1.py

import dask.dataframe as dd

# Load the CSV file
dataframe = dd.read_csv("/Users/thecreator/Downloads/Trips_by_Distance.csv", assume_missing=True)

# Check columns in the DataFrame
columns = dataframe.columns
print("Columns in the DataFrame:", columns)

# Ensure 'Year of Date' column is present or handle its absence gracefully
if 'Year of Date' in columns:
    # Remove rows with any missing values
    cleaned_dataframe = dataframe.dropna()
    
    # Compute the number of unique values in the 'Year of Date' column
    unique_year_count = cleaned_dataframe['Year of Date'].nunique().compute()
    print(f"Unique 'Year of Date' values: {unique_year_count}")
    
    # Calculate the mean of 'Trips 1-25 Miles' for each year
    mean_trips_per_year = cleaned_dataframe.groupby('Year of Date')['Trips 1-25 Miles'].mean().compute()
    print("Average 'Trips 1-25 Miles' per 'Year of Date':")
    print(mean_trips_per_year)
else:
    print("The 'Year of Date' column is missing from the DataFrame or has a different name.")