def analysis_diff_ask_bid(dic):
diff_ask_bid = dic['A1']['askPrice1'] - dic['A1']['bidPrice1']
count = 0
for i in range(diff_ask_bid.shape[0]):
if diff_ask_bid[i] > 5000:
count += 1
diff_ask = dic['A1']['askPrice1'][i] - dic['A1']['askPrice1'][i -
1]
diff_bid = dic['A1']['bidPrice1'][i] - dic['A1']['bidPrice1'][i -
1]
print("%d %d = %d %d" %
(diff_ask_bid[i - 1], diff_ask_bid[i], diff_ask, diff_bid))
print("%d %f" % (count, float(count) / diff_ask_bid.shape[0]))
lib.plot(diff_ask_bid, pj("fig", "A1_diff_askPrice1_bidPrice1"))
Roda essas duas linhas se vc quiser brincar com a parte do plot
file = 'data.txt'
plot(file, scale=100)
'''
# //.......................................//
# //..........VARIAVES DE ENTRADA..........//
# //.......................................//
Kcal = 76.8 # Modulo Bulk dos minerais (calcita, dolomita, quartzo)
Kdol = 95.0
Kqtz = 37.0
Gcal = 32.0 # Modulo Shear dos minerais (calcita, dolomita, quartzo)
Gdol = 45.0
Gqtz = 45.0
# //.......................................//
# //..........VARIAVES AUXILIARES..........//
# //.......................................//
K = np.array([Kcal, Kdol, Kqtz]) # Modulo Bulk maximo e minimo
G = np.array([Gcal, Gdol, Gqtz])
KHS_M, GHS_M = lib.matrix_calculation(K, G)
lib.save_file('KHS_ternary.txt', KHS_M)
lib.save_file('GHS_ternary.txt', GHS_M)
# file, scale (x+y+z=scale), color scale min, color scale max
lib.plot('KHS_ternary.txt', 100, 35, 95)
lib.plot('GHS_ternary.txt', 100, 32, 45)
def main():
num = int(sys.argv[1]) if len(sys.argv) > 1 else 100
plot(num)
return 0
fake_seqs = netG(noise)
errD_real, score_fake = lib.backprop(netD, fake_seqs, disc_exp="real", backward=False)
# How close the guesses are?
valid_score = score_real - score_fake
diff_vals.append((score_real+score_fake).cpu().item())
err_vals.append(errD_real+errD_fake)
data = next(valid_seqs)
disc_error_valid.append(np.mean(err_vals))
valid_counts.append(true_count)
# log results and figures
name = "valid_disc_cost"
if checkpoint_baseline > 0: name += "_{}".format(checkpoint_baseline)
lib.plot(valid_counts, disc_error_valid, logdir, name, xlabel="Iteration", ylabel="Discriminator cost")
# Calculating 'Computation Time' for this round of iteration
current_iteration_endpint = datetime.datetime.now(tz)
current_iteration_elapsed = str(current_iteration_endpint - former_iteration_endpint).split(".")[0]
temp = current_iteration_elapsed.split(":")
if int(temp[0])==0 and int(temp[1])==0: current_iteration_elapsed = temp[2]
elif int(temp[0])==0: current_iteration_elapsed = temp[1]+":"+temp[2]
former_iteration_endpint = current_iteration_endpint
print("Iteration {}/{}: train_diff={:.5f}, valid_diff={:.5f} ({}sec)".format(true_count, args.train_iters, train_score, valid_score, current_iteration_elapsed))
fake_seqs = fake_seqs.reshape([-1, args.max_seq_len, data_enc_dim])
lib.save_samples(logdir, fake_seqs.cpu().clone().detach().numpy(), true_count, rev_charmap, annotated=args.annotate)
name = "train_disc_cost"
if checkpoint_baseline > 0: name += "_{}".format(checkpoint_baseline)
train_counts += 1
train_data = next(train_feed)
# validation
cost_vals = []
valid_data = next(valid_feed)
while valid_data is not None:
valid_seqs, valid_vals = valid_data
cost_val = session.run(cost, {inputs:valid_seqs, true_vals:valid_vals})
cost_vals.append(cost_val)
valid_data = next(valid_feed)
valid_cost.append(np.mean(cost_vals))
valid_counts.append(epoch_count)
name = "valid_cost"
if checkpoint_baseline > 0: name += "_{}".format(checkpoint_baseline)
lib.plot(valid_counts, valid_cost, logdir, name, xlabel="Epoch", ylabel="Cost")
# log results
print("Epoch {}: train cost={:.8f}, valid_cost={:.8f}".format(epoch_count, cost_val, valid_cost[-1]))
name = "train_cost"
if checkpoint_baseline > 0: name += "_{}".format(checkpoint_baseline)
lib.plot(range(train_counts), train_cost, logdir,name, xlabel="Iteration", ylabel="Cost")
# save checkpoint
checkpoint_epoch = args.checkpoint_iters and (epoch_count % args.checkpoint_iters == 0) or (idx == args.num_epochs - 1)
if checkpoint_epoch:
ckpt_dir = os.path.join(logdir, "checkpoints", "checkpoint_{}".format(epoch_count))
os.makedirs(ckpt_dir, exist_ok=True)
saver.save(session, os.path.join(ckpt_dir, "trained_predictor.ckpt"))
# test
data = next(valid_seqs)
while data is not None:
noise = np.random.normal(size=[args.batch_size, args.latent_dim])
score_diff = session.run(disc_diff, {
latent_vars: noise,
real_data: data
})
cost_vals.append(score_diff)
data = next(valid_seqs)
valid_cost.append(np.mean(cost_vals))
valid_counts.append(true_count)
name = "valid_disc_cost"
if checkpoint_baseline > 0: name += "_{}".format(checkpoint_baseline)
lib.plot(valid_counts,
valid_cost,
logdir,
name,
xlabel="Iteration",
ylabel="Discriminator cost")
# log results
print("Iteration {}: train_disc_cost={:.5f}, valid_disc_cost={:.5f}".
format(true_count, cost, score_diff))
samples = session.run(gen_data, {
latent_vars: fixed_latents
}).reshape([-1, args.max_seq_len, data_enc_dim])
lib.save_samples(logdir,
samples,
true_count,
rev_charmap,
annotated=args.annotate)
name = "train_disc_cost"
import lib
import os
input_path = "dataset/epidural"
input_folder = os.fsencode(input_path)
files = os.listdir(input_folder)
files.sort()
slices = []
for file in files:
# if os.fsdecode(file) == "ID_3580adc72.dcm": # "ID_635f084fc.dcm": # "ID_559b1d8f7.dcm": #"ID_894a589ad.dcm":
if os.fsdecode(file) == "ID_0ed10ec08.dcm":
file = os.fsdecode(file)
filename = "{}/{}".format(input_path, file)
image = lib.read_image(filename)
lib.histogram(image, True)
lib.plot("original: {} ".format(file), image)
# features
hematoma = lib.substance_interval(image, 40, 90)
white_matter = lib.substance_interval(image, 20, 30)
blood = lib.substance_interval(image, 30, 45)
bone = lib.substance_interval(image, 600, 4000)
#lib.plot("blood: {}".format(file), blood)
#lib.plot("hematoma: {}".format(file), hematoma)
lib.histogram(blood, True)
print("Done")