Giter VIP home page Giter VIP logo

pgportfolio's People

Contributors

dexhunter avatar dlacombejr avatar jpa99 avatar kumkee avatar lytkarinskiy avatar zhengyaojiang avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

pgportfolio's Issues

ConvLayer Filters

Figure 2 in Paper (Attached image):
Shouldn't the convolutional filters be 3 dimensional? I mean, in the original convolution how do we go from 3 feature maps to 2 feature maps. I believe this would make sense if the filter was of dimension 2x1x3 (same as described but with additional depth of 2). And then the second convolution would be 2x48 to get the 20 11x1 feature maps.

net_config.json:
In ConvLayer, I don't understand how {"filter_shape":[1,2],"filter_number":3} corresponds to the filters outlined in the paper as described in my above question. (Excuse my ignorance of tflearn, but the params to conv2d() are not well explained in the documentation)

image

cash (btc) is always zero

In the new portfolio vector (raw omega) the cash (btc) is always zero. But this cannot be always the best choice: what if all the other currencies are losing value in a period? surely in this case the best choice is to move all the assets back to cash.

In the code, the cash bias is initialized to zero just before the final softmax, so it cannot be anything else than zero. Was this intended?

Change coins

Hello,

First of all i'd like to thank you for sharing code with great paper. I've got question about your idea to change coins, because its not uncommon especially in crypto markets that previously chosen coin simply disappears from market or just become unpopular with ~0 volume. I find that agent isn't ready for that is it? Obvious idea would be to just learn new agent after some time past (f.e. 1-2 month) but it seems there is a better way.

model response to coins trained on periods prior to their existance.

Hello,

I don't understand how the model response when a selected coin is not existing at the training period.

for example, choosing start date = 2015-07-01 and end date = 2017-11-01, BCH is chosen
The training/ backtest portfolio value decreases tremendously. is that because of the fact that BCH didn't exist most of that time ?

Learning procedure

Hello again!

May I ask here for more details about learning procedure, because I'm not really in shape to understand all the code, may be with your guides here I'll go through it again with more success.

  1. During training phase how many times CNN learns on the same batch? Do you use epochs to learn or CNN passes through the data only once?
  2. During CV and Test phases rolling learning is used. On what data do CNN weights get updated? After all orders have been completed in current period we add price history into local DB. Do we select N periods before current period into learning batch? Or we update weights only using last price window?

Sorry if it's newbie questions, I just want to understand how this magic works.

Weight of cash asset in omega is always near zero.

Thanks for the great work! I played around with model training and one thing I noticed when looking at the omega values omitted by the model is that the weight for the cash asset is always at zero or near zero. Is this intentional?

Here's the output of a small training run. I outputted the omega values to demonstrate:

python main.py --mode=train --processes=1
/usr/local/Cellar/python3/3.6.3/Frameworks/Python.framework/Versions/3.6/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.5 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.6
  return f(*args, **kwds)
training at 1 started
select coins offline from 2017-03-21 04:48 to 2017-04-20 04:48
feature type list is ['close', 'high', 'low']
the number of training examples is 3722, of test examples is 295
2017-12-21 12:07:28.513499: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
WARNING:tensorflow:From /Users/ielashi/dev/reinforcement-learning/rl/lib/python3.6/site-packages/tflearn/initializations.py:119: UniformUnitScaling.__init__ (from tensorflow.python.ops.init_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.initializers.variance_scaling instead with distribution=uniform to get equivalent behavior.
From /Users/ielashi/dev/reinforcement-learning/rl/lib/python3.6/site-packages/tflearn/initializations.py:119: UniformUnitScaling.__init__ (from tensorflow.python.ops.init_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.initializers.variance_scaling instead with distribution=uniform to get equivalent behavior.
upper bound in test is 61.0790493486
average time for data accessing is 1.550912857055664e-06
average time for training is 6.512188911437989e-05
==============================
step 0
------------------------------
the portfolio value on test set is 1.07209
log_mean is 0.000235952
loss_value is -0.000236
log mean without commission fee is 0.000249

==============================

average time for data accessing is 0.001526810646057129
average time for training is 0.009054662466049194
==============================
step 1000
------------------------------
the portfolio value on test set is 1.07329
log_mean is 0.000239769
loss_value is -0.000240
log mean without commission fee is 0.000312

==============================

average time for data accessing is 0.0014722917079925536
average time for training is 0.009154855251312256
==============================
step 2000
------------------------------
the portfolio value on test set is 1.06176
log_mean is 0.000203138
loss_value is -0.000203
log mean without commission fee is 0.000443

==============================

average time for data accessing is 0.001517345666885376
average time for training is 0.009293434143066406
==============================
step 3000
------------------------------
the portfolio value on test set is 1.05826
log_mean is 0.000191954
loss_value is -0.000192
log mean without commission fee is 0.000592

==============================

average time for data accessing is 0.00144854998588562
average time for training is 0.008849609851837158
==============================
step 4000
------------------------------
the portfolio value on test set is 1.06193
log_mean is 0.000203699
loss_value is -0.000204
log mean without commission fee is 0.000769

