XGBoost 错误 - 提供分类类型时，DMatrix 参数 `enable_categorical` 必须设置为 `True`

Question

我有四个分类特征和第五个数字特征 (Var5)。当我尝试以下代码时：

cat_attribs = ['var1','var2','var3','var4']

full_pipeline = ColumnTransformer([('cat', OneHotEncoder(handle_unknown = 'ignore'), cat_attribs)], remainder = 'passthrough')
X_train = full_pipeline.fit_transform(X_train)

model = XGBRegressor(n_estimators=10, max_depth=20, verbosity=2)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

当模型尝试进行预测时，我收到以下错误消息：

ValueError：数据的 DataFrame.dtypes 必须是 int、float、bool 或 categorical。什么时候 提供分类类型，DMatrix 参数 enable_categorical 必须设置为 True.Var1, Var2, Var3, Var4

有人知道这里出了什么问题吗？

如果有帮助，这里是 X_train 数据和 y_train 数据的小样本：

       Var1  Var2  Var3 Var4        Var5
1507856   JP  2009  6581  OME  325.787218
839624    FR  2018  5783  I_S   11.956326
1395729   BE  2015  6719  OME   42.888565
1971169   DK  2011  3506  RPP   70.094146
1140120   AT  2019  5474  NMM  270.082738

和：

          Ind_Var
1507856   8.013558
839624    4.105559
1395729   7.830077
1971169  83.000000
1140120  51.710526

Answer 1

您的代码的问题是您在X_train 中编码了分类特征，但在X_test 中没有编码，因此当您运行model.predict(X_test) 时，您会收到一条错误消息。为了解决这个问题，首先需要将编码器适配到X_train，然后使用编码器对X_train和X_test进行变换。请参阅下面的代码以获取示例。

import pandas as pd
from xgboost import XGBRegressor
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder

# define the input data
df = pd.DataFrame([
 {'Var1': 'JP', 'Var2': 2009, 'Var3': 6581, 'Var4': 'OME', 'Var5': 325.787218, 'Ind_Var': 8.013558},
 {'Var1': 'FR', 'Var2': 2018, 'Var3': 5783, 'Var4': 'I_S', 'Var5': 11.956326, 'Ind_Var': 4.105559},
 {'Var1': 'BE', 'Var2': 2015, 'Var3': 6719, 'Var4': 'OME', 'Var5': 42.888565, 'Ind_Var': 7.830077},
 {'Var1': 'DK', 'Var2': 2011, 'Var3': 3506, 'Var4': 'RPP', 'Var5': 70.094146, 'Ind_Var': 83.000000},
 {'Var1': 'AT', 'Var2': 2019, 'Var3': 5474, 'Var4': 'NMM', 'Var5': 270.082738, 'Ind_Var': 51.710526}
])

# extract the features and target
X_train, y_train = df.iloc[:3, :-1], df.iloc[:3, -1]
X_test, y_test = df.iloc[3:, :-1], df.iloc[3:, -1]

# one-hot encode the categorical features
cat_attribs = ['Var1', 'Var2', 'Var3', 'Var4']
full_pipeline = ColumnTransformer([('cat', OneHotEncoder(handle_unknown='ignore'), cat_attribs)], remainder='passthrough')

encoder = full_pipeline.fit(X_train)
X_train = encoder.transform(X_train)
X_test = encoder.transform(X_test)

# train the model
model = XGBRegressor(n_estimators=10, max_depth=20, verbosity=2)
model.fit(X_train, y_train)

# extract the training set predictions
model.predict(X_train)
# array([7.0887003, 3.7923286, 7.0887003], dtype=float32)

# extract the test set predictions
model.predict(X_test)
# array([7.0887003, 7.0887003], dtype=float32)