1. import pandas as pd
  2. import requests
  3. import time
  4. import logging
  6. logging.basicConfig(level=logging.INFO)
  8. def load_dataset(url, max_retries=3, retry_delay=5):
  9. """
  10. Loads a dataset from a URL with retry logic and fallback.
  12. Args:
  13. url (str): The URL of the dataset.
  14. max_retries (int): The maximum number of retries.
  15. retry_delay (int): The delay in seconds between retries.
  17. Returns:
  18. pandas.DataFrame: The loaded DataFrame, or None if loading fails after all retries.
  19. """
  20. for attempt in range(max_retries):
  21. try:
  22. # Attempt to load the dataset
  23. df = pd.read_csv(url) # Adjust function based on data format (e.g., read_excel, etc.)
  24. logging.info(f"Successfully loaded dataset from {url} on attempt {attempt + 1}")
  25. return df
  26. except requests.exceptions.RequestException as e:
  27. logging.warning(f"Attempt {attempt + 1} failed: {e}")
  28. if attempt < max_retries - 1:
  29. logging.info(f"Retrying in {retry_delay} seconds...")
  30. time.sleep(retry_delay)
  31. else:
  32. logging.error(f"Failed to load dataset from {url} after {max_retries} attempts.")
  33. return None
  34. except pd.errors.ParserError as e:
  35. logging.warning(f"Attempt {attempt + 1} failed parsing the dataset: {e}")
  36. if attempt < max_retries - 1:
  37. logging.info(f"Retrying in {retry_delay} seconds...")
  38. time.sleep(retry_delay)
  39. else:
  40. logging.error(f"Failed to load/parse dataset from {url} after {max_retries} attempts.")
  41. return None
  42. except Exception as e:
  43. logging.error(f"An unexpected error occurred: {e}")
  44. return None
  46. if __name__ == '__main__':
  47. # Example Usage
  48. url = "https://raw.githubusercontent.com/plotly/datasets/master/iris.csv" # Replace with your dataset URL
  49. df = load_dataset(url)
  51. if df is not None:
  52. print("Dataset loaded successfully:")
  53. print(df.head())
  54. else:
  55. print("Failed to load dataset.")

Add your comment