def get_jaccard_similarity(content1, content2): 

    content1_similarity = set(content1.split()) 
    content2_similarity = set(content2.split())


    intersection = content1_similarity.intersection(content2_similarity)

    return float(len(intersection)) / (len(content1_similarity) + len(content2_similarity) - len(intersection))

# test 2  
content1 = "These data could show that the people …

from constants import OPENAI_API_KEY

!pip show langchain-openai | grep "Version:"

Version: 0.2.9

import os

os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY

from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="gpt-4o-mini")

from langchain_core.output_parsers import JsonOutputParser

chain = (
    model | JsonOutputParser()
)  # Due to a bug in older versions of Langchain, JsonOutputParser did not stream results …

import xmltodict

content = {
  "note" : {
    "to" : "Tove",
    "from" : "Jani",
    "heading" : "Reminder",
    "body" : "Don't forget me this weekend!"
  }
}

content

{'note': {'body': "Don't forget me this weekend!",
  'from': 'Jani',
  'heading': 'Reminder',
  'to': 'Tove'}}

xml = xmltodict.unparse …

import kenlm

model = kenlm.Model('test.arpa')
print(model.score('this is a sentence .', bos = True, eos = True))

-49.579345703125

cities = [
    'chennai', 'delhi', 'madurai', 'pune', 'bengaluru'
    ]

cities

['chennai', 'delhi', 'madurai', 'pune', 'bengaluru']

def is_south_indian_city(city):
    if city == 'chennai' or city == 'madurai' or city == 'bengaluru':
        return True

    return False

new_list = list(filter(lambda x: is_south_indian_city(x) , cities …

def is_odd(digit):
    if digit % 2 != 0:
        return True

    return False 

digits = [
    1, 7, 18, 2, 4, 2, 8, 5, 3
    ]

digits

[1, 7, 18, 2, 4, 2, 8, 5, 3]

new_list = list(filter(lambda x …

squares = list(map(lambda x: x**2, range(10)))

squares

[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]

from nltk.stem import LancasterStemmer

l_stemmer = LancasterStemmer()

print(l_stemmer.stem("hunting"))

hunt

print(l_stemmer.stem("hunting"))

hunt

words = [
    "hunting",
    "bunnies",
    "flies"
]

result = [l_stemmer.stem(word) for word in words]

result

['hunt', 'bunny', 'fli']

import numpy as np
import pandas as pd

df = pd.read_csv('data1.csv')

df

import numpy as np
import pandas as pd

df = pd.read_csv('data1.csv')

df