导入
文本分词
了解字符、单词和句子的分词技术。
import pandas as pd
df = pd.read_csv('reviews.csv') df['character_tokens'] = df['review'].apply(list) print(df['character_tokens'])
import pandas as pd import nltk from nltk.tokenize import word_tokenize
df = pd.read_csv('reviews.csv') df['word_tokens'] = df['review'].apply(word_tokenize) print(df['word_tokens'])
import pandas as pd import nltk from nltk.tokenize import sent_tokenize
df = pd.read_csv('reviews.csv')
df['sentence_tokens'] = df['review'].apply(sent_tokenize)
print(df['sentence_tokens'])