# Import the urlretrieve function from the urllib.request module
# This function helps in downloading a file from a given URL
from urllib.request import urlretrieve

# Define the URL of the file to be downloaded
url = 'https://infinitepy.s3.amazonaws.com/samples/lorem_ipsum.txt'

# Define the local filename where the downloaded file will be saved
filename = 'lorem_ipsum.txt'

# Use the urlretrieve function to download the file from the given URL
# and save it locally with the specified filename
urlretrieve(url, filename)

# Open the downloaded file for reading ('r' stands for read mode)
# The 'with' statement ensures that the file is properly closed after its suite finishes
with open(filename, 'r') as file:
    # Read the entire content of the file
    content = file.read()
    
    # Print the content of the file to the console
    print(content)

# Basic file writing

# 'with' statement is used to ensure proper acquisition and release of resources.
# It's a context manager that simplifies working with files by handling file closing automatically.
with open('output.txt', 'w') as file:
    # 'open' function is used to open a file. 
    # The first argument is the name of the file. If the file does not exist, it will be created.
    # The second argument 'w' stands for 'write mode', which allows us to write to the file.
    
    # 'file.write' method is used to write the provided string to the file.
    # Here, it writes the string 'Hello, world!' to 'output.txt'.
    file.write('Hello, world!')

# At this point, the 'with' context manager will automatically close the file,
# even if an error occurs, ensuring that resources are properly released.

def write_tasks_to_file(filename, tasks):
    """
    Write a list of tasks to a specified file.

    Args:
        filename (str): The name of the file to write tasks to.
        tasks (list): A list of tasks to be written to the file.
    """
    
    # Open a file with the given filename in write ('w') mode.
    # The 'with' statement ensures proper acquisition and release of resources.
    # The file is automatically closed after the indented block of code.
    with open(filename, 'w') as file:
        
        # Iterate over each task in the provided tasks list.
        for task in tasks:
            
            # Write each task to the file followed by a newline character.
            file.write(task + '\n')
    
    # Print a message to the console indicating that tasks have been successfully written to the file.
    print(f"Tasks have been written to {filename}")

def read_tasks_from_file(filename):
    """
    Read tasks from a specified file.

    Args:
        filename (str): The name of the file to read tasks from.
    
    Returns:
        list: A list of tasks read from the file.
    """
    tasks = []  # Initialize an empty list to hold the tasks
    try:
        # Attempt to open the file in read-only mode ('r')
        with open(filename, 'r') as file:
            # Read all lines from the file into the list 'tasks'
            tasks = file.readlines()
        # Strip newline characters '\n' from the end of each task
        tasks = [task.strip() for task in tasks]
    except FileNotFoundError:
        # If the file is not found, print an error message
        print(f"The file {filename} does not exist.")
    # Return the list of tasks (or an empty list if the file was not found)
    return tasks

filename = 'tasks.txt'
# Define a list of tasks to write to the file
tasks_to_write = ['Buy groceries', 'Complete Python tutorial', 'Walk the dog']

# Call the function to write tasks to the file
write_tasks_to_file(filename, tasks_to_write)

# Call the function to read tasks from the file
tasks_read = read_tasks_from_file(filename)
print("Tasks read from file:")
# Print each task read from the file
for task in tasks_read:
    print("- " + task)

# Import the pandas library which is very commonly used for data manipulation and analysis in Python
import pandas as pd

# Read a CSV file from the provided URL into a DataFrame
# A DataFrame is a 2-dimensional labeled data structure with columns of potentially different types,
# similar to a table in a database or an Excel spreadsheet.
df = pd.read_csv('https://infinitepy.s3.amazonaws.com/samples/employees.csv')

# Display the first few rows of the DataFrame to verify the data has been loaded correctly
print(df.head())  # Optional line for quick data inspection

# The 'head' method of a pandas DataFrame returns the first n rows.
# By default, it returns the first 5 rows if no argument is given.

# So, the following line of code prints the first 5 rows of the DataFrame 'df'.
print(df.head())

# Print the 'Name' column from the DataFrame 'df'
# The 'Name' column is accessed using df['Name']
print(df['Name'])

# The following line filters the DataFrame 'df' to include only rows where the 'Salary' column is greater than 5000.
# The result is assigned to 'filtered_df', which is a new DataFrame containing the filtered rows.
filtered_df = df[df['Salary'] > 5000]

# The following line prints the first 5 rows of 'filtered_df' to the console.
# This is useful for quickly inspecting the filtered data to ensure it meets our expectations.
print(filtered_df.head())

# Sort the DataFrame 'df' by the values in the 'Salary' column in descending order (largest to smallest)
sorted_df = df.sort_values(by='Salary', ascending=False)

# Print the first 5 rows of the sorted DataFrame
# We use the head() method to display the top 5 entries of sorted_df
print(sorted_df.head())

# Read data from a CSV file available at the given URL and store it in a DataFrame called sales_df
# The read_csv function fetches the data and structures it into a format suitable for analysis
sales_df = pd.read_csv('https://infinitepy.s3.amazonaws.com/samples/sales_data.csv')

# 'head()' is a built-in method in pandas DataFrame that returns the first n rows.
# By default, it returns the first 5 rows. You can specify a different number as an argument like 'head(10)' for the first 10 rows.
sales_df.head()

# The .info() method is called on 'sales_df', used to get a concise summary of the DataFrame

# The output will include:
# - The class type of the DataFrame
# - The number of non-null entries in each column
# - The column names and their data types (dtype)
# - Memory usage of the DataFrame

# This method is very useful for getting a quick overview of your data,
# which can aid in understanding its structure and identifying any potential data issues.

sales_df.info()

# Drop duplicate rows from the DataFrame 'sales_df' in place.
# This means any duplicate rows will be removed directly from the 'sales_df' object,
# and no copy of the DataFrame will be created.
sales_df.drop_duplicates(inplace=True)

# Fill any missing (NaN) values in the DataFrame 'sales_df' with 0.
# The 'inplace=True' parameter means that the DataFrame will be modified directly,
# without creating a copy.
sales_df.fillna(0, inplace=True)

# Use groupby() to group the data by the 'Region' column
# Then, chain .sum() to calculate the total sales for each region
total_sales_region = sales_df.groupby('Region')['Sales'].sum()

# Print the result which shows the total sales per region
print(total_sales_region)

# Group the sales data by 'Product' and sum the 'Sales' for each product.
top_products_sales = sales_df.groupby('Product')['Sales'].sum()

# Sort the summed sales in descending order to get the best selling products at the top.
top_products_sales_sorted = top_products_sales.sort_values(ascending=False)

# Select the top 5 products with the highest sales.
top_5_products_sales_sorted = top_products_sales_sorted.head(5)

# Print the result to see the names and sales of the top 5 products.
print(top_5_products_sales_sorted) 

# Export the cleaned sales DataFrame to a CSV file
# 'index=False' specifies not to write the row index to the file.
sales_df.to_csv('cleaned_sales_data.csv', index=False)

# Export the total sales per region DataFrame to a CSV file
total_sales_region.to_csv('total_sales_region.csv')

# Export the top 5 products by sales DataFrame to a CSV file
top_5_products_sales_sorted.to_csv('top_products.csv')