如何使用编码的特征来预测sklearn中的值？

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder, LabelEncoder
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

# 假设我们有一个数据集
data = {
    'Country': ['USA', 'Canada', 'Mexico', 'USA', 'Canada'],
    'Gender': ['Male', 'Female', 'Male', 'Female', 'Male'],
    'Age': [25, 30, 35, 40, 45],
    'Purchased': [0, 1, 0, 1, 0]
}

df = pd.DataFrame(data)

# 分离特征和目标变量
X = df.drop('Purchased', axis=1)
y = df['Purchased']

# 对分类变量进行编码
label_encoder = LabelEncoder()
X['Country'] = label_encoder.fit_transform(X['Country'])
one_hot_encoder = OneHotEncoder(sparse=False)
encoded_gender = one_hot_encoder.fit_transform(X[['Gender']])
encoded_gender_df = pd.DataFrame(encoded_gender, columns=one_hot_encoder.get_feature_names_out(['Gender']))

# 合并编码后的特征
X_encoded = pd.concat([X.drop('Gender', axis=1), encoded_gender_df], axis=1)

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

# 训练模型
model = LogisticRegression()
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}')