def run(self, app=None, data_key=None, data_path=None, config_info=None):
"""
:param data_key : If no dataframe, get model from this model_key
:param data_path: If no dataframe and no data_key, get model from this model_path
:param config_info: 配置文件路径
:return: 结果返回到redis
"""
if isinstance(config_info, bytes):
config_info = json.loads(config_info.decode("utf-8"))
# from css.ai.algo.utils.public_methods import PublicMethods
# 获取上一个组件的输出结果，不动
data = PublicMethods().get_data(app=app, data_path=data_path, data_key=data_key)
model_path = config_info.get("model_path") # 用来保存训练好的模型
# 获取自定义参数，自行编写
inputCols = config_info.get("inputCols")
outputCol = config_info.get("outputCol")
custom_1 = config_info.get("custom_1")
custom_2 = config_info.get("custom_2")
# 生成新的参数及初始化自定义Estimator，自行编写
config_custom = {}
config_custom["inputCols"] = inputCols
config_custom["outputCol"] = outputCol
config_custom["custom_1"] = eval(custom_1) # 传递过来值类型都是str,所以使用eval()方法取值
config_custom["custom_2"] = eval(custom_2)
custom_stage = [("CustomEstimator", config_custom)]
# 不动
data_new, model, stage_list = PublicMethods().pipeline_fit_transform(custom_stage, data)
stage_model = PipelineModel(stage_list)
stage_model.write().overwrite().save(model_path)
ret = PublicMethods.wrapper_cols_keys_cache_data(app, data_new, stage_key=model.uid, stage_list=stage_list, class_name=self.name, postfixes=None)
ret.append(["trained_model", 1, model_path])
return ret
def save_pipeline(pipeline: PipelineModel, filepath:str) -> None:
'''
Serialize the fitted pipeline
:param pipeline:
:param filepath:
:return: None
'''
pipeline.write().overwrite().save(path=filepath)
