Created
December 24, 2019 17:40
-
-
Save kspicer80/f78d0cfccc43a9e07b05efca6b652b96 to your computer and use it in GitHub Desktop.
Messing around with spaCy and Kerouac
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 matplotlib.pyplot as plt | |
import spacy | |
nlp = spacy.load('en_core_web_lg') | |
import pandas as pd | |
from collections import Counter | |
kerouac_raw = open('kerouac.txt').read() | |
kerouac = nlp(kerouac_raw) | |
Counter([w.string.strip() for w in kerouac.ents if w.label_ == 'PERSON']).most_common(10) | |
#Function to give us all the adjectives describing a character | |
def adjectivesDescribingCharacters(text, character): | |
sents = [sent for sent in kerouac.sents if character in sent.string] | |
adjectives = [] | |
for sent in sents: | |
for word in sent: | |
if character in word.string: | |
for child in word.children: | |
if child.pos_ == 'ADJ': | |
adjectives.append(child.string.strip()) | |
return Counter(adjectives).most_common(10) | |
adjectivesDescribingCharacters(kerouac, 'Sal') | |
adjectivesDescribingCharacters(kerouac, 'Dean') | |
adjectivesDescribingCharacters(kerouac, 'Marylou') | |
#Define a function to give us all the verbs for describing a character | |
def verbsForCharacters(text, character): | |
sents = [sent for sent in kerouac.sents if character in sent.string] | |
charWords = [] | |
for sent in sents: | |
for word in sent: | |
if character in word.string: | |
charWords.append(word) | |
charAdjectives = [] | |
for word in charWords: | |
for ancestor in word.ancestors: | |
if ancestor.pos_.startswith('V'): | |
charAdjectives.append(ancestor.lemma_.strip()) | |
return Counter(charAdjectives).most_common(20) | |
marylouVerbs = verbsForCharacters(kerouac, 'Marylou') | |
deanVerbs = verbsForCharacters(kerouac, 'Dean') | |
salVerbs = verbsForCharacters(kerouac, 'Sal') | |
#Combine and visualize with Pandas | |
def verbsToMatrix(verbCounts): | |
return pd.Series({t[0]: t[1] for t in verbCounts}) | |
verbsDF = pd.DataFrame({'Marylou': verbsToMatrix(marylouVerbs), | |
'Dean': verbsToMatrix(deanVerbs), | |
'Sal': verbsToMatrix(salVerbs)}).fillna(0) | |
verbsDF.plot(kind='bar', figsize=(16,8)) | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment