Spaces:

cronjob-python
/

backend

Running

App Files Files Community

Soumik555 commited on Jul 14, 2025

Commit

4355ae7

1 Parent(s): 8733796

added csv-agent-default in next.js

Browse files

Files changed (5) hide show

charts/chart_67061795-658f-4411-a078-74ebe53ca1da.html +7 -0
data/test_output.csv +4 -0
data/test_output.xlsx +0 -0
main.py +24 -7
python_code_interpreter_service.py +117 -7

charts/chart_67061795-658f-4411-a078-74ebe53ca1da.html ADDED Viewed

	@@ -0,0 +1,7 @@

+<html>
+<head><meta charset="utf-8" /></head>
+<body>
+    <div>                        <script type="text/javascript">window.PlotlyConfig = {MathJaxConfig: 'local'};</script>
+        <script charset="utf-8" src="https://cdn.plot.ly/plotly-2.35.2.min.js"></script>                <div id="f21b13f1-7d59-4175-b117-76e29607bd2c" class="plotly-graph-div" style="height:100%; width:100%;"></div>            <script type="text/javascript">                                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById("f21b13f1-7d59-4175-b117-76e29607bd2c")) {                    Plotly.newPlot(                        "f21b13f1-7d59-4175-b117-76e29607bd2c",                        [{"alignmentgroup":"True","hovertemplate":"x=%{x}\u003cbr\u003ey=%{y}\u003cextra\u003e\u003c\u002fextra\u003e","legendgroup":"","marker":{"color":"#636efa","pattern":{"shape":""}},"name":"","offsetgroup":"","orientation":"v","showlegend":false,"textposition":"auto","x":["A","B","C"],"xaxis":"x","y":[1,3,2],"yaxis":"y","type":"bar"}],                        {"template":{"data":{"histogram2dcontour":[{"type":"histogram2dcontour","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"choropleth":[{"type":"choropleth","colorbar":{"outlinewidth":0,"ticks":""}}],"histogram2d":[{"type":"histogram2d","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"heatmap":[{"type":"heatmap","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"heatmapgl":[{"type":"heatmapgl","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"contourcarpet":[{"type":"contourcarpet","colorbar":{"outlinewidth":0,"ticks":""}}],"contour":[{"type":"contour","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"surface":[{"type":"surface","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"mesh3d":[{"type":"mesh3d","colorbar":{"outlinewidth":0,"ticks":""}}],"scatter":[{"fillpattern":{"fillmode":"overlay","size":10,"solidity":0.2},"type":"scatter"}],"parcoords":[{"type":"parcoords","line":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterpolargl":[{"type":"scatterpolargl","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"bar":[{"error_x":{"color":"#2a3f5f"},"error_y":{"color":"#2a3f5f"},"marker":{"line":{"color":"#E5ECF6","width":0.5},"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"bar"}],"scattergeo":[{"type":"scattergeo","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterpolar":[{"type":"scatterpolar","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"histogram":[{"marker":{"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"histogram"}],"scattergl":[{"type":"scattergl","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatter3d":[{"type":"scatter3d","line":{"colorbar":{"outlinewidth":0,"ticks":""}},"marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattermapbox":[{"type":"scattermapbox","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterternary":[{"type":"scatterternary","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattercarpet":[{"type":"scattercarpet","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"carpet":[{"aaxis":{"endlinecolor":"#2a3f5f","gridcolor":"white","linecolor":"white","minorgridcolor":"white","startlinecolor":"#2a3f5f"},"baxis":{"endlinecolor":"#2a3f5f","gridcolor":"white","linecolor":"white","minorgridcolor":"white","startlinecolor":"#2a3f5f"},"type":"carpet"}],"table":[{"cells":{"fill":{"color":"#EBF0F8"},"line":{"color":"white"}},"header":{"fill":{"color":"#C8D4E3"},"line":{"color":"white"}},"type":"table"}],"barpolar":[{"marker":{"line":{"color":"#E5ECF6","width":0.5},"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"barpolar"}],"pie":[{"automargin":true,"type":"pie"}]},"layout":{"autotypenumbers":"strict","colorway":["#636efa","#EF553B","#00cc96","#ab63fa","#FFA15A","#19d3f3","#FF6692","#B6E880","#FF97FF","#FECB52"],"font":{"color":"#2a3f5f"},"hovermode":"closest","hoverlabel":{"align":"left"},"paper_bgcolor":"white","plot_bgcolor":"#E5ECF6","polar":{"bgcolor":"#E5ECF6","angularaxis":{"gridcolor":"white","linecolor":"white","ticks":""},"radialaxis":{"gridcolor":"white","linecolor":"white","ticks":""}},"ternary":{"bgcolor":"#E5ECF6","aaxis":{"gridcolor":"white","linecolor":"white","ticks":""},"baxis":{"gridcolor":"white","linecolor":"white","ticks":""},"caxis":{"gridcolor":"white","linecolor":"white","ticks":""}},"coloraxis":{"colorbar":{"outlinewidth":0,"ticks":""}},"colorscale":{"sequential":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]],"sequentialminus":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]],"diverging":[[0,"#8e0152"],[0.1,"#c51b7d"],[0.2,"#de77ae"],[0.3,"#f1b6da"],[0.4,"#fde0ef"],[0.5,"#f7f7f7"],[0.6,"#e6f5d0"],[0.7,"#b8e186"],[0.8,"#7fbc41"],[0.9,"#4d9221"],[1,"#276419"]]},"xaxis":{"gridcolor":"white","linecolor":"white","ticks":"","title":{"standoff":15},"zerolinecolor":"white","automargin":true,"zerolinewidth":2},"yaxis":{"gridcolor":"white","linecolor":"white","ticks":"","title":{"standoff":15},"zerolinecolor":"white","automargin":true,"zerolinewidth":2},"scene":{"xaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2},"yaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2},"zaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2}},"shapedefaults":{"line":{"color":"#2a3f5f"}},"annotationdefaults":{"arrowcolor":"#2a3f5f","arrowhead":0,"arrowwidth":1},"geo":{"bgcolor":"white","landcolor":"#E5ECF6","subunitcolor":"white","showland":true,"showlakes":true,"lakecolor":"white"},"title":{"x":0.05},"mapbox":{"style":"light"}}},"xaxis":{"anchor":"y","domain":[0.0,1.0],"title":{"text":"x"}},"yaxis":{"anchor":"x","domain":[0.0,1.0],"title":{"text":"y"}},"legend":{"tracegroupgap":0},"title":{"text":"Plotly Test Plot"},"barmode":"relative"},                        {"responsive": true}                    )                };                            </script>        </div>
+</body>
+</html>

