2. Generate 100 random coordinate points (2D data representing height (h) and weight (w)) and label them a class: 'kid'. Follow exact same procedure for generating 100 data for another class: 'adult'. Make sure that they are not completely separated. Train 80% them using Gaussian classify and compute their prior probabilities (for both classes). Test the models using remaining 20% of the data and check whether you build your model right (hint: posterior probability can help you compute this). It is required to have complete Python source code (in Jupyter Notebook) and submit your final pdf after compiling your code. 2. Generate 100 random coordinate points (2D data representing height (h) and weight (w)) and label them a class: 'kid'. Follow exact same procedure for generating 100 data for another class: 'adult'. Make sure that they are not completely separated. Train 80% them using Gaussian classify and compute their prior probabilities (for both classes). Test the models using remaining 20% of the data and check whether you build your model right (hint: posterior probability can help you compute this). It is required to have complete Python source code (in Jupyter Notebook) and submit your final pdf after compiling your code