app.py

import pandas as pd
import os

def load_dataset(file_path: str) -> pd.DataFrame:
    """
    Loads a dataset from a specified file path into a Pandas DataFrame.

    This function reads a dataset from a given file path. The file can be in various formats
    supported by Pandas, such as CSV, Excel, or JSON. The function returns the dataset as a
    Pandas DataFrame, which is a powerful data structure for data manipulation and analysis.

    Parameters:
    - file_path (str): The path to the dataset file. This should be a string representing
                        the location of the file on the filesystem.

    Returns:
    pd.DataFrame: A DataFrame containing the loaded dataset.

    Raises:
    - FileNotFoundError: If the specified file path does not exist or cannot be found.
    - ValueError: If the file format is not supported or if the file is empty.
    - pd.errors.EmptyDataError: If the file is empty and cannot be read into a DataFrame.
    - pd.errors.ParserError: If there is an error while parsing the file.
    - TypeError: If the file path is not a string or is an unsupported file format.

    Examples:
    >>> df = load_dataset('data/my_dataset.csv')
    >>> print(df.head())
    """

    # Checking if file path is a string
    if not isinstance(file_path, str):
        raise TypeError(f"Expected file path to be a string, but got {type(file_path).__name__}.")

    # Checking if the file exists
    if not os.path.exists(file_path):
        raise FileNotFoundError(f"File not found: {file_path}. Please check the path and try again.")

    # Attempting to load the dataset based on the file extension
    try:
        # Determine the file extension and load the file accordingly
        file_extension = file_path.split('.')[-1].lower()

        if file_extension == 'csv':
            dataset = pd.read_csv(file_path)
        elif file_extension in ['xlsx', 'xls']:
            dataset = pd.read_excel(file_path)
        elif file_extension == 'json':
            dataset = pd.read_json(file_path)
        else:
            raise ValueError(f"Unsupported file format: {file_extension}. Supported formats are CSV, Excel, and JSON.")

        # Checking if the dataset is empty
        if dataset.empty:
            raise pd.errors.EmptyDataError(f"The file at {file_path} is empty and cannot be loaded into a DataFrame.")

        return dataset

    except ValueError as value_error:
        raise ValueError(f"Error loading the dataset from {file_path}. Please ensure the file is in a supported format and not empty.") from value_error

    except pd.errors.EmptyDataError as empty_data_error:
        raise pd.errors.EmptyDataError(f"The file at {file_path} is empty and cannot be loaded into a DataFrame.") from empty_data_error

    except pd.errors.ParserError as parser_error:
        raise pd.errors.ParserError(f"Error parsing the file at {file_path}. Please check the file format and contents.") from parser_error

    except Exception as e:
        raise Exception(f"An error occurred while loading the file: {file_path}. Error details: {str(e)}") from e


# Example usage of the load_dataset function:
try:
    # Example 1: Loading a dataset from a CSV file
    dataset = load_dataset('data/my_dataset.csv')
    print("Dataset loaded successfully!")
    print(dataset.head())  # Displaying the first few rows of the dataset

    # Example 2: Loading a dataset from an Excel file
    dataset = load_dataset('data/my_dataset.xlsx')
    print("Dataset loaded successfully!")
    print(dataset.head())  # Displaying the first few rows of the dataset

    # Example 3: Attempting to load a non-existent file (should raise an error)
    dataset = load_dataset('data/non_existent_file.csv')

except Exception as e:
    print(f"An error occurred: {e}")