56 lines
1.7 KiB
Python
56 lines
1.7 KiB
Python
|
#!/users/dsc/bin/Python3
|
|||
|
|
#-*-coding: UTF-8 -*-
|
|||
|
|
from sklearn.neural_network import MLPClassifier #多层感知机分类器 MLP
|
|||
|
|
from sklearn.linear_model import LogisticRegression #逻辑斯蒂回归分类器 LR
|
|||
|
|
from sklearn.ensemble import RandomForestClassifier#随机森林分类器 RFC
|
|||
|
|
from sklearn.tree import DecisionTreeClassifier#决策树 DTC
|
|||
|
|
|
|||
|
|
from sklearn.neural_network import MLPRegressor #多层感知机回归模型 MLPR
|
|||
|
|
from sklearn.linear_model import LinearRegression #线性回归模型 LRR
|
|||
|
|
from sklearn.ensemble import RandomForestRegressor #随机森林回归 RFR
|
|||
|
|
from sklearn.tree import DecisionTreeRegressor #决策树回归 DTR
|
|||
|
|
|
|||
|
|
import warnings
|
|||
|
|
warnings.filterwarnings("ignore")#忽略警告
|
|||
|
|
|
|||
|
|
class Models():
|
|||
|
|
"""_summary_
|
|||
|
|
模型集，包含：
|
|||
|
|
分类器
|
|||
|
|
1.多层感知机
|
|||
|
|
2.逻辑斯蒂回归
|
|||
|
|
3.随机森林
|
|||
|
|
4.决策树
|
|||
|
|
回归模型
|
|||
|
|
1.多层感知机
|
|||
|
|
2.逻辑斯蒂回归
|
|||
|
|
3.随机森林
|
|||
|
|
4.决策树
|
|||
|
|
"""
|
|||
|
|
def __init__(self):
|
|||
|
|
cf1=MLPClassifier()
|
|||
|
|
cf2=LogisticRegression()
|
|||
|
|
cf3=RandomForestClassifier()
|
|||
|
|
cf4=DecisionTreeClassifier()
|
|||
|
|
rf1=MLPRegressor()
|
|||
|
|
rf2=LinearRegression()
|
|||
|
|
rf3=RandomForestRegressor()
|
|||
|
|
rf4=DecisionTreeRegressor()
|
|||
|
|
self.models={"MLP":cf1,"LR":cf2,"RFC":cf3,"DTC":cf4}
|
|||
|
|
self.regressors={"MLPR":rf1,"LRR":rf2,"RFR":rf3,"DTR":rf4}
|
|||
|
|
def model(self,model_name="MLP"):
|
|||
|
|
try:
|
|||
|
|
return self.models[model_name]
|
|||
|
|
except:
|
|||
|
|
return self.models["MLP"]
|
|||
|
|
def regressor(self,regressor_name="MLPR"):
|
|||
|
|
try:
|
|||
|
|
return self.regressors[regressor_name]
|
|||
|
|
except:
|
|||
|
|
return self.regressors["MLPR"]
|
|||
|
|
models=Models()
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
|