src/distilabel_dataset_generator/pipelines/textcat.py

from typing import List

import pandas as pd

DEFAULT_DATASET_DESCRIPTIONS = [
    "A dataset covering customer reviews for an e-commerce website.",
    "A dataset covering news articles about various topics.",
]

DEFAULT_DATASETS = [
    pd.DataFrame.from_dict(
        {
            "text": [
                "I love the product! It's amazing and I'll buy it again.",
                "The product was okay, but I wouldn't buy it again.",
            ],
            "label": ["positive", "negative"],
        }
    ),
    pd.DataFrame.from_dict(
        {
            "text": [
                "Yesterday, the US stock market had a significant increase.",
                "New research suggests that the Earth is not a perfect sphere.",
            ],
            "label": [["economy", "politics"], ["science", "environment"]],
        }
    ),
]

DEFAULT_SYSTEM_PROMPTS = [
    "Classify the following customer review as positive or negative.",
    "Classify the following news article into one or more categories.",
]


def generate_pipeline_code(
    system_prompt: str,
    difficulty: str,
    clarity: str,
    labels: List[str],
    num_labels: int,
    num_rows: int,
) -> str:
    return """
    from distilabel import Distilabel

    #### PIPELINE CODE HERE
    """