companies:
  type: pandas.CSVDataset
  filepath: data/01_raw/companies.csv
reviews:
  type: pandas.CSVDataset
  filepath: data/01_raw/reviews.csv
shuttles:
  type: pandas.ExcelDataset
  filepath: data/01_raw/shuttles.xlsx
  load_args:
    engine: openpyxl

preprocessed_companies:
  type: pandas.ParquetDataset
  filepath: data/02_intermediate/preprocessed_companies.pq

preprocessed_shuttles:
  type: pandas.ParquetDataset
  filepath: data/02_intermediate/preprocessed_shuttles.pq  

--------------------

from kedro.pipeline import Pipeline, node, pipeline

from .nodes import preprocess_companies, preprocess_shuttles


def create_pipeline(**kwargs) -> Pipeline:
    return pipeline(
        [
            node(
                func=preprocess_companies,
                inputs="companies",
                outputs="preprocessed_companies",
                name="preprocess_companies_node",
            ),
            node(
                func=preprocess_shuttles,
                inputs="shuttles",
                outputs="preprocessed_shuttles",
                name="preprocess_shuttles_node",
            ),
        ]
    )