255 lines
15 KiB
Plaintext
255 lines
15 KiB
Plaintext
Дата: Вс 25 окт 2026 17:31:03 MSK
|
||
Каталог: /home/folen/Homework/NLP/lab1
|
||
Интерпретатор: python
|
||
|
||
=== Проверка окружения ===
|
||
Python: 3.11.2 (/home/folen/Homework/NLP/.venv/bin/python)
|
||
Каталог проекта: /home/folen/Homework/NLP/lab1
|
||
Версии библиотек:
|
||
numpy: 2.4.6
|
||
pandas: 3.1.0
|
||
scipy: 1.17.1
|
||
sklearn: 1.9.1
|
||
nltk: 3.10.4
|
||
matplotlib: 3.11.2
|
||
Корпус:
|
||
файл: /home/folen/Homework/NLP/lab1/data/dialogues.csv
|
||
SHA-256: 8946f08159daddb9d89c9d323205d4a7fb4bc617d16e300ff6c7606cb05030f7
|
||
реплик: 2005
|
||
персонажей: 34
|
||
словоупотреблений: 38207
|
||
NLTK:
|
||
токенизатор: NLTK
|
||
POS-теггер: доступен
|
||
пример токенов: ['Oh', ',', 'that', "'s", 'right', '...', 'I', 'heard']
|
||
пример POS: ['INTJ', 'PUNCT', 'DET', 'AUX', 'ADJ', 'PUNCT', 'PRON', 'VERB']
|
||
|
||
Окружение готово.
|
||
{"versions": {"numpy": "2.4.6", "pandas": "3.1.0", "scipy": "1.17.1", "sklearn": "1.9.1", "nltk": "3.10.4", "matplotlib": "3.11.2"}, "n_lines": 2005}
|
||
|
||
Git commit: 10e2444d2342e2d02c94a06de884ad7bbee83bca
|
||
|
||
Содержимое results:
|
||
results/ablation_stylometry_pos_lsa_20261025_170116/ablation.csv
|
||
results/benchmark_stylometry_pos_lsa_20261025_165348/summary.csv
|
||
results/char_multinomial_nb_20261025_155832/bootstrap_ci.json
|
||
results/char_multinomial_nb_20261025_155832/confusion_matrix.csv
|
||
results/char_multinomial_nb_20261025_155832/confusion_matrix_normalized.csv
|
||
results/char_multinomial_nb_20261025_155832/fold_metrics.csv
|
||
results/char_multinomial_nb_20261025_155832/fold_summary.csv
|
||
results/char_multinomial_nb_20261025_155832/oof_predictions.csv
|
||
results/char_multinomial_nb_20261025_155832/per_class_report.csv
|
||
results/char_multinomial_nb_20261025_155832/pooled_metrics.csv
|
||
results/char_multinomial_nb_20261025_155832/run_metadata.json
|
||
results/char_multinomial_nb_20261025_155832/summary.md
|
||
results/char_multinomial_nb_20261025_155832/top_confusions.csv
|
||
results/clustering_stylometry_pos_lsa_20261025_172241/character_centroids.csv
|
||
results/clustering_stylometry_pos_lsa_20261025_172241/clustering_metrics.csv
|
||
results/delta_20261025_172113/delta_sweep.csv
|
||
results/fw_logreg_20261025_160058/bootstrap_ci.json
|
||
results/fw_logreg_20261025_160058/confusion_matrix.csv
|
||
results/fw_logreg_20261025_160058/confusion_matrix_normalized.csv
|
||
results/fw_logreg_20261025_160058/fold_metrics.csv
|
||
results/fw_logreg_20261025_160058/fold_summary.csv
|
||
results/fw_logreg_20261025_160058/oof_predictions.csv
|
||
results/fw_logreg_20261025_160058/per_class_report.csv
|
||
results/fw_logreg_20261025_160058/pooled_metrics.csv
|
||
results/fw_logreg_20261025_160058/run_metadata.json
|
||
results/fw_logreg_20261025_160058/summary.md
|
||
results/fw_logreg_20261025_160058/top_confusions.csv
|
||
results/length_dummy_20261025_155747/bootstrap_ci.json
|
||
results/length_dummy_20261025_155747/confusion_matrix.csv
|
||
results/length_dummy_20261025_155747/confusion_matrix_normalized.csv
|
||
results/length_dummy_20261025_155747/fold_metrics.csv
|
||
results/length_dummy_20261025_155747/fold_summary.csv
|
||
results/length_dummy_20261025_155747/oof_predictions.csv
|
||
results/length_dummy_20261025_155747/per_class_report.csv
|
||
results/length_dummy_20261025_155747/pooled_metrics.csv
|
||
results/length_dummy_20261025_155747/run_metadata.json
|
||
results/length_dummy_20261025_155747/summary.md
|
||
results/length_dummy_20261025_155747/top_confusions.csv
|
||
results/length_logreg_20261025_155719/bootstrap_ci.json
|
||
results/length_logreg_20261025_155719/confusion_matrix.csv
|
||
results/length_logreg_20261025_155719/confusion_matrix_normalized.csv
|
||
results/length_logreg_20261025_155719/fold_metrics.csv
|
||
results/length_logreg_20261025_155719/fold_summary.csv
|
||
results/length_logreg_20261025_155719/oof_predictions.csv
|
||
