This repository has been archived by the owner on Dec 25, 2023. It is now read-only.
Laboratory work #3, Vladislava Tsvetkova - 22FPL2 #165
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
artyomtugaryov
suggested changes
Nov 30, 2023
lab_3_generate_by_ngrams/main.py
Outdated
| @@ -26,7 +24,7 @@ def __init__(self, end_of_word_token: str) -> None: | |||
| end_of_word_token (str): A token denoting word boundary | |||
| """ | |||
| self._end_of_word_token = end_of_word_token | |||
| self._storage = {end_of_word_token: 0} | |||
| self._storage = {'_': 0} | |||
lab_3_generate_by_ngrams/main.py
Outdated
| return token[0] | ||
|
|
||
| return None | ||
| return self._storage[element] |
| for token in element: | ||
| if token.isalpha(): | ||
| self._put(token) | ||
| if token in (' ', self._end_of_word_token): |
There was a problem hiding this comment.
you create it on each iteratiuon. Why?
There was a problem hiding this comment.
Create it once before loop
| @@ -1 +1 @@ | |||
| 10 | |||
| 0 | |||
artyomtugaryov
suggested changes
Dec 7, 2023
| @@ -105,13 +104,9 @@ def get_token(self, element_id: int) -> Optional[str]: | |||
| """ | |||
| if not isinstance(element_id, int): | |||
| return None | |||
| if element_id not in self._storage.values()): | |||
| return None | |||
There was a problem hiding this comment.
where is the imlementation?
There was a problem hiding this comment.
You removed it. Right now only checks are on the function
| print(greedy_text_generator.run(51, 'Vernon')) | ||
| n_gram_language_model = NGramLanguageModel(encoded[:100], 7) | ||
| print(n_gram_language_model.build()) | ||
| greedy_text_generator = GreedyTextGenerator(n_gram_language_model, text_processor) |
artyomtugaryov
suggested changes
Dec 14, 2023
| for token in element: | ||
| if token.isalpha(): | ||
| self._put(token) | ||
| if token in (' ', self._end_of_word_token): |
There was a problem hiding this comment.
Create it once before loop
lab_3_generate_by_ngrams/main.py
Outdated
| @@ -272,6 +260,7 @@ class NGramLanguageModel: | |||
| _encoded_corpus (tuple): Encoded text | |||
| """ | |||
|
|
|||
|
|
|||
lab_3_generate_by_ngrams/main.py
Outdated
| max_freq_tokens = [token for token, freq in tokens.items() if freq == max_freq] | ||
| max_freq_tokens = sorted(max_freq_tokens, reverse=True) | ||
| encoded_prompt += (max_freq_tokens[0],) | ||
| best_predictions = [token for token, freq in next_tokens.items() if freq == max(next_tokens.values())] |
There was a problem hiding this comment.
You can calculate max only once, not in the loop
artyomtugaryov
suggested changes
Dec 17, 2023
| @@ -105,13 +104,9 @@ def get_token(self, element_id: int) -> Optional[str]: | |||
| """ | |||
| if not isinstance(element_id, int): | |||
| return None | |||
| if element_id not in self._storage.values()): | |||
| return None | |||
There was a problem hiding this comment.
You removed it. Right now only checks are on the function
lab_3_generate_by_ngrams/main.py
Outdated
|
|
||
| for n_gram in set(n_grams): | ||
| number_of_n_grams = n_grams.count(n_gram) | ||
| context_count = len([context for context in n_grams |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.