使用Scikit-Learn使用分类数据建立回归模型

from sklearn.preprocessing import OneHotEncoder, LabelEncoder
from sklearn.compose import ColumnTransformer

# 假设我们有一个包含分类数据的数据集X和目标变量y

# 创建一个ColumnTransformer对象，指定需要进行编码的列和编码方式
# 这里假设第一列和第三列是分类数据需要进行编码
column_transformer = ColumnTransformer(
    [('encoder', OneHotEncoder(), [0, 2])],
    remainder='passthrough'
)

# 对X进行编码
X_encoded = column_transformer.fit_transform(X)

# 对y进行标签编码
label_encoder = LabelEncoder()
y_encoded = label_encoder.fit_transform(y)

from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error

X_train, X_test, y_train, y_test = train_test_split(X_encoded, y_encoded, test_size=0.2, random_state=42)

regression_model = LinearRegression()
regression_model.fit(X_train, y_train)

y_pred = regression_model.predict(X_test)

mse = mean_squared_error(y_test, y_pred)