results/length_logreg_20261025_155719/per_class_report.csv
|
||
results/length_logreg_20261025_155719/pooled_metrics.csv
|
||
results/length_logreg_20261025_155719/run_metadata.json
|
||
results/length_logreg_20261025_155719/summary.md
|
||
results/length_logreg_20261025_155719/top_confusions.csv
|
||
results/length_logreg_20261025_155813/bootstrap_ci.json
|
||
results/length_logreg_20261025_155813/confusion_matrix.csv
|
||
results/length_logreg_20261025_155813/confusion_matrix_normalized.csv
|
||
results/length_logreg_20261025_155813/fold_metrics.csv
|
||
results/length_logreg_20261025_155813/fold_summary.csv
|
||
results/length_logreg_20261025_155813/oof_predictions.csv
|
||
results/length_logreg_20261025_155813/per_class_report.csv
|
||
results/length_logreg_20261025_155813/pooled_metrics.csv
|
||
results/length_logreg_20261025_155813/run_metadata.json
|
||
results/length_logreg_20261025_155813/summary.md
|
||
results/length_logreg_20261025_155813/top_confusions.csv
|
||
results/logs/run_all_20261025_150915.log
|
||
results/logs/run_all_20261025_151312.log
|
||
results/logs/run_all_20261025_152356.log
|
||
results/logs/run_all_20261025_155738.log
|
||
results/lsa_char_logreg_20261025_164836/bootstrap_ci.json
|
||
results/lsa_char_logreg_20261025_164836/confusion_matrix.csv
|
||
results/lsa_char_logreg_20261025_164836/confusion_matrix_normalized.csv
|
||
results/lsa_char_logreg_20261025_164836/fold_metrics.csv
|
||
results/lsa_char_logreg_20261025_164836/fold_summary.csv
|
||
results/lsa_char_logreg_20261025_164836/oof_predictions.csv
|
||
results/lsa_char_logreg_20261025_164836/per_class_report.csv
|
||
results/lsa_char_logreg_20261025_164836/pooled_metrics.csv
|
||
results/lsa_char_logreg_20261025_164836/run_metadata.json
|
||
results/lsa_char_logreg_20261025_164836/summary.md
|
||
results/lsa_char_logreg_20261025_164836/top_confusions.csv
|
||
results/lsa_content_logreg_20261025_164717/bootstrap_ci.json
|
||
results/lsa_content_logreg_20261025_164717/confusion_matrix.csv
|
||
results/lsa_content_logreg_20261025_164717/confusion_matrix_normalized.csv
|
||
results/lsa_content_logreg_20261025_164717/fold_metrics.csv
|
||
results/lsa_content_logreg_20261025_164717/fold_summary.csv
|
||
results/lsa_content_logreg_20261025_164717/oof_predictions.csv
|
||
results/lsa_content_logreg_20261025_164717/per_class_report.csv
|
||
results/lsa_content_logreg_20261025_164717/pooled_metrics.csv
|
||
results/lsa_content_logreg_20261025_164717/run_metadata.json
|
||
results/lsa_content_logreg_20261025_164717/summary.md
|
||
results/lsa_content_logreg_20261025_164717/top_confusions.csv
|
||
results/lsa_fw_logreg_20261025_164750/bootstrap_ci.json
|
||
results/lsa_fw_logreg_20261025_164750/confusion_matrix.csv
|
||
results/lsa_fw_logreg_20261025_164750/confusion_matrix_normalized.csv
|
||
results/lsa_fw_logreg_20261025_164750/fold_metrics.csv
|
||
results/lsa_fw_logreg_20261025_164750/fold_summary.csv
|
||
results/lsa_fw_logreg_20261025_164750/oof_predictions.csv
|
||
results/lsa_fw_logreg_20261025_164750/per_class_report.csv
|
||
results/lsa_fw_logreg_20261025_164750/pooled_metrics.csv
|
||
results/lsa_fw_logreg_20261025_164750/run_metadata.json
|
||
results/lsa_fw_logreg_20261025_164750/summary.md
|
||
results/lsa_fw_logreg_20261025_164750/top_confusions.csv
|
||
results/lsa_pos_logreg_20261025_164912/bootstrap_ci.json
|
||
results/lsa_pos_logreg_20261025_164912/confusion_matrix.csv
|
||
results/lsa_pos_logreg_20261025_164912/confusion_matrix_normalized.csv
|
||
results/lsa_pos_logreg_20261025_164912/fold_metrics.csv
|
||
results/lsa_pos_logreg_20261025_164912/fold_summary.csv
|
||
results/lsa_pos_logreg_20261025_164912/oof_predictions.csv
|
||
results/lsa_pos_logreg_20261025_164912/per_class_report.csv
|
||
results/lsa_pos_logreg_20261025_164912/pooled_metrics.csv
|
||
results/lsa_pos_logreg_20261025_164912/run_metadata.json
|
||
results/lsa_pos_logreg_20261025_164912/summary.md
|
||
results/lsa_pos_logreg_20261025_164912/top_confusions.csv
