edsl 0.1.45__py3-none-any.whl → 0.1.47__py3-none-any.whl

edsl/auto/StagePersona.py

@@ -1,61 +0,0 @@
-from textwrap import dedent
-from dataclasses import dataclass
-from typing import List
-
-from edsl.auto.StageBase import StageBase
-from edsl.auto.StageBase import FlowDataBase
-from edsl import Model
-from edsl.auto.StageQuestions import StageQuestions
-
-from edsl.questions import QuestionFreeText
-from edsl.scenarios import Scenario
-
-from edsl.auto.utilities import gen_pipeline
-
-
-class StagePersona(StageBase):
-    input = StageQuestions.output
-
-    @dataclass
-    class Output(FlowDataBase):
-        persona: str
-        questions: List[str]
-
-    output = Output
-
-    def handle_data(self, data):
-        m = Model()
-        q_persona = QuestionFreeText(
-            question_text=dedent(
-                """\
-        Imagine a person from the population {{ population }} responding to these questions: "{{ questions }}"
-        Make up a 1 paragraph persona for this person who would have answers for these questions.
-        """
-            ),
-            question_name="persona",
-        )
-        results = (
-            q_persona.by(m)
-            .by(Scenario({"questions": data.questions, "population": data.population}))
-            .run()
-        )
-        print("Constructing a persona that could answer the following questions:")
-        print(data.questions)
-        results.select("persona").print(
-            pretty_labels={
-                "answer.persona": f"Persona that can answer: {data.questions}"
-            },
-            split_at_dot=False,
-        )
-        persona = results.select("persona").first()
-        return self.output(persona=persona, questions=data.questions)
-
-
-if __name__ == "__main__":
-    pipeline = gen_pipeline([StageQuestions, StagePersona])
-    pipeline.process(
-        pipeline.input(
-            overall_question="What are some factors that could determine whether someone likes ice cream?",
-            persona="People",
-        )
-    )

edsl/auto/StagePersonaDimensionValueRanges.py

@@ -1,88 +0,0 @@
-from textwrap import dedent
-from dataclasses import dataclass
-
-from typing import List
-
-from edsl.auto.StageBase import StageBase
-from edsl.auto.StageBase import FlowDataBase
-
-from edsl.auto.StagePersonaDimensionValues import StagePersonaDimensionValues
-
-from edsl.questions import QuestionList
-from edsl.scenarios import Scenario
-from edsl import Model
-from edsl.auto.utilities import gen_pipeline
-
-
-class StagePersonaDimensionValueRanges(StageBase):
-    input = StagePersonaDimensionValues.output
-
-    @dataclass
-    class Output(FlowDataBase):
-        focal_dimension_values: List[dict]
-        mapping: dict
-        persona: str
-
-    output = Output
-
-    def handle_data(self, data):
-        # breakpoint()
-        """Goal with this stage is to, for each dimension, get a range of values that the persona might have for that dimension."""
-        dimension_values = data["dimension_values"]
-        attribute_results = data["attribute_results"]
-        persona = data["persona"]
-        m = Model()
-        d = dict(zip(attribute_results, dimension_values))
-        q = QuestionList(
-            question_text=dedent(
-                """\
-            Consider the following persona: {{ persona }}.
-            They were categorized as having the following attributes: {{ d }}.
-            For this dimension: {{ focal_dimension }}, 
-            What are values that other people might have on this attribute?
-            """
-            ),
-            question_name="focal_dimension_values",
-        )
-        s = [
-            Scenario({"persona": persona, "d": d, "focal_dimension": k})
-            for k in d.keys()
-        ]
-        results = q.by(s).by(m).run()
-        # breakpoint()
-        results.select("focal_dimension", "answer.*").print(
-            pretty_labels={
-                "scenario.focal_dimension": f"Dimensions of a persona",
-                "answer.focal_dimension_values": f"Values a person might have for that dimension",
-            },
-            split_at_dot=False,
-        )
-
-        focal_dimension_values = results.select("focal_dimension_values").to_list()
-        mapping = dict(zip(attribute_results, focal_dimension_values))
-        return self.output(
-            focal_dimension_values=focal_dimension_values,
-            mapping=mapping,
-            persona=persona,
-        )
-
-
-if __name__ == "__main__":
-    from edsl.auto.StageQuestions import StageQuestions
-    from edsl.auto.StagePersona import StagePersona
-    from edsl.auto.StagePersonaDimensions import StagePersonaDimensions
-
-    pipeline = gen_pipeline(
-        [
-            StageQuestions,
-            StagePersona,
-            StagePersonaDimensions,
-            StagePersonaDimensionValues,
-            StagePersonaDimensionValueRanges,
-        ]
-    )
-    pipeline.process(
-        pipeline.input(
-            overall_question="What are some factors that could determine whether someone likes ice cream?"
-        )
-    )

