Python script for showing a histogram of the file creation times of all files in a directory.

oldest-newest.py

import os
import time
import matplotlib.pyplot as plt
from datetime import datetime

def format_time(epoch_time):
    return time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(epoch_time))

# Global figure and axis for single window
fig, ax = None, None

def init_plot():
    global fig, ax
    if fig is None:
        fig, ax = plt.subplots(figsize=(12, 6))
        plt.ion()  # Turn on interactive mode
        plt.show(block=False)

def update_histogram(creation_times):
    global fig, ax
    
    if not creation_times:
        return
    
    init_plot()
    
    # Clear previous plot
    ax.clear()
    
    # Convert timestamps to datetime objects for better binning
    dates = [datetime.fromtimestamp(ts) for ts in creation_times]
    
    # Create histogram
    ax.hist(dates, bins=50, alpha=0.7, color='skyblue', edgecolor='black')
    ax.set_title(f'File Creation Time Distribution ({len(creation_times)} files)')
    ax.set_xlabel('Creation Date')
    ax.set_ylabel('Number of Files')
    ax.tick_params(axis='x', rotation=45)
    ax.grid(True, alpha=0.3)
    
    # Update the display
    plt.tight_layout()
    plt.draw()
    plt.pause(0.01)

def find_file_times(base_path):
    creation_times = []
    last_update_time = 0
    files_processed = 0

    for root, dirs, files in os.walk(base_path):
        for file in files:
            filepath = os.path.join(root, file)
            try:
                ctime = os.path.getctime(filepath)
                creation_times.append(ctime)
                files_processed += 1
            except OSError:
                continue

            current_time = time.time()
            # Update histogram no more than once per second
            if current_time - last_update_time >= 1.0:
                print(f"Processed {files_processed} files. Updating histogram...")
                update_histogram(creation_times)
                last_update_time = current_time

    # Final update
    print(f"Scan complete. Total files processed: {files_processed}")
    update_histogram(creation_times)
    
    if creation_times:
        oldest = min(creation_times)
        newest = max(creation_times)
        print(f"\nTime range:")
        print(f"  Oldest: {format_time(oldest)}")
        print(f"  Newest: {format_time(newest)}")

if __name__ == "__main__":
    base_directory = input("Enter the directory to scan: ").strip()
    if os.path.isdir(base_directory):
        find_file_times(base_directory)
        # Keep the plot window open
        input("Press Enter to close...")
    else:
        print("Invalid directory.")