from mab import arm
from mab import scorer as sc
import time
import pickle
is_post_per_subject = False
is_update_db = True
param = common_params.CommonParams()
bot = slack_news_bot.SlackNewsBot(param, is_update_db)
df = bot.df
num_arms = param.num_news
path = 'log/mab.log'
if util_funcs.check_file(path) is False:
algorithm = bd.EpsilonGreedyAlgorithm(num_arms, 0.1)
trials = 0
with open(path, 'wb') as f:
pickle.dump(algorithm, f)
pickle.dump(trials, f)
print("MAB started")
else:
with open(path, 'rb') as f:
algorithm = pickle.load(f)
trials = pickle.load(f)
print("MAB object loaded")
print(trials)
selected_arm = algorithm.select_arm()
if is_update_db:
from mab import ArticleArms
from mab import scorer as sc
import numpy as np
import time
num_trials = 2000
print('total number of trials: {}'.format(num_trials))
arms = ArticleArms('yahoo_r6_full.db')
num_arms = arms.get_num_arms()
print('number of arms: {}'.format(num_arms))
param_c = 10000000 # very large c: not assuming mortality
# param_c = None
algorithms = [
bd.EpsilonGreedyAlgorithm(num_arms, 0.1, c=param_c),
bd.UCB1Algorithm(num_arms, c=param_c)
]
num_algorithms = len(algorithms)
print('number of algorithms: {}'.format(num_algorithms))
total_cumulative_rewards = np.zeros(num_algorithms)
total_cumulative_logging_rewards = np.zeros(num_algorithms)
total_cumulative_diff_rewards = np.zeros(num_algorithms)
trials = np.zeros(num_algorithms)
num_arms_added = 0
removing_arms_indices = []
print_point_divisor = np.power(10, np.ceil(np.log10(num_trials)) - 2)
print_num_trials_divisor = print_point_divisor * 10