==============================

INFO:tensorflow:Restoring parameters from ./train_package/1/netfile
Restoring parameters from ./train_package/1/netfile
the portfolio value train No.1 is 1.06193 log_mean is 0.000203699, the training time is 56 seconds
select coins offline from 2017-03-21 04:48 to 2017-04-20 04:48
feature type list is ['close', 'high', 'low']
the number of training examples is 3722, of test examples is 295
Omega: [  1.61122671e-25   7.94072356e-03   3.74337249e-02   8.64713918e-03
   1.97610576e-02   2.97623407e-02   2.36446653e-02   1.37573415e-02
   1.77555159e-01   9.56027657e-02   3.54102045e-01   2.31793016e-01]
the step is 0
total assets are 1.015672 BTC
Omega: [  8.80024691e-26   1.49688162e-02   4.84430306e-02   1.46317724e-02
   3.44342999e-02   4.92817871e-02   3.69634740e-02   6.29115058e-03
   1.48920476e-01   1.04111277e-01   3.59725028e-01   1.82228863e-01]
the step is 1
total assets are 1.021221 BTC
Omega: [  2.95938334e-26   1.26678515e-02   4.24146950e-02   1.29151903e-02
   2.64123473e-02   5.01841977e-02   6.50991872e-02   9.08971019e-03
   4.99374926e-01   1.06937259e-01   5.01048155e-02   1.24799803e-01]
the step is 2
total assets are 1.024862 BTC
Omega: [  2.38269612e-26   1.38902040e-02   2.50125993e-02   1.39350500e-02
   5.00419214e-02   5.38142733e-02   4.80199531e-02   2.48596407e-02
   4.45612341e-01   1.16050862e-01   2.08833478e-02   1.87879711e-01]
the step is 3
total assets are 1.038799 BTC
Omega: [  2.52868577e-26   2.50642654e-02   3.01404595e-02   1.45591367e-02
   1.12846062e-01   9.85511914e-02   9.11209658e-02   2.05693040e-02
   1.74638107e-01   1.29577696e-01   7.00687766e-02   2.32864022e-01]
the step is 4
total assets are 1.030233 BTC
Omega: [  4.18522411e-27   2.98684128e-02   4.45971079e-02   1.36763733e-02
   5.91860116e-02   7.98829421e-02   9.88799930e-02   2.22022478e-02
   1.69115424e-01   9.07965973e-02   9.87736806e-02   2.93021202e-01]
the step is 5
total assets are 1.031832 BTC
Omega: [  1.87215605e-27   2.38634758e-02   2.25463044e-02   2.09571049e-02
   6.08692169e-02   7.89556354e-02   5.29895015e-02   8.71249661e-02
   2.87531316e-02   1.42325893e-01   8.16501752e-02   3.99964601e-01]
the step is 6
total assets are 1.037791 BTC
Omega: [  2.03753296e-27   2.75911596e-02   1.79383699e-02   2.40262672e-02
   6.69842958e-02   9.00059715e-02   7.29413554e-02   1.48778498e-01
   1.05563760e-01   1.73161775e-01   6.98354319e-02   2.03173101e-01]
the step is 7
total assets are 1.042734 BTC
Omega: [  1.24977369e-27   2.70075835e-02   6.51344704e-03   1.36636151e-02
   6.51784986e-02   8.57863873e-02   7.35566244e-02   1.88305482e-01
   8.16493034e-02   2.07424656e-01   1.37151564e-02   2.37199262e-01]
the step is 8
total assets are 1.043383 BTC
Omega: [  6.68791162e-28   3.85836363e-02   2.74673826e-03   2.24224273e-02
   7.08901361e-02   1.02698922e-01   5.99917956e-02   1.98704839e-01
   1.24408461e-01   2.13171050e-01   5.50767453e-03   1.60874367e-01]
the step is 9
total assets are 1.041659 BTC
Omega: [  2.97321069e-28   3.89271490e-02   5.00685303e-03   2.22212635e-02
   8.86700898e-02   1.19350508e-01   1.44255012e-01   1.03619978e-01
   1.99151471e-01   1.79459095e-01   6.43162476e-03   9.29070264e-02]
the step is 10
total assets are 1.039224 BTC
Omega: [  2.69564662e-28   4.06317264e-02   8.14044662e-03   2.30540521e-02
   6.60812408e-02   1.00490093e-01   1.36528820e-01   1.01284035e-01
   3.04048508e-01   1.54350773e-01   5.27903531e-03   6.01112209e-02]
the step is 11
total assets are 1.035903 BTC
Omega: [  1.03823645e-28   2.93898452e-02   3.45003349e-03   1.79139171e-02
   4.43162322e-02   8.95256922e-02   3.68504912e-01   6.16414063e-02
   2.05027223e-01   1.10657059e-01   4.93706437e-03   6.46366104e-02]
the step is 12
total assets are 1.030233 BTC
Omega: [  6.75025325e-29   2.65279748e-02   2.23271130e-03   2.75795758e-02
   3.38157043e-02   6.92890361e-02   5.78530073e-01   2.95317322e-02
   1.06946290e-01   8.21494684e-02   4.12766123e-03   3.92697193e-02]
the step is 13
total assets are 1.038030 BTC
Omega: [  3.05692207e-29   4.49951366e-02   1.26438087e-03   5.29327579e-02
   5.30502088e-02   8.97282586e-02   4.06322211e-01   3.80690619e-02
   1.19775981e-01   1.68099999e-01   5.21530537e-03   2.05468293e-02]
the step is 14
total assets are 1.037359 BTC
Omega: [  1.53709703e-29   5.19051068e-02   1.76389434e-03   4.38303687e-02
   4.90076058e-02   1.15680449e-01   3.09319615e-01   1.35933101e-01
   2.23523993e-02   2.29593396e-01   9.18906182e-03   3.14250477e-02]
the step is 15
total assets are 1.034302 BTC
Omega: [  6.64309511e-30   4.49559018e-02   1.08325062e-03   3.38552371e-02
   6.49177656e-02   7.61018172e-02   5.37377119e-01   7.92052448e-02
   1.51698468e-02   1.14616886e-01   1.30547956e-02   1.96621940e-02]
the step is 16
total assets are 1.033343 BTC
Omega: [  1.61480499e-30   6.60500973e-02   9.80200944e-04   4.90367226e-02
   9.29730311e-02   1.12165712e-01   4.36509728e-01   1.03590012e-01
   1.87539253e-02   8.63772184e-02   1.59648973e-02   1.75984725e-02]
the step is 17
total assets are 1.034852 BTC
Omega: [  1.75251594e-30   7.14431629e-02   3.03784618e-04   5.07412516e-02
   7.40859434e-02   1.36064410e-01   3.18130940e-01   1.12693831e-01
   1.29496651e-02   1.37384996e-01   3.02269477e-02   5.59750795e-02]
the step is 18
total assets are 1.035724 BTC
Omega: [  1.09732322e-30   7.30977207e-02   1.30707433e-03   2.74412036e-02
   4.65783812e-02   1.60659626e-01   3.33825678e-01   1.27724051e-01
   1.42396754e-02   1.40051812e-01   1.05746035e-02   6.45001456e-02]
the step is 19
total assets are 1.039057 BTC
Omega: [  1.48259507e-30   8.18088874e-02   4.87733661e-04   1.53014632e-02
   2.27508079e-02   1.90615222e-01   3.66795868e-01   7.46636465e-02
   1.70590803e-02   1.01687819e-01   2.33736355e-02   1.05455823e-01]
the step is 20
total assets are 1.043655 BTC
Omega: [  1.97106441e-30   9.00461972e-02   1.05009449e-03   2.57369373e-02
   2.46618129e-02   2.05886751e-01   2.56114900e-01   3.66208926e-02
   1.57660786e-02   1.02027141e-01   1.84938274e-02   2.23595411e-01]
the step is 21
total assets are 1.042543 BTC
Omega: [  9.32715929e-31   1.00598924e-01   4.39209025e-03   3.46918665e-02
   4.45370860e-02   2.25526631e-01   1.93894699e-01   4.05276604e-02
   2.32999027e-02   1.49549261e-01   2.63762791e-02   1.56605557e-01]
the step is 22
total assets are 1.044600 BTC
Omega: [  5.34199223e-31   1.20451115e-01   2.53007598e-02   2.68365256e-02
   5.73835969e-02   2.92491555e-01   2.36110881e-01   3.00470013e-02
   3.24947536e-02   6.26352727e-02   3.18251885e-02   8.44233409e-02]
the step is 23
total assets are 1.044965 BTC
Omega: [  1.97507360e-31   1.05899706e-01   1.46820294e-02   2.26648003e-02
   8.64921883e-02   2.13359311e-01   4.14555997e-01   2.58721691e-02
   2.82610841e-02   3.44050042e-02   5.00945151e-02   3.71313305e-03]
the step is 24
total assets are 1.048253 BTC
Omega: [  1.03327540e-31   1.26015574e-01   1.53532308e-02   3.58474366e-02
   1.30994484e-01   2.18660966e-01   2.98099846e-01   3.81905586e-02
   2.79107690e-02   3.93034816e-02   5.04481867e-02   1.91756021e-02]
the step is 25
total assets are 1.047873 BTC
Omega: [  4.55854358e-32   1.29478946e-01   2.86072772e-02   3.89229283e-02
   1.69491947e-01   1.77715495e-01   2.98436016e-01   2.57394444e-02
   1.89963151e-02   2.82405764e-02   6.56923726e-02   1.86787024e-02]
the step is 26
total assets are 1.048881 BTC
Omega: [  3.81036464e-32   1.52003065e-01   3.28666978e-02   2.14057043e-02
   1.82151616e-01   1.59217641e-01   1.57291889e-01   2.14495156e-02
   1.00036502e-01   2.41378788e-02   1.34531692e-01   1.49078341e-02]
the step is 27
total assets are 1.046020 BTC
Omega: [  1.15417272e-32   1.05085872e-01   2.92277634e-01   8.74685217e-03
   8.90641883e-02   1.20196007e-01   2.02186227e-01   1.69067569e-02
   5.92594184e-02   1.75931267e-02   7.57702440e-02   1.29137011e-02]
the step is 28
total assets are 1.050952 BTC
Omega: [  3.32487108e-33   1.42071292e-01   9.96155292e-02   3.48853157e-03
   1.14648022e-01   1.06074162e-01   2.66054660e-01   4.13918160e-02
   9.90524441e-02   1.79921947e-02   7.71686062e-02   3.24427374e-02]
the step is 29
total assets are 1.051544 BTC
Omega: [  2.64148164e-33   1.46989346e-01   1.36604175e-01   5.52745862e-03
   9.18160155e-02   1.21633679e-01   2.05383420e-01   3.97083052e-02
   1.40521705e-01   1.20330779e-02   6.76569939e-02   3.21258716e-02]
the step is 30
total assets are 1.049028 BTC
Omega: [  3.16233621e-33   1.42531261e-01   1.75307095e-01   1.34734418e-02
   1.12451695e-01   9.92269143e-02   1.72159180e-01   4.12014127e-02
   1.21598549e-01   8.76218639e-03   9.36241746e-02   1.96641106e-02]
the step is 31
total assets are 1.046276 BTC
Omega: [  2.03749997e-33   1.97739273e-01   8.88320878e-02   8.95817205e-03
   1.04140878e-01   1.24894463e-01   1.36548460e-01   1.00940645e-01
   1.02220930e-01   7.31858984e-03   1.13888741e-01   1.45178232e-02]
the step is 32
total assets are 1.046889 BTC
Omega: [  1.93849102e-33   1.71333939e-01   6.89826459e-02   1.24140410e-02
   1.28062055e-01   1.16963573e-01   1.18272796e-01   1.16245642e-01
   1.24025442e-01   1.84617601e-02   9.67563316e-02   2.84817871e-02]
the step is 33
total assets are 1.045584 BTC
Omega: [  3.54939578e-34   1.85285524e-01   2.33648922e-02   1.05095506e-02
   1.18852414e-01   1.00308515e-01   1.00671917e-01   1.20513335e-01
   1.69102579e-01   2.72832103e-02   1.15585715e-01   2.85224020e-02]
the step is 34
total assets are 1.043532 BTC
Omega: [  5.58774913e-34   1.72019124e-01   2.17257589e-02   8.85353144e-03
   6.42464906e-02   8.48495364e-02   7.84317032e-02   1.95943072e-01
   1.98326916e-01   3.13102826e-02   1.30616874e-01   1.36767803e-02]
the step is 35
total assets are 1.027277 BTC
Omega: [  2.57250395e-35   1.92587413e-02   1.18435333e-02   8.23703340e-06
   6.23591477e-03   1.27581274e-02   4.24996251e-03   2.03663751e-01
   7.17224658e-01   4.91757086e-03   1.44962817e-02   5.34322858e-03]
the step is 36
total assets are 1.035256 BTC
