Last active
July 14, 2023 22:05
-
-
Save ygivenx/1064d8913c33d1689c14ccb2b3467395 to your computer and use it in GitHub Desktop.
Gzip Text classification Algorithm
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
import gzip | |
import numpy as np | |
import concurrent.futures | |
from sklearn.datasets import fetch_20newsgroups | |
# dataset | |
newsgroups_train = fetch_20newsgroups(subset='train') | |
newsgroups_test = fetch_20newsgroups(subset='test') | |
# format for GZIP | |
training_set = np.array(list(zip(newsgroups_train.data, newsgroups_train.target))) | |
test_set = np.array(list(zip(newsgroups_test.data, newsgroups_test.target))) | |
# model | |
def get_gzip_preds(item, k=10): | |
# for i, ( x1 , target ) in enumerate(test_set): | |
(x1, target) = item | |
Cx1 = len( gzip . compress ( x1 . encode () ) ) | |
distance_from_x1 = [] | |
for ( x2 , _ ) in training_set : | |
Cx2 = len(gzip.compress(x2.encode())) | |
x1x2 = " ".join ([ x1 , x2 ]) | |
Cx1x2 = len( gzip.compress (x1x2.encode())) | |
ncd = ( Cx1x2 - min ( Cx1 , Cx2 ) ) / max (Cx1 , Cx2 ) | |
distance_from_x1.append ( ncd ) | |
sorted_idx = np.argsort ( np.array (distance_from_x1 ) ) | |
top_k_class = list(training_set [ sorted_idx[: k ] , 1]) | |
predict_class = max(set( top_k_class ) , key = top_k_class.count ) | |
# print(f"# Pred : {predict_class}\t Actual: {target}") | |
return predict_class | |
# parallel | |
with concurrent.futures.ProcessPoolExecutor() as executor: | |
# Start the function for each item. | |
futures = {executor.submit(get_gzip_preds, item): item for item in test_set} | |
correct_predictions = 0 | |
total_predictions = 0 | |
for future in concurrent.futures.as_completed(futures): | |
result = future.result() | |
item = futures[future] | |
total_predictions += 1 | |
if result == item[1]: # Assuming item[1] is the actual class | |
correct_predictions += 1 | |
# Calculate the accuracy | |
accuracy = correct_predictions / total_predictions | |
print(f'Accuracy so far: {accuracy}') | |
# Print final accuracy | |
print(f'Final accuracy: {accuracy}') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment