案例背景
投资商经常会通过多个不同渠道投放广告,以此来获得经济利益。在本案例中我们选取公司在电视、广播和报纸上的投入,来预测广告收益,这对公司策略的制定是有较重要的意义。
模型搭建
# 读取数据
import pandas as pd
df = pd.read_excel('广告收益数据.xlsx')
df.head()
# 1.提取特征变量和目标变量
X = df.drop(columns='收益')
y = df['收益']
# 2.划分训练集和测试集
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=123)
# 3. 模型训练和搭建
from lightgbm import LGBMRegressor
model = LGBMRegressor()
model.fit(X_train, y_train)
模型预测及评估
# 预测测试数据
y_pred = model.predict(X_test)
y_pred[0:5]
# 预测值和实际值对比
a = pd.DataFrame() # 创建一个空DataFrame
a['预测值'] = list(y_pred)
a['实际值'] = list(y_test)
a.head()
# 查看评分
model.score(X_test, y_test)
# 特征重要性
model.feature_importances_
模型参数调优
# 参数调优
from sklearn.model_selection import GridSearchCV # 网格搜索合适的超参数
parameters = {'num_leaves': [15, 31, 62], 'n_estimators': [20, 30, 50, 70], 'learning_rate': [0.1, 0.2, 0.3, 0.4]} # 指定分类器中参数的范围
model = LGBMRegressor() # 构建模型
grid_search = GridSearchCV(model, parameters,scoring='r2',cv=5) # cv=5表示交叉验证5次,scoring='r2'表示以R-squared作为模型评价准则
# 输出参数最优值
grid_search.fit(X_train, y_train) # 传入数据
grid_search.best_params_ # 输出参数的最优值
# 重新搭建LightGBM回归模型
model = LGBMRegressor(num_leaves=31, n_estimators=50,learning_rate=0.3)
model.fit(X_train, y_train)
# 查看得分
model.score(X_test, y_test)