# agentBuying.py - Paper-buying agent
# AIFCA Python code Version 0.9.7 Documentation at http://aipython.org
# Download the zip file and read aipython.pdf for documentation

# Artificial Intelligence: Foundations of Computational Agents http://artint.info
# Copyright 2017-2023 David L. Poole and Alan K. Mackworth
# This work is licensed under a Creative Commons
# Attribution-NonCommercial-ShareAlike 4.0 International License.
# See: http://creativecommons.org/licenses/by-nc-sa/4.0/deed.en

import random
from agents import Agent, Environment, Simulate
from utilities import pick_from_dist

class TP_env(Environment):
    prices = [234, 234, 234, 234, 255, 255, 275, 275, 211, 211, 211,
    234, 234, 234, 234, 199, 199, 275, 275, 234, 234, 234, 234, 255,
    255, 260, 260, 265, 265, 265, 265, 270, 270, 255, 255, 260, 260,
    265, 265, 150, 150, 265, 265, 270, 270, 255, 255, 260, 260, 265,
    265, 265, 265, 270, 270, 211, 211, 255, 255, 260, 260, 265, 265,
    260, 265, 270, 270, 205, 255, 255, 260, 260, 265, 265, 265, 265,
    270, 270]
    max_price_addon = 20  # maximum of random value added to get price

    def __init__(self):
        """paper buying agent"""
        self.time=0
        self.stock=20
        self.stock_history = []  # memory of the stock history
        self.price_history = []  # memory of the price history

    def initial_percept(self):
        """return initial percept"""
        self.stock_history.append(self.stock)
        price = self.prices[0]+random.randrange(self.max_price_addon)
        self.price_history.append(price)
        return {'price': price,
                'instock': self.stock}

    def do(self, action):
        """does action (buy) and returns percept consiting of price and instock"""
        used = pick_from_dist({6:0.1, 5:0.1, 4:0.1, 3:0.3, 2:0.2, 1:0.2})
        # used = pick_from_dist({7:0.1, 6:0.2, 5:0.2, 4:0.3, 3:0.1, 2:0.1}) # uses more paper
        bought = action['buy']
        self.stock = self.stock+bought-used
        self.stock_history.append(self.stock)
        self.time += 1
        price = (self.prices[self.time%len(self.prices)] # repeating pattern
                 +random.randrange(self.max_price_addon) # plus randomness
                 +self.time//2)                          # plus inflation
        self.price_history.append(price)
        return {'price': price,
                'instock': self.stock}

class TP_agent(Agent):
    def __init__(self):
        self.spent = 0
        percept = env.initial_percept()
        self.ave = self.last_price = percept['price']
        self.instock = percept['instock']
        self.buy_history = []
        
    def select_action(self, percept):
        """return next action to caurry out
        """
        self.last_price = percept['price']
        self.ave = self.ave+(self.last_price-self.ave)*0.05
        self.instock = percept['instock']
        if self.last_price < 0.9*self.ave and self.instock < 60:
            tobuy = 48
        elif self.instock < 12:
            tobuy = 12
        else:
            tobuy = 0
        self.spent += tobuy*self.last_price
        self.buy_history.append(tobuy)
        return {'buy': tobuy}

env = TP_env()
ag = TP_agent()
sim = Simulate(ag,env)
#sim.go(90)
#ag.spent/env.time   ## average spent per time period

import matplotlib.pyplot as plt

class Plot_history(object):
    """Set up the plot for history of price and number in stock"""
    def __init__(self, ag, env):
        self.ag = ag
        self.env = env
        plt.ion()
        plt.xlabel("Time")
        plt.ylabel("Value")
        

    def plot_env_hist(self):
        """plot history of price and instock"""
        num = len(env.stock_history)
        plt.plot(range(num),env.price_history,label="Price")
        plt.plot(range(num),env.stock_history,label="In stock")
        plt.legend()
        #plt.draw()

    def plot_agent_hist(self):
        """plot history of buying"""
        num = len(ag.buy_history)
        plt.bar(range(1,num+1), ag.buy_history, label="Bought")
        plt.legend()
        #plt.draw()

#pl = Plot_history(ag,env)
#sim.go(90)
#pl.plot_env_hist()
#pl.plot_agent_hist()