def run(p0_strategy, p1_strategy):
n_simulation = 30
data = []
tqdm.write("\n********* {} VS {} *************".format(
p0_strategy, p1_strategy))
for r in (0.25, 0.5):
tqdm.write("Computing {} radius simulations.".format(r))
for _ in tqdm(range(n_simulation)):
m = __old__.model.simulation.Model(r=r,
p0_strategy=p0_strategy,
p1_strategy=p1_strategy)
results = m.run()
b = BackupSimulation(*results, r)
data.append(b)
tqdm.write("*********************************")
file_name = "data/simulation_{}_vs_{}.p".format(p0_strategy, p1_strategy)
backup.save(obj=data, file_name=file_name)
def get_fit_b_all(args):
# get all strategies
s = list(run_simulation.treat_args("all"))
# store strategies
strategies = {k: v for k, v in zip(range(len(s)), s)}
reversed_strategies = {k: v for v, k in strategies.items()}
file_name = "data/fit_simulation_all.p"
if not os.path.exists(file_name) or args.do_it_again:
backups = []
for strategy in strategies.values():
args.p0_strategy, args.p1_strategy = strategy
backups.append(
get_fit(
force=args.force,
p0_strategy=args.p0_strategy,
p1_strategy=args.p1_strategy,
softmax=args.softmax,
reversed_strategies=reversed_strategies,
)
)
backup.save(obj=backups, file_name=file_name)
else:
backups = backup.load(file_name=file_name)
return backups, strategies
def get_all_backup_round_profiler(force, strategies):
backups = backup.get_data(force)
backups = [b for b in backups if b.pvp]
profiler = RoundProfiler(strategies=strategies, const=200, force=force)
profiler_backup = BackupRoundProfiler(size_player=len(backups * 2),
size_round=len(backups),
strategies=strategies)
tqdm.write("Profiling rounds...")
with tqdm(total=len(backups * 2)) as pbar:
i = 0
for rd_idx, b in enumerate(backups):
for player in (0, 1):
# Register information
profiler_backup.score[i] = np.sum(b.profits[:, player])
profiler_backup.user_id[i] = b.user_id[player]
profiler_backup.room_id[i] = b.room_id
profiler_backup.firm_id[i] = player
i += 1
pbar.update()
# Save round's radius
profiler_backup.round_id[rd_idx] = b.round_id
profiler_backup.r[rd_idx] = b.r
profiler_backup.display_opponent_score[
rd_idx] = b.display_opponent_score
# Prepare means to compare
means = {
"price":
np.mean(b.prices[:, :]),
"score":
np.mean(b.profits[:, :]),
"distance":
np.mean(
np.absolute(b.positions[:, 0] - b.positions[:, 1]) / 21)
}
# Compare means with each strategies means
for k, v in strategies.items():
profiler_backup.fit_scores[rd_idx,
k] = profiler.score(r=b.r,
means=means,
strategy=v)
backup.save(profiler_backup, "data/round_profiler_all.p")
return profiler_backup
def get_fit(force):
backups = backup.get_data(force)
backups = [b for b in backups if b.pvp]
m = {
0.25: score.Score(r=0.25),
0.50: score.Score(r=0.5)
}
fit_backup = BackupFit(size=len(backups*2))
with tqdm(total=len(backups*2)) as pbar:
i = 0
for b in backups:
for player in (0, 1):
# Register information
fit_backup.display_opponent_score[i] = b.display_opponent_score
fit_backup.r[i] = b.r
fit_backup.score[i] = np.sum(b.profits[:, player])
fit_backup.user_id[i] = b.user_id[player]
fit_backup.room_id[i] = b.room_id
fit_backup.round_id[i] = b.round_id
fit_backup.firm_id[i] = player
# Compute score
kwargs = {
"dm_model": m[b.r],
"firm_id": player,
"active_player_t0": b.active_player_t0,
"positions": b.positions,
"prices": b.prices,
"t_max": b.t_max
}
for str_method in score.Score.names:
rm = RunModel(**kwargs, str_method=str_method)
sc = rm.run()
fit_backup.fit_scores[str_method][i] = sc
tqdm.write("[id={}, r={:.2f}, s={}] [{}] score: {:.2f}".format(
i, b.r, int(b.display_opponent_score), str_method, sc))
i += 1
pbar.update(1)
tqdm.write("\n")
backup.save(fit_backup, "data/fit.p")
return fit_backup
def save_filtered_data():
backups = backup.load_data_from_db()
means = {
