人工智能 特征筛选 求取特征重要程度

例子：鸢尾花数据集，使用Xgboost输出特征重要程度

import xgboost as xgb
from sklearn import datasets
iris = datasets.load_iris()
y = iris['target']
X = iris['data']
xgb_model = xgb.XGBClassifier().fit(X,y)

temp = pd.DataFrame()
temp['feature_names'] = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width']
temp['feature_importances'] = xgb_model.feature_importances_
temp = temp.sort_values('feature_importances',ascending = False)
temp

分组交叉特征筛选

• 当前关注训练后从模型中获取特征重要程度

lst = ['td_score', 'jxl_score', 'mj_score', 'rh_score', 'zzc_score', 'zcx_score', 'person_info', 'finance_info', 'credit_info', 'act_info']

#定义lgb函数
def LGB_test(train_x,train_y,test_x,test_y):
    from multiprocessing import cpu_count
    clf = lgb.LGBMClassifier(
        boosting_type='gbdt', num_leaves=31, reg_alpha=0.0, reg_lambda=1,
        max_depth=2, n_estimators=800,max_features = 140, objective='binary',
        subsample=0.7, colsample_bytree=0.7, subsample_freq=1,
        learning_rate=0.05, min_child_weight=50,random_state=None,n_jobs=cpu_count()-1,
        num_iterations = 800 #迭代次数
    )
    clf.fit(train_x, train_y,eval_set=[(train_x, train_y),(test_x,test_y)],eval_metric='auc',early_stopping_rounds=100)
    print(clf.n_features_)

    return clf,clf.best_score_[ 'valid_1']['auc']

feature_lst = []
ks_train_lst = []
ks_test_lst = []
for rk in set(df_train['rank']):
    # rank为分箱后的特征列，值包含0，1，2，3，4
    # 训练集已分5组，4组训练，一组测试。

    #定义模型训练集与测试集
    ttest = df_train[df_train['rank'] ==  rk]
    ttrain = df_train[df_train['rank'] !=  rk]

    train = ttrain[lst]
    train_y = ttrain.bad_ind

    test = ttest[lst]
    test_y = ttest.bad_ind

    model,auc = LGB_test(train,train_y,test,test_y)


    #模型贡献度放在feture中
    feature = pd.DataFrame(
                {'name' : model.booster_.feature_name(),
                'importance' : model.feature_importances_
              }).set_index('name')
    feature_lst.append(feature)

    #计算训练集、测试集、验证集上的KS和AUC

    y_pred_train_lgb = model.predict_proba(train)[:, 1]
    y_pred_test_lgb = model.predict_proba(test)[:, 1]


    train_fpr_lgb, train_tpr_lgb, _ = roc_curve(train_y, y_pred_train_lgb)
    test_fpr_lgb, test_tpr_lgb, _ = roc_curve(test_y, y_pred_test_lgb)


    train_ks = abs(train_fpr_lgb - train_tpr_lgb).max()
    test_ks = abs(test_fpr_lgb - test_tpr_lgb).max()


    train_auc = metrics.auc(train_fpr_lgb, train_tpr_lgb)
    test_auc = metrics.auc(test_fpr_lgb, test_tpr_lgb)

    ks_train_lst.append(train_ks)
    ks_test_lst.append(test_ks)

train_ks = np.mean(ks_train_lst)
test_ks = np.mean(ks_test_lst)


print('train_ks: ',train_ks)
print('test_ks: ',test_ks)

分组后进行5轮计算，得到5组特征重要程度

• 将5组重要程度拼接后排序

feature_importance = pd.concat(feature_lst,axis = 1).mean(1).sort_values(ascending = False)
feature_importance

输出内容

• 取出特征

feature_importance[(feature_importance>20)].index.tolist()

输出内容

心得：记录一下使用Xgboost输出特征重要程度，分组交叉筛选可以使数据更加可靠