data/test_output.csv ADDED Viewed

	@@ -0,0 +1,4 @@

+Name,Age,Score
+Alice,25,85
+Bob,30,92
+Charlie,35,88

data/test_output.xlsx ADDED Viewed

Binary file (5.01 kB). View file

main.py CHANGED Viewed

@@ -20,6 +20,7 @@ from fastapi.concurrency import run_in_threadpool
 from fastapi import Depends, HTTPException, status
 from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
 import logging
 load_dotenv()
@@ -81,19 +82,21 @@ async def verify_token(credentials: HTTPAuthorizationCredentials = Depends(secur
         )
     return True
 @app.post("/python/execute")
 async def execute_code(
     code_request: dict,
     token_valid: bool = Depends(verify_token)
 ) -> Dict[str, Any]:
     """
-    Execute Python code and return the results
     Args:
         code_request: Dictionary containing 'code' key with the Python code to execute
     Returns:
-        dict: Dictionary containing execution results with all plots, output, variables, and any errors
     """
     if not token_valid:
         raise HTTPException(status_code=401, detail="Not authenticated")
@@ -118,13 +121,14 @@ async def execute_code(
         response_content = {
             "success": result['error'] is None,
             "output": result['output'],
-            # "variables": result['variables'],
             "plots": [],
-            "html_charts": result.get('html_charts', [])
         }
         # Add all plots if they exist
-        if result['plots']:
             response_content["plots"] = [
                 {
                     "image": plot_data,
@@ -134,13 +138,27 @@ async def execute_code(
                 for index, plot_data in enumerate(result['plots'])
             ]
         # Add error information if exists
-        if result['error']:
             response_content["error"] = result['error']
         return response_content
     except Exception as e:
         raise HTTPException(
             status_code=500,
             detail={
@@ -148,7 +166,6 @@ async def execute_code(
                 "traceback": traceback.format_exc()
             }
         )