edsl/auto/StagePersonaDimensionValues.py

@@ -1,74 +0,0 @@
-from textwrap import dedent
-from dataclasses import dataclass
-
-from typing import List, Dict
-
-from edsl.auto.StageBase import StageBase
-from edsl.auto.StageBase import FlowDataBase
-
-from edsl.auto.StagePersonaDimensions import StagePersonaDimensions
-from edsl import Model
-from edsl.questions import QuestionList, QuestionExtract
-from edsl.scenarios import Scenario
-
-from edsl.auto.utilities import gen_pipeline
-
-
-class StagePersonaDimensionValues(StageBase):
-    input = StagePersonaDimensions.output
-
-    @dataclass
-    class Output(FlowDataBase):
-        attribute_results: List[str]
-        dimension_values: Dict[str, str]
-        persona: str
-
-    output = Output
-
-    def handle_data(self, data):
-        attribute_results = data.attribute_results
-        persona = data.persona
-        m = Model()
-        q = QuestionExtract(
-            question_text=dedent(
-                """\
-            This is a persona: "{{ persona }}"
-            They vary on the following dimensions: "{{ attribute_results }}"
-            For each dimenion, what are some values that this persona might have for that dimension?
-            Please keep answers very short, ideally one word.
-            """
-            ),
-            answer_template={k: None for k in attribute_results},
-            question_name="dimension_values",
-        )
-        results = (
-            q.by(Scenario({"attribute_results": attribute_results, "persona": persona}))
-            .by(m)
-            .run()
-        )
-        results.select("attribute_results", "dimension_values").print()
-        return self.output(
-            dimension_values=results.select("dimension_values").first(),
-            attribute_results=attribute_results,
-            persona=persona,
-        )
-
-
-if __name__ == "__main__":
-    from edsl.auto.StageQuestions import StageQuestions
-    from edsl.auto.StagePersona import StagePersona
-    from edsl.auto.StagePersonaDimensions import StagePersonaDimensions
-
-    pipeline = gen_pipeline(
-        [
-            StageQuestions,
-            StagePersona,
-            StagePersonaDimensions,
-            StagePersonaDimensionValues,
-        ]
-    )
-    pipeline.process(
-        pipeline.input(
-            overall_question="What are some factors that could determine whether someone likes ice cream?"
-        )
-    )