Omega: [  1.56082217e-35   2.64986139e-02   4.36826376e-03   7.95157689e-07
   1.41955931e-02   1.51995849e-02   4.34761634e-03   2.69768745e-01
   6.03524506e-01   1.31181646e-02   3.76190431e-02   1.13590639e-02]
the step is 37
total assets are 1.050018 BTC
Omega: [  4.01480223e-35   6.01387322e-02   3.48639488e-03   1.32961986e-05
   2.90421676e-02   2.83047650e-02   1.22989165e-02   4.04577404e-01
   2.14977667e-01   2.27931980e-02   1.94050238e-01   3.03172711e-02]
the step is 38
total assets are 1.048455 BTC
Omega: [  2.10955462e-35   2.73707192e-02   5.21286158e-04   1.96119709e-05
   4.23592962e-02   2.29291916e-02   7.82355573e-03   4.30561006e-01
   2.80796260e-01   3.72640640e-02   9.15556997e-02   5.87992929e-02]
the step is 39
total assets are 1.039887 BTC
Omega: [  2.92492396e-36   9.79422405e-03   1.58716957e-05   1.79847138e-05
   1.48050785e-02   9.97118093e-03   2.52767676e-03   3.32690954e-01
   4.94405001e-01   5.83278313e-02   4.86255325e-02   2.88186893e-02]
the step is 40
total assets are 1.038000 BTC
Omega: [  3.02252536e-36   9.90297366e-03   4.68355847e-06   3.37203965e-05
   1.34533970e-02   7.75681995e-03   3.28178913e-03   3.70428801e-01
   5.05451620e-01   3.25790383e-02   3.00783198e-02   2.70287637e-02]
the step is 41
total assets are 1.048838 BTC
Omega: [  2.39692309e-35   1.86589547e-02   6.62857710e-05   3.05131398e-05
   3.31385583e-02   2.92254928e-02   8.50010850e-03   2.27614567e-01
   4.72615749e-01   8.95666555e-02   6.10511974e-02   5.95319383e-02]
the step is 42
total assets are 1.046191 BTC
Omega: [  8.48071764e-35   2.32132580e-02   1.11619054e-04   7.75318622e-05
   2.87289154e-02   2.49711610e-02   1.11210300e-02   9.67123210e-02
   6.90768838e-01   4.69837449e-02   3.82625572e-02   3.90490852e-02]
the step is 43
total assets are 1.051013 BTC
Omega: [  2.84415817e-34   4.04653363e-02   1.20649944e-04   3.78668687e-04
   5.98011538e-02   4.06671241e-02   2.47069187e-02   1.18846253e-01
   5.41436732e-01   3.69006507e-02   9.06206369e-02   4.60558832e-02]
the step is 44
total assets are 1.047020 BTC
Omega: [  3.72809250e-34   3.28524262e-02   2.89213149e-05   5.66660543e-04
   4.06726971e-02   3.19343545e-02   2.07008030e-02   1.11125611e-01
   6.53580666e-01   2.10820511e-02   6.02954589e-02   2.71602944e-02]
the step is 45
total assets are 1.047422 BTC
Omega: [  3.43260582e-34   4.89946119e-02   4.72051943e-05   5.01629373e-04
   3.68186571e-02   3.20069119e-02   2.49717422e-02   2.33979285e-01
   5.47365427e-01   9.48760845e-03   4.05510776e-02   2.52759345e-02]
the step is 46
total assets are 1.046076 BTC
Omega: [  8.22454826e-34   5.36367483e-02   2.67670781e-04   8.53627105e-04
   3.52147743e-02   5.14722802e-02   2.60524619e-02   2.57152855e-01
   4.24766630e-01   1.31494664e-02   1.14962012e-01   2.24714819e-02]
the step is 47
total assets are 1.048351 BTC
Omega: [  9.17401801e-34   7.52565116e-02   7.70516635e-04   1.21509098e-03
   2.10768320e-02   5.00934049e-02   3.49036641e-02   1.62800267e-01
   4.58532542e-01   2.84011681e-02   1.35866016e-01   3.10840141e-02]
the step is 48
total assets are 1.046270 BTC
Omega: [  4.84413462e-34   7.90709108e-02   3.06697475e-04   2.93570920e-03
   2.75142454e-02   5.28884195e-02   2.72404142e-02   2.56810606e-01
   4.09553289e-01   4.21968959e-02   8.35690647e-02   1.79136973e-02]
the step is 49
total assets are 1.045869 BTC
Omega: [  1.00541478e-34   1.13879494e-01   4.70903353e-04   9.69698746e-03
   2.86322366e-02   7.39903748e-02   2.97317281e-02   2.75821477e-01
   3.22438449e-01   3.67614292e-02   9.50127691e-02   1.35641787e-02]
the step is 50
total assets are 1.046420 BTC
Omega: [  1.74637112e-34   9.74821746e-02   2.86159664e-03   9.98315308e-03
   5.04293703e-02   9.10820067e-02   3.20365205e-02   3.01473647e-01
   3.03439677e-01   3.98223698e-02   5.50677143e-02   1.63217597e-02]
the step is 51
total assets are 1.045969 BTC
Omega: [  3.31203684e-34   8.18462968e-02   1.96718215e-03   1.31541993e-02
   4.54508737e-02   9.78929475e-02   3.47581133e-02   3.14991325e-01
   2.69103825e-01   5.99129312e-02   6.99977651e-02   1.09245330e-02]
the step is 52
total assets are 1.044987 BTC
Omega: [  9.62809403e-34   9.26187038e-02   2.21625203e-03   3.28553356e-02
   6.27766252e-02   9.93623286e-02   4.48360257e-02   3.10604602e-01
   2.35399440e-01   6.55028597e-02   4.41409089e-02   9.68693290e-03]
the step is 53
total assets are 1.044941 BTC
Omega: [  3.97309147e-34   1.10205673e-01   3.19811353e-03   3.96721885e-02
   5.97188063e-02   9.16961133e-02   3.73916104e-02   3.77083331e-01
   1.67920545e-01   6.58193678e-02   3.51234861e-02   1.21707153e-02]
the step is 54
total assets are 1.045502 BTC
Omega: [  3.42285014e-34   1.14713855e-01   4.14694753e-03   5.52279130e-02
   5.27366512e-02   9.36474279e-02   4.97915894e-02   3.56307805e-01
   1.35089651e-01   7.56230727e-02   3.87218520e-02   2.39932854e-02]
the step is 55
total assets are 1.046160 BTC
Omega: [  2.28442597e-33   1.28511965e-01   2.03449419e-03   8.33110213e-02
   5.70381545e-02   1.06818520e-01   5.58202565e-02   3.16718966e-01
   1.31755412e-01   8.02350342e-02   2.75173225e-02   1.02387900e-02]
the step is 56
total assets are 1.048007 BTC
Omega: [  5.94552847e-33   1.40406638e-01   2.31704977e-03   3.48764583e-02
   7.64963478e-02   1.32362545e-01   6.61344230e-02   3.07918876e-01
   1.23956650e-01   1.05105169e-01   4.43966314e-03   5.98621974e-03]
the step is 57
total assets are 1.051444 BTC
Omega: [  1.17872053e-33   1.44442037e-01   3.83149437e-03   3.19571048e-02
   1.01061687e-01   1.54363081e-01   9.30427462e-02   3.03263009e-01
   3.72233614e-02   1.11853145e-01   1.23562384e-02   6.60600048e-03]
the step is 58
total assets are 1.051873 BTC
Omega: [  1.63361315e-33   2.54261553e-01   7.54643511e-03   3.46156806e-02
   1.15507044e-01   1.62091419e-01   8.56968611e-02   1.86399624e-01
   3.00955102e-02   1.04559921e-01   8.25311709e-03   1.09728798e-02]
the step is 59
total assets are 1.046453 BTC
Omega: [  1.66281666e-33   2.73680091e-01   6.34608325e-03   2.98593547e-02
   1.66289434e-01   1.47360250e-01   6.26614988e-02   1.58170477e-01
   1.08881881e-02   1.08930551e-01   1.56751033e-02   2.01390591e-02]
the step is 60
total assets are 1.048927 BTC
Omega: [  5.01162833e-33   2.39609227e-01   9.87183675e-03   6.87849820e-02
   1.66825578e-01   1.51381597e-01   7.79673830e-02   1.34792656e-01
   1.49110192e-02   8.20358023e-02   3.02412845e-02   2.35785451e-02]
the step is 61
total assets are 1.046826 BTC
Omega: [  2.02512477e-32   2.45912045e-01   1.58073455e-02   9.64321494e-02
   2.02221557e-01   1.42109230e-01   7.44323209e-02   1.11347243e-01
   1.27622690e-02   4.81323414e-02   3.38033810e-02   1.70401242e-02]
the step is 62
total assets are 1.046629 BTC
Omega: [  2.61061926e-32   2.34051138e-01   6.51893169e-02   9.47623774e-02
   2.27741480e-01   1.40410259e-01   5.09841442e-02   8.75486434e-02
   1.73870269e-02   4.14539240e-02   2.21209079e-02   1.83507726e-02]
the step is 63
total assets are 1.048414 BTC
Omega: [  5.73569244e-32   2.24052548e-01   1.52045684e-02   1.22691073e-01
   2.23927811e-01   1.54294670e-01   6.62641749e-02   8.94434601e-02
   1.76890865e-02   4.44157645e-02   2.11718716e-02   2.08450630e-02]
the step is 64
total assets are 1.048845 BTC
Omega: [  1.47421380e-31   1.85759038e-01   3.83016802e-02   1.50737852e-01
   2.20488325e-01   1.44199863e-01   9.41682756e-02   7.55336732e-02
   1.71504933e-02   3.93046215e-02   1.79841258e-02   1.63719840e-02]
the step is 65
total assets are 1.052618 BTC
Omega: [  1.81797795e-31   1.97595745e-01   6.36575297e-02   5.37024401e-02
   2.46883780e-01   1.43686667e-01   9.77565646e-02   5.85586727e-02
   3.26934233e-02   5.18239327e-02   2.87152529e-02   2.49259844e-02]
the step is 66
total assets are 1.051572 BTC
Omega: [  4.60392501e-32   1.87380761e-01   1.33043274e-01   6.98163733e-02
   1.70692846e-01   1.34214669e-01   7.56613240e-02   5.23770899e-02
   5.89385815e-02   4.83603887e-02   2.29963120e-02   4.65183742e-02]
the step is 67
total assets are 1.052795 BTC
Omega: [  2.96854759e-32   1.91242531e-01   7.07347095e-02   6.57135472e-02
   1.43173933e-01   1.24432497e-01   1.14269346e-01   5.71534969e-02
   8.47255662e-02   5.45920357e-02   1.38607519e-02   8.01015794e-02]
the step is 68
total assets are 1.053415 BTC
Omega: [  3.51733712e-32   1.46899387e-01   1.00110203e-01   1.33770183e-02
   1.76359639e-01   1.20665707e-01   1.16943404e-01   5.03220633e-02
   1.24639556e-01   8.43533576e-02   1.06022954e-02   5.57273738e-02]
the step is 69
total assets are 1.052195 BTC
Omega: [  8.79565999e-33   1.53228775e-01   1.18067741e-01   6.29298063e-03
   1.87646747e-01   1.02095738e-01   9.69473794e-02   4.80048880e-02
   1.15802661e-01   9.79876965e-02   1.85217988e-02   5.54035641e-02]
the step is 70
total assets are 1.052315 BTC
Omega: [  4.98266305e-33   1.21084139e-01   1.23985842e-01   8.70736409e-03
   1.65499881e-01   9.46261808e-02   1.33145317e-01   3.22018154e-02
   1.12388521e-01   1.23559959e-01   1.55973444e-02   6.92035854e-02]
the step is 71
total assets are 1.052689 BTC
Omega: [  4.63936213e-33   1.16613597e-01   1.27245158e-01   1.10487947e-02
   1.47478640e-01   9.89211127e-02   1.11402579e-01   2.48680878e-02
   9.74856094e-02   1.58372447e-01   2.16534603e-02   8.49104747e-02]
the step is 72
total assets are 1.053301 BTC
Omega: [  1.06975489e-32   1.23158626e-01   2.15465173e-01   6.97383797e-03
   1.37410149e-01   1.10645741e-01   1.08278237e-01   1.95429511e-02
   7.84326419e-02   8.50339606e-02   3.14260125e-02   8.36326480e-02]
the step is 73
total assets are 1.053292 BTC
Omega: [  1.77703213e-32   1.20896384e-01   1.91116020e-01   1.30930198e-02
   1.33384854e-01   1.12265632e-01   1.12570964e-01   2.25010123e-02
   7.62559623e-02   8.02969262e-02   3.67974080e-02   1.00821771e-01]
the step is 74
total assets are 1.054736 BTC
Omega: [  6.47824047e-32   1.39657363e-01   9.60238278e-02   4.30640811e-03
   1.37878746e-01   1.01167120e-01   1.65363312e-01   5.24039865e-02
