Text similarity detection.txt

### this is not included with numpy files

import math
import re
from collections import Counter
##plagiarism / text similarity detection program 
WORD = re.compile(r"\w+")

def get_cosine(vec1, vec2):  ##function
    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)
print(" PLAGIARISM DETECTION I ")
text1 = input("Enter the first text: ")
text2 = input("Enter the second text to compare: ")

vector1 = text_to_vector(text1)
vector2 = text_to_vector(text2)

print(" PLAGIARISM DETECTION II ")

text3 = input("Enter the first text: ")
text4 = input("Enter the second text to compare: ")


vector3 = text_to_vector(text3)
vector4 = text_to_vector(text4)

cosine1 = get_cosine(vector1, vector2)
cosine2 = get_cosine(vector3, vector4)

print("The Cosine Similarity Ratio for 1st comparison is: ", cosine1)
print("The Cosine Similarity Ratio for 2nd comparison is: ", cosine2)