edsl/auto/StagePersonaDimensions.py

@@ -1,69 +0,0 @@
-from textwrap import dedent
-from dataclasses import dataclass
-
-from typing import List
-
-from edsl.auto.StageBase import StageBase
-from edsl.auto.StageBase import FlowDataBase
-
-from edsl.auto.StagePersona import StagePersona
-
-from edsl.questions import QuestionList
-from edsl.scenarios import Scenario
-from edsl import Model
-
-from edsl.auto.utilities import gen_pipeline
-
-
-class StagePersonaDimensions(StageBase):
-    input = StagePersona.output
-
-    @dataclass
-    class Output(FlowDataBase):
-        attribute_results: List[str]
-        persona: str
-
-    output = Output
-
-    def handle_data(self, data):
-        q_attributes = QuestionList(
-            question_text=dedent(
-                """\
-            Here is a persona: "{{ persona }}"
-            It was construced to be someone who could answer these questions: "{{ questions }}"
-
-            We want to identify the general dimensions that make up this persona.
-            E.g., if the person is desribed as 'happy' then a dimenion would be  'mood'
-            """
-            ),
-            question_name="find_attributes",
-        )
-        m = Model()
-        results = (
-            q_attributes.by(
-                Scenario({"persona": data.persona, "questions": data.questions})
-            )
-            .by(m)
-            .run()
-        )
-        (
-            results.select("find_attributes").print(
-                pretty_labels={
-                    "answer.find_attributes": f'Persona dimensions for: "{data.persona}"'
-                },
-                split_at_dot=False,
-            )
-        )
-        attribute_results = results.select("find_attributes").first()
-        return self.output(attribute_results=attribute_results, persona=data.persona)
-
-
-if __name__ == "__main__":
-    from edsl.auto.StageQuestions import StageQuestions
-
-    pipeline = gen_pipeline([StageQuestions, StagePersona, StagePersonaDimensions])
-    pipeline.process(
-        pipeline.input(
-            overall_question="What are some factors that could determine whether someone likes ice cream?"
-        )
-    )

edsl/auto/StageQuestions.py

@@ -1,74 +0,0 @@
-from dataclasses import dataclass
-from typing import List
-from textwrap import dedent
-
-
-from edsl import Scenario
-from edsl import Model
-from edsl.questions.QuestionList import QuestionList
-
-from edsl.auto.StageBase import StageBase
-from edsl.auto.StageBase import FlowDataBase
-
-from edsl.auto.utilities import gen_pipeline
-
-
-class StageQuestions(StageBase):
-    "This stages takes as input an overall question and returns a list of questions"
-
-    @dataclass
-    class Input(FlowDataBase):
-        overall_question: str
-        population: str
-
-    @dataclass
-    class Output(FlowDataBase):
-        questions: List[str]
-        population: str
-
-    input = Input
-    output = Output
-
-    def handle_data(self, data):
-        m = Model()
-        overall_question = data.overall_question
-        population = data.population
-        s = Scenario({"overall_question": overall_question, "population": population})
-        q = QuestionList(
-            question_text=dedent(
-                """\
-            Suppose I am interested in the question: 
-            "{{ overall_question }}" 
-            What would be some survey questions I could ask to {{ population }} that might shed light on this question?
-            """
-            ),
-            question_name="questions",
-        )
-        results = q.by(s).by(m).run()
-        (
-            results.select("questions").print(
-                pretty_labels={
-                    "answer.questions": f'Questions for overall question: "{overall_question }"'
-                },
-                split_at_dot=False,
-            )
-        )
-
-        raw_questions = results.select("questions").first()
-        questions = [q.replace("'", "").replace(":", "") for q in raw_questions]
-        return self.Output(questions=questions, population=population)
-
-
-if __name__ == "__main__":
-    pipeline = gen_pipeline([StageQuestions])
-
-    pipeline.process(
-        pipeline.input(
-            overall_question="What are some factors that could determine whether someone likes ice cream?",
-            population="Consumers",
-        )
-    )
-
-    results = StageQuestions.func(
-        overall_question="Why aren't my students studying more?", population="Tech"
-    )

edsl/auto/SurveyCreatorPipeline.py

@@ -1,21 +0,0 @@
-import random
-from typing import Dict, List, Any, TypeVar, Generator, Optional
-
-from textwrap import dedent
-
-# from edsl.language_models.model_interfaces.LanguageModelOpenAIFour import LanguageModelOpenAIFour
-from edsl import Model
-from edsl.agents.AgentList import AgentList
-from edsl.results.Results import Results
-from edsl import Agent
-
-from edsl import Scenario
-from edsl.surveys.Survey import Survey
-
-from edsl.questions.QuestionMultipleChoice import QuestionMultipleChoice
-from edsl.questions.QuestionFreeText import QuestionFreeText
-from edsl.auto.utilities import gen_pipeline
-from edsl.utilities.naming_utilities import sanitize_string
-
-
-m = Model()

