# HW3: Text clustering for Douban-Book data
- to run the script for reproduction: `cd HW3` as working dir and `python run.py`
# Result
- the numeric results are saved in [json format: *.json](./result). You can [check one](./result/k_is_5.json)
- The [plots: *.png](./result) of `silhouette_score` - `k` are provided. You can [check one](./result/(5,%2040)-k_is_5.png)
# Log
- <del>Unsolved: `TF-IDF vectorizer` somehow does not work in multiprocessing, since I've fitted the vectorizer in process but throw bug of not fitted. Changing it to single process works. </del>
## Author: LiuShu
- contact: `liushu_public@yeah.net`
## The Project is also saved in [My GitHub](https://github.com/uhSuiL/TextMining) where you can give a star
I'm not satisfied with this hw since I finally make it spaghetti code. Maybe ML code doesn't need much encapsulation.
I will take use of fp more making it easier to read, check intermediate result, explore param and models and strategies.
文本挖掘-DUFE大数据实验-含实验报告.zip
版权申诉
17 浏览量
2024-06-02
14:45:26
上传
评论
收藏 3.9MB ZIP 举报
文本挖掘-DUFE大数据实验-含实验报告.zip （187个子文件） 
extended_data.csv 2.69MB data.csv 999KB metrics summary.csv 27KB models.csv 4KB classify polar.ipynb 38.2MB eda.ipynb 550KB plot.ipynb 111KB preprocess.ipynb 51KB test.ipynb 6KB config_2.json 11KB k_is_38.json 5KB configs_1.json 2KB k_is_5.json 700B metrics-train.json 144B metrics-extra feature train.json 144B metrics-train.json 143B metrics-train.json 143B metrics-train.json 143B metrics-extra feature train.json 142B metrics-train.json 142B metrics-extra feature train.json 142B metrics-extra feature train.json 141B metrics-train.json 141B metrics-train.json 141B metrics-extra feature train.json 141B metrics-extra feature train.json 140B metrics-train.json 140B metrics-extra feature train.json 140B metrics-train.json 140B metrics-extra feature train.json 140B metrics-train.json 140B metrics-extra feature train.json 140B metrics-train.json 139B metrics-train.json 139B metrics-extra feature train.json 139B metrics-train.json 139B metrics-extra feature train.json 139B metrics-extra feature train.json 139B metrics-extra feature train.json 139B metrics-extra feature train.json 139B metrics-extra feature train.json 139B metrics-extra feature train.json 139B metrics-train.json 139B metrics-train.json 139B metrics-extra feature train.json 139B metrics-train.json 139B metrics-train.json 139B metrics-train.json 139B metrics-extra feature train.json 139B metrics-train.json 139B metrics-train.json 139B metrics-extra feature train.json 139B metrics-train.json 139B metrics-train.json 139B metrics-extra feature train.json 139B metrics-train.json 139B metrics-extra feature train.json 139B metrics-extra feature train.json 139B metrics-train.json 139B metrics-extra feature train.json 139B metrics-train.json 138B metrics-extra feature train.json 138B metrics-train.json 138B metrics-extra feature train.json 138B metrics-train.json 138B metrics-train.json 138B metrics-extra feature train.json 138B metrics-extra feature train.json 138B metrics-extra feature train.json 138B metrics-extra feature train.json 138B metrics-extra feature train.json 138B metrics-extra feature train.json 138B metrics-extra feature train.json 138B metrics-train.json 138B metrics-train.json 136B metrics-train.json 136B metrics-train.json 135B metrics-eval.json 129B metrics-eval.json 127B metrics-eval.json 127B metrics-eval.json 127B metrics-eval.json 126B metrics-eval.json 126B metrics-eval.json 126B metrics-eval.json 126B metrics-extra feature eval.json 126B metrics-extra feature eval.json 126B metrics-eval.json 126B metrics-eval.json 126B metrics-extra feature eval.json 126B metrics-eval.json 126B metrics-extra feature eval.json 126B metrics-eval.json 126B metrics-extra feature eval.json 126B metrics-eval.json 125B metrics-extra feature eval.json 125B metrics-extra feature eval.json 125B metrics-eval.json 125B metrics-extra feature eval.json 125B metrics-extra feature eval.json 125B共 187 条
- 1
- 2
资源评论