   6.79240227e-02   1.08171090e-01   3.90569977e-02   8.80471990e-02]
the step is 75
total assets are 1.057660 BTC
Omega: [  1.03169577e-31   1.60673574e-01   6.19125813e-02   6.24517165e-03
   6.68526068e-02   1.30868092e-01   1.30350918e-01   7.25268647e-02
   4.51282226e-02   1.44196182e-01   5.41182458e-02   1.27127498e-01]
the step is 76
total assets are 1.058520 BTC
Omega: [  2.41923038e-31   1.63340271e-01   1.19018242e-01   3.52686434e-03
   5.48923388e-02   1.23657443e-01   1.03471123e-01   6.95218369e-02
   1.73316468e-02   2.11697564e-01   5.19222766e-02   8.16204175e-02]
the step is 77
total assets are 1.058747 BTC
Omega: [  8.27115911e-32   1.15865968e-01   1.32911950e-01   5.03755454e-03
   6.95795044e-02   1.29752830e-01   1.08871751e-01   5.17489314e-02
   1.50857866e-02   2.71884531e-01   6.03171960e-02   3.89440097e-02]
the step is 78
total assets are 1.057634 BTC
Omega: [  3.04910304e-32   1.17295906e-01   1.31224930e-01   3.13859084e-03
   8.90911594e-02   1.13941506e-01   1.45305961e-01   7.48530403e-02
   2.46241018e-02   2.19008893e-01   4.69255410e-02   3.45904306e-02]
the step is 79
total assets are 1.055834 BTC
Omega: [  2.83069384e-32   1.02068730e-01   1.63887456e-01   3.63921770e-03
   1.08747795e-01   1.09496236e-01   1.34205699e-01   7.36127570e-02
   1.40087819e-02   1.74593106e-01   8.32253844e-02   3.25147882e-02]
the step is 80
total assets are 1.057582 BTC
Omega: [  9.55270715e-32   7.44487941e-02   2.46981904e-01   5.14353532e-03
   6.75236732e-02   1.01397522e-01   7.90094435e-02   5.17453402e-02
   1.90648250e-02   1.60087630e-01   1.69024318e-01   2.55730376e-02]
the step is 81
total assets are 1.057550 BTC
Omega: [  7.09290353e-32   5.72720505e-02   3.47827524e-01   9.42539331e-03
   7.71261975e-02   9.83948559e-02   5.74339479e-02   4.00708951e-02
   1.98762212e-02   1.71084523e-01   1.03385545e-01   1.81027539e-02]
the step is 82
total assets are 1.055340 BTC
Omega: [  3.47107113e-32   5.26833758e-02   4.26944375e-01   1.67596675e-02
   6.75163418e-02   8.10021535e-02   6.35419786e-02   3.43844034e-02
   1.41330948e-02   1.00561455e-01   1.19332254e-01   2.31408477e-02]
the step is 83
total assets are 1.061495 BTC
Omega: [  5.28117345e-32   7.28762299e-02   2.35577837e-01   4.63450188e-03
   7.31012076e-02   9.31951851e-02   7.26558343e-02   3.92748080e-02
   1.17903668e-02   1.51181877e-01   2.15899825e-01   2.98124366e-02]
the step is 84
total assets are 1.056159 BTC
Omega: [  1.22573946e-32   4.86612506e-02   1.80730894e-01   8.15195381e-04
   4.77845445e-02   5.63701428e-02   7.08114281e-02   2.37371419e-02
   3.95685621e-02   1.10757932e-01   3.93135607e-01   2.76273116e-02]
the step is 85
total assets are 1.064625 BTC
Omega: [  4.09962287e-33   5.74711710e-02   2.67050862e-01   8.10212863e-04
   6.45579323e-02   6.55220672e-02   8.05381984e-02   3.11254263e-02
   8.48999619e-02   1.12536825e-01   2.31289655e-01   4.19761101e-03]
the step is 86
total assets are 1.059519 BTC
Omega: [  1.60402614e-33   1.93176512e-02   5.86348593e-01   3.48886751e-05
   2.07716692e-02   2.66666748e-02   5.20286895e-02   2.93641295e-02
   1.17861032e-01   3.52627076e-02   1.07360363e-01   4.98360349e-03]
the step is 87
total assets are 1.058010 BTC
Omega: [  1.62222482e-33   1.20857935e-02   6.96830809e-01   2.13474868e-05
   4.00128402e-03   1.85513608e-02   5.05696125e-02   1.54477088e-02
   1.13408737e-01   2.54505128e-02   5.77624440e-02   5.87044982e-03]
the step is 88
total assets are 1.063170 BTC
Omega: [  4.05203556e-33   1.89784113e-02   6.01536036e-01   3.62969695e-05
   5.66592533e-03   2.54456680e-02   6.53416887e-02   3.41933742e-02
   1.45161659e-01   2.91791670e-02   6.76265433e-02   6.83524553e-03]
the step is 89
total assets are 1.064962 BTC
Omega: [  2.76989786e-32   4.36717942e-02   4.63564783e-01   3.66433873e-04
   3.10739689e-02   7.46211037e-02   1.13694213e-01   3.92090194e-02
   1.08416617e-01   7.54465833e-02   3.61367501e-02   1.37986718e-02]
the step is 90
total assets are 1.058965 BTC
Omega: [  2.88876179e-32   3.68622355e-02   5.08490980e-01   6.58901816e-04
   2.82621756e-02   6.12391345e-02   9.87727121e-02   4.83817197e-02
   1.12677254e-01   5.76105379e-02   2.78784093e-02   1.91659406e-02]
the step is 91
total assets are 1.059125 BTC
Omega: [  1.79221364e-32   5.38438708e-02   4.19315875e-01   5.04097552e-04
   3.17312740e-02   6.64994642e-02   1.07870124e-01   4.95654643e-02
   1.41230121e-01   7.89682567e-02   3.06743979e-02   1.97970234e-02]
the step is 92
total assets are 1.058258 BTC
Omega: [  4.68578467e-32   6.40084893e-02   2.75533617e-01   2.11145045e-04
   5.23000322e-02   1.04583167e-01   1.52827278e-01   4.82741371e-02
   1.35210618e-01   7.38027096e-02   7.50227198e-02   1.82260368e-02]
the step is 93
total assets are 1.051495 BTC
Omega: [  1.10341252e-32   1.12141795e-01   1.79289609e-01   1.34350688e-04
   5.41298576e-02   8.88482854e-02   1.99696392e-01   6.97708204e-02
   1.01421498e-01   4.90970165e-02   1.31774932e-01   1.36954673e-02]
the step is 94
total assets are 1.050844 BTC
Omega: [  3.36956007e-33   8.89384970e-02   2.28401750e-01   6.90871457e-05
   4.58648205e-02   8.98668095e-02   2.05523640e-01   6.66871145e-02
   6.62803203e-02   5.23960590e-02   1.25246495e-01   3.07253040e-02]
the step is 95
total assets are 1.055366 BTC
Omega: [  5.65717860e-33   1.05815522e-01   1.20527461e-01   1.44679347e-04
   4.86714952e-02   1.05700940e-01   1.80872411e-01   1.07277058e-01
   4.37508412e-02   7.65727609e-02   1.63070843e-01   4.75959182e-02]
the step is 96
total assets are 1.050713 BTC
Omega: [  4.00400559e-33   7.35194981e-02   8.46572295e-02   1.75272624e-04
   5.36855198e-02   8.68932307e-02   1.31263822e-01   7.48495236e-02
   9.43922698e-02   5.94534762e-02   3.25275421e-01   1.58347003e-02]
the step is 97
total assets are 1.055081 BTC
Omega: [  6.30664750e-34   9.48020294e-02   1.06431954e-01   2.14069252e-04
   7.54945874e-02   1.07664362e-01   1.59388557e-01   1.28099665e-01
   1.11521013e-01   6.17185161e-02   1.19780667e-01   3.48844975e-02]
the step is 98
total assets are 1.047718 BTC
Omega: [  7.50286728e-34   8.65006521e-02   1.47084206e-01   2.26966850e-03
   7.53361955e-02   1.30047172e-01   1.47701561e-01   1.31454706e-01
   1.07048191e-01   3.78288552e-02   1.24573767e-01   1.01549672e-02]
the step is 99
total assets are 1.050827 BTC
Omega: [  2.57151107e-33   8.25405344e-02   1.55953541e-01   1.08096283e-02
   6.10578433e-02   1.32407561e-01   1.29686177e-01   1.84864834e-01
   7.64844194e-02   3.93044800e-02   1.10277563e-01   1.66133847e-02]
the step is 100
total assets are 1.049952 BTC
Omega: [  2.21300679e-33   6.04039095e-02   1.97929904e-01   4.66425018e-03
   9.80736464e-02   1.14217050e-01   1.14720970e-01   1.76941976e-01
   5.99644855e-02   4.91785184e-02   9.02862847e-02   3.36190686e-02]
the step is 101
total assets are 1.047822 BTC
Omega: [  5.46912816e-33   6.70120046e-02   2.88722485e-01   1.20100472e-03
   7.89666623e-02   9.39363539e-02   1.13175824e-01   1.23044424e-01
   5.30238040e-02   3.95340323e-02   9.15260985e-02   4.98572588e-02]
the step is 102
total assets are 1.044542 BTC
Omega: [  9.04199438e-33   5.60473986e-02   1.99300438e-01   1.31098775e-03
   6.24472015e-02   1.53437451e-01   9.84661058e-02   9.29715559e-02
   1.30009234e-01   3.70187946e-02   1.12471558e-01   5.65193109e-02]
the step is 103
total assets are 1.039594 BTC
Omega: [  3.97236349e-33   4.57340293e-02   2.77239770e-01   2.05386570e-03
   5.69842681e-02   1.36213005e-01   6.94742650e-02   7.14257658e-02
   1.18032821e-01   2.58424617e-02   1.63431615e-01   3.35681438e-02]
the step is 104
total assets are 1.040520 BTC
Omega: [  5.87768922e-33   4.47634198e-02   1.90441221e-01   3.91236925e-03
   6.07512929e-02   1.15002826e-01   5.67544550e-02   7.27835968e-02
   1.28917977e-01   3.99561301e-02   2.54812270e-01   3.19044478e-02]
the step is 105
total assets are 1.039616 BTC
Omega: [  1.67535514e-33   3.87015529e-02   1.10335439e-01   2.06651608e-03
   8.09229240e-02   1.00072950e-01   6.02589808e-02   4.65151742e-02
   1.44687280e-01   2.87761334e-02   3.56398225e-01   3.12648080e-02]
the step is 106
total assets are 1.043008 BTC
Omega: [  4.31327154e-33   4.38619815e-02   1.16362482e-01   3.26080015e-03
   9.38758552e-02   1.48239464e-01   5.97777478e-02   8.31744745e-02
   2.08274275e-01   2.88826004e-02   1.64007276e-01   5.02830222e-02]
the step is 107
total assets are 1.045304 BTC
Omega: [  6.72906644e-34   4.94062975e-02   1.25150084e-01   6.59529062e-04
   8.28144997e-02   1.78176999e-01   7.50115663e-02   3.30773257e-02
   2.47287467e-01   2.70717964e-02   1.28885567e-01   5.24588786e-02]
the step is 108
total assets are 1.047910 BTC
Omega: [  1.09072312e-33   7.18552545e-02   1.02796055e-01   1.08676101e-03
   2.24569105e-02   1.49976462e-01   7.23762959e-02   5.24550416e-02
   3.37276518e-01   3.52682732e-02   9.95110497e-02   5.49413860e-02]
the step is 109
total assets are 1.041603 BTC
Omega: [  2.93106761e-34   5.84538504e-02   8.05327967e-02   5.58525571e-05
   2.39756890e-02   1.00755990e-01   6.64687455e-02   3.05945668e-02
   5.24859428e-01   2.34151110e-02   5.22487946e-02   3.86391729e-02]
the step is 110
total assets are 1.041539 BTC
Omega: [  4.44564663e-34   6.44065961e-02   9.92455184e-02   1.36624440e-05
   3.51047330e-02   1.41386017e-01   6.80419803e-02   4.51101176e-02
   4.29386139e-01   5.63747920e-02   5.10911122e-02   9.83931497e-03]
the step is 111
total assets are 1.037126 BTC
Omega: [  1.54642986e-34   5.11500314e-02   1.75782070e-01   4.75048728e-06
   4.88841012e-02   1.45918697e-01   6.33993968e-02   6.33515269e-02
   2.42089063e-01   6.09264262e-02   1.25639200e-01   2.28547752e-02]
the step is 112
total assets are 1.041884 BTC
Omega: [  1.14814069e-34   7.33479410e-02   1.55893669e-01   7.96814857e-06
   5.87966107e-02   1.68574110e-01   7.27116615e-02   9.85567272e-02
   1.14701748e-01   1.22103095e-01   1.12435162e-01   2.28713620e-02]
the step is 113
total assets are 1.040730 BTC