edsl/auto/utilities.py

@@ -1,218 +0,0 @@
-from textwrap import dedent
-import random
-from typing import List, TypeVar, Generator, Optional
-from edsl.auto.StageBase import StageBase
-from edsl.utilities.naming_utilities import sanitize_string
-from edsl import Agent, Survey, Model, Cache, AgentList
-from edsl import QuestionFreeText, Scenario
-from edsl import QuestionMultipleChoice, Scenario, Agent, ScenarioList
-
-StageClassType = TypeVar("StageClassType", bound=StageBase)
-
-
-def gen_pipeline(stages_list: List[StageClassType]) -> StageBase:
-    """Takes as input a list of Stage classes & returns a pipeline of instantiated stages.
-    A pipeline is a linked list of stages where each stage has a next_stage attribute.
-
-    """
-    pipeline = stages_list[0]()
-    last_stage = pipeline
-    for stage in stages_list[1:]:
-        while last_stage.next_stage is not None:  # find the end of the pipeline
-            last_stage = last_stage.next_stage
-        stage_to_add = stage()
-        last_stage.next_stage = stage_to_add
-    return pipeline
-
-
-q_eligibility = QuestionMultipleChoice(
-    question_text=dedent(
-        """\
-        Consider this set of question: '{{ questions }}'.
-        Consider this persona: '{{ persona }}'.
-        Would this persona be able to answer all of these questions?
-        """
-    ),
-    question_options=["No", "Yes"],
-    question_name="eligibility",
-)
-
-
-def agent_list_eligibility(
-    agent_list: AgentList,
-    survey: Optional[Survey] = None,
-    model: Optional[Model] = None,
-    cache: Optional[Cache] = None,
-) -> List[bool]:
-    """
-    Returns whether each agent in a list is elgible for a survey i.e., can answer every question.
-
-    >>> from edsl.language_models import LanguageModel
-    >>> m = LanguageModel.example(canned_response = "1", test_model = True)
-    >>> agent_list_eligibility(AgentList.example())
-    [True, True]
-    >>> agent_list_eligibility(AgentList.example().add_trait('persona', 2*["Cool dude"]), survey = Survey.example(), model = m)
-    [True, True]
-    """
-    if survey is None:
-        return [True] * len(agent_list)
-    if "persona" not in agent_list.all_traits:
-        raise ValueError(
-            f"Each agent needs to have a persona attribute; traits are {agent_list.all_traits}"
-        )
-    sl = agent_list.select("persona").to_scenario_list()
-    sl.add_value("questions", [q.question_text for q in survey._questions])
-    results = q_eligibility.by(sl).by(model).run(cache=cache)
-    return [r == "Yes" for r in results.select("eligibility").to_list()]
-
-
-def agent_eligibility(
-    agent: Agent,
-    survey: Survey,
-    model: Optional[Model] = None,
-    cache: Optional[Cache] = None,
-) -> bool:
-    """NB: This could be parallelized.
-
-    >>> from edsl.language_models import LanguageModel
-    >>> m = LanguageModel.example(canned_response = "1", test_model = True)
-    >>> agent_eligibility(agent = Agent.example().add_trait({'persona': "Persona"}), survey = Survey.example(), model = m)
-    True
-
-    """
-    model = model or Model()
-
-    questions = [q.question_text for q in survey._questions]
-    persona = agent.traits["persona"]
-    return (
-        q_eligibility(model=model, questions=questions, persona=persona, cache=cache)
-        == "Yes"
-    )
-
-
-def gen_agent_traits(dimension_dict: dict, seed_value: Optional[str] = None):
-    """
-    >>> dimension_dict = {'attitude':['positive', 'negative']}
-    >>> ag = gen_agent_traits(dimension_dict)
-    >>> a = next(ag)
-    >>> a == {'attitude': 'positive'} or a == {'attitude': 'negative'}
-    True
-    >>> len([next(ag) for _ in range(100)])
-    100
-    """
-    if seed_value is None:
-        seed_value = "edsl"
-
-    random.seed(seed_value)
-
-    while True:
-        new_agent_traits = {}
