AutoX
AutoX copied to clipboard
AutoX is an efficient automl tool, which is mainly aimed at data mining tasks with tabular data.
autoX能否针对块状和间歇性需求的时间序列进行预测?
@poteman
当前glove模型使用的是glove-python-binary包,对windows系统及mac系统安装较困难,可通过其他方式实现glove。 代码链接:[https://github.com/4paradigm/AutoX/blob/master/autox/autox_nlp/feature_engineer/nlp_feature.py](url)
当前Word2Vec和Glove模型无法处理测试数据中未见过的词,需要对测试数据重新进行词表构建,对整体效果影响较大。 代码链接:[https://github.com/4paradigm/AutoX/blob/master/autox/autox_nlp/feature_engineer/nlp_feature.py](url)
参考: https://github.com/4paradigm/AutoX/blob/master/autox/autox_recommend/recall_and_rank/recalls/itemcf_recall.py
当前使用fasttext进行特征提取的效率较慢,同等数据量下与BERT-tiny用时相当,可针对性优化。 代码链接:[https://github.com/4paradigm/AutoX/blob/master/autox/autox_nlp/feature_engineer/nlp_feature.py](url)
代码结构可以参考: https://github.com/4paradigm/AutoX/blob/master/autox/autox_recommend/recall_and_rank/feature_engineer/user_feature_engineer.py
代码结构可以参考: https://github.com/4paradigm/AutoX/blob/master/autox/autox_recommend/recall_and_rank/ranker/ranker.py
代码结构可以参考: https://github.com/4paradigm/AutoX/blob/master/autox/autox_recommend/recall_and_rank/recalls/history_recall.py
代码结构可以参考: https://github.com/4paradigm/AutoX/blob/master/autox/autox_recommend/recall_and_rank/recalls/history_recall.py