 from fastapi import Depends, HTTPException, status
 from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
 import logging
+import base64
 load_dotenv()
         )
     return True
 @app.post("/python/execute")
 async def execute_code(
     code_request: dict,
     token_valid: bool = Depends(verify_token)
 ) -> Dict[str, Any]:
     """
+    Execute Python code and return the results including generated files
     Args:
         code_request: Dictionary containing 'code' key with the Python code to execute
     Returns:
+        dict: Dictionary containing execution results with all plots, output, variables,
+              generated files, and any errors
     """
     if not token_valid:
         raise HTTPException(status_code=401, detail="Not authenticated")
         response_content = {
             "success": result['error'] is None,
             "output": result['output'],
+            # "variables": result.get('variables', {}),
             "plots": [],
+            "html_charts": result.get('html_charts', []),
+            "generated_files": []
         }
         # Add all plots if they exist
+        if result.get('plots'):
             response_content["plots"] = [
                 {
                     "image": plot_data,
                 for index, plot_data in enumerate(result['plots'])
             ]
+        # Add generated files if they exist
+        if result.get('generated_files'):
+            response_content["generated_files"] = [
+                {
+                    "filename": file['filename'],
+                    "filetype": file['filetype'],
+                    "content": file['content'],
+                    "size": len(base64.b64decode(file['content']))
+                }
+                for file in result['generated_files']
+            ]
         # Add error information if exists
+        if result.get('error'):
             response_content["error"] = result['error']
         return response_content
     except Exception as e:
+        logger.error(f"Error executing code: {str(e)}")
+        logger.error(traceback.format_exc())
         raise HTTPException(
             status_code=500,
             detail={
                 "traceback": traceback.format_exc()
             }
         )

python_code_interpreter_service.py CHANGED Viewed

@@ -19,7 +19,7 @@ import sklearn
 import pytz
 from dateutil import parser
 import json
-from typing import Any, Dict
 import traceback
 import warnings
 import plotly.express as px
@@ -36,7 +36,7 @@ def execute_python_code(code: str, df: pd.DataFrame = None) -> Dict[str, Any]:
         df (pd.DataFrame): Optional DataFrame to make available in the execution context
     Returns:
-        dict: Dictionary containing execution results, variables, and any generated plots
     """
     # Create directories if they don't exist
     charts_dir = Path("charts")
@@ -51,6 +51,7 @@ def execute_python_code(code: str, df: pd.DataFrame = None) -> Dict[str, Any]:
     plot_base64 = []
     variables = {}
     html_charts = []
     # Monkey patch plt.show() to save figures
     original_show = plt.show
@@ -113,6 +114,7 @@ def execute_python_code(code: str, df: pd.DataFrame = None) -> Dict[str, Any]:
             'sys': sys,
             'warnings': warnings,
             'json': json,
             # File paths
             'DATA_DIR': data_dir,
@@ -154,15 +156,26 @@ def execute_python_code(code: str, df: pd.DataFrame = None) -> Dict[str, Any]:
             # First execute to get variables
             exec(code, exec_globals)
             # Capture all variables that were created
             for name, value in exec_globals.items():
                 if not name.startswith('_') and name not in [
                     'np', 'pd', 'plt', 'sns', 'sm', 'stats', 'sklearn',
                     'px', 'go', 'datetime', 'parser', 'pytz', 'holidays',
                     'os', 'sys', 'warnings', 'json', 'DATA_DIR', 'CHARTS_DIR',
-                    'datasets', 'preprocessing', 'model_selection', 'linear_model',
-                    'ensemble', 'metrics', 'svm', 'decomposition', 'cluster',
-                    'feature_selection', 'df'  # Exclude our parameter from variables
                 ]:
                     variables[name] = value
@@ -221,5 +234,102 @@ def execute_python_code(code: str, df: pd.DataFrame = None) -> Dict[str, Any]:
         'output': output,
         'error': error,
         'plots': plot_base64,
-        'html_charts': html_charts
-    }

