Train-test splits
In this exercise you are going to take the candy production dataset and split it into a train and a test set. Like you understood in the video exercise, the reason to do this is so that you can test the quality of your model fit when you are done.
The candy production data set has been loaded in for you as candy
already and pyplot
has been loaded in as plt
.
This exercise is part of the course
ARIMA Models in Python
Exercise instructions
- Split the time series into train and test sets by slicing with
datetime
indexes. Take the train set as everything up to the end of 2006 and the test set as everything from the start of 2007. - Make a
pyplot
axes using thesubplots()
function. - Use the DataFrame's
.plot()
method to plot the train and test sets on the axisax
.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Split the data into a train and test set
candy_train = candy.____
candy_test = candy.____
# Create an axis
fig, ax = ____
# Plot the train and test sets on the axis ax
candy_train.____(ax=____)
candy_test.____(ax=____)
plt.show()