LightGBM回归预测实战

数据集下载

链接：https://pan.baidu.com/s/17ou-yYTlUKACnrbmq1TV-Q 
提取码：gsjy 

核心代码

1️⃣基模型

import lightgbm as lgb

# 读取数据集
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")

# 构建训练集和验证集
X = train.drop(columns=['Id', 'SalePrice'], axis=1).values # 说明：Id不是特征，SalePrice是标签，需要屏蔽
y = train['SalePrice'].values # 标签 SalePrice

# K折交叉验证
kf = KFold(n_splits=10)

rmse_scores = [] 

for train_indices, test_indices in kf.split(X):
    X_train, X_test = X[train_indices], X[test_indices]
    y_train, y_test = y[train_indices], y[test_indices]
    # 初始化模型
    LGBR = lgb.LGBMRegressor() # 基模型
    # 训练/fit拟合
    LGBR.fit(X_train, y_train)
    # 预测
    y_pred = LGBR.predict(X_test)
    # 评估
    rmse = mean_squared_error(y_test, y_pred)
    # 累计结果
    rmse_scores.append(rmse)

print("rmse scores : ", rmse_scores)
print(f'average rmse scores : {np.mean(rmse_scores)}')

2️⃣调参模型

train_data = lgb.Dataset(X_train, label=y_train) # 训练集
test_data = lgb.Dataset(X_test, label=y_test, reference=train_data) # 验证集


# 参数
params = {
    'objective':'regression', # 目标任务
    'metric':'rmse', # 评估指标
    'learning_rate':0.1, # 学习率
    'max_depth':15, # 树的深度
    'num_leaves':20, # 叶子数
}

# 创建模型对象
model = lgb.train(params=params,
                  train_set=train_data,
                  num_boost_round=300,
                  early_stopping_rounds=30,
                  valid_names=['test'],
                  valid_sets=[test_data])

3️⃣预测

score = model.best_score['test']['rmse']
score


test_pred = model.predict(test.drop('Id',axis=1).values)