kevanoullio / apples-to-apples-agent

Apples-to-Apples game with AI agent using various natural language processing and machine learning techniques.
GNU General Public License v3.0
0 stars 2 forks source link

AssertionError: x_vector_array must have more than 1 row #29

Closed kevanoullio closed 3 months ago

kevanoullio commented 3 months ago

Error occurs during train_model() phase of game_loop().

MORE INFO:

the alternate linear regression algorithm I made uses the scipy library, I think it outputs the same slope and bias vectors (not sure) but it needs more than 1 vector to run the linear regression, the existing algorithm (which is commented out) I think can use just one.

But the way the choose red and choose winning red apple functions work is it works off of training data, so you need to train the specific AI archetype first and it should solve at least part of the problem

Further testing is required, but I'm assuming the way the functions work right now is that they need to do the same check for if 2 chosen_apple objects exist if not it grabs enough to make 2 from the trained data, then continues on to the linear regression stuff