# -*- coding: utf-8 -*-
"""
Created on Fri Jul 31 11:33:27 2026

@author: muhuri
"""

import pandas as pd
from datetime import datetime
import os

# ---------------------------------------------------------------------------
# Configuration
# ---------------------------------------------------------------------------
INPUT_CSV = r"C:\Explore\PythonBDM_YouTube\Output\YouTube_Videos_Classified.csv"
OUTPUT_FOLDER = r"C:\Explore\PythonBDM_YouTube\Output"

# ---------------------------------------------------------------------------
# Read the CSV file
# ---------------------------------------------------------------------------
df = pd.read_csv(INPUT_CSV)

print(df.columns)
print(df.columns.tolist())
  
for col in df.columns:
   print(col)
   
for i, col in enumerate(df.columns, start=1):
    print(f"{i:2d}. {col}")
  
# ---------------------------------------------------------------------------
# Generate frequency table for publicationyear
# ---------------------------------------------------------------------------
freq_table = (
    df["PublicationYear"]
    .value_counts(dropna=False)
    .sort_index()
    .rename_axis("Publication Year")
    .reset_index(name="Frequency")
)

# Display the frequency table
print("\nFrequency Table for Publication Year")
print(freq_table)
print(f"Total videos: {freq_table['Frequency'].sum():,}")

# ---------------------------------------------------------------------------
# Optional: Save frequency table to a CSV file
# ---------------------------------------------------------------------------
output_file = os.path.join(OUTPUT_FOLDER, "PublicationYear_Frequency.csv")
freq_table.to_csv(output_file, index=False)

print(f"\nFrequency table saved to:\n{output_file}")