Omega: [  8.38984699e-35   5.86294532e-02   1.29063860e-01   5.90105883e-05
   4.72767986e-02   1.58372626e-01   5.00876345e-02   1.04162462e-01
   5.73403835e-02   1.59836546e-01   2.00822845e-01   3.43483500e-02]
the step is 114
total assets are 1.045848 BTC
Omega: [  1.70376255e-34   3.00891902e-02   9.21032131e-02   5.11948820e-05
   6.96117952e-02   1.13577083e-01   1.05472870e-01   7.31024072e-02
   5.50733432e-02   1.64052755e-01   2.44011194e-01   5.28549328e-02]
the step is 115
total assets are 1.046131 BTC
Omega: [  1.50633567e-33   4.84830737e-02   8.72879326e-02   1.56270587e-04
   3.69755477e-02   1.28987446e-01   1.61007062e-01   7.72272795e-02
   7.89839104e-02   1.32464036e-01   1.97687313e-01   5.07400967e-02]
the step is 116
total assets are 1.044848 BTC
Omega: [  4.89128232e-33   4.19346839e-02   6.55300766e-02   2.32475519e-04
   8.81406665e-02   1.50209397e-01   1.41898930e-01   6.66123182e-02
   6.59161732e-02   9.45820585e-02   2.31081560e-01   5.38616367e-02]
the step is 117
total assets are 1.043716 BTC
Omega: [  1.09418430e-33   5.53517118e-02   5.84759973e-02   7.68607351e-05
   7.64978454e-02   1.32203653e-01   8.17776918e-02   4.37978357e-02
   8.92251283e-02   6.07159473e-02   3.50905508e-01   5.09717725e-02]
the step is 118
total assets are 1.041312 BTC
Omega: [  7.86000083e-34   5.51815294e-02   8.24469998e-02   2.77447489e-05
   9.92946476e-02   9.24758539e-02   5.35703525e-02   6.31742924e-02
   4.31011803e-02   5.32626584e-02   4.14511263e-01   4.29534577e-02]
the step is 119
total assets are 1.041971 BTC
Omega: [  1.84816927e-34   7.07261264e-02   7.07072392e-02   1.60295094e-04
   7.47603998e-02   8.18561763e-02   6.85150772e-02   6.56724945e-02
   4.43579890e-02   7.83225223e-02   4.10809875e-01   3.41117978e-02]
the step is 120
total assets are 1.044122 BTC
Omega: [  3.12656059e-34   1.00809745e-01   6.86514080e-02   2.65790592e-03
   9.67962667e-02   8.72362405e-02   5.39344586e-02   6.30355701e-02
   6.74577579e-02   8.88001770e-02   3.28142822e-01   4.24776115e-02]
the step is 121
total assets are 1.042087 BTC
Omega: [  4.74934816e-35   7.60025531e-02   7.33557343e-02   2.50340137e-03
   8.82439092e-02   9.12237614e-02   4.40520570e-02   6.78693727e-02
   2.87345350e-01   9.24491882e-02   1.67051733e-01   9.90288332e-03]
the step is 122
total assets are 1.046299 BTC
Omega: [  3.70214025e-35   8.50710720e-02   7.69221783e-02   2.18925136e-03
   1.36409655e-01   1.15293406e-01   6.59644082e-02   9.59717929e-02
   1.98101223e-01   1.23452298e-01   7.75219351e-02   2.31027473e-02]
the step is 123
total assets are 1.045542 BTC
Omega: [  3.90536158e-35   8.79279450e-02   4.84045520e-02   2.22191913e-03
   1.16215743e-01   1.46035463e-01   8.72796327e-02   1.10032529e-01
   1.48188129e-01   1.66247979e-01   7.29320943e-02   1.45140681e-02]
the step is 124
total assets are 1.045830 BTC
Omega: [  1.07783311e-35   8.61412659e-02   3.83023135e-02   3.36186681e-03
   1.39972627e-01   1.60623953e-01   1.22446358e-01   1.21178731e-01
   1.10798448e-01   1.40873626e-01   6.31117895e-02   1.31889423e-02]
the step is 125
total assets are 1.044522 BTC
Omega: [  2.08142024e-35   6.56334832e-02   3.76120098e-02   2.27085478e-03
   1.26907244e-01   1.48500979e-01   1.50099069e-01   9.51478034e-02
   1.32009983e-01   1.42795652e-01   7.28844851e-02   2.61384882e-02]
the step is 126
total assets are 1.041726 BTC
Omega: [  1.91866636e-35   4.33890633e-02   8.90829265e-02   2.40114678e-04
   1.36438698e-01   1.01979911e-01   1.20515175e-01   6.97930157e-02
   2.41096213e-01   1.07663780e-01   7.85614476e-02   1.12396302e-02]
the step is 127
total assets are 1.041893 BTC
Omega: [  1.97501490e-35   6.02824874e-02   2.67212261e-02   2.95373058e-04
   8.86462852e-02   1.04274079e-01   7.66017511e-02   4.05623168e-02
   3.89030606e-01   1.03639588e-01   8.55369568e-02   2.44093444e-02]
the step is 128
total assets are 1.034796 BTC
Omega: [  1.22034293e-35   2.90111862e-02   1.24408649e-02   8.24696326e-05
   1.39433756e-01   4.22310010e-02   2.93589849e-02   1.86085328e-02
   6.40518725e-01   4.87074405e-02   1.79369319e-02   2.16700993e-02]
the step is 129
total assets are 1.048932 BTC
Omega: [  6.00135820e-36   8.71816352e-02   5.71563542e-02   1.38171436e-03
   2.11249843e-01   9.15784240e-02   5.78049533e-02   1.55617911e-02
   2.68687934e-01   1.15660906e-01   5.11030667e-02   4.26334329e-02]
the step is 130
total assets are 1.047462 BTC
Omega: [  5.61832167e-36   9.94016975e-02   1.28767908e-01   1.44909008e-03
   2.38526866e-01   7.36934394e-02   5.86764850e-02   2.13538390e-03
   1.99622303e-01   1.44220918e-01   3.52714732e-02   1.82344913e-02]
the step is 131
total assets are 1.046520 BTC
Omega: [  1.09512265e-35   9.70426723e-02   9.50409025e-02   6.06520195e-03
   9.64823589e-02   5.92694283e-02   5.19439951e-02   1.09509041e-03
   3.93972665e-01   1.67615876e-01   2.25578360e-02   8.91400222e-03]
the step is 132
total assets are 1.049189 BTC
Omega: [  8.39696604e-37   9.38536525e-02   8.14929530e-02   1.58191156e-02
   9.83585194e-02   6.17233105e-02   8.95837918e-02   4.29945358e-04
   3.45222354e-01   1.72303542e-01   3.98336276e-02   1.37913029e-03]
the step is 133
total assets are 1.049300 BTC
Omega: [  6.07387147e-37   1.02761745e-01   7.00544342e-02   2.73893755e-02
   1.30939841e-01   8.51606354e-02   9.08656046e-02   2.07169703e-03
   2.47460440e-01   1.28983587e-01   1.12056047e-01   2.25662580e-03]
the step is 134
total assets are 1.050496 BTC
Omega: [  8.92475782e-38   1.03010885e-01   1.33509547e-01   7.08442107e-02
   1.04566038e-01   5.78165017e-02   2.28806570e-01   1.85050024e-03
   5.09594716e-02   1.49811357e-01   9.22721624e-02   6.55278983e-03]
the step is 135
total assets are 1.051931 BTC
Omega: [  1.67018320e-37   1.05273984e-01   1.06012270e-01   7.44405687e-02
   1.29090711e-01   6.73459247e-02   2.44677857e-01   1.60617812e-03
   2.12810934e-02   1.39304787e-01   9.77174863e-02   1.32491635e-02]
the step is 136
total assets are 1.051435 BTC
Omega: [  2.15845209e-37   8.93608704e-02   5.48151620e-02   2.04969302e-01
   1.29575655e-01   8.24846625e-02   1.37185335e-01   5.94177574e-04
   1.91352088e-02   1.11099459e-01   1.55262887e-01   1.55173400e-02]
the step is 137
total assets are 1.045269 BTC
Omega: [  4.06111093e-37   2.96817776e-02   3.18978801e-02   6.39114022e-01
   7.28680566e-02   4.99623641e-02   4.69790027e-02   1.57784161e-04
   1.43458350e-02   5.53218648e-02   5.82708232e-02   1.40054373e-03]
the step is 138
total assets are 1.040095 BTC
Omega: [  3.91976784e-38   2.16135774e-02   1.87554359e-02   7.67248154e-01
   4.81563956e-02   4.23829220e-02   3.84496152e-02   1.68687809e-04
   9.89873987e-03   1.94296483e-02   3.33722346e-02   5.24674018e-04]
the step is 139
total assets are 1.054797 BTC
Omega: [  6.82290989e-38   5.42918332e-02   3.13441269e-02   4.72511709e-01
   8.95148367e-02   1.14586473e-01   7.00870007e-02   2.79925880e-03
   1.98121294e-02   4.37113382e-02   9.73128453e-02   4.02845768e-03]
the step is 140
total assets are 1.049016 BTC
Omega: [  4.67468543e-38   5.09326644e-02   1.19834371e-01   4.97496098e-01
   9.20008495e-02   9.19671580e-02   8.02623183e-02   2.23396975e-03
   1.24085713e-02   2.32769027e-02   2.78101750e-02   1.77690934e-03]
the step is 141
total assets are 1.054944 BTC
Omega: [  1.11432857e-37   8.09585005e-02   1.88793644e-01   2.46327266e-01
   1.15160964e-01   1.11467205e-01   9.99307483e-02   2.89026601e-03
   3.16984840e-02   6.39126301e-02   4.45794202e-02   1.42809777e-02]
the step is 142
total assets are 1.060344 BTC
Omega: [  3.52971613e-38   1.00769900e-01   1.66043907e-01   4.65253480e-02
   1.31063238e-01   9.34553817e-02   1.15439855e-01   7.16659008e-03
   1.78288668e-01   7.40517899e-02   6.78620413e-02   1.93333402e-02]
the step is 143
total assets are 1.057913 BTC
Omega: [  2.53716494e-38   6.63527325e-02   1.39142916e-01   2.54168715e-02
   1.88623741e-01   1.07013099e-01   1.11097030e-01   1.26109980e-02
   1.86866224e-01   9.98918787e-02   4.14730906e-02   2.15113610e-02]
the step is 144
total assets are 1.058623 BTC
Omega: [ 0.          0.04453967  0.14253291  0.06135317  0.17306061  0.10143019
  0.14212787  0.0158326   0.15037373  0.11475933  0.03180679  0.02218305]
the step is 145
total assets are 1.066670 BTC
Omega: [ 0.          0.07952623  0.11845667  0.04349175  0.1929516   0.12059872
  0.18940301  0.04342511  0.00381756  0.16328557  0.02334972  0.02169404]
the step is 146
total assets are 1.064494 BTC
Omega: [  0.00000000e+00   6.94705546e-02   1.36137158e-01   3.92699949e-02
   2.06678882e-01   8.44031870e-02   1.92168817e-01   2.96066124e-02
   1.59911124e-05   1.53174102e-01   1.69320032e-02   7.21426606e-02]
the step is 147
total assets are 1.064912 BTC
Omega: [  0.00000000e+00   6.63865432e-02   1.30295262e-01   9.45289806e-03
   1.86653569e-01   1.03071243e-01   1.84640929e-01   1.95094738e-02
   3.05431467e-06   2.32402265e-01   2.02640574e-02   4.73206863e-02]
the step is 148
total assets are 1.064856 BTC
Omega: [  0.00000000e+00   4.89140078e-02   2.54552811e-01   2.16618553e-03
   2.04782516e-01   9.49925259e-02   8.97527188e-02   1.59542505e-02
   2.31731829e-05   2.43829921e-01   3.04818936e-02   1.45500256e-02]
the step is 149
total assets are 1.065846 BTC
Omega: [  0.00000000e+00   1.02682188e-01   2.18220651e-01   2.00393982e-03
   1.55816108e-01   1.10876083e-01   9.75556001e-02   1.58591904e-02
   5.84025111e-06   2.32112199e-01   5.35009392e-02   1.13673061e-02]
the step is 150
total assets are 1.064967 BTC
Omega: [  0.00000000e+00   1.26476631e-01   2.28198096e-01   2.45460216e-03
   1.60751075e-01   1.01204365e-01   6.82050809e-02   1.36507247e-02
   5.75451049e-05   2.30886266e-01   5.33553734e-02   1.47601785e-02]
the step is 151
total assets are 1.065258 BTC
Omega: [ 0.          0.13244233  0.13907716  0.01567729  0.16759661  0.11705128
  0.05555921  0.00774202  0.0004297   0.26080748  0.04334885  0.06026801]
the step is 152
total assets are 1.066875 BTC
