gavindiaz/NexQuant
1
0
Fork 0
mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-07-28 16:07:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

help yuante on the final version of data code

Browse Source
This commit is contained in:
Xu Yang
2024-07-15 08:28:34 +00:00
parent 57ae5c93ea
commit 1ed2f655b9
19 changed files with 267 additions and 214 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rdagent/components/coder/factor_coder/CoSTEER/evaluators.py
+28 -3
View File
@@ -84,7 +84,7 @@ class FactorCodeEvaluator(FactorEvaluator):
gt_implementation: Implementation = None,
**kwargs,
):
factor_information = target_task.get_factor_information()
factor_information = target_task.get_task_information()
code = implementation.code
system_prompt = (
@@ -181,6 +181,28 @@ class FactorOutputFormatEvaluator(FactorEvaluator):
)
class FactorDatetimeDailyEvaluator(FactorEvaluator):
def evaluate(
self,
implementation: Implementation,
gt_implementation: Implementation,
) -> Tuple[str | object]:
_, gen_df = self._get_df(gt_implementation, implementation)
if gen_df is None:
return "The source dataframe is None. Skip the evaluation of the datetime format.", False
if "datetime" not in gen_df.index.names:
return "The source dataframe does not have a datetime index. Please check the implementation.", False
time_diff = gen_df.index.get_level_values("datetime").to_series().diff().dropna().unique()
if pd.Timedelta(minutes=1) in time_diff:
return (
"The generated dataframe is not daily. The implementation is definitely wrong. Please check the implementation.",
False,
)
return "The generated dataframe is daily.", True
class FactorRowCountEvaluator(FactorEvaluator):
def evaluate(
self,
@@ -314,6 +336,9 @@ class FactorValueEvaluator(FactorEvaluator):
feedback_str, _ = FactorOutputFormatEvaluator(self.scen).evaluate(implementation, gt_implementation)
conclusions.append(feedback_str)
feedback_str, _ = FactorDatetimeDailyEvaluator(self.scen).evaluate(implementation, gt_implementation)
conclusions.append(feedback_str)
# Check if both dataframe have the same rows count
if gt_implementation is not None:
feedback_str, _ = FactorRowCountEvaluator(self.scen).evaluate(implementation, gt_implementation)
@@ -373,7 +398,7 @@ class FactorFinalDecisionEvaluator(Evaluator):
evaluate_prompts["evaluator_final_decision_v1_user"],
)
.render(
factor_information=target_task.get_factor_information(),
factor_information=target_task.get_task_information(),
execution_feedback=execution_feedback_to_render,
code_feedback=code_feedback,
factor_value_feedback=(
@@ -475,7 +500,7 @@ class FactorEvaluatorForCoder(FactorEvaluator):
if implementation is None:
return None
target_task_information = target_task.get_factor_information()
target_task_information = target_task.get_task_information()
if (
queried_knowledge is not None
and target_task_information in queried_knowledge.success_task_to_knowledge_dict
rdagent/components/coder/factor_coder/CoSTEER/evolving_strategy.py
+3 -3
View File
@@ -59,7 +59,7 @@ class MultiProcessEvolvingStrategy(EvolvingStrategy):
# 1.找出需要evolve的factor
to_be_finished_task_index = []
for index, target_factor_task in enumerate(new_evo.sub_tasks):
target_factor_task_desc = target_factor_task.get_factor_information()
target_factor_task_desc = target_factor_task.get_task_information()
if target_factor_task_desc in queried_knowledge.success_task_to_knowledge_dict:
new_evo.sub_implementations[index] = queried_knowledge.success_task_to_knowledge_dict[
target_factor_task_desc
@@ -119,7 +119,7 @@ class FactorEvolvingStrategy(MultiProcessEvolvingStrategy):
target_task: FactorTask,
queried_knowledge: FactorQueriedKnowledgeV1 = None,
) -> Implementation:
factor_information_str = target_task.get_factor_information()
factor_information_str = target_task.get_task_information()
if queried_knowledge is not None and factor_information_str in queried_knowledge.success_task_to_knowledge_dict:
return queried_knowledge.success_task_to_knowledge_dict[factor_information_str].implementation
@@ -208,7 +208,7 @@ class FactorEvolvingStrategyWithGraph(MultiProcessEvolvingStrategy):
) -> Implementation:
error_summary = FACTOR_IMPLEMENT_SETTINGS.v2_error_summary
# 1. 提取因子的背景信息
target_factor_task_information = target_task.get_factor_information()
target_factor_task_information = target_task.get_task_information()
# 2. 检查该因子是否需要继续做（是否已经作对，是否做错太多）
if (
rdagent/components/coder/factor_coder/CoSTEER/knowledge_management.py
+6 -6
View File
@@ -114,7 +114,7 @@ class FactorRAGStrategyV1(RAGStrategy):
feedback = evo_step.feedback
for task_index in range(len(implementations.sub_tasks)):
target_task = implementations.sub_tasks[task_index]
target_task_information = target_task.get_factor_information()
target_task_information = target_task.get_task_information()
implementation = implementations.sub_implementations[task_index]
single_feedback = feedback[task_index]
if single_feedback is None:
@@ -147,7 +147,7 @@ class FactorRAGStrategyV1(RAGStrategy):
queried_knowledge = FactorQueriedKnowledgeV1()
for target_factor_task in evo.sub_tasks:
target_factor_task_information = target_factor_task.get_factor_information()
target_factor_task_information = target_factor_task.get_task_information()
if target_factor_task_information in self.knowledgebase.success_task_info_set:
queried_knowledge.success_task_to_knowledge_dict[target_factor_task_information] = (
