具有相同的MSE，RMSE，MAE的山脊和Randomforest

发布于 2025-02-11 00:53:29 字数 962 浏览 1 评论 0原文

我已经使用给定的代码来预测值，但是，我对所有3个指标都取得了相同的分数，同时对所有其他模型都具有不同的指标。

def metrics(valid, pred):
  mse = mean_squared_error(valid, pred)
  rmse = np.sqrt(mean_squared_error(valid, pred))
  mae = mean_absolute_error(valid,pred)
  return mse, rmse, made

model = Ridge().fit(X_train, y_train)
y_pred = model.predict(X_test)

df_models_temp = pd.DataFrame(data=[['Ridge', *metrics(y_test, y_pred)]], columns=['Model Name', 'MSE', 'RMSE', 'MAE'])
df_models = df_models.append(df_models_temp, ignore_index=True)

clf = RandomForestRegressor().fit(X_train, y_train)
y_pred = model.predict(X_test)

df_models_temp = pd.DataFrame(data=[['Random Forest', *metrics(y_test, y_pred)]], columns=['Model Name', 'MSE', 'RMSE', 'MAE'])
df_models = df_models.append(df_models_temp, ignore_index=True)

原文

I have used the given code to predict values, however, I have landed the same score, for all 3 metrics, while having different metrics for all other models.

def metrics(valid, pred):
  mse = mean_squared_error(valid, pred)
  rmse = np.sqrt(mean_squared_error(valid, pred))
  mae = mean_absolute_error(valid,pred)
  return mse, rmse, made

model = Ridge().fit(X_train, y_train)
y_pred = model.predict(X_test)

df_models_temp = pd.DataFrame(data=[['Ridge', *metrics(y_test, y_pred)]], columns=['Model Name', 'MSE', 'RMSE', 'MAE'])
df_models = df_models.append(df_models_temp, ignore_index=True)

clf = RandomForestRegressor().fit(X_train, y_train)
y_pred = model.predict(X_test)

df_models_temp = pd.DataFrame(data=[['Random Forest', *metrics(y_test, y_pred)]], columns=['Model Name', 'MSE', 'RMSE', 'MAE'])
df_models = df_models.append(df_models_temp, ignore_index=True)

分享到QQ

分享到微博

如果你对这篇内容有疑问，欢迎到本站社区发帖提问参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

发布评论

需要登录才能够评论，你可以免费注册一个本站的账号。

余罪 2025-02-18 00:53:29

您仍在使用山脊来对Randomforest进行预测，代码应该是：

model = Ridge().fit(X_train, y_train)
y_pred = model.predict(X_test)

df_models_temp = pd.DataFrame(data=[['Ridge', *metrics(y_test, y_pred)]], columns=['Model Name', 'MSE', 'RMSE', 'MAE'])
df_models = df_models.append(df_models_temp, ignore_index=True)

clf = RandomForestRegressor().fit(X_train, y_train)
# Here predict with clf not model
y_pred = clf.predict(X_test)

You are still using the Ridge to make prediction for the RandomForest, code should be like:

model = Ridge().fit(X_train, y_train)
y_pred = model.predict(X_test)

df_models_temp = pd.DataFrame(data=[['Ridge', *metrics(y_test, y_pred)]], columns=['Model Name', 'MSE', 'RMSE', 'MAE'])
df_models = df_models.append(df_models_temp, ignore_index=True)

clf = RandomForestRegressor().fit(X_train, y_train)
# Here predict with clf not model
y_pred = clf.predict(X_test)

回复收藏 0 原文

~没有更多了~