Creating a digital twin

from edsl import (
    QuestionMultipleChoice,
    QuestionCheckBox,
    QuestionFreeText,
    QuestionLinearScale,
    Agent,
    ScenarioList,
    Survey
)

# Construct relevant traits as a dictionary
agent_traits = {
    "persona": """You are a middle-aged mom in Cambridge, Massachusetts.
        You hope to own a driverless minivan in the near future.
        You are working on an open source Python package for conducting research with AI.""",
    "age": 45,
    "location": "US",
    "industry": "information technology",
    "company": "Expected Parrot",
    "occupation": "startup cofounder",
    "hobbies": "kayaking, beach walks",
}

# Pass the traits and an optional name to an agent
agent = Agent(name="Robin", traits=agent_traits)

# Optionally create some special instructions for the task
context = """You are answering questions about a software package for conducting surveys and experiments
          with large language models. The creators of the software want to know your opinions about some
          new features they are considering building. Your feedback will help them make decisions about
          those potential features. """

# Construct questions for the task
q1 = QuestionMultipleChoice(
    question_name="use_often",
    question_text=context
    + """Consider the following new feature: {{ scenario.content }}
    How often do you think you would use it?""",
    question_options=["Never", "Occasionally", "Frequently", "All the time"],
)

q2 = QuestionCheckBox(
    question_name="checkbox",
    question_text=context
    + """Consider the following new feature: {{ scenario.content }}
    Select all that apply.""",
    question_options=[
        "This feature would be useful to me.",
        "This feature would make me more productive.",
        "This feature will be important to me.",
        "The benefits of this feature are not clear to me.",
        "I would like to see some examples of how to use this feature.",
    ],
)

q3 = QuestionFreeText(
    question_name="concerns",
    question_text=context
    + "Do you have any concerns about the value and usefulness of this new feature: {{ scenario.content }}",
)

q4 = QuestionLinearScale(
    question_name="likely_to_use",
    question_text=context
    + """Consider the following new feature: {{ scenario.content }}
    On a scale from 1 to 5, how likely are you to use this new feature?
    (1 = not at all likely, 5 = very likely)""",
    question_options=[1, 2, 3, 4, 5],
    option_labels={1: "Not at all likely", 5: "Very likely"},
)

# Create a survey with the questions
survey = Survey(questions=[q1, q2, q3, q4])

# Create some content for the agent to review
contents = [
    "An optional progress bar that shows how many of your questions have been answered while your survey is running.",
    "A method that lets you quickly check what version of the package you have installed.",
    "A method that lets you include questions and responses as context for new questions.",
]

# Parameterize the questions with the content
scenarios = ScenarioList.from_list("content", contents)

agent

# Run the survey and store the results; we can also see a progress bar
results = survey.by(scenarios).by(agent).run()

# Show all columns of the Results object
results.columns

# Print the responses
results.select(
    "content",
    "use_often",
    "checkbox",
    "concerns",
    "likely_to_use",
)

# Post the notebook on Expected Parrot
from edsl import Notebook

nb = Notebook(path = "digital_twin.ipynb")

if refresh := False:
    nb.push(
        description = "Example code for creating a digital twin",
        alias = "digital-twin-notebook",
        visibility = "public"
    )

# update if it already exists
else:
    nb.patch('b403f472-757a-4b6b-8c03-a00c941d157d', value = nb)