k: v for k, v in zip((0.25, 0.5), _get_bot_mean_profits("random", "profit"))
}
filtered_backups = []
for b in backups:
for player_id in (0, 1):
cond = np.mean(b.profits[:, player_id]) > means[b.r]
if cond:
filtered_backups.append(b)
backup.save(obj=filtered_backups, file_name="data/filtered_data.p")
def get_profile_all(args):
strategies = {
0: ("profit", "profit"),
1: ("competition", "competition"),
}
file_name = "data/round_profiler_all.p"
if not os.path.exists(file_name) or args.do_it_again:
backups = get_all_backup_round_profiler(args.force, strategies)
backup.save(obj=backups, file_name=file_name)
else:
backups = backup.load(file_name=file_name)
return backups, strategies
def main(args):
if not args.all:
run_simulation.treat_args(args.p0_strategy, args.p1_strategy)
file_name = "data/simulation_{}_vs_{}.p".format(args.p0_strategy, args.p1_strategy)
backups = run_simulation.backup_simulation(file_name, args)
individual_plot(backups, args.p0_strategy, args.p1_strategy)
else:
# get all strategies
s = list(run_simulation.treat_args("all"))
# store strategies
strategies = {k: v for k, v in zip(range(len(s)), s)}
reversed_strategies = {k: v for v, k in strategies.items()}
file_name = "data/simulation_all.p"
if not os.path.exists(file_name) or args.force:
backups = []
for strategy in strategies.values():
args.p0_strategy, args.p1_strategy = strategy
file_name = "data/simulation_{}_vs_{}.p".format(args.p0_strategy, args.p1_strategy)
backups += run_simulation.backup_simulation(file_name=file_name, args=args)
backup.save(obj=backups, file_name=file_name)
else:
backups = backup.load(file_name=file_name)
# Finally plot all the data
all_plot(backups, strategies, reversed_strategies)
def get_fit(force, p0_strategy, p1_strategy, softmax, reversed_strategies=None):
file_name = "data/simulation_{}_vs_{}.p".format(p0_strategy, p1_strategy)
if not os.path.exists(file_name) or force:
run_simulation.main(
p0_strategy=p0_strategy,
p1_strategy=p1_strategy
)
backups = backup.load(file_name)
m = {
0.25: fit.Model(r=0.25),
0.50: fit.Model(r=0.5)
}
temp_c = []
prediction_accuracy_c = []
temp_p = []
prediction_accuracy_p = []
r = []
score = []
strategy = []
idx_strategy = []
tqdm.write("Creating fit backup file...")
for b in tqdm(backups):
for player in (0, 1):
kwargs = {
"dm_model": m[b.r],
"str_method": "p_profit",
"firm_id": player,
"active_player_t0": b.active_player_t0,
"positions": b.positions,
"prices": b.prices,
"t_max": b.t_max
}
if not softmax:
# --- Profit based ---- #
rm = RunModel(**kwargs)
p = rm.run(temp=None) * -1
temp_p.append(-1)
prediction_accuracy_p.append(p)
# --- Competition based --- #
kwargs["str_method"] = "p_competition"
rm = RunModel(**kwargs)
c = rm.run(temp=None) * -1
temp_c.append(-1)
prediction_accuracy_c.append(c)
else:
# --- Profit based ---- #
best_temp = optimize_model(**kwargs)
rm = RunModel(**kwargs)
p = rm.run(temp=best_temp) * -1
temp_p.append(best_temp)
prediction_accuracy_p.append(p)
# --- Competition based --- #
kwargs["str_method"] = "p_competition"
best_temp = optimize_model(**kwargs)
rm = RunModel(**kwargs)
c = rm.run(temp=best_temp) * -1
temp_c.append(best_temp)
prediction_accuracy_c.append(c)
r.append(b.r)
score.append(np.sum(b.profits[:, player]))
strategy.append(p0_strategy if not player else p1_strategy)
if reversed_strategies:
idx_strategy.append(reversed_strategies[(p0_strategy, p1_strategy)])
fit_b = BackupFit(
temp_c=np.array(temp_c),
temp_p=np.array(temp_p),
prediction_accuracy_p=np.array(prediction_accuracy_p),
prediction_accuracy_c=np.array(prediction_accuracy_c),
r=np.array(r),
score=np.array(score),
strategy=np.array(strategy),
idx_strategy=np.array(idx_strategy)
)
file_name = "data/fit_simulation_{}_vs_{}.p".format(p0_strategy, p1_strategy)
backup.save(fit_b, file_name)
return fit_b
