AcidificationModel/api/model_optimize/data_increase_5cv_score.py

# 导入常用包
import os
import pandas as pd
import numpy as np
from PIL import Image
from model_saver import save_model

# 机器学习模型导入
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
from sklearn.ensemble import GradientBoostingRegressor as GBSTR
from sklearn.neighbors import KNeighborsRegressor
from xgboost import XGBRegressor as XGBR



# 导入数据处理函数
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import MinMaxScaler

# 导入评分函数
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error 
from sklearn.metrics import mean_absolute_error
from sklearn.metrics import accuracy_score
from sklearn.metrics import log_loss
from sklearn.metrics import roc_auc_score
from sklearn.model_selection import cross_val_score

import pickle
import pandas as pd
import numpy as np
from sklearn.metrics import mean_squared_error
from pathlib import Path



# 导入数据
data = pd.read_excel('model_optimize/data/data_filt.xlsx')
x = data.iloc[:, 1:10]
y = data.iloc[:, -1]

# 为 x 赋予列名
x.columns = [
    'organic_matter',        # OM g/kg
    'chloride',              # CL g/kg
    'cec',                   # CEC cmol/kg
    'h_concentration',       # H+ cmol/kg
    'hn',                    # HN mg/kg
    'al_concentration',      # Al3+ cmol/kg
    'free_alumina',          # Free alumina g/kg
    'free_iron',             # Free iron oxides g/kg
    'delta_ph'               # ΔpH
]

y.name = 'target_ph'

Xtrain, Xtest, Ytrain, Ytest = train_test_split(x, y, test_size=0.2, random_state=42)

## 模型
# 随机森林回归模型
rfc = RandomForestRegressor(random_state=1)
# XGBR
XGB = XGBR(random_state=1)
# GBSTR
GBST = GBSTR(random_state=1)
# KNN
KNN = KNeighborsRegressor(n_neighbors=5)

# 增量训练：每次增加10%的训练数据
increment = 0.1  # 每次增加的比例
train_sizes = np.arange(0.1, 1.1, increment)  # 从0.1到1.0的训练集大小
# 记录各模型交叉验证评分
cv5_scores_rfc = []  
cv5_scores_xgb = []  
cv5_scores_gbst = []  
cv5_scores_knn = []  


# 对于每种训练集大小，训练模型并记录r2_score
for size in train_sizes:
    # 计算当前训练集的大小
    current_size = int(size * len(Xtrain))
    
    # 交叉验证评分
    score_rfc = cross_val_score(rfc, Xtrain, Ytrain, cv=5).mean()
    cv5_scores_rfc.append(score_rfc)

    # XGBRegressor的交叉验证评分
    score_xgb = cross_val_score(XGB, Xtrain, Ytrain, cv=5).mean()
    cv5_scores_xgb.append(score_xgb)

    # GBST的交叉验证评分
    score_gbst = cross_val_score(GBST, Xtrain, Ytrain, cv=5).mean()
    cv5_scores_gbst.append(score_gbst)

    # KNN的交叉验证评分
    score_knn = cross_val_score(KNN, Xtrain, Ytrain, cv=5).mean()
    cv5_scores_knn.append(score_knn)

    # 输出当前的训练进度与评分
    print(f"Training with {size * 100:.2f}% of the data:")
    print(f"  - Random Forest CV5 score: {score_rfc}")
    print(f"  - XGB CV5 score: {score_xgb}")
    print(f"  - GBST CV5 score: {score_gbst}")
    print(f"  - KNN CV5 score: {score_knn}")

# 绘制R2评分随训练数据大小变化的图形
import matplotlib.pyplot as plt

plt.plot(train_sizes * 100, cv5_scores_rfc, marker='o', label='Random Forest')
plt.plot(train_sizes * 100, cv5_scores_xgb, marker='x', label='XGBoost')
plt.plot(train_sizes * 100, cv5_scores_gbst, marker='s', label='Gradient Boosting')
plt.plot(train_sizes * 100, cv5_scores_knn, marker='^', label='KNN')


plt.xlabel('Training data size (%)')
plt.ylabel('CV5 Score')
plt.title('Model Performance with Incremental Data')
plt.legend()
plt.grid(True)
plt.show()