |
| import networkx as nx | |
| import matplotlib.pyplot as plt | |
| G=nx.Graph() | |
| for _, row in tt.iterrows(): | |
| G.add_edge(row.pp[0], row.pp[1], weight=row['count']) | |
| nx.draw(G) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
need to fix line 41 to
mult = people_in_sent[people_in_sent.num_person == 2].copy()