如何根据人的属性来近似状态转换？

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

# 假设我们有一个包含人属性和职业状态的数据集
data = {
    'age': [25, 30, 35, 40, 45],
    'gender': ['M', 'F', 'M', 'F', 'M'],
    'education': ['Bachelor', 'Master', 'PhD', 'Bachelor', 'Master'],
    'income': [50000, 60000, 80000, 70000, 90000],
    'current_status': ['Student', 'Employee', 'Employee', 'Manager', 'Manager']
}

df = pd.DataFrame(data)

# 将分类变量转换为数值
df['gender'] = df['gender'].map({'M': 0, 'F': 1})
df['education'] = df['education'].map({'Bachelor': 0, 'Master': 1, 'PhD': 2})

# 特征和标签
X = df[['age', 'gender', 'education', 'income']]
y = df['current_status']

# 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)

# 预测
y_pred = model.predict(X_test)

# 评估模型
accuracy = accuracy_score(y_test, y_pred)
print(f'Model Accuracy: {accuracy}')