Omega: [ 0.          0.12405261  0.05915846  0.05975086  0.15305601  0.11641311
  0.0472982   0.00358307  0.00041194  0.31947106  0.05739568  0.05940903]
the step is 153
total assets are 1.064876 BTC
Omega: [ 0.          0.0994457   0.0578921   0.12242954  0.13887486  0.09839517
  0.0578475   0.00051083  0.00209256  0.28058845  0.04440774  0.09751555]
the step is 154
total assets are 1.061683 BTC
Omega: [ 0.          0.06401924  0.04965097  0.31106499  0.12227758  0.0861381
  0.05397587  0.00032372  0.00212698  0.17739506  0.02947879  0.10354865]
the step is 155
total assets are 1.063754 BTC
Omega: [  0.00000000e+00   4.60647084e-02   1.53477946e-02   3.58075708e-01
   1.21339343e-01   9.94674191e-02   8.47317800e-02   2.92771292e-04
   4.38251393e-03   1.45525858e-01   4.06252965e-02   8.41468275e-02]
the step is 156
total assets are 1.060573 BTC
Omega: [  0.00000000e+00   1.25529300e-02   4.12597656e-02   5.74864686e-01
   7.26289302e-02   8.27457383e-02   5.01595028e-02   2.47438202e-05
   6.55089458e-03   5.60308732e-02   3.26025784e-02   7.05793649e-02]
the step is 157
total assets are 1.052303 BTC
Omega: [  0.00000000e+00   2.54204962e-03   2.58706138e-02   7.81139672e-01
   2.48698499e-02   4.56628054e-02   3.68915126e-02   1.77254344e-06
   1.04844617e-02   2.00056043e-02   1.93189234e-02   3.32126990e-02]
the step is 158
total assets are 1.047309 BTC
Omega: [  0.00000000e+00   1.92012114e-03   2.09862571e-02   8.77512038e-01
   1.55750886e-02   1.88672952e-02   1.96704399e-02   1.28209831e-06
   4.56067221e-03   1.58708952e-02   1.44799706e-02   1.05559332e-02]
the step is 159
total assets are 1.047815 BTC
Omega: [  0.00000000e+00   1.69877557e-03   7.85020646e-03   9.01529670e-01
   1.94797628e-02   2.26001982e-02   1.44265154e-02   8.79565869e-06
   2.68813153e-03   7.90737104e-03   1.50118517e-02   6.79866085e-03]
the step is 160
total assets are 1.045060 BTC
Omega: [  0.00000000e+00   1.50490669e-03   6.92229345e-03   9.02714193e-01
   1.83090549e-02   1.77334286e-02   8.18200782e-03   3.67778534e-06
   1.02830715e-02   5.88613469e-03   1.76165141e-02   1.08446945e-02]
the step is 161
total assets are 1.047553 BTC
Omega: [  0.00000000e+00   2.47969199e-03   1.80063434e-02   7.72184312e-01
   4.66618054e-02   2.64037512e-02   2.23604124e-02   9.27059045e-06
   5.44475615e-02   8.58310331e-03   1.35164130e-02   3.53473574e-02]
the step is 162
total assets are 1.027903 BTC
Omega: [  0.00000000e+00   6.63943705e-04   3.79426894e-03   9.64410126e-01
   5.11026755e-03   4.19875188e-03   2.59521673e-03   9.56967824e-07
   6.97995350e-03   2.26664683e-03   2.18772702e-03   7.79216783e-03]
the step is 163
total assets are 1.031056 BTC
Omega: [  0.00000000e+00   1.76276779e-03   9.27614234e-03   9.38463688e-01
   1.11840433e-02   6.33181538e-03   5.60326129e-03   1.39568665e-05
   8.92779231e-03   3.21280072e-03   5.32493088e-03   9.89869051e-03]
the step is 164
total assets are 1.028115 BTC
Omega: [  0.00000000e+00   2.40957527e-03   1.21890334e-02   9.07466173e-01
   2.19246354e-02   8.71855579e-03   1.26385717e-02   3.44643748e-04
   6.02867128e-03   7.20492285e-03   8.55468679e-03   1.25204287e-02]
the step is 165
total assets are 1.028385 BTC
Omega: [  0.00000000e+00   5.88540174e-03   3.88813093e-02   8.12265992e-01
   3.47693190e-02   1.79559756e-02   2.59640422e-02   3.75369505e-04
   2.09115259e-03   1.59778092e-02   2.62430571e-02   1.95906162e-02]
the step is 166
total assets are 1.031463 BTC
Omega: [ 0.          0.01414642  0.0808555   0.46319449  0.07605298  0.0422492
  0.06995646  0.00121427  0.00050559  0.1335576   0.09409002  0.02417741]
the step is 167
total assets are 1.034684 BTC
Omega: [  0.00000000e+00   2.12347824e-02   1.17548689e-01   8.89086276e-02
   7.37500265e-02   5.38793355e-02   1.05842911e-01   2.89560342e-03
   2.45798117e-04   1.10477336e-01   3.06301683e-01   1.18915267e-01]
the step is 168
total assets are 1.034923 BTC
Omega: [ 0.          0.0265296   0.12720361  0.15347901  0.04293124  0.05693717
  0.06553078  0.0064191   0.00038274  0.08830518  0.23481625  0.19746526]
the step is 169
total assets are 1.034155 BTC
Omega: [ 0.          0.03797473  0.08813236  0.1291922   0.03952032  0.0566915
  0.09168021  0.0127667   0.00041566  0.09783015  0.07983384  0.36596239]
the step is 170
total assets are 1.034325 BTC
Omega: [ 0.          0.05214358  0.07368643  0.14995062  0.03171826  0.02961818
  0.03702643  0.00390271  0.00213129  0.09517998  0.12105723  0.40358528]
the step is 171
total assets are 1.040752 BTC
Omega: [ 0.          0.07791815  0.07130342  0.22087179  0.03128783  0.02596168
  0.04067429  0.00395516  0.00232262  0.14469993  0.16158955  0.21941561]
the step is 172
total assets are 1.033179 BTC
Omega: [  0.00000000e+00   1.51145114e-02   2.54060719e-02   8.23318899e-01
   7.60765327e-03   7.13196816e-03   1.37439761e-02   2.26701668e-04
   1.05240883e-03   3.93656082e-02   4.00682837e-02   2.69638617e-02]
the step is 173
total assets are 1.039813 BTC
Omega: [  0.00000000e+00   4.91413428e-03   1.70221720e-02   8.42254519e-01
   1.08648678e-02   8.88044294e-03   1.29954116e-02   6.69665098e-07
   3.51701421e-03   2.24384740e-02   5.85756078e-02   1.85365546e-02]
the step is 174
total assets are 1.057918 BTC
Omega: [  0.00000000e+00   1.99534874e-02   9.90180448e-02   3.23638856e-01
   1.52721629e-02   2.37248372e-02   4.93401587e-02   4.71481917e-06
   2.70185590e-01   4.78728674e-02   1.34776950e-01   1.62122957e-02]
the step is 175
total assets are 1.057980 BTC
Omega: [  0.00000000e+00   2.31251176e-02   9.62275714e-02   3.91133055e-02
   2.68297009e-02   2.19963863e-02   6.06413707e-02   1.96193396e-05
   4.49740142e-01   5.62113263e-02   2.09938332e-01   1.61571186e-02]
the step is 176
total assets are 1.059739 BTC
Omega: [  0.00000000e+00   2.43956372e-02   6.66530430e-02   1.64058991e-03
   2.47422177e-02   1.76156797e-02   4.56107929e-02   1.47388246e-05
   3.44565719e-01   2.85446811e-02   4.38639939e-01   7.57692987e-03]
the step is 177
total assets are 1.053863 BTC
Omega: [  0.00000000e+00   9.28286463e-03   2.61764433e-02   4.45192866e-03
   2.15686560e-02   1.20255733e-02   2.83676926e-02   6.24279892e-06
   7.32025564e-01   1.14700682e-02   1.50198951e-01   4.42595314e-03]
the step is 178
total assets are 1.057412 BTC
Omega: [  0.00000000e+00   3.44889797e-03   3.99833769e-02   1.07997898e-02
   1.55644566e-02   1.46561880e-02   3.39432843e-02   1.22203858e-06
   4.51244593e-01   1.35203646e-02   4.13400322e-01   3.43752326e-03]
the step is 179
total assets are 1.056527 BTC
Omega: [  0.00000000e+00   5.11576282e-03   1.42914671e-02   4.02607024e-02
   1.59899388e-02   1.47851184e-02   4.38184328e-02   8.87592250e-07
   6.67501986e-01   4.83959168e-03   1.70777291e-01   2.26188656e-02]
the step is 180
total assets are 1.049140 BTC
Omega: [  0.00000000e+00   2.74622929e-03   1.96194649e-02   1.28837526e-02
   5.64186554e-03   5.60531113e-03   2.23063510e-02   3.52371984e-07
   8.83800089e-01   1.00724900e-03   3.87722589e-02   7.61696510e-03]
the step is 181
total assets are 1.043362 BTC
Omega: [  0.00000000e+00   3.16160684e-03   3.24542373e-02   2.67264936e-02
   7.14002782e-03   4.95530805e-03   1.79122705e-02   5.25390442e-06
   8.35474610e-01   5.99082152e-04   5.95687293e-02   1.20023554e-02]
the step is 182
total assets are 1.056428 BTC
Omega: [ 0.          0.01458739  0.08280097  0.01458027  0.02549232  0.02451928
  0.05424506  0.00075319  0.41440225  0.00252844  0.32516134  0.04092946]
the step is 183
total assets are 1.052314 BTC
Omega: [ 0.          0.01367097  0.04890049  0.04474063  0.01939274  0.037024
  0.04633375  0.00278655  0.65394199  0.00366076  0.09885484  0.03069327]
the step is 184
total assets are 1.052510 BTC
Omega: [ 0.          0.01951384  0.02752543  0.01238276  0.02285022  0.03671428
  0.07690013  0.00267271  0.66324723  0.00427604  0.07846054  0.05545674]
the step is 185
total assets are 1.055745 BTC
Omega: [ 0.          0.03284114  0.05082578  0.02322823  0.03851018  0.06689186
  0.12502481  0.00215301  0.42850429  0.01035863  0.07880525  0.1428569 ]
the step is 186
total assets are 1.055281 BTC
Omega: [ 0.          0.08186212  0.01831936  0.0284284   0.05138732  0.08244628
  0.23034945  0.01398937  0.2339091   0.03305006  0.0428026   0.18345593]
the step is 187
total assets are 1.058182 BTC
Omega: [ 0.          0.09793733  0.04909368  0.03822165  0.07519665  0.0904481
  0.33346567  0.00547924  0.0832802   0.05643539  0.06226178  0.10818036]
the step is 188
total assets are 1.056976 BTC
Omega: [ 0.          0.08278182  0.0232418   0.13895008  0.07263011  0.09350756
  0.23101005  0.01149991  0.00428829  0.06876744  0.06835003  0.20497297]
the step is 189
total assets are 1.056047 BTC
Omega: [ 0.          0.06402545  0.06456701  0.13104837  0.03945216  0.09263768
  0.27348271  0.00630547  0.00524235  0.06943167  0.03717714  0.21663001]
the step is 190
total assets are 1.053843 BTC
Omega: [ 0.          0.06525572  0.06629802  0.0645186   0.02650951  0.07123654
  0.39654121  0.00171709  0.01326438  0.10796428  0.0196535   0.16704109]
the step is 191
total assets are 1.050165 BTC
Omega: [ 0.          0.08768476  0.20513073  0.04599313  0.0156986   0.04658537
  0.37216708  0.00686208  0.05201059  0.09775899  0.00893688  0.06117181]
the step is 192
total assets are 1.049701 BTC
Omega: [ 0.          0.03930875  0.15272167  0.03866096  0.01472811  0.02225912
  0.10804582  0.00592763  0.47366071  0.11578367  0.0058124   0.02309115]
the step is 193
total assets are 1.047534 BTC
Omega: [ 0.          0.03492169  0.08021146  0.03955486  0.01127505  0.03088938
  0.07026176  0.02867084  0.57770872  0.0971018   0.00119512  0.02820934]
the step is 194
total assets are 1.045520 BTC
Omega: [ 0.          0.05155413  0.13984068  0.01874618  0.01064813  0.0397769
  0.03334482  0.00922786  0.53700149  0.1121921   0.00095352  0.04671406]
the step is 195
total assets are 1.044018 BTC
Omega: [  0.00000000e+00   4.08488810e-02   6.54109269e-02   1.04820598e-02
   8.27530678e-03   3.37120444e-02   5.22883832e-02   4.72816778e-03
