Can you make a Python script with scikit learn which adapts a deep NN model to a real air heater using the time series of data in time interval from 70 to 220 sec in the following csv file?   

https://techteach.no/control/python/air_heater_v01.csv

In the file:

Time step is 0.1 s.  
# Column 0: t [s] (time in seconds) 
# Column 1: u [V] (input signal)  
# Column 2: T [deg C] (output)  

Please load the data into Python workspace with numpy loadtxt, not pandas.

You can use 60 % of data for training, 20 % for testing (validation), and 20 % for recursive predictions (simulations). 

Please plot as follows: subplot(2,3,1): train T and predicted T. subplot(2,3,2): test T and predicted T. subplot(2,3,3): simulated (recursive prediction) T, and actual T. subplot(2,3,4): training input u. subplot(2,3,5): test input u. subplot(2,3,6): input u used for simulation. In all subplots: time (t) in sec should be along the abscissa axes.