Data Partitioning: Split the data into train and test. The training data should contain $80\%$ of the full data and the test data should contain the most recent $20\%$ of the full data. Same data partition as used in the last question.

Build a Simple Exponential Smoothing model $[$set the 'initialization$\_$method' parameter value as 'estimated' and when using the $\text{'}.$fit' command, please do make sure that the parameter is optimized$=$True$]$ and calculate the Root Mean Squared Error on the test data. For this particular model, take logarithm on both the training and test data.

Hint: Use the function np$.$log$(),$ where numpy has been imported under the alias np$.$