Hypogenic Hypothesis Generation

pip install hypogenic

# Optional: clone example datasets
git clone https://github.com/ChicagoHAI/HypoGeniC-datasets.git ./data
git clone https://github.com/ChicagoHAI/Hypothesis-agent-datasets.git ./data_lit

from hypogenic import BaseTask
import re

# Custom label extractor (must match dataset label format)
def extract_label(text: str) -> str:
    match = re.search(r'final answer:\s+(.*)', text, re.IGNORECASE)
    return match.group(1).strip() if match else text.strip()

# 1. Load task from config
task = BaseTask(
    config_path="./data/your_task/config.yaml",
    extract_label=extract_label
)

# 2. Generate hypotheses (data-driven)
task.generate_hypotheses(
    method="hypogenic",
    num_hypotheses=20,
    output_path="./output/hypotheses.json"
)

# 3. Run inference on test set
results = task.inference(
    hypothesis_bank="./output/hypotheses.json",
    test_data="./data/your_task/your_task_test.json"
)
print(f"Accuracy: {results['accuracy']:.3f}")

import json

# Dataset: each key maps to a list of equal length
dataset = {
    "headline_1": [
        "What Up, Comet? You Just Got *PROBED*",
        "Scientists Made a Breakthrough in Quantum Computing"
    ],
    "headline_2": [
        "Scientists Were Holding Their Breath Today. Here's Why.",
        "New Quantum Computer Achieves Milestone"
    ],
    "label": [
        "Headline 2 has more clicks than Headline 1",
        "Headline 1 has more clicks than Headline 2"
    ]
}

# All lists must have equal length; labels must match extract_label output
for split in ["train", "val", "test"]:
    with open(f"my_task_{split}.json", "w") as f:
        json.dump(dataset, f, indent=2)
print(f"Created dataset with {len(dataset['label'])} samples")

# config.yaml structure (write as YAML file)
config = """
task_name: my_task

train_data_path: ./my_task_train.json
val_data_path: ./my_task_val.json
test_data_path: ./my_task_test.json

prompt_templates:
  observations: |
    Feature 1: ${text_features_1}
    Feature 2: ${text_features_2}
    Observation: ${label}

  batched_generation:
    system: "You are a research scientist generating hypotheses."
    user: "Generate ${num_hypotheses} testable hypotheses from these observations."

  inference:
    system: "You are evaluating a hypothesis against data."
    user: "Hypothesis: ${hypothesis}\\nSample: ${sample_text}\\nFinal answer: ${label}"

  is_relevant:
    system: "Check hypothesis relevance."
    user: "Is this hypothesis relevant? ${hypothesis}"
"""

with open("config.yaml", "w") as f:
    f.write(config)
print("Configuration written to config.yaml")

import re

def extract_label(llm_output: str) -> str:
    """Parse LLM output to extract predicted label.

    Must return labels matching the 'label' field values in the dataset.
    Default: searches for 'final answer: <label>' pattern.
    """
    match = re.search(r'final answer:\s+(.*)', llm_output, re.IGNORECASE)
    if match:
        return match.group(1).strip()
    # Domain-specific fallback
    if "Final prediction:" in llm_output:
        return llm_output.split("Final prediction:")[-1].strip()
    return llm_output.strip()

# Test against expected labels
assert extract_label("Final answer: Headline 1") == "Headline 1"
print("Label extractor validated")

from hypogenic import BaseTask

task = BaseTask(
    config_path="./config.yaml",
    extract_label=extract_label
)

# Generate hypotheses: initializes from data subset, iteratively refines
task.generate_hypotheses(
    method="hypogenic",       # Data-driven generation
    num_hypotheses=20,        # Target number of hypotheses
    output_path="./output/hypotheses.json"
)
# CLI equivalent:
# hypogenic_generation --config config.yaml --method hypogenic --num_hypotheses 20
print("Hypothesis bank saved to ./output/hypotheses.json")

results = task.inference(
    hypothesis_bank="./output/hypotheses.json",
    test_data="./my_task_test.json"
)
print(f"Test accuracy: {results['accuracy']:.3f}")
print(f"Predictions: {results['predictions'][:5]}")
# CLI equivalent:
# hypogenic_inference --config config.yaml --hypotheses output/hypotheses.json

