What is seasonal ARIMA model How to use it?
This recipe explains what is seasonal ARIMA model is and helps you use it
Recipe Objective
A seasonal ARIMA model is formed by including additional seasonal terms in the ARIMA models. The additional seasonal terms are simply multiplied by the non-seasonal terms.
So this recipe is a short example on What is seasonal ARIMA model and how to use it. Let's get started.
Step 1 - Import the library
import numpy as np
import pandas as pd
from statsmodels.tsa.seasonal import seasonal_decompose
import matplotlib.pyplot as plt
Let's pause and look at these imports. Numpy and pandas are general ones. Here, seasonal_decompose will help us in understanding the seasonilty of data.
Step 2 - Setup the Data
df = pd.read_csv('https://raw.githubusercontent.com/selva86/datasets/master/a10.csv', parse_dates=['date']).set_index('date')
Here, we have used one time series data from github. Also, we have set our index to date.
Now our dataset is ready.
Step 3 - Plotting the pattern
decomposition = seasonal_decompose(df.value, freq=12)
fig = plt.figure()
fig = decomposition.plot()
fig.set_size_inches(20, 10)
Here, we have broken our datset using seasonal_decompose into trend, residual and seasonal. Residual is the stationary pattern and will almost remain constant. Seasonal is what our seasonal pattern will be. Trend is just our upward or downward movement with time.
Step 4 - Creating Seasonal Dataframe
trend = decomposition.trend
seasonal = decomposition.seasonal
residual = decomposition.resid
print(seasonal)
Apart from visualizing our pattern, we have produced various dataframes based on their patter. Finally, we have printed down our seasonal dataframe.
Step 5 - Lets look at our dataset now
Once we run the above code snippet, we will see:
Srcoll down the ipython file to visualize the results.
Seasonal, Residual and Trend is visible. Also, we have produced our seasonal dataset in one separte dataframe for further analysis if needed.
What Users are saying..
Ray han
I think that they are fantastic. I attended Yale and Stanford and have worked at Honeywell,Oracle, and Arthur Andersen(Accenture) in the US. I have taken Big Data and Hadoop,NoSQL, Spark, Hadoop... Read More