机器学习-SVM预测

news2025/1/20 5:12:29

本文使用机器学习SVM对数据进行预测。仅供参考

1、数据

1.1 训练数据集：

medol.xlsx文件示例

o	t	v
30	15	-1.915362209
30	18	-1.963409776
30	21	-1.762028408
30	24	-1.789477583

1.2 预测数据集

test.xlsx文件示例

o	t
35	16
35	19

2、模型训练

train.py

import pandas as pd
from sklearn.svm import SVR
from sklearn.model_selection import GridSearchCV, train_test_split
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
from sklearn.preprocessing import StandardScaler
import joblib
import numpy as np
import matplotlib.pyplot as plt

# 加载数据
df = pd.read_excel("model.xlsx")

# 定义特征列
feature_columns = ['o', 't']

# 初始化标准化器
scaler = StandardScaler()

# 归一化数据集
X_scaled = scaler.fit_transform(df[feature_columns])

target_column = 'v'

# 将数据拆分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X_scaled, df[target_column], test_size=0.1)

# 初始化SVM回归器
svm = SVR()

# 定义参数网格
param_grid = {
    'kernel': ['linear', 'rbf'],
    'C': [1, 10, 100],
    'gamma': [0.1, 1, 10],
}

# 使用GridSearchCV进行网格搜索
grid_search = GridSearchCV(svm, param_grid, cv=5, scoring='neg_mean_squared_error', verbose=1)
grid_search.fit(X_train, y_train)

# 获取最佳模型
best_model_svm = grid_search.best_estimator_

# 输出最佳超参数
print("最佳超参数 for SVM:", grid_search.best_params_)

# 计算训练集和测试集的指标
train_predictions_svm = best_model_svm.predict(X_train)
test_predictions_svm = best_model_svm.predict(X_test)

# 训练集指标
print("\n[训练集指标 - SVM]")
print("平均绝对误差: {}".format(mean_absolute_error(y_train, train_predictions_svm)))
print("均方误差: {}".format(mean_squared_error(y_train, train_predictions_svm)))
print("均方根误差: {}".format(np.sqrt(mean_squared_error(y_train, train_predictions_svm))))
print("R2分数: {}".format(r2_score(y_train, train_predictions_svm)))

# 测试集指标
print("\n[测试集指标 - SVM]")
print("平均绝对误差: {}".format(mean_absolute_error(y_test, test_predictions_svm)))
print("均方误差: {}".format(mean_squared_error(y_test, test_predictions_svm)))
print("均方根误差: {}".format(np.sqrt(mean_squared_error(y_test, test_predictions_svm))))
print("R2分数: {}".format(r2_score(y_test, test_predictions_svm)))

# 绘制训练集误差随循环次数的变化图
plt.plot(range(1, len(best_model_svm.support_vectors_) + 1), best_model_svm.dual_coef_.ravel(), label='Train Error')
plt.xlabel('Support Vectors')
plt.ylabel('Dual Coefficients')
plt.title('Training Set Error Over Support Vectors')
plt.legend()
plt.show()

# 绘制测试集的实际值和预测值的对比图
plt.scatter(y_test, test_predictions_svm, alpha=0.5)
plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], '--', color='red', label='Identity Line')
plt.xlabel('Actual Values')
plt.ylabel('Predicted Values')
plt.title('Actual vs Predicted Values on Test Set - SVM')
plt.legend()
plt.show()

# 保存训练好的SVM模型
svm_model_filename = 'svm_model'
joblib.dump(best_model_svm, svm_model_filename)

# 保存训练好的标准化器
joblib.dump(scaler, 'scaler_model_svm')

3、预测模型

test.py

import pandas as pd
import joblib
from sklearn.preprocessing import StandardScaler

# 加载训练好的模型并在新数据上进行预测 (test.xlsx)
test_df = pd.read_excel("test.xlsx")

# 初始化 StandardScaler
scaler = joblib.load('scaler_model')

predicted_columns = []


model_filename = f'svm_model'

# 加载模型
loaded_model = joblib.load(model_filename)

# 在新数据上进行预测
predictions = loaded_model.predict(scaler.transform(test_df[['o', 't']]))

# 将预测结果存储在列表中
predicted_columns.append(predictions)

# 使用 pd.concat(axis=1) 将所有列一次性连接到 DataFrame 中
predicted_df = pd.concat([test_df] + [pd.Series(predictions, name=f'v') for i, predictions in enumerate(predicted_columns, start=1)], axis=1)

# 保存更新后的 test_df
predicted_df.to_excel("predicted.xlsx", index=False)