Mustehson commited on
Commit
476f578
·
1 Parent(s): 28623de

Edit Prompt

Browse files
Files changed (1) hide show
  1. app.py +19 -7
app.py CHANGED
@@ -49,21 +49,33 @@ def get_table_schema(table):
49
  ddl_create = ddl_create.replace(old_path, full_path)
50
  return ddl_create, full_path
51
 
 
52
  def get_visualization(question, tool):
53
  agent = ReactCodeAgent(tools=[tool], llm_engine=llm_engine, add_base_tools=True,
54
  additional_authorized_imports=['matplotlib.pyplot',
55
  'pandas', 'plotly.express',
56
- 'seaborn'], max_iterations=20)
57
  fig = agent.run(
 
58
  task=f'''
59
- Use seaborn. Always
60
- Question: {question}
61
- Always use the right colors.
62
- If the question is about showing n number of rows return empty figure.
63
- In the end you have to return a final fig using the `final_answer` tool
 
 
 
 
 
 
 
 
 
 
64
  ''',
65
  )
66
-
67
  return fig
68
 
69
 
 
49
  ddl_create = ddl_create.replace(old_path, full_path)
50
  return ddl_create, full_path
51
 
52
+
53
  def get_visualization(question, tool):
54
  agent = ReactCodeAgent(tools=[tool], llm_engine=llm_engine, add_base_tools=True,
55
  additional_authorized_imports=['matplotlib.pyplot',
56
  'pandas', 'plotly.express',
57
+ 'seaborn'], max_iterations=10)
58
  fig = agent.run(
59
+
60
  task=f'''
61
+ Here are the steps you should follow while writing code for Visualization:
62
+ 1. Select the most effective visualization type for the data and purpose.
63
+ 2. Ensure clear and appropriate labels, colors, and design elements, keeping visual elements legible and uncluttered.
64
+ 3. Follow best practices, avoiding unnecessary visual distractions (chartjunk).
65
+ 4. Ensure the code is error-free, with correct fields, transformations, and aesthetics.
66
+ 5. Use descriptive and accurate x and y axis labels that reflect the data.
67
+ 6. Ensure units of measurement are clearly indicated on axes (e.g., %, $, cm).
68
+ 7. Ensure that categorical data is plotted on one axis and numerical data on the other, with appropriate labels that clearly represent the data being visualized.
69
+ 8. When plotting categorical data, arrange categories in a meaningful order (e.g., by size, time, or frequency) rather than randomly.
70
+ 9. Ensure that the categorical data are plotted on the x-axis, and the frequencies (numerical data) are plotted on the y-axis.
71
+ 9. Use seaborn
72
+ 10. In the end you have to return a final fig using the `final_answer` tool.
73
+
74
+ Here is the task:
75
+ task: {question}
76
  ''',
77
  )
78
+
79
  return fig
80
 
81