kedro-datasets

import pandas as pd import os from kedro_datasets.pandas import CSVDataset # 1. Create a dummy CSV file data = {"col1": [1, 2, 3], "col2": ["A", "B", "C"]} df = pd.DataFrame(data) filepath = "my_dummy_data.csv" df.to_csv(filepath, index=False) print(f"Created dummy data at: {filepath}\n") # 2. Initialize the CSVDataset csv_dataset = CSVDataset(filepath=filepath, save_args={"index": False}) # 3. Load data loaded_df = csv_dataset.load() print("Loaded DataFrame from CSVDataset:\n") print(loaded_df) # 4. Save new data using the dataset new_data = pd.DataFrame({"col1": [4, 5], "col2": ["D", "E"]}) csv_dataset.save(new_data) print("\nSaved new data to the CSV file.\n") # 5. Verify by loading again reloaded_df = csv_dataset.load() print("Reloaded DataFrame after saving new data:\n") print(reloaded_df) # 6. Clean up the dummy file os.remove(filepath) print(f"\nCleaned up dummy data file: {filepath}")