# Requires GROBID setup and preprocessed PDFs
# bash ./modules/setup_grobid.sh  # first time
# bash ./modules/run_grobid.sh    # start GROBID service
# python pdf_preprocess.py --task_name my_task

task.generate_hypotheses(
    method="hyporefine",
    num_hypotheses=15,
    literature_path="./literature/my_task/",
    output_path="./output/"
)
# Generates 3 hypothesis banks:
# - HypoRefine (integrated literature+data)
# - Literature-only hypotheses
# - Literature union HypoRefine
print("HypoRefine generation complete: 3 hypothesis banks created")

from examples.multi_hyp_inference import run_multi_hypothesis_inference

results = run_multi_hypothesis_inference(
    config_path="./config.yaml",
    hypothesis_bank="./output/hypotheses.json",
    test_data="./my_task_test.json"
)
print(f"Multi-hypothesis accuracy: {results['accuracy']:.3f}")

{
  "text_features_1": ["sample_1_feat1", "sample_2_feat1"],
  "text_features_2": ["sample_1_feat2", "sample_2_feat2"],
  "label": ["class_A", "class_B"]
}

task_name: my_task
train_data_path: ./my_task_train.json
val_data_path: ./my_task_val.json
test_data_path: ./my_task_test.json

model:
  name: "gpt-4"                    # or claude-3, gpt-3.5-turbo
  api_key_env: "OPENAI_API_KEY"
  temperature: 0.7

generation:
  method: "hypogenic"
  num_hypotheses: 20
  batch_size: 5
  max_iterations: 10

cache:
  enabled: true                    # Redis on localhost:6832
  host: "localhost"
  port: 6832

prompt_templates:
  observations: |
    Feature 1: ${text_features_1}
    Observation: ${label}
  batched_generation:
    system: "Generate testable hypotheses."
    user: "Generate ${num_hypotheses} hypotheses."
  inference:
    system: "Evaluate hypothesis against sample."
    user: "Hypothesis: ${hypothesis}\nSample: ${sample_text}"
  is_relevant:
    system: "Check relevance."
    user: "Is ${hypothesis} relevant?"

import json
from hypogenic import BaseTask

# 1. Prepare data splits
for split_name, data in [("train", train_data), ("val", val_data), ("test", test_data)]:
    with open(f"my_task_{split_name}.json", "w") as f:
        json.dump(data, f)

# 2. Define domain-specific label extractor
def my_extractor(text):
    if "positive" in text.lower():
        return "positive"
    elif "negative" in text.lower():
        return "negative"
    return text.strip()

# 3. Create task and run full pipeline
task = BaseTask(config_path="./my_task/config.yaml", extract_label=my_extractor)
task.generate_hypotheses(method="hypogenic", num_hypotheses=15, output_path="./output/")
results = task.inference(hypothesis_bank="./output/hypotheses.json")
print(f"Custom task accuracy: {results['accuracy']:.3f}")

# 1. Setup GROBID (first time only)
bash ./modules/setup_grobid.sh

# 2. Place PDFs in literature directory
mkdir -p literature/my_task/raw/
cp papers/*.pdf literature/my_task/raw/

# 3. Start GROBID and process
bash ./modules/run_grobid.sh
cd examples && python pdf_preprocess.py --task_name my_task
# Output: structured text files in literature/my_task/processed/

# Generate literature hypotheses first (via HypoRefine)
task.generate_hypotheses(
    method="hyporefine",
    num_hypotheses=15,
    literature_path="./literature/my_task/",
    output_path="./output/"
)

# Union combines and deduplicates both banks
# CLI alternative:
# hypogenic_generation --config config.yaml --method union \
#   --literature_hypotheses output/lit_hypotheses.json

# Compare all three approaches
for bank in ["hypogenic", "hyporefine", "union"]:
    r = task.inference(hypothesis_bank=f"./output/{bank}_hypotheses.json")
    print(f"{bank}: accuracy={r['accuracy']:.3f}")