Concept induction

from edsl import QuestionList

q_concepts = QuestionList(
    question_name="concepts",
    question_text="Identify the key concepts in the following text: {{ scenario.text }}",
    # max_list_items = # Optional,
    # min_list_items = # Optional
)

from edsl import QuestionMultipleChoice

q_sentiment = QuestionMultipleChoice(
    question_name="sentiment",
    question_text="Identify the sentiment of this text: {{ scenario.text }}",
    question_options=["Negative", "Neutral", "Positive"],
)

# Replace with your data
texts = [  # POTUS recent tweets
    "Tune in as I deliver the keynote address at the U.S. Holocaust Memorial Museum’s Annual Days of Remembrance ceremony in Washington, D.C.",
    "We’re a nation of immigrants. A nation of dreamers. And as Cinco de Mayo represents, a nation of freedom.",
    "Medicare is stronger and Social Security remains strong. My economic plan has helped extend Medicare solvency by a decade. And I am committed to extending Social Security solvency by making the rich pay their fair share.",
    "Today, the Army Black Knights are taking home West Point’s 10th Commander-in-Chief Trophy. They should be proud. I’m proud of them too – not for the wins, but because after every game they hang up their uniforms and put on another: one representing the United States.",
    "This Holocaust Remembrance Day, we mourn the six million Jews who were killed by the Nazis during one of the darkest chapters in human history. And we recommit to heeding the lessons of the Shoah and realizing the responsibility of 'Never Again.'",
    "The recipients of the Presidential Medal of Freedom haven't just kept faith in freedom. They kept all of America's faith in a better tomorrow.",
    "Like Jill says, 'Teaching isn’t just a job. It’s a calling.' She knows that in her bones, and I know every educator who joined us at the White House for the first-ever Teacher State Dinner lives out that truth every day.",
    "Jill and I send warm wishes to Orthodox Christian communities around the world as they celebrate Easter. May the Lord bless and keep you this Easter Sunday and in the year ahead.",
    "Dreamers are our loved ones, nurses, teachers, and small business owners – they deserve the promise of health care just like all of us. Today, my Administration is making that real by expanding affordable health coverage through the Affordable Care Act to DACA recipients.",
    "With today’s report of 175,000 new jobs, the American comeback continues. Congressional Republicans are fighting to cut taxes for billionaires and let special interests rip folks off, I'm focused on job creation and building an economy that works for the families I grew up with.",
]
len(texts)

from edsl import ScenarioList

scenarios = ScenarioList.from_source("list", "text", texts)
scenarios

from edsl import Survey

survey = Survey(questions=[q_concepts, q_sentiment])

results = survey.by(scenarios).run()

results.columns

results.select("text", "concepts", "sentiment")

# Flattening our list of lists for all the texts to use in a follow-on question:
concepts_list = results.select("concepts").to_list(flatten=True)
concepts_list

from edsl import Scenario

scenario = Scenario({"concepts":concepts_list})

q_condense = QuestionList(
    question_name="condense",
    question_text="Return a condensed list of the following set of concepts: {{ scenario.concepts }}",
    max_list_items=10,
)

results = q_condense.by(scenario).run()

results.select("condense")

from edsl import QuestionFreeText

q_criteria = QuestionFreeText(
    question_name="criteria",
    question_text="""Describe key criteria for determining whether a text is primarily about the
    following concept: {{ scenario.concept }}""",
)

condensed_concepts_list = results.select("condense").to_list(flatten=True)

scenarios = ScenarioList.from_source("list", "concept", condensed_concepts_list)
scenarios

results = q_criteria.by(scenarios).run()

results.select("concept", "criteria")

from edsl import QuestionLinearScale

q_score = QuestionLinearScale(
    question_name="score",
    question_text="""Consider the following concept and criteria for determining whether
    a given text addresses this concept. Then score how well the following text satisfies
    the criteria for the concept.
    Concept: {{ scenario.concept }}
    Criteria: {{ scenario.criteria }}
    Text: {{ scenario.text }}""",
    question_options=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
    option_labels={0: "Not at all", 10: "Very well"},  # Optional
)

concepts_criteria = [
    list(pair)
    for pair in zip(
        results.select("concept").to_list(), results.select("criteria").to_list()
    )
]
len(concepts_criteria)

10

from edsl import ScenarioList, Scenario

scenarios = ScenarioList(
    Scenario({"text": text, "concept": concept, "criteria": criteria})
    for text in texts
    for [concept, criteria] in concepts_criteria
)

```python
results = q_score.by(scenarios).run()

(
    results
        .filter("score > 0")
        .select("text", "concept", "score")
)

# scenarios.push(description = "Example scenarios", alias = "example-scenarios", visibility = "public")

# survey.push(description = "Example survey", alias = "example-survey", visibility = "public")

# results.push(description = "Example results", alias = "example-results", visibility = "public")

# from edsl import Notebook

# nb = Notebook(path = "concept_induction.ipynb")

# nb.push(
#     description = "Example code for concept induction",
#     alias = "concept-induction-notebook",
#     visibility = "public"
# )

from edsl import Notebook

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

nb.patch("https://www.expectedparrot.com/content/RobinHorton/concept-induction-notebook", value = nb)