“Używanie TFIDFVECTERIZER” Kod odpowiedzi

Używanie TFIDFVECTERIZER

Text1 = “Natural Language Processing is a subfield of AI”
tag1 = "NLP"

Text2 = “Computer Vision is a subfield of AI”
tag2 = "CV"


from sklearn.feature_extraction.text import TfidfVectorizer as tf_idf
import pandas as pd
tfidf = tf_idf(norm = None)
tfidf.fit([Text1, Text2])
x= tfidf.transform([Text1]).toarray()
y= tfidf.transform([Text2]).toarray()
columns = tfidf.get_feature_names()
df1 = pd.DataFrame(x, columns= columns, index= ["Text1"])
df2 = pd.DataFrame(y, columns= columns, index= ["Text2"])
df = pd.concat([df1,df2])
df["tag"] = ["NLP", "CV"]
df