https://github.com/mylamour/w2vcluster
word2vec & k-means cluster
https://github.com/mylamour/w2vcluster
clustering-algorithm gensim-word2vec k-means security word2vec
Last synced: 2 months ago
JSON representation
word2vec & k-means cluster
- Host: GitHub
- URL: https://github.com/mylamour/w2vcluster
- Owner: mylamour
- Created: 2019-06-06T03:12:36.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2024-06-17T22:51:44.000Z (over 1 year ago)
- Last Synced: 2025-03-05T14:48:40.266Z (7 months ago)
- Topics: clustering-algorithm, gensim-word2vec, k-means, security, word2vec
- Language: Python
- Size: 3.91 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
That's a basic word2vec cluster demo. You can run it with :
* step1:
`pip install -r requirements.txt`
* step2:
`python cluster.py kmeans --filename data/alert_pcmline_20190617.csv -o output/pcmdline_3.csv -k 3`
Now, you would see the result of predict. Have fun.
In my sence, i count the cmdline from alert datastets then cluster it.
```sql
select srv_cmd, count(*) srv_cmd_cnt
from xxxxxxxx.xxxx_alert_log_xxxxx
where ds = max_pt("xxxx.xxxxx")
group by srv_cmd
order by srv_cmd_cnt desc
limit 10000;
```
so that i can find the problem from millions alerts. Actually, it was useful.(also still have some problem)
