forecast.py

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from statsmodels.tsa.holtwinters import SimpleExpSmoothing
from sklearn.metrics import mean_squared_error

# Assuming df_list[100]['y_lag'] is your time series data
# Ensure it's a pandas Series for compatibility with SimpleExpSmoothing
data = pd.Series(df_list[100]['y_lag'])

N = 20  # Forecasting 20 steps into the future

# Range of alphas to explore
alphas = np.linspace(0.01, 1, 100)
mse_errors = []

# Try fitting models with different alphas
for alpha in alphas:
    model = SimpleExpSmoothing(data).fit(smoothing_level=alpha)
    predictions = model.fittedvalues
    mse = mean_squared_error(data, predictions)
    mse_errors.append(mse)

# Find the alpha with the lowest MSE
min_mse = min(mse_errors)
best_alpha = alphas[mse_errors.index(min_mse)]
print(f"Best Alpha: {best_alpha} with MSE: {min_mse}")

# Fit model with the best alpha
best_model = SimpleExpSmoothing(data).fit(smoothing_level=best_alpha)
forecast = best_model.forecast(steps=N)

# Add forecast to the plot
plt.figure(figsize=(10, 6))
plt.plot(data.index, data, label='Original Data')
plt.plot(best_model.fittedvalues.index, best_model.fittedvalues, label='Fitted Values')
forecast_index = np.arange(len(data), len(data) + N)
plt.plot(forecast_index, forecast, label='Forecast', marker='o', linestyle='--', color='red')
plt.legend()
plt.title("Simple Exponential Smoothing Forecast")
plt.xlabel("Time")
plt.ylabel("Value")
plt.show()

from statsmodels.tsa.holtwinters import ExponentialSmoothing

Assuming data is your time series

model_holt = ExponentialSmoothing(data, trend='add').fit()

forecast_holt = model_holt.forecast(20)

Plotting

plt.figure(figsize=(10, 6))
plt.plot(data.index, data, label='Original Data')
plt.plot(forecast_holt.index, forecast_holt, label='Holt’s Linear Trend Forecast', marker='o', linestyle='--', color='green')
plt.legend()
plt.title("Holt’s Linear Trend Method Forecast")
plt.xlabel("Time")
plt.ylabel("Value")
plt.show()