Code and files of the practical work of my thesis
├── README.md <- The top-level README for developers using this project
├── data
│ ├── processed <- Contains the pre-processed datasets ready for feature extracting
│ └── raw <- Contains the original datasets (records.bib is converted to WagnerPrester_2023.csv)
│
├── notebooks
│ ├── bib-csv-converter.ipynb <- bib to csv converter for WagnerPrester_2023 dataset
│ ├── Complete Comparison.ipynb <- Complete implementation to receive results for all combinations of Datasets&Feature Extractor&Classifier
│ └── Feature Extractor&Classifier&Dataset Averager.ipynb <- Averages the results for every Datasets&Feature Extractor&Classifier and sorts the results by dataset and recall
│
├── references
│ └── Datasets sources.txt <- Contains the references of the used datasets
│
├── reports
│ ├── average_classifier.txt <- Average performance results for the classifiers sorted by recall
│ ├── average_combination.txt <- Average performance results for the combinations of feature extractor&classifier sorted by recall
│ ├── average_datasets.txt <- Average performance results for the datasets sorted by recall
│ ├── average_feature_extractor.txt <- Average performance results for the feature extractor sorted by recall
│ ├── full_results.csv <- Results for all combinations of Datasets&Feature Extractor&Classifier as csv file
│ ├── full_results <- Results for all combinations of Datasets&Feature Extractor&Classifier as txt file
│ └── full_results_sortedByDataset&Recall <- Results for all combinations of Datasets&Feature Extractor&Classifier sorted by datasets and recall
Project based on the cookiecutter data science project template. #cookiecutterdatascience