def predict(self, rows_new):
"""
:param rows_new: 待预测数据集
:return: 判别: 投票最高标签; 回归: 预测结果均值
"""
results = []
for r in rows_new:
sub_results = []
for t in self.trees:
predicted = dts.predict_single(t, r, out="value")
sub_results.append(predicted)
if self.target == "classification": # 判别: 投票
tmp_dict = {}
for i in sub_results:
tmp_dict[i] = tmp_dict.get(i, 0) + 1
k_tracker = None
v_tracker = 0.0
for k, v in tmp_dict.items():
if v > v_tracker:
k_tracker = k
v_tracker = v
results.append(k_tracker)
else: # 回归: 求均值
results.append(np.mean(sub_results))
return results
def predict(self, rows_new):
"""
将self.trees的每个预测结果累加, 得到最终预测值
:param rows_new: 待预测数据, 嵌套的list或tuple
:return: gbdt预测的y值
"""
result = []
for r in rows_new:
y_new = 0.0
# 预测结果为所有树的结果累加
for t in self.trees:
y_new += dts.predict_single(t, r)
result.append(y_new)
return result