|
||
results/lsa_sweep_20261025_164924/lsa_sweep.csv
|
||
results/lsa_word2_logreg_20261025_164641/bootstrap_ci.json
|
||
results/lsa_word2_logreg_20261025_164641/confusion_matrix.csv
|
||
results/lsa_word2_logreg_20261025_164641/confusion_matrix_normalized.csv
|
||
results/lsa_word2_logreg_20261025_164641/fold_metrics.csv
|
||
results/lsa_word2_logreg_20261025_164641/fold_summary.csv
|
||
results/lsa_word2_logreg_20261025_164641/oof_predictions.csv
|
||
results/lsa_word2_logreg_20261025_164641/per_class_report.csv
|
||
results/lsa_word2_logreg_20261025_164641/pooled_metrics.csv
|
||
results/lsa_word2_logreg_20261025_164641/run_metadata.json
|
||
results/lsa_word2_logreg_20261025_164641/summary.md
|
||
results/lsa_word2_logreg_20261025_164641/top_confusions.csv
|
||
results/lsa_word_logreg_20261025_164608/bootstrap_ci.json
|
||
results/lsa_word_logreg_20261025_164608/confusion_matrix.csv
|
||
results/lsa_word_logreg_20261025_164608/confusion_matrix_normalized.csv
|
||
results/lsa_word_logreg_20261025_164608/fold_metrics.csv
|
||
results/lsa_word_logreg_20261025_164608/fold_summary.csv
|
||
results/lsa_word_logreg_20261025_164608/oof_predictions.csv
|
||
results/lsa_word_logreg_20261025_164608/per_class_report.csv
|
||
results/lsa_word_logreg_20261025_164608/pooled_metrics.csv
|
||
results/lsa_word_logreg_20261025_164608/run_metadata.json
|
||
results/lsa_word_logreg_20261025_164608/summary.md
|
||
results/lsa_word_logreg_20261025_164608/top_confusions.csv
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/best_params.json
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/bootstrap_ci.json
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/confusion_matrix.csv
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/confusion_matrix_normalized.csv
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/fold_metrics.csv
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/fold_summary.csv
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/oof_predictions.csv
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/per_class_report.csv
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/pooled_metrics.csv
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/run_metadata.json
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/summary.md
|
||
results/nested_stylometry_pos_lsa_linear_svc_20261025_172442/top_confusions.csv
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/best_params.json
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/bootstrap_ci.json
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/confusion_matrix.csv
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/confusion_matrix_normalized.csv
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/fold_metrics.csv
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/fold_summary.csv
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/oof_predictions.csv
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/per_class_report.csv
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/pooled_metrics.csv
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/run_metadata.json
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/summary.md
|
||
results/nested_stylometry_pos_lsa_logreg_20261025_172348/top_confusions.csv
|
||
results/pos_multinomial_nb_20261025_155848/bootstrap_ci.json
|
||
results/pos_multinomial_nb_20261025_155848/confusion_matrix.csv
|
||
results/pos_multinomial_nb_20261025_155848/confusion_matrix_normalized.csv
|
||
results/pos_multinomial_nb_20261025_155848/fold_metrics.csv
|
||
results/pos_multinomial_nb_20261025_155848/fold_summary.csv
|
||
results/pos_multinomial_nb_20261025_155848/oof_predictions.csv
|
||
results/pos_multinomial_nb_20261025_155848/per_class_report.csv
|
||
results/pos_multinomial_nb_20261025_155848/pooled_metrics.csv
|
||
results/pos_multinomial_nb_20261025_155848/run_metadata.json
|
||
results/pos_multinomial_nb_20261025_155848/summary.md
|
||
