1. sklearn Chinese text classification（Naive Bayes, Logistic Regression, XGboost, lightGBM, SVM, KNN,

Random Forest, Decision Tree, GBDT）to test the result of bio-text classification，the data i use（neg.txt, pos.txt）

The results are as follows：

Naive Bayes	0.9032786885245901
Logistic Regression	0.8737704918032787
SVM	0.8836065573770492
Xgboost	0.8442622950819673
LightGBM	0.8508196721311475
knn	0.6081967213114754
RFC	0.8721311475409836
DT	0.8
GBDT	0.8508196721311475

2. The method to optimize the above algorithm