Merge pull request #865 from buttogo/code_interpreter

add eda prompt

examples/ml_engineer_with_tools.py

@@ -0,0 +1,16 @@
+import asyncio
+
+from metagpt.roles.ci.ml_engineer import MLEngineer
+
+
+async def main(requirement: str, auto_run: bool = True, use_tools: bool = True):
+    role = MLEngineer(goal=requirement, auto_run=auto_run, use_tools=use_tools)
+    await role.run(requirement)
+
+
+if __name__ == "__main__":
+    data_path = "your_path_to_icr/icr-identify-age-related-conditions"  # 替换 'your_path_to_icr' 为实际数据存放的路径
+    train_path = f"{data_path}/your_train_data.csv"  # 替换 'your_train_data.csv' 为你的训练数据文件名
+    eval_path = f"{data_path}/your_eval_data.csv"  # 替换 'your_eval_data.csv' 为你的评估数据文件名
+    requirement = f"This is a medical dataset with over fifty anonymized health characteristics linked to three age-related conditions. Your goal is to predict whether a subject has or has not been diagnosed with one of these conditions.The target column is Class. Perform data analysis, data preprocessing, feature engineering, and modeling to predict the target. Report f1 score on the eval data. Train data path: {train_path}, eval data path:{eval_path}."
+    asyncio.run(main(requirement))

metagpt/prompts/tool_types.py

@@ -1,3 +1,10 @@
+# Prompt for using tools of "eda" type
+EDA_PROMPT = """
+The current task is about exploratory data analysis, please note the following:
+- Distinguish column types with `select_dtypes` for tailored analysis and visualization, such as correlation.
+- Remember to `import numpy as np` before using Numpy functions.
+"""
+
 # Prompt for using tools of "data_preprocess" type
 DATA_PREPROCESS_PROMPT = """
 The current task is about data preprocessing, please note the following:

metagpt/tools/tool_type.py

@@ -1,6 +1,7 @@
 from enum import Enum
 
 from metagpt.prompts.tool_types import (
+    EDA_PROMPT,
     DATA_PREPROCESS_PROMPT,
     FEATURE_ENGINEERING_PROMPT,
     IMAGE2WEBPAGE_PROMPT,
@@ -11,7 +12,11 @@ from metagpt.tools.tool_data_type import ToolTypeDef
 
 
 class ToolType(Enum):
-    EDA = ToolTypeDef(name="eda", desc="For performing exploratory data analysis")
+    EDA = ToolTypeDef(
+        name="eda",
+        desc="For performing exploratory data analysis",
+        usage_prompt=EDA_PROMPT,
+    )
     DATA_PREPROCESS = ToolTypeDef(
         name="data_preprocess",
         desc="Only for changing value inplace.",