Final commit

alberto-paparella · Jul 17, 2023 · abcf91a · abcf91a
1 parent 0c905d4
commit abcf91a
Show file tree

Hide file tree

Showing 12 changed files with 10 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -20,3 +20,10 @@ The designed model must predict a probability of each type of toxicity for each
  - test_labels.csv - labels for the test data; value of -1 indicates it was not used for scoring
 
 The dataset is under [CC0](https://creativecommons.org/share-your-work/public-domain/cc0/), with the underlying comment text being governed by [Wikipedia's CC-SA-3.0](https://creativecommons.org/licenses/by-sa/3.0/).
+
+## Python notebooks
+
+The project is divided into 3 notebooks:
+ - `toxic_comment_classifier` contains the core kernel, featuring data analysis and machine learning algorithms as logistic regression and naive-bayes
+ - `lstm-tcc` contains the LSTM kernel
+ - `bert-tcc` contains the BERT fine-tuning kernel
diff --git a/Toxic_Comment_Classifier.pdf b/Toxic_Comment_Classifier.pdf
diff --git a/bert-tcc.ipynb b/bert-tcc.ipynb
diff --git a/dataset/test.zip b/dataset/test.zip
diff --git a/dataset/test_labels.zip b/dataset/test_labels.zip
diff --git a/dataset/train.zip b/dataset/train.zip
diff --git a/images/ROC AUC score.png b/images/ROC AUC score.png
diff --git a/images/correlations.png b/images/correlations.png
diff --git a/images/text_length.png b/images/text_length.png
diff --git a/images/words_distribution.png b/images/words_distribution.png
diff --git a/lstm-tcc.ipynb b/lstm-tcc.ipynb
diff --git a/toxic_comment_classifier.ipynb b/toxic_comment_classifier.ipynb