code implementation on random values

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error
import joblib

np.random.seed(42)
n_samples = 500

data = pd.DataFrame({
    "day_of_week": np.random.randint(0, 7, n_samples),
    "month": np.random.randint(1, 13, n_samples),
    "local_event": np.random.choice([0, 1], n_samples),
    "competitor_avg_price": np.random.randint(50, 200, n_samples),
    "occupancy_last_week": np.random.uniform(0.3, 1.0, n_samples),
    "days_to_booking": np.random.randint(0, 90, n_samples),
    "base_price": np.random.randint(60, 150, n_samples),
})

data["optimal_price"] = (
    data["base_price"]
    + (data["local_event"] * 1000)
    + ((1 - data["occupancy_last_week"]) * 1000)
    + np.random.normal(0, 5, n_samples)
)

features = data.drop("optimal_price", axis=1)
target = data["optimal_price"]

X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2)

model = RandomForestRegressor(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

predictions = model.predict(X_test)
mae = mean_absolute_error(y_test, predictions)
print(f"Mean Absolute Error: rs{mae:.2f}")

joblib.dump(model, "pricepilot_model.pkl")


  
  
  # Step 6: Sample Prediction
sample_input = pd.DataFrame([{
    "day_of_week": 5,  # Saturday
    "month": 7,  # July
    "local_event": 1,
    "competitor_avg_price": 140,
    "occupancy_last_week": 0.6,
    "days_to_booking": 10,
    "base_price": 100,
}])

predicted_price = model.predict(sample_input)[0]
print(f"Suggested Price for Listing: rs{predicted_price:.2f}")