One Hot Encoding using numpy [duplicate]

Answer 1

Use np.identity or np.eye. You can try something like this with your input i, and the array size s:

np.identity(s)[i:i+1]

For example, print(np.identity(5)[0:1]) will result:

[[ 1.  0.  0.  0.  0.  0.  0.  0.  0.  0.]]

If you are using TensorFlow, you can use tf.one_hot: https://www.tensorflow.org/api_docs/python/array_ops/slicing_and_joining#one_hot