results/pos_multinomial_nb_20261025_155848/top_confusions.csv
|
||
results/README.md
|
||
results/stylometry_linear_svc_20261025_164018/bootstrap_ci.json
|
||
results/stylometry_linear_svc_20261025_164018/confusion_matrix.csv
|
||
results/stylometry_linear_svc_20261025_164018/confusion_matrix_normalized.csv
|
||
results/stylometry_linear_svc_20261025_164018/fold_metrics.csv
|
||
results/stylometry_linear_svc_20261025_164018/fold_summary.csv
|
||
results/stylometry_linear_svc_20261025_164018/oof_predictions.csv
|
||
results/stylometry_linear_svc_20261025_164018/per_class_report.csv
|
||
results/stylometry_linear_svc_20261025_164018/pooled_metrics.csv
|
||
results/stylometry_linear_svc_20261025_164018/run_metadata.json
|
||
results/stylometry_linear_svc_20261025_164018/summary.md
|
||
results/stylometry_linear_svc_20261025_164018/top_confusions.csv
|
||
results/stylometry_logreg_20261025_160722/bootstrap_ci.json
|
||
results/stylometry_logreg_20261025_160722/confusion_matrix.csv
|
||
results/stylometry_logreg_20261025_160722/confusion_matrix_normalized.csv
|
||
results/stylometry_logreg_20261025_160722/fold_metrics.csv
|
||
results/stylometry_logreg_20261025_160722/fold_summary.csv
|
||
results/stylometry_logreg_20261025_160722/oof_predictions.csv
|
||
results/stylometry_logreg_20261025_160722/per_class_report.csv
|
||
results/stylometry_logreg_20261025_160722/pooled_metrics.csv
|
||
results/stylometry_logreg_20261025_160722/run_metadata.json
|
||
results/stylometry_logreg_20261025_160722/summary.md
|
||
results/stylometry_logreg_20261025_160722/top_confusions.csv
|
||
results/stylometry_pos_logreg_20261025_164246/bootstrap_ci.json
|
||
results/stylometry_pos_logreg_20261025_164246/confusion_matrix.csv
|
||
results/stylometry_pos_logreg_20261025_164246/confusion_matrix_normalized.csv
|
||
results/stylometry_pos_logreg_20261025_164246/fold_metrics.csv
|
||
results/stylometry_pos_logreg_20261025_164246/fold_summary.csv
|
||
results/stylometry_pos_logreg_20261025_164246/oof_predictions.csv
|
||
results/stylometry_pos_logreg_20261025_164246/per_class_report.csv
|
||
results/stylometry_pos_logreg_20261025_164246/pooled_metrics.csv
|
||
results/stylometry_pos_logreg_20261025_164246/run_metadata.json
|
||
results/stylometry_pos_logreg_20261025_164246/summary.md
|
||
results/stylometry_pos_logreg_20261025_164246/top_confusions.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/bootstrap_ci.json
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/comparison_main_vs_pos.json
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/confusion_matrix.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/confusion_matrix_normalized.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/fold_metrics.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/fold_summary.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/length_bins.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/oof_predictions.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/per_class_report.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/pooled_metrics.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/run_metadata.json
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/subgroup_age_group_confusions.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/subgroup_age_group_metrics.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/subgroup_gender_confusions.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/subgroup_gender_metrics.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/subgroup_species_confusions.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/subgroup_species_metrics.csv
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/summary.md
|
||
results/stylometry_pos_lsa_logreg_20261025_164534/top_confusions.csv
|
||
results/verification_stylometry_pos_lsa_20261025_172237/fold_metrics.csv
|
||
results/verification_stylometry_pos_lsa_20261025_172237/pair_scores.csv
|
||
results/verification_stylometry_pos_lsa_20261025_172237/summary.json
|