import numpy as np
import time
import os
import matplotlib.pyplot as plt #we might do some other tool later.
from ActionModel import ActionModel
from BisbasModel import BisbasModel
baseline_pos_expectancy=1
baseline_neg_expectancy=1
action_state_elicitations=10
# actions = [(ActionModel("Action" + str(i),0,0,baseline_pos_expectancy,baseline_neg_expectancy,1,1,1,0))
# for i in (range(1,action_state_elicitations+1))]
bb=BisbasModel.asSimpleModel(action_state_elicitations=4,
baseline_pos_expectancy=1,
baseline_neg_expectancy=1,
baseline_action_threshold=3,
learning_rate=0.1,
action_tendency_persistence=0.9)
#keep it simple - map each action to the corresponding state
bb.action_elicitor = np.identity(len(bb.actions))/10
bb.action_state = np.identity(len(bb.actions))/10
bb.actions[0].name="Eat"
bb.actions[1].name="Study"
bb.actions[2].name="Approach Partner"
bb.actions[3].name="Meet Friends"
#bb.actions[4].name="Be Happy"
#let's make the model hungry...
__author__ = 'benjaminsmith' from BisbasModel import BisbasModel student_model = BisbasModel.asSimpleModel()
