/leftypol/ - Leftist Politically Incorrect

#install these
#pip install xgboost pandas numpy scikit-learn

import pandas as pd
import numpy as np
import xgboost as xgb
import matplotlib.pyplot as plt
from sklearn.metrics import mean_squared_error
import warnings

# Suppress warnings for cleaner output
warnings.filterwarnings('ignore')

# ==========================================
# 1. THE SIMULATION (The Potato Market)
# ==========================================
def generate_potato_data(days=730):
    """
    Simulates 2 years of daily potato demand.
    Unlike electricity (hourly), food is daily/weekly.
    Factors:
    - Price Elasticity (Price goes up, demand goes down)
    - Weekly Cycle (People buy groceries on weekends)
    - Seasonal/Holiday Spikes (Thanksgiving, Christmas)
    """
    np.random.seed(42)
    dates = pd.date_range(start='2023-01-01', periods=days, freq='D')
    n = len(dates)

    # Factor A: Market Price (Fluctuates randomly)
    # Simulating a price between $0.50 and $1.50 per kg
    price = 1.0 + np.random.normal(0, 0.1, n).cumsum() * 0.05
    price = np.clip(price, 0.5, 2.0)

    # Factor B: Seasonality (Potatoes are winter food)
    # Cosine wave: High in winter, Low in summer
    seasonality = 1000 * np.cos(np.linspace(0, 2 * 2 * np.pi, n))

    # Factor C: The "Weekend Grocery Run"
    # Demand spikes on Saturday (5) and Sunday (6)
    day_of_week = dates.dayofweek
    weekend_bump = np.where(day_of_week >= 5, 2000, 0)

    # Factor D: The "Holiday Spike" (Thanksgiving/Christmas)
    # Nov (11) and Dec (12) get a massive boost
    month = dates.month
    holiday_bump = np.where((month == 11) | (month == 12), 3000, 0)

    # TOTAL DEMAND CALCULATION
    # Base Demand (10,000 kg) - Price Sensitivity + Seasons + Weekends + Holidays + Noise
    demand = (
        10000
        - (price * 2000)             # Price Elasticity (High price = Low demand)
        + seasonality
        + weekend_bump
        + holiday_bump
        + np.random.normal(0, 500, n) # Random noise
    )

    df = pd.DataFrame({