Try All Model by sklearn

导入所需包

import pandas as pd

from sklearn.model_selection import train_test_split,GridSearchCV
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier,GradientBoostingClassifier
#from lightgbm import LGBMClassifier
from xgboost import XGBClassifier
from sklearn.metrics import accuracy_score,f1_score,precision_score,recall_score,roc_auc_score,roc_curve,auc
import matplotlib
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler

import os
os.chdir("E:\\Academic\\Graduation thesis\\PSSP_experiment")
import datetime 
start_time=datetime.datetime.now()

载入特征集

import pickle
#pkl_file_name='CB513_AAC_pssm_X.pkl'
pkl_file_name='CB513_AAC_pssm_40_not_C_X.pkl'#66340
#pkl_file_name='CB513_AAC_pssm_head_tail_flag_X.pkl'
with open(pkl_file_name, "rb") as f:
    x=pickle.load(f)
    
#pkl_file_name='CB513_AAC_pssm_Y.pkl'
pkl_file_name='CB513_AAC_pssm_not_C_Y.pkl'#66340
#pkl_file_name='CB513_AAC_pssm_not_C_Y.pkl'

#pkl_file_name='CB513_AAC_pssm_Y_onehot.pkl'

with open(pkl_file_name, "rb") as f:
    y=pickle.load(f)

X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=2018