Python xgboost 模块，plot_importance() 实例源码

def fea_plot(xg_model, feature, label, type = 'weight', max_num_features = None):
    fig, AX = plt.subplots(nrows=1, ncols=2)
    xgb.plot_importance(xg_model, xlabel=type, importance_type='weight', ax=AX[0], max_num_features=max_num_features)

    fscore = xg_model.get_score(importance_type=type)
    fscore = sorted(fscore.items(), key=itemgetter(1), reverse=True) # sort scores
    fea_index = get_fea_index(fscore, max_num_features)
    feature = feature[:, fea_index]
    dimension = len(fea_index)
    X = range(1, dimension+1)
    Yp = np.mean(feature[np.where(label==1)[0]], axis=0)
    Yn = np.mean(feature[np.where(label!=1)[0]], axis=0)
    for i in range(0, dimension):
        param = np.fmax(Yp[i], Yn[i])
        Yp[i] /= param
        Yn[i] /= param
    p1 = AX[1].bar(X, +Yp, facecolor='#ff9999', edgecolor='white')
    p2 = AX[1].bar(X, -Yn, facecolor='#9999ff', edgecolor='white')
    AX[1].legend((p1,p2), ('Malware', 'Normal'))
    AX[1].set_title('Comparison of selected features by their means')
    AX[1].set_xlabel('Feature Index')
    AX[1].set_ylabel('Mean Value')
    AX[1].set_ylim(-1.1, 1.1)
    plt.xticks(X, fea_index+1, rotation=80)
    plt.suptitle('Feature Selection results')

def run_train_validation(self):
        x_train, y_train,x_validation,y_validation = self.get_train_validationset()
        dtrain = xgb.DMatrix(x_train, label= y_train,feature_names=x_train.columns)
        dvalidation = xgb.DMatrix(x_validation, label= y_validation,feature_names=x_validation.columns)
        self.set_xgb_parameters()

        evals=[(dtrain,'train'),(dvalidation,'eval')]
        model = xgb.train(self.xgb_params, dtrain, evals=evals, **self.xgb_learning_params)
        xgb.plot_importance(model)
        plt.show()

        print "features used:\n {}".format(self.get_used_features())

        return

def plot_importance(importance_type='weight'):
  """
  How the importance is calculated: either "weight", "gain", or "cover" 
    "weight" is the number of times a feature appears in a tree 
    "gain" is the average"gain"of splits which use the feature 
    "cover" is the average coverage of splits which use the feature
      where coverage is defined as the number of samples affected by the split
  """
  xgb.plot_importance(model, importance_type=importance_type,
      max_num_features=40,
      )

def plot_importance(self):
        ax = xgb.plot_importance(self.model)
        self.save_topn_features()
        return ax

def save_topn_features(self, fname="XGBRegressor_topn_features.txt", topn=-1):
        ax = xgb.plot_importance(self.model)
        yticklabels = ax.get_yticklabels()[::-1]
        if topn == -1:
            topn = len(yticklabels)
        else:
            topn = min(topn, len(yticklabels))
        with open(fname, "w") as f:
            for i in range(topn):
                f.write("%s\n"%yticklabels[i].get_text())

def plot_importance(self):
        ax = xgb.plot_importance(self.model)
        self.save_topn_features()
        return ax

def save_topn_features(self, fname="XGBClassifier_topn_features.txt", topn=10):
        ax = xgb.plot_importance(self.model)
        yticklabels = ax.get_yticklabels()[::-1]
        if topn == -1:
            topn = len(yticklabels)
        else:
            topn = min(topn, len(yticklabels))
        with open(fname, "w") as f:
            for i in range(topn):
                f.write("%s\n"%yticklabels[i].get_text())