Validating array for optimal neural network performance

A little bit of validation goes a long way in ensuring that our array is normalized for optimal performance within our upcoming neural network.  

Getting ready

This section will require a bit of numpy magic using the numpy.stack() function.

How to do it...

The following steps walk through validating that our array has been normalized.

1. Execute the following step to print the mean and standard deviation of array inputs:

print('standard deviation')
print(round(X[:,0].std(axis=0),0))
print('mean')
print(round(X[:,0].mean(axis=0),0))

2. Execute the following script to combine height, weight, and gender into one array, data_array:

data_array = np.column_stack((X[:,0], X[:,1],y))

How it works...

This section explains how the array is validated and constructed for optimal future use within the neural network.

1. The new mean of the height should be 0 and the standard deviation should be 1. This can be seen in the following screenshot:

2. This is confirmation of...