MetricsTrackerRollingWindow#

class langchain_experimental.rl_chain.metrics.MetricsTrackerRollingWindow(window_size: int, step: int)[source]#

指标跟踪器滚动窗口。

属性

score

方法

__init__(window_size, step)

on_decision()

on_feedback(value)

to_pandas()

Parameters:
  • window_size (int)

  • step (int)

__init__(window_size: int, step: int)[来源]#
Parameters:
  • window_size (int)

  • step (int)

on_decision() None[source]#
Return type:

on_feedback(value: float) None[source]#
Parameters:

(浮点数)

Return type:

to_pandas() pd.DataFrame[source]#
Return type:

pd.DataFrame