本文整理汇总了Python中xgboost.XGBClassifier.booster方法的典型用法代码示例。如果您正苦于以下问题:Python XGBClassifier.booster方法的具体用法?Python XGBClassifier.booster怎么用?Python XGBClassifier.booster使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类xgboost.XGBClassifier
的用法示例。
在下文中一共展示了XGBClassifier.booster方法的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: get_xgb_feature_importance_plot
# 需要导入模块: from xgboost import XGBClassifier [as 别名]
# 或者: from xgboost.XGBClassifier import booster [as 别名]
def get_xgb_feature_importance_plot(best_param_, experiment_,
png_folder,
png_fname,
score_threshold=0.8):
# 1.
train_X, train_y = experiment_.get_train_data()
clf = XGBClassifier()
try:
del best_param_['model_type']
except:
pass
clf.set_params(**best_param_)
clf.fit(train_X, train_y)
index2feature = clf.booster().get_fscore()
fis = pd.DataFrame({'name':index2feature.keys(),
'score':index2feature.values()})
fis = fis.sort('score', ascending=False)
if len(fis.index) > 20:
score_threshold = fis['score'][fis['score'] > 0.0].quantile(score_threshold)
#where_str = 'score > %f & score > %f' % (score_threshold, 0.0)
where_str = 'score >= %f' % (score_threshold)
fis = fis.query(where_str)
# 2. plot
#gs = GridSpec(2,2)
#ax1 = plt.subplot(gs[:,0])
#ax2 = plt.subplot(gs[0,1])
#ax3 = plt.subplot(gs[1,1])
# 3.1 feature importance
sns.barplot(x = 'score', y = 'name',
data = fis,
#ax=ax1,
color="blue")
#plt.title("Feature_Importance", fontsize=10)
plt.ylabel("Feature", fontsize=10)
plt.xlabel("Feature_Importance : f-Score", fontsize=10)
"""
# 3.2 PDF
confidence_score = clf.oob_decision_function_[:,1]
sns.distplot(confidence_score, kde=False, rug=False, ax=ax2)
ax2.set_title("PDF")
# 3.3 CDF
num_bins = min(best_param_.get('n_estimators',1), 100)
counts, bin_edges = np.histogram(confidence_score, bins=num_bins, normed=True)
cdf = np.cumsum(counts)
ax3.plot(bin_edges[1:], cdf / cdf.max())
ax3.set_title("CDF")
ax3.set_xlabel("Oob_Decision_Function:Confidence_Score", fontsize=10)
"""
png_fname = os.path.join(Config.get_string('data.path'), 'graph', png_fname)
plt.tight_layout()
plt.savefig(png_fname)#, bbox_inches='tight', pad_inches=1)
plt.close()
return True
示例2: XGBClassifier
# 需要导入模块: from xgboost import XGBClassifier [as 别名]
# 或者: from xgboost.XGBClassifier import booster [as 别名]
df_all = pd.concat([df_all, bow], axis=1)
df_all['num_zero'] = num_zero
df_all = pipeline.fit(df_all).transform(df_all)
X_train = df_all.iloc[:df_train.shape[0], :]
X_test = df_all.iloc[df_train.shape[0]:, :]
y_train = df_target
ID_test = df_id
# best params so far using column/row subsampling, even longer training
learning_rate = 0.01
n_estimators = 800
max_depth = 6
subsample = 0.9
colsample_bytree = 0.85
min_child_weight = 1 # default
xgb = XGBClassifier(seed=0, learning_rate=learning_rate, n_estimators=n_estimators,
min_child_weight=min_child_weight, max_depth=max_depth,
colsample_bytree=colsample_bytree, subsample=subsample)
xgb = xgb.fit(X_train, y_train, eval_set=[(X_train, y_train)], eval_metric='auc')
importances = xgb.booster().get_fscore()
df_importance = pd.DataFrame(zip(importances.keys(), importances.values()), columns=['feature', 'importance'])
print df_importance.sort_values('importance', ascending=False).reset_index(drop=True)
y_pred = xgb.predict_proba(X_test)
submission = pd.DataFrame({'ID': ID_test, 'TARGET': y_pred[:, 1]})
submission.to_csv(filename, index=False)
print 'Wrote %s' % filename