self.knowledgebase.implementation_trace[target_factor_task_information][-1]
@@ -233,7 +233,7 @@ class FactorGraphRAGStrategy(RAGStrategy):
for task_index in range(len(implementations.sub_tasks)):
single_feedback = feedback[task_index]
target_task = implementations.sub_tasks[task_index]
target_task_information = target_task.get_factor_information()
target_task_information = target_task.get_task_information()
implementation = implementations.sub_implementations[task_index]
single_feedback = feedback[task_index]
if single_feedback is None:
@@ -395,7 +395,7 @@ class FactorGraphRAGStrategy(RAGStrategy):
fail_task_trial_limit = FACTOR_IMPLEMENT_SETTINGS.fail_task_trial_limit
for target_factor_task in evo.sub_tasks:
target_factor_task_information = target_factor_task.get_factor_information()
target_factor_task_information = target_factor_task.get_task_information()
if (
target_factor_task_information not in self.knowledgebase.success_task_to_knowledge_dict
and target_factor_task_information in self.knowledgebase.working_trace_knowledge
@@ -442,7 +442,7 @@ class FactorGraphRAGStrategy(RAGStrategy):
) -> QueriedKnowledge | None:
# queried_component_knowledge = FactorQueriedGraphComponentKnowledge()
for target_factor_task in evo.sub_tasks:
target_factor_task_information = target_factor_task.get_factor_information()
target_factor_task_information = target_factor_task.get_task_information()
if (
target_factor_task_information in self.knowledgebase.success_task_to_knowledge_dict
or target_factor_task_information in factor_implementation_queried_graph_knowledge.failed_task_info_set
@@ -582,7 +582,7 @@ class FactorGraphRAGStrategy(RAGStrategy):
) -> QueriedKnowledge | None:
# queried_error_knowledge = FactorQueriedGraphErrorKnowledge()
for task_index, target_factor_task in enumerate(evo.sub_tasks):
target_factor_task_information = target_factor_task.get_factor_information()
target_factor_task_information = target_factor_task.get_task_information()
factor_implementation_queried_graph_knowledge.error_with_success_task[target_factor_task_information] = {}
if (
target_factor_task_information in self.knowledgebase.success_task_to_knowledge_dict
rdagent/components/coder/factor_coder/CoSTEER/scheduler.py
+1 -1
View File
@@ -39,7 +39,7 @@ def LLMSelect(
tasks = []
for i in to_be_finished_task_index:
# find corresponding former trace for each task
target_factor_task_information = evo.sub_tasks[i].get_factor_information()
target_factor_task_information = evo.sub_tasks[i].get_task_information()
if target_factor_task_information in former_trace:
tasks.append((i, evo.sub_tasks[i], former_trace[target_factor_task_information]))
rdagent/components/coder/factor_coder/factor.py
+1 -1
View File
@@ -37,7 +37,7 @@ class FactorTask(Task):
self.variables = variables
self.factor_resources = resource
def get_factor_information(self):
def get_task_information(self):
return f"""factor_name: {self.factor_name}
factor_description: {self.factor_description}
factor_formulation: {self.factor_formulation}
rdagent/components/coder/factor_coder/prompts.yaml
+4 -4
View File
@@ -68,7 +68,7 @@ evolving_strategy_factor_implementation_v1_user: |-
--------------Correct code to similar factors:---------------
{% for similar_successful_knowledge in queried_similar_successful_knowledge %}
=====Factor {{loop.index}}:=====
{{ similar_successful_knowledge.target_task.get_factor_information() }}
{{ similar_successful_knowledge.target_task.get_task_information() }}
=====Code:=====
{{ similar_successful_knowledge.implementation.code }}
{% endfor %}
@@ -94,7 +94,7 @@ evolving_strategy_factor_implementation_v2_user: |-
When doing other tasks, you met some similar errors but you finally solve them. Here are some examples:
{% for error_content, similar_error_knowledge in queried_similar_error_knowledge %}
--------------Factor information to similar error ({{error_content}}):---------------
{{ similar_error_knowledge[0].target_task.get_factor_information() }}
{{ similar_error_knowledge[0].target_task.get_task_information() }}
=====Code with similar error ({{error_content}}):=====
{{ similar_error_knowledge[0].implementation.code }}
=====Success code to former code with similar error ({{error_content}}):=====
@@ -111,7 +111,7 @@ evolving_strategy_factor_implementation_v2_user: |-
--------------Correct code to similar factors:---------------
{% for similar_component_knowledge in queried_similar_component_knowledge %}
=====Factor {{loop.index}}:=====
{{ similar_component_knowledge.target_task.get_factor_information() }}
{{ similar_component_knowledge.target_task.get_task_information() }}
=====Code:=====
{{ similar_component_knowledge.implementation.code }}
{% endfor %}
@@ -137,7 +137,7 @@ evolving_strategy_error_summary_v2_user: |-
{% if queried_similar_error_knowledge|length != 0 %}
{% for error_content, similar_error_knowledge in queried_similar_error_knowledge %}
--------------Factor information to similar error ({{error_content}}):---------------
{{ similar_error_knowledge[0].target_task.get_factor_information() }}
{{ similar_error_knowledge[0].target_task.get_task_information() }}
=====Code with similar error ({{error_content}}):=====
{{ similar_error_knowledge[0].implementation.code }}
=====Success code to former code with similar error ({{error_content}}):=====