anarcute 0.1.94

My hy toolbox

My toolbox for dynamic programming

#to be documented #tf-id

from anarcute import *

import requests, json

sentence=”Eat more of those french fries and drink cola”

alice=requests.get(”https://gist.githubusercontent.com/phillipj/4944029/raw/75ba2243dd5ec2875f629bf5d79f6c1e4b5a8b46/alice_in_wonderland.txt”).text

print(tf_idf(sentence,alice))

>> {‘eat’: 168.7962962962963, ‘more’: 62.006802721088434, ‘of’: 5.9111543450064845, ‘those’: 303.8333333333333, ‘french’: 759.5833333333333, ‘and’: 3.4843272171253816, ‘drink’: 434.047619047619}

#If text is too big it’s frequencies can be pre-cached.

filename=”alice.json”

vector=vectorize(alice)

open(filename,”w+”).write(json.dumps(vector))

vector=json.load(open(filename,”r+”))

print(tf_idf(sentence,vector))

>>{‘eat’: 168.7962962962902, ‘more’: 62.00680272108618, ‘of’: 5.91115434500627, ‘those’: 303.8333333333223, ‘french’: 759.5833333333056, ‘and’: 3.484327217125255, ‘drink’: 434.0476190476033}

#we can sort by value

print(sort_by_value(tf_idf(sentence,vector)))

>>{‘french’: 759.5833333332979, ‘drink’: 434.04761904759886, ‘those’: 303.8333333333192, ‘eat’: 168.7962962962885, ‘more’: 62.006802721085556, ‘of’: 5.911154345006209, ‘and’: 3.4843272171252204}