-        for key, list_of_values in dimension_dict.items():
-            new_agent_traits[key] = random.choice(list_of_values)
-        yield new_agent_traits
-
-
-def agent_generator(
-    persona: str,
-    dimension_dict: dict,
-    model: Optional[Model] = None,
-    cache: Optional["Cache"] = None,
-) -> Generator["Results", None, None]:
-    """
-    >>> from edsl.language_models import LanguageModel
-    >>> m = LanguageModel.example(canned_response = "This is a cool dude.", test_model = True)
-    >>> ag = agent_generator(persona = "Base person", dimension_dict = {'attitude':['Positive', 'Negative']}, model = m)
-    >>> next(ag).select('new_agent_persona').first()
-    'This is a cool dude.'
-    >>> next(ag).select('new_agent_persona').first()
-    'This is a cool dude.'
-    """
-
-    if model is None:
-        model = Model()
-
-    q = QuestionFreeText(
-        question_text=dedent(
-            """\
-    Consider this persona: '{{ persona }}'.
-    Now imagine writing a new persona with these traits: 
-    '{{ new_agent_traits }}'
-    Please write this persona as a narrative.
-    """
-        ),
-        question_name="new_agent_persona",
-    )
-    agent_trait_generator = gen_agent_traits(dimension_dict)
-    codebook = {sanitize_string(k): k for k in dimension_dict.keys()}
-    while True:
-        new_agent_traits = next(agent_trait_generator)
-        yield q(
-            persona=persona,
-            new_agent_traits=new_agent_traits,
-            codebook=codebook,
-            just_answer=False,
-            cache=cache,
-            model=model,
-        )
-
-
-def create_agents(
-    agent_generator: Generator["Results", None, None],
-    survey: Optional[Survey] = None,
-    num_agents=11,
-) -> AgentList:
-    """
-    >>> from edsl.language_models import LanguageModel
-    >>> m = LanguageModel.example(canned_response = "This is a cool dude.", test_model = True)
-    >>> ag = agent_generator(persona = "Base person", dimension_dict = {'attitude':['Positive', 'Negative']}, model = m)
-    >>> new_agent_list = create_agents(agent_generator = ag)
-    >>> new_agent_list
-
-    """
-    agent_list = AgentList([])
-
-    MAX_ITERATIONS_MULTIPLIER = 2
-    iterations = 0
-
-    while len(agent_list) < num_agents:
-        iterations += 1
-        candidate_agent = next(agent_generator)
-        codebook = candidate_agent.select("codebook").to_list()[0]
-
-        koobedoc = {v: k for k, v in codebook.items()}
-        persona = candidate_agent.select("new_agent_persona").to_list()[0]
-        traits = candidate_agent.select("new_agent_traits").to_list()[0]
-        new_traits = {koobedoc[key]: value for key, value in traits.items()} | {
-            "persona": persona
-        }
-        agent = Agent(traits=new_traits, codebook=codebook)
-        if survey is not None:
-            if agent_eligibility(agent, survey):
-                agent_list.append(agent)
-            else:
-                print("Agent not eligible")
-        else:
-            agent_list.append(agent)
-
-        if iterations > MAX_ITERATIONS_MULTIPLIER * num_agents:
-            raise Exception("Too many failures")
-
-    return agent_list
-
-
-if __name__ == "__main__":
-    import doctest
-
-    doctest.testmod()
-    # from edsl.language_models import LanguageModel
-
-    # m = LanguageModel.example(canned_response="This is a cool dude.", test_model=True)
-    # ag = agent_generator(
-    #     persona="Base person",
-    #     dimension_dict={"attitude": ["Positive", "Negative"]},
-    #     model=m,
-    # )
-    # example = [next(ag).select("new_agent_persona").first() for _ in range(10)]
-    # dimension_dict = {"attitude": ["positive", "negative"]}
-    # ag = gen_agent_traits(dimension_dict)
-    # example = [next(ag) for _ in range(100)]