   7.08197951e-01   4.61295508e-02   1.33506066e-04   2.97932494e-02]
the step is 196
total assets are 1.050312 BTC
Omega: [  0.00000000e+00   6.23180903e-02   8.82131010e-02   1.19437203e-02
   9.06677544e-03   5.35889231e-02   6.36967123e-02   5.62397903e-03
   5.60624897e-01   5.65783009e-02   1.53215224e-04   8.81922394e-02]
the step is 197
total assets are 1.048581 BTC
Omega: [  0.00000000e+00   6.63371235e-02   5.89258820e-02   7.58631527e-03
   9.84059274e-03   3.17997709e-02   8.89081657e-02   5.69521170e-03
   5.37339687e-01   4.42517884e-02   3.17718514e-04   1.48997694e-01]
the step is 198
total assets are 1.050306 BTC
Omega: [ 0.          0.06286649  0.06197312  0.00920305  0.01577144  0.04900382
  0.0520371   0.01524916  0.39441696  0.04121124  0.0013559   0.29691175]
the step is 199
total assets are 1.062289 BTC
Omega: [ 0.          0.07052381  0.1340739   0.02709017  0.02432445  0.07921889
  0.08556134  0.00991662  0.00964899  0.04027933  0.00195829  0.51740426]
the step is 200
total assets are 1.061876 BTC
Omega: [ 0.          0.03931366  0.11350037  0.0237897   0.04165709  0.08597315
  0.34002525  0.00395165  0.00641881  0.0309352   0.00283154  0.31160361]
the step is 201
total assets are 1.061665 BTC
Omega: [ 0.          0.02175798  0.04012606  0.01487892  0.03941364  0.04454853
  0.70735502  0.00147687  0.00612762  0.01689504  0.00234956  0.10507078]
the step is 202
total assets are 1.059660 BTC
Omega: [ 0.          0.01691102  0.03712806  0.01893295  0.01511056  0.03483391
  0.76694781  0.00098346  0.00536511  0.01326238  0.002862    0.08766269]
the step is 203
total assets are 1.058994 BTC
Omega: [ 0.          0.02262281  0.01917485  0.00646959  0.01087527  0.04549305
  0.74482769  0.00145317  0.01062999  0.02197535  0.00487643  0.11160174]
the step is 204
total assets are 1.057722 BTC
Omega: [ 0.          0.02631087  0.01791715  0.00306554  0.02422466  0.04554755
  0.69848973  0.00199934  0.00141554  0.02107439  0.03210568  0.12784949]
the step is 205
total assets are 1.060288 BTC
Omega: [ 0.          0.05817163  0.0316363   0.01336584  0.03439542  0.06921981
  0.59371293  0.00345299  0.0014192   0.02122179  0.04057968  0.13282441]
the step is 206
total assets are 1.057577 BTC
Omega: [ 0.          0.05819219  0.02503674  0.01324093  0.06153874  0.0727048
  0.61747354  0.00185838  0.00129438  0.01992756  0.0614168   0.06731589]
the step is 207
total assets are 1.060884 BTC
Omega: [ 0.          0.0577223   0.03706359  0.11595642  0.06078901  0.08803011
  0.3313362   0.00046411  0.00263204  0.03539602  0.20238729  0.06822293]
the step is 208
total assets are 1.059810 BTC
Omega: [ 0.          0.07015298  0.03008094  0.19821033  0.04992156  0.07075337
  0.0994029   0.02964826  0.0034291   0.04317781  0.35735509  0.04786755]
the step is 209
total assets are 1.058676 BTC
Omega: [ 0.          0.03780407  0.00570129  0.58632803  0.01448365  0.04539492
  0.02555103  0.01603903  0.00176156  0.04798135  0.20252289  0.01643217]
the step is 210
total assets are 1.057444 BTC
Omega: [  0.00000000e+00   6.34078383e-02   6.33521646e-04   4.99464780e-01
   2.60889214e-02   4.43591177e-02   1.60806458e-02   1.25636216e-02
   7.11730390e-05   2.16420088e-02   3.05601031e-01   1.00873774e-02]
the step is 211
total assets are 1.065773 BTC
Omega: [  0.00000000e+00   2.31626451e-01   7.88492180e-05   2.37008989e-01
   4.86089885e-02   1.09158285e-01   3.18433084e-02   3.60248797e-02
   6.06010493e-04   1.37304306e-01   1.43463969e-01   2.42759902e-02]
the step is 212
total assets are 1.065340 BTC
Omega: [  0.00000000e+00   3.20377469e-01   3.40002771e-05   2.21514702e-01
   5.14422245e-02   9.61155370e-02   2.85594780e-02   8.79922062e-02
   3.71505087e-03   9.90962312e-02   4.82451916e-02   4.29078676e-02]
the step is 213
total assets are 1.060864 BTC
Omega: [  0.00000000e+00   2.60280997e-01   1.56622809e-05   2.62833238e-01
   2.67411415e-02   8.95398855e-02   1.60133708e-02   1.58439115e-01
   4.27300856e-03   5.92048280e-02   6.01656213e-02   6.24931753e-02]
the step is 214
total assets are 1.062193 BTC
Omega: [  0.00000000e+00   1.87712282e-01   5.89197007e-05   3.62977862e-01
   1.55909434e-02   1.06192559e-01   1.58803836e-02   1.66697666e-01
   2.39667539e-02   5.05911224e-02   1.74037069e-02   5.29276989e-02]
the step is 215
total assets are 1.066457 BTC
Omega: [ 0.          0.25557533  0.00108505  0.15013956  0.01553818  0.13201135
  0.0188722   0.19308183  0.00259891  0.08467359  0.00748077  0.13894328]
the step is 216
total assets are 1.065167 BTC
Omega: [ 0.          0.3048583   0.00194575  0.08837295  0.01836132  0.14482571
  0.03697674  0.09284964  0.00479243  0.19588901  0.00695653  0.10417169]
the step is 217
total assets are 1.065338 BTC
Omega: [ 0.          0.19782573  0.00554016  0.14557737  0.01502104  0.15886167
  0.08806302  0.1275399   0.0056299   0.17202616  0.00179624  0.08211884]
the step is 218
total assets are 1.062264 BTC
Omega: [ 0.          0.14541401  0.00062917  0.15120779  0.0381378   0.14838843
  0.10400361  0.11747359  0.02367922  0.23431675  0.00361673  0.03313293]
the step is 219
total assets are 1.060768 BTC
Omega: [ 0.          0.08768443  0.00323723  0.18301097  0.04551161  0.17970552
  0.18786193  0.05537535  0.00820072  0.21262549  0.00491229  0.03187444]
the step is 220
total assets are 1.062101 BTC
Omega: [ 0.          0.1058839   0.0097288   0.10802418  0.04307902  0.16143396
  0.27086303  0.0391372   0.03935338  0.13684322  0.0410339   0.04461943]
the step is 221
total assets are 1.062034 BTC
Omega: [ 0.          0.07156564  0.0065438   0.1269068   0.0592052   0.14846759
  0.36598355  0.01822305  0.03885528  0.10302347  0.00784374  0.05338185]
the step is 222
total assets are 1.062699 BTC
Omega: [ 0.          0.0574937   0.01206366  0.2566565   0.07835049  0.14225377
  0.27030882  0.01592443  0.01455011  0.09273311  0.0079728   0.05169256]
the step is 223
total assets are 1.060263 BTC
Omega: [ 0.          0.0288908   0.01565919  0.33888936  0.08257645  0.1267526
  0.3073124   0.00077644  0.00624164  0.04375142  0.0154959   0.03365381]
the step is 224
total assets are 1.056974 BTC
Omega: [  0.00000000e+00   1.47852357e-02   2.41752248e-02   6.28478050e-01
   3.99486274e-02   8.57740343e-02   1.29658163e-01   2.49140779e-04
   2.72627641e-02   2.27162410e-02   2.62767053e-03   2.43248995e-02]
the step is 225
total assets are 1.047381 BTC
Omega: [  0.00000000e+00   2.88439519e-03   3.20891477e-02   8.69964302e-01
   1.22072017e-02   2.38408055e-02   2.37619951e-02   1.41970420e-04
   1.06601538e-02   7.29136681e-03   1.75557111e-03   1.54031189e-02]
the step is 226
total assets are 1.043482 BTC
Omega: [ 0.          0.00643025  0.00726394  0.7057671   0.00733674  0.01466719
  0.00821563  0.00290915  0.17734651  0.00379199  0.00100891  0.06526254]
the step is 227
total assets are 1.035025 BTC
Omega: [  0.00000000e+00   5.70161548e-03   2.68278178e-04   6.23159945e-01
   5.82730351e-03   6.47874409e-03   2.81656720e-03   2.92494823e-03
   2.67764330e-01   1.28442247e-03   9.20502178e-04   8.28533694e-02]
the step is 228
total assets are 1.045851 BTC
Omega: [ 0.          0.02000101  0.00055547  0.55432057  0.02166142  0.01408278
  0.0026945   0.05182447  0.16216052  0.00795082  0.0073755   0.15737295]
the step is 229
total assets are 1.054735 BTC
Omega: [ 0.          0.06424308  0.00194865  0.33093873  0.06688076  0.06957736
  0.00465233  0.11114529  0.12866744  0.03153829  0.01564001  0.17476806]
the step is 230
total assets are 1.052103 BTC
Omega: [ 0.          0.06445956  0.00310516  0.40467399  0.02257605  0.0463241
  0.00316203  0.01870721  0.01109643  0.01345262  0.00626551  0.40617728]
the step is 231
total assets are 1.059259 BTC
Omega: [ 0.          0.12483011  0.00560325  0.20940867  0.01853877  0.07638692
  0.02023002  0.10164346  0.03195646  0.05405621  0.0163331   0.34101295]
the step is 232
total assets are 1.060882 BTC
Omega: [ 0.          0.10028506  0.01012232  0.05917219  0.03763395  0.1285889
  0.03576156  0.08841352  0.07617652  0.09692118  0.04109697  0.32582781]
the step is 233
total assets are 1.056636 BTC
Omega: [ 0.          0.06541942  0.0044661   0.03885921  0.02281768  0.10540166
  0.0397868   0.02982191  0.0423299   0.06817143  0.01226412  0.57066178]
the step is 234
total assets are 1.054828 BTC
Omega: [ 0.          0.05506243  0.00452805  0.02773893  0.03615824  0.0975822
  0.04668847  0.02886439  0.01933906  0.05938879  0.0267674   0.59788203]
the step is 235
total assets are 1.054175 BTC
Omega: [ 0.          0.08876565  0.01996224  0.03381525  0.0419994   0.07784509
  0.05282917  0.040798    0.03026996  0.0667034   0.01386706  0.53314477]
the step is 236
total assets are 1.030864 BTC
Omega: [ 0.          0.00326194  0.01286428  0.00184163  0.00119414  0.00251487
  0.00176224  0.03057763  0.34478009  0.0015126   0.00663056  0.59306008]
the step is 237
total assets are 1.035402 BTC
Omega: [  0.00000000e+00   9.19777842e-04   4.79984377e-03   1.57746766e-03
   6.74249721e-04   1.25222863e-03   1.80515705e-03   7.19943643e-01
   2.23358497e-01   5.58282249e-04   2.57501891e-03   4.25357968e-02]
the step is 238
total assets are 1.034285 BTC
Omega: [  0.00000000e+00   6.02129148e-04   9.61245853e-04   8.01816233e-04
   6.37831341e-04   1.42295053e-03   3.76227032e-03   7.24207640e-01
   2.49783501e-01   5.20868809e-04   8.80835019e-03   8.49135406e-03]
the step is 239
total assets are 1.048077 BTC
Omega: [ 0.          0.00518886  0.02958274  0.01092181  0.0030521   0.00991261
  0.05765127  0.39598793  0.4142642   0.00571269  0.04066933  0.0270565 ]
the step is 240
total assets are 1.057274 BTC
Omega: [ 0.          0.01348966  0.13458163  0.02926162  0.04807157  0.03241834
  0.21312687  0.08880384  0.29325441  0.02528752  0.05844908  0.06325544]
the step is 241
total assets are 1.048463 BTC
Omega: [ 0.          0.00367934  0.0483196   0.01018273  0.00870218  0.00657266
  0.02820609  0.03438577  0.83663225  0.00469512  0.01556666  0.0030575 ]
