uncertainity_based_assessment.py

"""
MIT License

Copyright (c) 2023 Aimon Labs Inc.

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
"""
import numpy as np

def max_neg_log_p(prob_matrix):
    # Calculating -log(p_ij) and finding the maximum value over all tokens in each sentence
    max_neg_log_p_values = np.max(-np.log(prob_matrix), axis=1)
    return max_neg_log_p_values  # This will be an array of shape (num_sentences,)

def entropy(prob_matrix):
    prob_matrix = np.clip(prob_matrix, 1e-10, 1)
    # Calculating the entropy for each token in each sentence
    entropy_values = -np.sum(prob_matrix * np.log(prob_matrix), axis=1)
    return entropy_values  # This will be an array of shape (num_sentences,)

def max_entropy(prob_matrix):
    # Calculating the maximum entropy over all tokens in each sentence
    entropy_values = entropy(prob_matrix)
    max_entropy_values = np.max(entropy_values)  # This should be np.max instead of np.mean
    return max_entropy_values  # This will return a single value

# Assume a simplified scenario with 3 sentences and a vocabulary of 5 words
# Each row in prob_matrix represents a sentence, and each column represents the probability of a word in the vocabulary
prob_matrix = np.array([
    [0.7, 0.1, 0.1, 0.05, 0.05],  # Sentence 1
    [0.2, 0.3, 0.1, 0.2, 0.2],    # Sentence 2
    [0.1, 0.1, 0.6, 0.1, 0.1]     # Sentence 3
])

max_entropy_value = max_entropy(prob_matrix)
print(f'Maximum Entropy: {max_entropy_value}')

max_neglogp_value = max_neg_log_p(prob_matrix)
print(f'Maximum Neg Log P: {max_neglogp_value}')