Overview¶

In the 10x series of notebooks, we will look at Time Series modeling in pycaret using univariate data and no exogenous variables. We will use the famous airline dataset for illustration. Our plan of action is as follows:

Perform EDA on the dataset to extract valuable insight about the process generating the time series. (Covered in this notebook)
Model the dataset based on exploratory analysis (univariable model without exogenous variables).
Use an automated approach (AutoML) to improve the performance.
User customizations, potential pitfalls and how to overcome them.

def what_is_installed():
    from pycaret import show_versions
    show_versions()

try:
    what_is_installed()
except ModuleNotFoundError:
    !pip install pycaret-ts-alpha
    what_is_installed()

System:
    python: 3.8.12 (default, Oct 12 2021, 03:01:40) [MSC v.1916 64 bit (AMD64)]
executable: C:\Users\Nikhil\.conda\envs\pycaret_dev_sktime_0p10p0\python.exe
   machine: Windows-10-10.0.19044-SP0

Python dependencies:
          pip: 21.2.2
   setuptools: 60.8.2
      pycaret: 3.0.0
      sklearn: 1.0.2
       sktime: 0.10.1
  statsmodels: 0.12.2
        numpy: 1.21.5
        scipy: 1.7.3
       pandas: 1.4.2
   matplotlib: 3.5.1
       plotly: 5.5.0
       joblib: 1.0.1
        numba: 0.55.1
       mlflow: 1.23.1
     lightgbm: 3.3.2
      xgboost: Not installed
     pmdarima: 1.8.4
        tbats: Installed but version unavailable
      prophet: 1.0
      tsfresh: Not installed

import time
import numpy as np
import pandas as pd

from pycaret.datasets import get_data
from pycaret.time_series import TSForecastingExperiment

y = get_data('airline', verbose=False)

# We want to forecast the next 12 months of data and we will use 3 fold cross-validation to test the models.
fh = 12 # or alternately fh = np.arange(1,13)
fold = 3

# Global Plot Settings
fig_kwargs={'renderer': 'notebook'}

Exploratory Analysis¶

pycaret Time Series Forecasting module provides a conventient interface for perform exploratory analysis using plot_model.

NOTE:

Without an estimator argument, plot_model will plot using the original dataset. We will cover this in the current notebook.
If an estimator (model) is passed to plot_model, the the plots are made using the model data (e.g. future forecasts, or analysis on insample residuals). We will cover this in a subsequent notebook.

Let's see how this works next.

First, we will plots the original dataset.

eda = TSForecastingExperiment()
eda.setup(data=y, fh=fh, fig_kwargs=fig_kwargs)

<pycaret.time_series.forecasting.oop.TSForecastingExperiment at 0x27999bbb910>

# NOTE: This is the same as `eda.plot_model(plot="ts")`
eda.plot_model()

	Description	Value
0	session_id	5291
1	Target	Number of airline passengers
2	Approach	Univariate
3	Exogenous Variables	Not Present
4	Data shape	(144, 1)
5	Train data shape	(132, 1)
6	Test data shape	(12, 1)
7	Fold Generator	ExpandingWindowSplitter
8	Fold Number	3
9	Enforce Prediction Interval	False
10	Seasonal Period(s) Tested	12
11	Seasonality Present	True
12	Seasonalities Detected	[12]
13	Primary Seasonality	12
14	Target Strictly Positive	True
15	Target White Noise	No
16	Recommended d	1
17	Recommended Seasonal D	1
18	Missing Values	0
19	Preprocess	True
20	CPU Jobs	-1
21	Use GPU	False
22	Log Experiment	False
23	Experiment Name	ts-default-name
24	USI	3627