 import pytz
 from dateutil import parser
 import json
+from typing import Any, Dict, List
 import traceback
 import warnings
 import plotly.express as px
         df (pd.DataFrame): Optional DataFrame to make available in the execution context
     Returns:
+        dict: Dictionary containing execution results, variables, and any generated files
     """
     # Create directories if they don't exist
     charts_dir = Path("charts")
     plot_base64 = []
     variables = {}
     html_charts = []
+    generated_files = []
     # Monkey patch plt.show() to save figures
     original_show = plt.show
             'sys': sys,
             'warnings': warnings,
             'json': json,
+            'Path': Path,
             # File paths
             'DATA_DIR': data_dir,
             # First execute to get variables
             exec(code, exec_globals)
+            # Check for newly created files in the data directory
+            for file in data_dir.glob('*'):
+                if file.suffix.lower() in ['.xlsx', '.csv']:
+                    with open(file, 'rb') as f:
+                        file_content = f.read()
+                    generated_files.append({
+                        'filename': file.name,
+                        'content': base64.b64encode(file_content).decode('utf-8'),
+                        'filetype': file.suffix.lower()[1:]  # 'xlsx' or 'csv'
+                    })
             # Capture all variables that were created
             for name, value in exec_globals.items():
                 if not name.startswith('_') and name not in [
                     'np', 'pd', 'plt', 'sns', 'sm', 'stats', 'sklearn',
                     'px', 'go', 'datetime', 'parser', 'pytz', 'holidays',
                     'os', 'sys', 'warnings', 'json', 'DATA_DIR', 'CHARTS_DIR',
+                    'Path', 'datasets', 'preprocessing', 'model_selection',
+                    'linear_model', 'ensemble', 'metrics', 'svm', 'decomposition',
+                    'cluster', 'feature_selection', 'df'  # Exclude our parameter from variables
                 ]:
                     variables[name] = value
         'output': output,
         'error': error,
         'plots': plot_base64,
+        'html_charts': html_charts,
+        'generated_files': generated_files,
+        'variables': processed_vars
+    }
+# EXAMPLE CODE:
+# test_code = """
+# # Test case that generates all types of outputs
+# import pandas as pd
+# import numpy as np
+# import matplotlib.pyplot as plt
+# import plotly.express as px
+# from pathlib import Path
+# # 1. Test basic output
+# print("Starting test execution...")
+# print("This is standard output")
+# # 2. Test variable creation
+# test_var = "Hello, World!"
+# numeric_var = 42
+# array_var = np.array([1, 2, 3])
+# df_var = pd.DataFrame({'A': [1, 2], 'B': ['x', 'y']})
+# # 3. Test matplotlib plot generation
+# plt.figure()
+# plt.plot([1, 2, 3], [4, 5, 6], label='Test Line')
+# plt.title('Matplotlib Test Plot')
+# plt.legend()
+# plt.show()
+# # 4. Test plotly plot generation
+# fig = px.bar(x=['A', 'B', 'C'], y=[1, 3, 2], title='Plotly Test Plot')
+# fig.show()
+# # 5. Test Excel file generation
+# excel_path = Path('data') / 'test_output.xlsx'
+# df_excel = pd.DataFrame({
+#     'Product': ['A', 'B', 'C'],
+#     'Sales': [100, 200, 150],
+#     'Profit': [30, 50, 40]
+# })
+# df_excel.to_excel(excel_path, index=False)
+# print(f"Generated Excel file at {excel_path}")
+# # 6. Test CSV file generation
+# csv_path = Path('data') / 'test_output.csv'
+# df_csv = pd.DataFrame({
+#     'Name': ['Alice', 'Bob', 'Charlie'],
+#     'Age': [25, 30, 35],
+#     'Score': [85, 92, 88]
+# })
+# df_csv.to_csv(csv_path, index=False)
+# print(f"Generated CSV file at {csv_path}")
+# # 7. Test error case (commented out by default)
+# # Uncomment to test error handling
+# # 1 / 0
+# # 8. Test empty case (commented out)
+# # Uncomment to test empty response
+# # print("No plots or files generated")
+# print("Test execution completed successfully")
+# """
+# # Execute the test code
+# result = execute_python_code(test_code)
+# # Print the results in a structured way
+# print("\n=== Execution Results ===")
+# print(f"Output:\n{result['output']}\n")
+# if result['error']:
+#     print("=== Error ===")
+#     print(f"Message: {result['error']['message']}")
+#     print(f"Traceback:\n{result['error']['traceback']}\n")
+# print("=== Variables ===")
+# for var_name, var_value in result['variables'].items():
+#     print(f"{var_name}: {str(var_value)[:100]}... (type: {type(var_value)})")
+# print("\n=== Generated Files ===")
+# for file in result['generated_files']:
+#     print(f"{file['filename']} ({file['filetype']}), size: {len(base64.b64decode(file['content']))} bytes")
+# print("\n=== Plots ===")
+# print(f"Matplotlib plots generated: {len(result['plots'])}")
+# print(f"Plotly HTML charts generated: {len(result['html_charts'])}")
+# # To actually view the plots (in a notebook environment):
+# if result['plots']:
+#     from IPython.display import display, Image
+#     display(Image(base64.b64decode(result['plots'][0])))