首页 > 解决方案 > 如何在特征重要性图中显示原始特征名称?

问题描述

我创建了 XGBoost 模型如下:

y = XY.DELAY_MIN
X = standardized_df

train_X, test_X, train_y, test_y = train_test_split(X.as_matrix(), y.as_matrix(), test_size=0.25)

my_imputer = preprocessing.Imputer()
train_X = my_imputer.fit_transform(train_X)
test_X = my_imputer.transform(test_X)

xgb_model = XGBRegressor()

# Add silent=True to avoid printing out updates with each cycle
xgb_model = XGBRegressor(n_estimators=1000, learning_rate=0.05)
xgb_model.fit(train_X, train_y, early_stopping_rounds=5, 
             eval_set=[(test_X, test_y)], verbose=False)

创建特征重要性图时,特征名称显示为“f1”、“f2”等。如何显示原始特征名称?

fig, ax = plt.subplots(figsize=(12,18))
xgb.plot_importance(xgb_model, max_num_features=30, height=0.8, ax=ax)
plt.show()

标签: pythonpandasxgboost

解决方案


问题是Imputer不返回 apd.DataFrame作为 的输出transform(),因此,当您这样做时,您的列名会丢失

train_X = my_imputer.fit_transform(train_X)
test_X = my_imputer.transform(test_X)

简单的解决方案,将 imputer 输出包装到数据框中,例如:

train_X = pd.DataFrame(my_imputer.fit_transform(train_X), columns=train_X.columns)
test_X  = pd.DataFrame(my_imputer.transform(test_X), columns=test_X.columns)

推荐阅读