Time series components (trend, seasonality) in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to extract the trend component from a time series using moving average.

ML Python

trend = time_series.rolling(window=[1]).mean()

Drag options to blanks, or click blank then click option'

A12

B1

C3

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using window size 1 does not smooth the data.

Using window size 0 causes an error.

The moving average window size of 3 smooths short-term fluctuations to reveal the trend.

2fill in blank

medium

Complete the code to decompose a time series into trend, seasonality, and residual using statsmodels.

ML Python

from statsmodels.tsa.seasonal import seasonal_decompose
result = seasonal_decompose(time_series, model=[1], period=12)

Drag options to blanks, or click blank then click option'

A"additive"

B"multiplicative"

C"linear"

D"exponential"

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'multiplicative' when seasonal effects are not proportional.

Using unsupported model types like 'linear'.

The 'additive' model assumes components add together: observed = trend + seasonality + residual.

3fill in blank

hard

Fix the error in the code to plot the seasonal component after decomposition.

ML Python

import matplotlib.pyplot as plt
result = seasonal_decompose(time_series, model="additive", period=12)
plt.plot(result.[1])
plt.show()

Drag options to blanks, or click blank then click option'

Aseasonal

Btrend

Cobserved

Dresidual

Attempts:

3 left

💡 Hint

Common Mistakes

Plotting trend or residual instead of seasonal component.

Using an attribute that does not exist.

The seasonal component is accessed with result.seasonal to plot seasonality.

4fill in blank

hard

Fill both blanks to create a dictionary of time series components with keys 'trend' and 'seasonality'.

ML Python

components = {"trend": result.[1], "seasonality": result.[2]

Drag options to blanks, or click blank then click option'

Atrend

Bseasonal

Cresidual

Dobserved

Attempts:

3 left

💡 Hint

Common Mistakes

Using residual or observed instead of trend or seasonal.

Mixing up keys and values.

The trend and seasonal components are accessed via result.trend and result.seasonal.

5fill in blank

hard

Fill all three blanks to compute the residual component by subtracting trend and seasonality from the original series.

ML Python

residual = time_series - result.[1] - result.[2]
print(residual.[3]())

Drag options to blanks, or click blank then click option'

Atrend

Bseasonal

Cdropna

Dfillna

Attempts:

3 left

💡 Hint

Common Mistakes

Using fillna() instead of dropna(), which fills missing values instead of removing them.

Mixing up trend and seasonal in subtraction.

Residual is original minus trend and seasonal. Use dropna() to remove missing values after subtraction.