Säsongsberoende tidsserier

ARIMA-modeller i Python

James Fulton

Climate informatics researcher

Säsongsdata

time series = trend + seasonal + residual

# Import 
from statsmodels.tsa.seasonal import seasonal_decompose

# Decompose data
decomp_results = seasonal_decompose(df['IPG3113N'], period=12)

type(decomp_results)

statsmodels.tsa.seasonal.DecomposeResult

# Plot decomposed data
decomp_results.plot()
plt.show()

# Subtract long rolling average over N steps
df = df - df.rolling(N).mean()

# Drop NaN values
df = df.dropna()

# Create figure
fig, ax = plt.subplots(1,1, figsize=(8,4))

# Plot ACF
plot_acf(df.dropna(), ax=ax, lags=25, zero=False)
plt.show()

ARIMA-modeller i Python