🟢 Time Series Analysis with Exponential Smoothing – Forecasting Monthly Sunspot Numbers

AIVIA Project Engine Recommender & Decision Systems
, , , , , ,
1

Time Series Analysis with Exponential Smoothing – Forecasting Monthly Sunspot Numbers

Objective

Create a forecasting model to predict monthly sunspot numbers using basic time series analysis techniques.


Learning Outcomes

By completing this project, you will:

  • Learn to visualize time series data
  • Understand seasonal decomposition
  • Implement simple exponential smoothing
  • Evaluate forecasting models

Prerequisites

  • Basic Python skills
  • Basic statistics understanding
  • Familiarity with pandas and matplotlib

Dataset Details

  • Monthly Sunspot Numbers Dataset: Link
  • Size: ~30KB
  • Monthly counts of sunspots from 1749 to 1983
  • Features: Month, Sunspot Count

Tools Required

# Core libraries
pip install pandas numpy matplotlib

# Statistical modeling
pip install statsmodels

Project Structure

sunspot_forecasting/
│
├── data/
│   └── monthly-sunspots.csv
│
├── src/
│   ├── data_processing.py
│   ├── model.py
│   └── evaluation.py
│
└── notebooks/
    ├── data_exploration.ipynb
    ├── time_series_decomposition.ipynb
    ├── model_implementation.ipynb

Steps and Tasks

1. Data Acquisition and Exploration

Load and visualize the sunspot data.

import pandas as pd
import matplotlib.pyplot as plt

# Load data
df = pd.read_csv('monthly-sunspots.csv', parse_dates=['Month'], index_col='Month')

# Plot time series
plt.figure(figsize=(12, 6))
plt.plot(df['Sunspots'])
plt.title('Monthly Sunspot Numbers')
plt.xlabel('Year')
plt.ylabel('Sunspot Count')
plt.show()

2. Time Series Decomposition

Analyze the components of the time series.

from statsmodels.tsa.seasonal import seasonal_decompose

# Decompose the time series
decomposition = seasonal_decompose(df['Sunspots'], model='additive', period=12)
decomposition.plot()
plt.show()

3. Forecasting with Simple Exponential Smoothing

Implement and evaluate a simple forecasting model.

from statsmodels.tsa.holtwinters import SimpleExpSmoothing

# Split data
train = df['Sunspots'][:-24]
test = df['Sunspots'][-24:]

# Fit the model
model = SimpleExpSmoothing(train).fit()

# Forecast
forecast = model.forecast(len(test))

# Plot forecast vs actual
plt.figure(figsize=(12, 6))
plt.plot(test.index, test, label='Actual')
plt.plot(test.index, forecast, label='Forecast', color='red')
plt.legend()
plt.show()

4. Model Evaluation

Assess the forecasting accuracy.

from sklearn.metrics import mean_squared_error

mse = mean_squared_error(test, forecast)
print(f'Mean Squared Error: {mse:.2f}')