Calculate cosine similarity given 2 sentence strings

Question

From Python: tf-idf-cosine: to find document similarity , it is possible to calculate document similarity using tf-idf cosine. Without importing external libraries, are that

Answer 1

I have similar solution but might be useful for pandas

import math
import re
from collections import Counter
import pandas as pd

WORD = re.compile(r"\w+")


def get_cosine(vec1, vec2):
    intersection = set(vec1.keys()) & set(vec2.keys())
    numerator = sum([vec1[x] * vec2[x] for x in intersection])

    sum1 = sum([vec1[x] ** 2 for x in list(vec1.keys())])
    sum2 = sum([vec2[x] ** 2 for x in list(vec2.keys())])
    denominator = math.sqrt(sum1) * math.sqrt(sum2)

    if not denominator:
        return 0.0
    else:
        return float(numerator) / denominator


def text_to_vector(text):
    words = WORD.findall(text)
    return Counter(words)

df=pd.read_csv('/content/drive/article.csv')
df['vector1']=df['headline'].apply(lambda x: text_to_vector(x)) 
df['vector2']=df['snippet'].apply(lambda x: text_to_vector(x)) 
df['simscore']=df.apply(lambda x: get_cosine(x['vector1'],x['vector2']),axis=1)