代碼實(shí)現(xiàn)

數(shù)據(jù)讀取

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as sns

from sklearn import metrics

import scipy.stats as stats

plt.rcParams['font.family'] = 'Times New Roman'

plt.rcParams['axes.unicode_minus'] = False



df_train = pd.read_excel('GBDT_train.xlsx')

df_test = pd.read_excel('GBDT_test.xlsx')

從 Excel 文件中分別加載訓(xùn)練數(shù)據(jù) (GBDT_train.xlsx) 和測(cè)試數(shù)據(jù) (GBDT_test.xlsx) 到數(shù)據(jù)框 (df_train 和 df_test) 中，里面包含真實(shí)值以及預(yù)測(cè)值。

模型性能計(jì)算

from sklearn import metrics

# 真實(shí)

y_train = df_train['Experimental value']

y_test = df_test['Experimental value']

# 預(yù)測(cè)

y_pred_train = df_train['Predicted value']

y_pred_test = df_test['Predicted value']



y_pred_train_list = y_pred_train.tolist()

y_pred_test_list = y_pred_test.tolist()



# 計(jì)算訓(xùn)練集的指標(biāo)

mse_train = metrics.mean_squared_error(y_train, y_pred_train_list)

rmse_train = np.sqrt(mse_train)

mae_train = metrics.mean_absolute_error(y_train, y_pred_train_list)

r2_train = metrics.r2_score(y_train, y_pred_train_list)



# 計(jì)算測(cè)試集的指標(biāo)

mse_test = metrics.mean_squared_error(y_test, y_pred_test_list)

rmse_test = np.sqrt(mse_test)

mae_test = metrics.mean_absolute_error(y_test, y_pred_test_list)

r2_test = metrics.r2_score(y_test, y_pred_test_list)



print("訓(xùn)練集評(píng)價(jià)指標(biāo):")

print("均方誤差 (MSE):", mse_train)

print("均方根誤差 (RMSE):", rmse_train)

print("平均絕對(duì)誤差 (MAE):", mae_train)

print("擬合優(yōu)度 (R-squared):", r2_train)



print("\n測(cè)試集評(píng)價(jià)指標(biāo):")

print("均方誤差 (MSE):", mse_test)

print("均方根誤差 (RMSE):", rmse_test)

print("平均絕對(duì)誤差 (MAE):", mae_test)

print("擬合優(yōu)度 (R-squared):", r2_test)

從訓(xùn)練集和測(cè)試集的數(shù)據(jù)中提取真實(shí)值 (Experimental value) 和預(yù)測(cè)值 (Predicted value)，計(jì)算模型在訓(xùn)練集和測(cè)試集上的回歸性能指標(biāo)。

文章一可視化

# 創(chuàng)建一個(gè)包含訓(xùn)練集和測(cè)試集真實(shí)值與預(yù)測(cè)值的數(shù)據(jù)框

data_train = pd.DataFrame({

    'True': y_train,

    'Predicted': y_pred_train,

    'Data Set': 'Train'

})



data_test = pd.DataFrame({

    'True': y_test,

    'Predicted': y_pred_test,

    'Data Set': 'Test'

})



data = pd.concat([data_train, data_test])



# 自定義調(diào)色板

palette = {'Train': '#b4d4e1', 'Test': '#f4ba8a'}



# 創(chuàng)建 JointGrid 對(duì)象

plt.figure(figsize=(8, 6), dpi=1200)

g = sns.JointGrid(data=data, x="True", y="Predicted", hue="Data Set", height=10, palette=palette)



# 繪制中心的散點(diǎn)圖

g.plot_joint(sns.scatterplot, alpha=0.5)

# 添加訓(xùn)練集的回歸線

sns.regplot(data=data_train, x="True", y="Predicted", scatter=False, ax=g.ax_joint, color='#b4d4e1', label='Train Regression Line')

# 添加測(cè)試集的回歸線

sns.regplot(data=data_test, x="True", y="Predicted", scatter=False, ax=g.ax_joint, color='#f4ba8a', label='Test Regression Line')

# 添加邊緣的柱狀圖

g.plot_marginals(sns.histplot, kde=False, element='bars', multiple='stack', alpha=0.5)



# 添加擬合優(yōu)度文本在右下角

ax = g.ax_joint

ax.text(0.95, 0.1, f'Train $R^2$ = {r2_train:.3f}', transform=ax.transAxes, fontsize=12,

        verticalalignment='bottom', horizontalalignment='right', bbox=dict(boxstyle="round,pad=0.3", edgecolor="black", facecolor="white"))

ax.text(0.95, 0.05, f'Test $R^2$ = {r2_test:.3f}', transform=ax.transAxes, fontsize=12,

        verticalalignment='bottom', horizontalalignment='right', bbox=dict(boxstyle="round,pad=0.3", edgecolor="black", facecolor="white"))

# 在左上角添加模型名稱文本

ax.text(0.75, 0.99, 'Model = GBDT', transform=ax.transAxes, fontsize=12,

        verticalalignment='top', horizontalalignment='left', bbox=dict(boxstyle="round,pad=0.3", edgecolor="black", facecolor="white"))



# 添加中心線

ax.plot([data['True'].min(), data['True'].max()], [data['True'].min(), data['True'].max()], c="black", alpha=0.5, linestyle='--', label='x=y')

ax.legend()

plt.savefig("TrueFalse.pdf", format='pdf', bbox_inches='tight')

plt.show()

文章二基礎(chǔ)可視化

plt.figure(figsize=(8, 6), dpi=1200)

plt.scatter(y_test, y_pred_test, color='coral', label="Predicted N?O concentration", alpha=0.2)  # 預(yù)測(cè)值散點(diǎn)圖

plt.plot(y_test, y_test, color='grey', alpha=0.6, label="1:1 Line")  # 1:1灰色虛線



# 擬合線

z = np.polyfit(y_test, y_pred_test, 1)

p = np.poly1d(z)

plt.plot(y_test, p(y_test), color='blue', alpha=0.6, 

         label=f"Line of Best Fit\n$R^2$ = {r2_test:.2f},MAE = {mae_test:.2f}")

plt.title("GBDT Regression")

plt.xlabel("Observed Values")

plt.ylabel("Predicted Values")

plt.legend(loc="upper left")

plt.savefig('1.pdf', format='pdf', bbox_inches='tight')

plt.show()

集成置信區(qū)間與邊緣柱狀圖

通過多項(xiàng)式擬合計(jì)算訓(xùn)練集和測(cè)試集的預(yù)測(cè)值，并利用置信區(qū)間公式估算預(yù)測(cè)結(jié)果的不確定性，分別繪制訓(xùn)練集和測(cè)試集的擬合曲線、95%置信區(qū)間、散點(diǎn)圖以及誤差分布直方圖，此外添加對(duì)角線（1:1參考線）以顯示預(yù)測(cè)值與真實(shí)值的理想匹配，最終生成一張包含主要信息和輔助分布圖的可視化圖表。

文章轉(zhuǎn)自微信公眾號(hào)@Python機(jī)器學(xué)習(xí)AI