Before we can begin training our neural network, we need to split the dataset into training and testing datasets. This will allow us to test our network after we are done training in order to determine how well it will generalize new data. This step is incredibly easy when using the train_test_split() function provided by scikit-learn. So, we reserve some of the data that we have to test so that we can see how well our algorithm is performing.
- To do that, we will import the model_selection package from sklearn. From this package, we're going to use the train_test_split function. The following lines of code show us how to split the data into the required training and testing sets:
from sklearn import model_selection
# split the X and Y data into training and testing datasets
X_train, X_test, Y_train, Y_test = model_selection...