数据分析

添加代码，分析点赞数、热度指数、浏览量之间的相关性

sns.pairplot(df_ads[['点赞数', '热度指数', '浏览量']]) plt.show()

特征工程

添加代码，将热度指数也加入到特征中

X = df_ads[['点赞数', '热度指数']] y = df_ads['浏览量']

模型构建

添加代码，使用其他模型构建预测模型，如岭回归、Lasso回归等

model = RandomForestRegressor() model.fit(X_train, y_train)

预测结果

y_pred = model.predict(X_test)

模型评估

添加代码，输出更多的评估指标，如平均绝对误差、解释方差等

print('随机森林模型评估：') print('均方误差：%.2f' % mean_squared_error(y_test, y_pred)) print('平均绝对误差：%.2f' % np.mean(np.abs(y_test - y_pred))) print('解释方差：%.2f' % model.score(X_test, y_test))

模型构建

model = DecisionTreeRegressor() model.fit(X_train, y_train)

预测结果

y_pred = model.predict(X_test)

模型评估

print('决策树模型评估：') print('均方误差：%.2f' % mean_squared_error(y_test, y_pred)) print('平均绝对误差：%.2f' % np.mean(np.abs(y_test - y_pred))) print('解释方差：%.2f' % model.score(X_test, y_test))

模型构建

model = LinearRegression() model.fit(X_train, y_train)

预测结果

y_pred = model.predict(X_test)

模型评估

print('线性回归模型评估：') print('均方误差：%.2f' % mean_squared_error(y_test, y_pred)) print('平均绝对误差：%.2f' % np.mean(np.abs(y_test - y_pred))) print('解释方差：%.2f' % model.score(X_test, y_test))

model_svr = SVR(kernel='rbf', C=1e3, gamma=0.1) model_svr.fit(X_train, y_train) y_pred_svr = model_svr.predict(X_test) df_ads_pred_svr = X_test.copy() df_ads_pred_svr['浏览量真值'] = y_test df_ads_pred_svr['浏览量预测值'] = y_pred_svr df_ads_pred_svr

print("支持向量机预测集评分：", model_svr.score(X_test, y_test)) print("支持向量机训练集评分：", model_svr.score(X_train, y_train))

model_mlp = MLPRegressor(hidden_layer_sizes=(100,50,10), max_iter=1000, alpha=0.001, solver='adam', verbose=0, random_state=21) model_mlp.fit(X_train, y_train) y_pred_mlp = model_mlp.predict(X_test) df_ads_pred_mlp = X_test.copy() df_ads_pred_mlp['浏览量真值'] = y_test df_ads_pred_mlp['浏览量预测值'] = y_pred_mlp df_ads_pred_mlp

print("神经网络预测集评分：", model_mlp.score(X_test, y_test)) print("神经网络训练集评分：", model_mlp.score(X_train, y_train)