A combination of Model Ensembling methods that is extremely useful for increasing accuracy of this contest.
More details see Entire Project
Given an article, we need to create algorithms that judge types of authors (automatic summary, machine translation, robot writer or human writer). More details see SMP EUPT 2018
- lightgbm
- gensim
- scikit-learn
- pickle
- numpy
We have improved the traditional Stacking method, concating the probability vectors generated by each classifier, and reclassifying them with Lightgbm.
$ python3 smp_sta_all_vec.py
Performing the Blending method on the stitched probability vector.
$ python3 smp_lgb_blending.py
| Parameter | Description | |
|---|---|---|
| 1 | num_class | 4 |
| 2 | n_estimators | 5000 |
| 3 | objective | multiclass |
| 4 | learning_rate | 0.005 |
| 5 | num_leaves | 65 |
| 6 | n_jobs | -1 |
Thanks for all the efforts of my teammates in GDUFS-iiip
We hope that more people will join in our labs: Data Mining Lab in GDUFS(广外数据挖掘实验室）