EasyNLPnlp-037

Term Frequency

Problem

Return the term frequency of token in doc. With log_tf=False return the raw count as a float; with log_tf=True return 1 + math.log(count).

A token that never appears yields 0.0.

Hint

The log variant dampens repeated counts with 1 + log(count).

case 1

in: ["cat",["the","cat","sat","on","the","cat"],false]

expected: 2

case 2

in: ["dog",["the","cat"],false]

expected: 0

case 3

in: ["cat",["cat","cat","cat"],true]

expected: 2.09861228866811

case 4

in: ["the",["the","cat","the"],true]

expected: 1.6931471805599454

case 5

in: ["a",[],false]

expected: 0

Starter codePython

import math
def tf(token, doc, log_tf=False):
    # Your code here
    pass

5 test cases · run your code against them in the editor