Merge remote-tracking branch 'origin/feat/data_visualization_hackathon' into feat/data_visualization_hack_czx

app/agent/data_analysis.py

@@ -4,11 +4,9 @@ from app.agent.toolcall import ToolCallAgent
 from app.config import config
 from app.prompt.visualization import NEXT_STEP_PROMPT, SYSTEM_PROMPT
 from app.tool import Terminate, ToolCollection
+from app.tool.chart_visualization.chart_prepare import VisualizationPrepare
 from app.tool.chart_visualization.chart_visualization import ChartVisualization
 from app.tool.chart_visualization.normal_python_execute import NormalPythonExecute
-from app.tool.chart_visualization.chart_prepare import (
-    VisualizationPrepare,
-)
 
 
 class DataAnalysis(ToolCallAgent):
@@ -34,8 +32,8 @@ class DataAnalysis(ToolCallAgent):
     available_tools: ToolCollection = Field(
         default_factory=lambda: ToolCollection(
             NormalPythonExecute(),
-            VisualizationPrepare(),
-            ChartVisualization(),
+            # VisualizationPrepare(),
+            # ChartVisualization(),
             Terminate(),
         )
     )

app/tool/chart_visualization/normal_python_execute.py

@@ -6,27 +6,19 @@ class NormalPythonExecute(PythonExecute):
 
     name: str = "common_python_execute"
     description: str = (
-        """Executes Python code strings to tasks such as data process and data report"""
+        "Execute Python code for in-depth data analysis without direct visualization. "
+        "The code should generate a comprehensive text-based report containing dataset overview, "
+        "column details, basic statistics, derived metrics, day-of-week comparisons, outliers, and key insights. "
+        "Use print() for all outputs so the analysis (including sections like 'Dataset Overview' or 'Preprocessing Results') "
+        "is clearly visible, and save any final report or processed files to config.workspace. "
+        "Include try-except blocks for error handling, and provide the code as a single string with '\\n' for line breaks."
     )
     parameters: dict = {
         "type": "object",
         "properties": {
             "code": {
                 "type": "string",
-                "description": """The Python code to execute. Note:
-1. Only outputs from print() are visible; function return values are not captured. Use print() statements to display results
-2. Do data process (cleaning / transform) saved in *.csv
-3. Generate a data analysis report in html""",
-            },
-            "code_type": {
-                "description": "code type",
-                "type": "string",
-                "default": "process",
-                "enum": ["process", "report", "others"],
             },
         },
         "required": ["code"],
     }
-
-    async def execute(self, code: str, code_type: str | None = None, timeout=5):
-        return await super().execute(code, timeout)

app/tool/chart_visualization/test/amazon_fashion_analysis.py

@@ -0,0 +1,48 @@
+import asyncio
+import time
+
+from app.agent.data_analysis import DataAnalysis
+from app.agent.manus import Manus
+from app.flow.base import FlowType
+from app.flow.flow_factory import FlowFactory
+from app.logger import logger
+
+
+async def run_flow():
+    agents = {
+        # "manus": Manus(),
+        "visactor": DataAnalysis(),
+    }
+
+    try:
+        prompt = """Here's last month's sales data from my Amazon store in './data/amazon_sales_jan2025.xlsx'. Could you analyze it？"""
+
+        flow = FlowFactory.create_flow(
+            flow_type=FlowType.PLANNING,
+            agents=agents,
+        )
+        logger.warning("Processing your request...")
+
+        try:
+            start_time = time.time()
+            result = await asyncio.wait_for(
+                flow.execute(prompt),
+                timeout=3600,  # 60 minute timeout for the entire execution
+            )
+            elapsed_time = time.time() - start_time
+            logger.info(f"Request processed in {elapsed_time:.2f} seconds")
+            logger.info(result)
+        except asyncio.TimeoutError:
+            logger.error("Request processing timed out after 1 hour")
+            logger.info(
+                "Operation terminated due to timeout. Please try a simpler request."
+            )
+
+    except KeyboardInterrupt:
+        logger.info("Operation cancelled by user.")
+    except Exception as e:
+        logger.error(f"Error: {str(e)}")
+
+
+if __name__ == "__main__":
+    asyncio.run(run_flow())