Task 1.2模型构建之集成模型

最新推荐文章于 2025-05-24 19:54:02 发布

原创最新推荐文章于 2025-05-24 19:54:02 发布 · 198 阅读

0 ·

CC 4.0 BY-SA版权

本文构建了随机森林、GBDT、XGBoost和LightGBM四种机器学习模型，并对每种模型进行了评分，通过准确度和AUC值来评估模型性能。文章详细展示了从数据预处理到模型训练及评估的全过程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

目标：构建随机森林、GBDT、XGBoost和LightGBM这4个模型，并对每一个模型进行评分，评分方式任意，例如准确度和auc值。
构建随机森林并评分

#构建随机森林

#导入工具包
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandarScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier

#读取。
data = pd.read_csv("data_all.csv")
x = data.drop(labels = 'status', axis = 1)
y = data['status']
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3, random_size = 2018)

#数据标准化
scaler = StandardScaler()
scaler.fit(x_train)
x_train = scaler.transform(x_train)
x_test = scaler.transform(x_test) 

#建立模型，并进行模型训练。
rfc = RandomForestClassifier()
rfc.fit(x_train,y_train)
rfc_score = rfc.score(x_test, y_test)

#打印
print(rfc_score)

构建GBDT并评分

#构建GBDT算法

#导入工具包
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandarScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier

#读取。
data = pd.read_csv("data_all.csv")
x = data.drop(labels = 'status', axis = 1)
y = data['status']
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3, random_size = 2018)

#数据标准化
scaler = StandardScaler()
scaler.fit(x_train)
x_train = scaler.transform(x_train)
x_test = scaler.transform(x_test) 
#模型训练，使用GBDT算法
gbdt = GradientBoostingRegressor()
gbdt.fit(x_train, y_train
gdbt_score = gdbt.score(x_test, y_test)

#打印
print(gdbt_score)

构建XDBoost并评分

#构建XGBoost模型

#导入工具包
import pandas as pd
import xgboost as xgb 
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandarScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier

#读取
data = pd.read_csv("data_all.csv")
x = data.drop(labels = 'status', axis = 1)
y = data['status']
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3, random_size = 2018)

#数据标准化
scaler = StandardScaler()
scaler.fit(x_train)
x_train = scaler.transform(x_train)
x_test = scaler.transform(x_test) 

#XDBoost模型
xgb = xgb.XGBClassifier()
xbg.fit(x_traim, y_train)
xgb_score = xgb.score(x_test, y_test)

#打印
print(xgb_score)

4 构建lightGBM并评分

#构建lightGBM模型

#导入工具包
import pandas as pd
import lightgbm as lgb
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandarScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier

#读取
data = pd.read_csv("data_all.csv")
x = data.drop(labels = 'status', axis = 1)
y = data['status']
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3, random_size = 2018)

#数据标准化
scaler = StandardScaler()
scaler.fit(x_train)
x_train = scaler.transform(x_train)
x_test = scaler.transform(x_test) 

#lightGBM模型
gbm = lgb.LGBMRegressor()
gbm.fit(x_train, y_train)
gbm_score = gbm.score(x_test, y_test)

#打印
print(gbm_score)