土壤属性特征重要性代码编写

在编写土壤属性特征重要性（Feature Importance for Soil Properties）的代码时，通常涉及到机器学习中的模型评估和特征选择过程。以下是一个简单的Python示例，假设我们使用的是决策树（如`sklearn`库的`DecisionTreeClassifier`）作为模型：

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.feature_selection import SelectFromModel
from sklearn.metrics import accuracy_score

# 加载土壤属性数据集
data = pd.read_csv('soil_data.csv') # 假设csv文件里有土壤属性和标签列
X = data.drop('target_column', axis=1) # 特征数据
y = data['target_column'] # 目标变量

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 训练决策树模型
model = DecisionTreeClassifier()
model.fit(X_train, y_train)

# 使用特征重要性计算
importance = model.feature_importances_
feature_names = X.columns
sorted_idx = np.argsort(importance)[::-1] # 从高到低排序

# 提取最重要的前n个特征
n_features = 5
top_features = feature_names[sorted_idx[:n_features]]

# 验证重要性
selected_X_train = SelectFromModel(model, prefit=True).transform(X_train)
selected_X_test = SelectFromModel(model, prefit=True).transform(X_test)

# 用新选的特征训练和评估模型
reduced_model = DecisionTreeClassifier()
reduced_model.fit(selected_X_train, y_train)
predictions = reduced_model.predict(selected_X_test)
accuracy = accuracy_score(y_test, predictions)

print(f"Top {n_features} features with highest importance:")
for i in range(n_features):
    print(f"{i+1}. {top_features[i]}: {importance[sorted_idx[i]]}")