├── .DS_Store ├── README.md ├── articles ├── An-Evaluation-of-Machine-Learning-Approaches-to-Natural-Language-Processing-for-Legal-Text-Classification.pdf ├── Class_Imbalance_Text_Classifcn.pdf ├── Jerrold_Soh_Legal_Text_Classi.pdf └── Stanford_dependencies_manual.pdf ├── code ├── .DS_Store ├── .ipynb_checkpoints │ ├── 1.Web_Scraping-checkpoint.ipynb │ ├── 2.Cleaning_Statistical_EDA-checkpoint.ipynb │ ├── 3.Textual_EDA_LDA_Visuals-checkpoint.ipynb │ ├── 4.Preprocessing_Modelling-checkpoint.ipynb │ ├── 5. BERT_Conclusions-checkpoint.ipynb │ ├── 5.BERT_Conclusions-checkpoint.ipynb │ ├── Dry_Run_draft-checkpoint.ipynb │ └── Single_ Contract_EDA_Draft-checkpoint.ipynb ├── 1.Web_Scraping.ipynb ├── 2.Cleaning_Statistical_EDA.ipynb ├── 3.Textual_EDA_LDA_Visuals.ipynb ├── 4.Preprocessing_Modelling.ipynb └── 5.BERT_Conclusions.ipynb ├── data ├── .DS_Store ├── dep.png ├── dep.svg ├── df_clean_draft.csv ├── df_clean_draft_1.csv ├── df_clean_draft_2.csv ├── df_clean_draft_3.csv ├── df_clean_final.csv └── df_raw.csv └── images ├── .DS_Store ├── BERTviz.png ├── clause_type_plotly.png ├── clause_word_count.png ├── displacy_dependency.png ├── displacy_sample.png ├── profile_1.png ├── profile_2.png ├── top_25_indemnity.png ├── top_25_words_all_clauses.png ├── topic_1.png └── topic_2.png /.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/.DS_Store -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/README.md -------------------------------------------------------------------------------- /articles/An-Evaluation-of-Machine-Learning-Approaches-to-Natural-Language-Processing-for-Legal-Text-Classification.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/articles/An-Evaluation-of-Machine-Learning-Approaches-to-Natural-Language-Processing-for-Legal-Text-Classification.pdf -------------------------------------------------------------------------------- /articles/Class_Imbalance_Text_Classifcn.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/articles/Class_Imbalance_Text_Classifcn.pdf -------------------------------------------------------------------------------- /articles/Jerrold_Soh_Legal_Text_Classi.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/articles/Jerrold_Soh_Legal_Text_Classi.pdf -------------------------------------------------------------------------------- /articles/Stanford_dependencies_manual.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/articles/Stanford_dependencies_manual.pdf -------------------------------------------------------------------------------- /code/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/.DS_Store -------------------------------------------------------------------------------- /code/.ipynb_checkpoints/1.Web_Scraping-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/.ipynb_checkpoints/1.Web_Scraping-checkpoint.ipynb -------------------------------------------------------------------------------- /code/.ipynb_checkpoints/2.Cleaning_Statistical_EDA-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/.ipynb_checkpoints/2.Cleaning_Statistical_EDA-checkpoint.ipynb -------------------------------------------------------------------------------- /code/.ipynb_checkpoints/3.Textual_EDA_LDA_Visuals-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/.ipynb_checkpoints/3.Textual_EDA_LDA_Visuals-checkpoint.ipynb -------------------------------------------------------------------------------- /code/.ipynb_checkpoints/4.Preprocessing_Modelling-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/.ipynb_checkpoints/4.Preprocessing_Modelling-checkpoint.ipynb -------------------------------------------------------------------------------- /code/.ipynb_checkpoints/5. BERT_Conclusions-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/.ipynb_checkpoints/5. BERT_Conclusions-checkpoint.ipynb -------------------------------------------------------------------------------- /code/.ipynb_checkpoints/5.BERT_Conclusions-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/.ipynb_checkpoints/5.BERT_Conclusions-checkpoint.ipynb -------------------------------------------------------------------------------- /code/.ipynb_checkpoints/Dry_Run_draft-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/.ipynb_checkpoints/Dry_Run_draft-checkpoint.ipynb -------------------------------------------------------------------------------- /code/.ipynb_checkpoints/Single_ Contract_EDA_Draft-checkpoint.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/.ipynb_checkpoints/Single_ Contract_EDA_Draft-checkpoint.ipynb -------------------------------------------------------------------------------- /code/1.Web_Scraping.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/1.Web_Scraping.ipynb -------------------------------------------------------------------------------- /code/2.Cleaning_Statistical_EDA.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/2.Cleaning_Statistical_EDA.ipynb -------------------------------------------------------------------------------- /code/3.Textual_EDA_LDA_Visuals.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/3.Textual_EDA_LDA_Visuals.ipynb -------------------------------------------------------------------------------- /code/4.Preprocessing_Modelling.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/4.Preprocessing_Modelling.ipynb -------------------------------------------------------------------------------- /code/5.BERT_Conclusions.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/code/5.BERT_Conclusions.ipynb -------------------------------------------------------------------------------- /data/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/data/.DS_Store -------------------------------------------------------------------------------- /data/dep.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/data/dep.png -------------------------------------------------------------------------------- /data/dep.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/data/dep.svg -------------------------------------------------------------------------------- /data/df_clean_draft.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/data/df_clean_draft.csv -------------------------------------------------------------------------------- /data/df_clean_draft_1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/data/df_clean_draft_1.csv -------------------------------------------------------------------------------- /data/df_clean_draft_2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/data/df_clean_draft_2.csv -------------------------------------------------------------------------------- /data/df_clean_draft_3.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/data/df_clean_draft_3.csv -------------------------------------------------------------------------------- /data/df_clean_final.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/data/df_clean_final.csv -------------------------------------------------------------------------------- /data/df_raw.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/data/df_raw.csv -------------------------------------------------------------------------------- /images/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/.DS_Store -------------------------------------------------------------------------------- /images/BERTviz.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/BERTviz.png -------------------------------------------------------------------------------- /images/clause_type_plotly.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/clause_type_plotly.png -------------------------------------------------------------------------------- /images/clause_word_count.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/clause_word_count.png -------------------------------------------------------------------------------- /images/displacy_dependency.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/displacy_dependency.png -------------------------------------------------------------------------------- /images/displacy_sample.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/displacy_sample.png -------------------------------------------------------------------------------- /images/profile_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/profile_1.png -------------------------------------------------------------------------------- /images/profile_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/profile_2.png -------------------------------------------------------------------------------- /images/top_25_indemnity.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/top_25_indemnity.png -------------------------------------------------------------------------------- /images/top_25_words_all_clauses.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/top_25_words_all_clauses.png -------------------------------------------------------------------------------- /images/topic_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/topic_1.png -------------------------------------------------------------------------------- /images/topic_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chevalier88/GA_Project_5_Capstone_Multiclass_Legal_Text_Classification_BERT/HEAD/images/topic_2.png --------------------------------------------------------------------------------