Components of Time Series

A Time Series can usually be broken down into a handful of underlying components, each capturing a different kind of pattern in the data.

Trend

The long-term upward or downward movement in the data over an extended period, ignoring short-term fluctuations.

Seasonality

Regular, repeating patterns tied to a fixed calendar period - such as higher retail sales every December or increased electricity usage every summer.

Cyclic Variation

# Unlike seasonality, cycles don't have a fixed period
# Example: economic boom-and-bust cycles lasting several years,
# with no exact repeating interval

Irregular (Residual) Variation

The remaining random noise left after trend, seasonality, and cyclic patterns have been accounted for - often caused by unpredictable, one-off events.

Decomposing a Time Series in Python

from statsmodels.tsa.seasonal import seasonal_decompose

result = seasonal_decompose(df["Sales"], model="additive", period=12)
result.plot()

An "additive" model assumes components simply sum together, while a "multiplicative" model assumes they multiply - the right choice depends on whether seasonal swings grow with the trend.

Coming Up Next

Next, you'll learn practical techniques for visualizing Time Series data.