python sklearn机械学习模型-分类

🌈所属专栏：【机械学习】
✨作者主页： Mr.Zwq
✔️个人简介：一个正在努力学技术的Python领域创作者，擅长爬虫，逆向，全栈方向，专注基础和实战分享，欢迎咨询！

您的点赞、关注、收藏、评论，是对我最大的激励和支持！！！🤩🥰😍

安装

数据

使用

MLP模型

逻辑回归模型

随机森林模型

SGDClassifier模型

XGBoost模型

网格搜索优化XGBoost模型

总结

安装

pip install scikit-learn

数据

X,y即为所需要进行回归处理的数据。

操作：拆分为训练集和测试集

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.3, random_state=12)

使用

MLP模型

# 训练MLP模型
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import roc_auc_score

mlp_model = MLPClassifier(hidden_layer_sizes=(64,32), activation='relu', solver='adam',max_iter=200, random_state=12)
mlp_model.fit(X_train,y_train)
y_pred_mlp = mlp_model.predict_proba(X_test)[:,1]

# auc分数越接近1表示模型性能越好
auc_mlp = roc_auc_score(y_test, y_pred_mlp)
print(f'MLP Model AUC：{auc_mlp:.4f}')

逻辑回归模型

# 逻辑回归模型
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_auc_score

lrmodel=LogisticRegression(solver='liblinear')
lrmodel.fit(X_train,y_train)
y_lrpred=lrmodel.predict_proba(X_test)[:,1]
auc = roc_auc_score(y_test, y_lrpred)

print(f'LogisticRegression Model AUC：{auc:.4f}')

随机森林模型

# 随机森林模型
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import roc_auc_score

rfmodel=RandomForestClassifier()
rfmodel.fit(X_train,y_train)
y_rfpred=rfmodel.predict_proba(X_test)[:,1]

auc = roc_auc_score(y_test, y_rfpred)
print(f'RandomForestClassifier Model AUC：{auc:.4f}')

SGDClassifier模型

# SGDClassifier模型
from sklearn.linear_model import SGDClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import matthews_corrcoef,make_scorer,roc_auc_score

param_grid=[{
    'loss':['hinge'],
    'alpha':[10**k for k in range(-3,4)],
    'max_iter':[1000],
    'tol':[1e-3],
    'random_state':[random_state],
    'class_weight':[None,'balanced'],
    'warm_start':[True]},
    {'loss':['log'],
    'penalty':['l2','l1'],
    'alpha':[10**k for k in range(-3,4)],
    'max_iter':[1000],
    'tol':[1e-3],
    'random_state':[random_state],
    'class_weight':[None,'balanced'],
    'warm_start':[True]}]
grid=GridSearchCV(estimator=SGDClassifier(),param_grid=param_grid,scoring=make_scorer(matthews_corrcoef),n_jobs=1,pre_dispatch=1,verbose=1,return_train_score=True)
grid.fit(X_train,y_train)
y_SGDCpred=grid.predict(X_test)

auc = roc_auc_score(y_test, y_SGDCpred)
print(f'SGDClassifier Model AUC：{auc:.4f}')

XGBoost模型

安装：pip install xgboost

import xgboost as xgb
from sklearn.metrics import roc_auc_score

# 训练XGBoost模型
xgb_model = xgb.XGBClassifier(use_label_encoder=False, eval_metric='logloss')
xgb_model.fit(X_train, y_train)
y_pred_xgb = xgb_model.predict_proba(X_test)[:,1]

auc_xgb = roc_auc_score(y_test, y_pred_xgb)
print(f'XGBoost Model AUC：{auc_xgb:.4f}')

网格搜索优化XGBoost模型

# 网格搜索优化XGBoost模型
import xgboost as xgb
from sklearn.metrics import roc_auc_score
from sklearn.model_selection import GridSearchCV

param_grid = {
    'n_estimators':[50,100,200],
    'max_depth':[3,4,5],
    'learning_rate':[0.01,0.1,0.2]
}
xgb_model = xgb.XGBClassifier(use_label_encoder=False, eval_metric='logloss')
grid_search = GridSearchCV(estimator=xgb_model, param_grid=param_grid, scoring='roc_auc',cv=3)
grid_search.fit(X_train, y_train)
best_xgb_model = grid_search.best_estimator_
y_pred_best_xgb = best_xgb_model.predict_proba(X_test)[:,1]

auc_best_xgb = roc_auc_score(y_test, y_pred_best_xgb)
print(f'Optimized XGBoost Model AUC：{auc_best_xgb:.4f}')