the step is 242
total assets are 1.053491 BTC
Omega: [ 0.          0.00428608  0.08301024  0.02243448  0.01592349  0.00980464
  0.05704334  0.04538118  0.74558538  0.00436774  0.00907999  0.00308347]
the step is 243
total assets are 1.041061 BTC
Omega: [  0.00000000e+00   2.19989498e-03   3.05009652e-02   5.22558950e-03
   4.14951751e-03   2.91323126e-03   1.26560451e-02   3.25678438e-02
   9.05917227e-01   1.19272689e-03   1.87436247e-03   8.02544877e-04]
the step is 244
total assets are 1.048765 BTC
Omega: [ 0.          0.01440864  0.08271127  0.0296998   0.0110071   0.01270918
  0.08806719  0.10625687  0.64030266  0.00548436  0.00332902  0.00602385]
the step is 245
total assets are 1.052974 BTC
Omega: [ 0.          0.01924404  0.02689768  0.01932673  0.01396541  0.01979864
  0.18335012  0.6355077   0.06723084  0.00546251  0.00373975  0.00547653]
the step is 246
total assets are 1.054662 BTC
Omega: [ 0.          0.01136821  0.00612315  0.00151686  0.00940935  0.01618018
  0.15701233  0.74298525  0.03539528  0.00655606  0.00687112  0.00658223]
the step is 247
total assets are 1.059884 BTC
Omega: [ 0.          0.02317343  0.00894302  0.00162971  0.01752588  0.0336026
  0.10028362  0.75797206  0.01960202  0.01305238  0.01161363  0.01260167]
the step is 248
total assets are 1.058236 BTC
Omega: [  0.00000000e+00   2.90977899e-02   2.04578619e-02   3.72133181e-05
   1.76894125e-02   3.08348518e-02   3.42051052e-02   7.77270138e-01
   5.47497533e-02   1.16627663e-02   7.58655882e-03   1.64085329e-02]
the step is 249
total assets are 1.067345 BTC
Omega: [  0.00000000e+00   7.08077773e-02   3.92604098e-02   4.81885581e-05
   1.18123814e-01   6.79405332e-02   1.37141079e-01   3.13392580e-01
   5.47226891e-02   5.30916788e-02   5.77105545e-02   8.77607390e-02]
the step is 250
total assets are 1.068300 BTC
Omega: [  0.00000000e+00   8.65029842e-02   6.86040893e-02   1.84959630e-04
   1.65573895e-01   6.98467866e-02   3.36853713e-02   2.37456877e-02
   6.30094334e-02   9.86561924e-02   2.75988191e-01   1.14202455e-01]
the step is 251
total assets are 1.070543 BTC
Omega: [  0.00000000e+00   1.16653517e-01   1.05939075e-01   4.39667492e-05
   1.48649916e-01   6.28185570e-02   2.21731924e-02   6.43403688e-03
   6.13602996e-03   9.23720971e-02   8.76672417e-02   3.51112366e-01]
the step is 252
total assets are 1.069806 BTC
Omega: [  0.00000000e+00   5.21041192e-02   5.00377491e-02   2.14483298e-04
   7.86447898e-02   5.92999160e-02   2.24545393e-02   1.39168361e-02
   8.48049205e-03   3.93128507e-02   5.61611727e-02   6.19373083e-01]
the step is 253
total assets are 1.069044 BTC
Omega: [  0.00000000e+00   3.54057178e-02   3.08824610e-03   4.76835528e-04
   9.81649011e-02   6.92068860e-02   7.05675632e-02   2.18271464e-02
   1.48773277e-02   4.28281762e-02   2.64687426e-02   6.17088437e-01]
the step is 254
total assets are 1.068163 BTC
Omega: [ 0.          0.02580447  0.00436706  0.0007701   0.08677482  0.06112175
  0.22597837  0.0116774   0.01765118  0.02025973  0.02401391  0.52158123]
the step is 255
total assets are 1.069025 BTC
Omega: [ 0.          0.01068245  0.00284659  0.00144584  0.03846781  0.02170894
  0.23716614  0.00634171  0.02078795  0.03189726  0.01735759  0.61129767]
the step is 256
total assets are 1.076629 BTC
Omega: [ 0.          0.03417967  0.00216813  0.01106524  0.0922714   0.04154938
  0.48342326  0.00888235  0.00864052  0.05430649  0.05263405  0.21087962]
the step is 257
total assets are 1.074899 BTC
Omega: [ 0.          0.04162823  0.00673574  0.00814335  0.16526453  0.04761716
  0.35483274  0.00410474  0.00075091  0.04570223  0.06369086  0.26152948]
the step is 258
total assets are 1.072901 BTC
Omega: [ 0.          0.04541799  0.01204357  0.00790741  0.17378911  0.05822272
  0.35782394  0.01505632  0.00385753  0.02718786  0.04887309  0.24982043]
the step is 259
total assets are 1.072092 BTC
Omega: [ 0.          0.03349705  0.01152797  0.02238649  0.19375603  0.04625059
  0.39644086  0.03698632  0.0637508   0.00490305  0.02652829  0.16397256]
the step is 260
total assets are 1.072298 BTC
Omega: [ 0.          0.04774447  0.17090648  0.0387846   0.25204825  0.03222429
  0.30844393  0.03177508  0.02233167  0.00262559  0.01489404  0.07822162]
the step is 261
total assets are 1.072852 BTC
Omega: [ 0.          0.05692745  0.07742213  0.0557404   0.30702457  0.05066169
  0.23245554  0.04915547  0.05031424  0.00295138  0.03161728  0.08572988]
the step is 262
total assets are 1.073894 BTC
Omega: [ 0.          0.1062092   0.13814719  0.05888925  0.35544038  0.04346132
  0.16675432  0.05978378  0.03628394  0.00694565  0.01588421  0.01220079]
the step is 263
total assets are 1.072804 BTC
Omega: [ 0.          0.15370357  0.09017035  0.00733261  0.28882155  0.05001764
  0.19542943  0.16232601  0.03901862  0.00369704  0.00506035  0.00442282]
the step is 264
total assets are 1.073072 BTC
Omega: [ 0.          0.1859957   0.20836888  0.0161259   0.17777106  0.07564259
  0.1885906   0.03957842  0.08090291  0.00240746  0.02331102  0.0013054 ]
the step is 265
total assets are 1.069136 BTC
Omega: [  0.00000000e+00   1.08230002e-01   1.34669751e-01   1.43176420e-02
   1.22302413e-01   8.33699182e-02   4.46197867e-01   3.09455488e-02
   4.42180112e-02   4.03899612e-05   1.37052098e-02   2.00328254e-03]
the step is 266
total assets are 1.069824 BTC
Omega: [  0.00000000e+00   9.99041945e-02   2.33634979e-01   9.82716307e-03
   1.16287678e-01   6.12512603e-02   4.44445044e-01   1.49864657e-02
   6.30186126e-03   7.95957385e-06   1.18158991e-02   1.53751881e-03]
the step is 267
total assets are 1.070341 BTC
Omega: [  0.00000000e+00   5.69408871e-02   4.07763511e-01   6.74934406e-03
   1.50218531e-01   1.13043666e-01   2.30078787e-01   1.58302598e-02
   1.15439091e-02   6.72987153e-06   4.86671366e-03   2.95762718e-03]
the step is 268
total assets are 1.071856 BTC
Omega: [  0.00000000e+00   3.54443006e-02   1.87005863e-01   2.71107396e-03
   1.95872843e-01   2.04017669e-01   2.38248020e-01   9.26509276e-02
   1.99040025e-02   3.78603982e-05   4.73497901e-03   1.93724465e-02]
the step is 269
total assets are 1.068013 BTC
Omega: [  0.00000000e+00   1.22024333e-02   3.68175656e-02   1.00647809e-03
   2.02857301e-01   2.09229618e-01   1.24637768e-01   2.07715452e-01
   1.92246139e-01   5.65628252e-05   1.07742334e-03   1.21531915e-02]
the step is 270
total assets are 1.069783 BTC
Omega: [ 0.          0.00486136  0.05079356  0.00106388  0.22036126  0.26339605
  0.15103884  0.18143857  0.08984464  0.00034029  0.00263997  0.03422159]
the step is 271
total assets are 1.068893 BTC
Omega: [  0.00000000e+00   5.56784775e-03   1.26014039e-01   3.53047872e-05
   1.19227618e-01   1.26768097e-01   9.49753523e-02   4.82744336e-01
   1.74567085e-02   1.01129175e-03   2.75792507e-03   2.34415159e-02]
the step is 272
total assets are 1.072932 BTC
Omega: [  0.00000000e+00   9.66345426e-03   9.94009450e-02   1.00811805e-04
   1.61058351e-01   1.81409091e-01   1.89891875e-01   2.79279262e-01
   2.38582287e-02   5.96985547e-03   2.69652903e-02   2.24028174e-02]
the step is 273
total assets are 1.074359 BTC
Omega: [  0.00000000e+00   5.38494380e-04   3.39601152e-02   2.27460332e-04
   5.15346937e-02   3.35111350e-01   3.43508780e-01   3.81003246e-02
   2.03585010e-02   6.20612986e-02   3.76260020e-02   7.69729912e-02]
the step is 274
total assets are 1.071104 BTC
Omega: [  0.00000000e+00   2.42563066e-04   1.06786964e-02   5.21210663e-04
   3.24599221e-02   1.96335718e-01   3.12520444e-01   8.77588429e-03
   1.63146537e-02   3.73313844e-01   2.07063346e-03   4.67663631e-02]
the step is 275
total assets are 1.070197 BTC
Omega: [  0.00000000e+00   4.99163812e-04   7.19833467e-03   1.72524236e-03
   3.17552090e-02   1.47083521e-01   9.33579654e-02   1.10117132e-02
   2.03019083e-02   6.47232294e-01   1.09275558e-03   3.87420133e-02]
the step is 276
total assets are 1.065359 BTC
Omega: [  0.00000000e+00   2.13051826e-04   8.40719882e-03   2.26607658e-02
   7.85645992e-02   8.56344402e-02   3.36107463e-02   1.84929203e-02
   7.15022311e-02   6.63873553e-01   5.74652478e-03   1.12939775e-02]
the step is 277
total assets are 1.064761 BTC
Omega: [  0.00000000e+00   1.18875549e-04   1.35570867e-02   3.69471349e-02
   1.60153449e-01   1.18320622e-01   1.06147721e-01   9.49567911e-05
   9.99770835e-02   4.52449471e-01   8.86510883e-04   1.13470899e-02]
the step is 278
total assets are 1.061400 BTC
Omega: [  0.00000000e+00   7.98586370e-06   1.20703131e-02   6.97710887e-02
   3.81630838e-01   3.00677568e-02   2.57717408e-02   2.65705657e-09
   4.05692607e-01   6.67418391e-02   8.11194070e-04   7.43460236e-03]
the step is 279
total assets are 1.060303 BTC
Omega: [  0.00000000e+00   2.26004322e-05   7.89309014e-03   1.24234483e-02
   2.74705827e-01   1.67145170e-02   3.57635133e-02   5.99388006e-09
   6.23962104e-01   1.40527161e-02   8.46665644e-04   1.36155803e-02]
the step is 280
total assets are 1.067103 BTC
Omega: [  0.00000000e+00   1.66831102e-04   5.80643639e-02   9.09322575e-02
   1.02069534e-01   5.85948229e-02   1.55054346e-01   1.76446344e-10
   5.03724158e-01   1.05741452e-02   3.95199284e-03   1.68675538e-02]
the step is 281
total assets are 1.054575 BTC
Omega: [  0.00000000e+00   6.49678695e-05   4.35730256e-02   2.24322826e-03
   3.64082940e-02   5.88806625e-03   2.33582184e-02   6.18944254e-14
   8.69755983e-01   9.54550167e-04   3.89741990e-03   1.38561903e-02]
the step is 282
total assets are 1.068482 BTC
Omega: [  0.00000000e+00   2.92209763e-04   3.73869479e-01   1.10972591e-03
   6.41345084e-02   1.45992711e-02   7.78464824e-02   4.84649734e-12
   4.01213586e-01   9.66459047e-04   1.70139316e-02   4.89542745e-02]
the step is 283
total assets are 1.064330 BTC
Omega: [  0.00000000e+00   7.85811862e-04   6.79579616e-01   2.16738018e-03
   1.40282456e-02   3.56179886e-02   6.04554499e-03   6.10538675e-10
   2.26898953e-01   9.42030456e-04   1.24404794e-02   2.14939080e-02]
the step is 284
total assets are 1.076091 BTC
Omega: [  0.00000000e+00   1.29217366e-02   1.30025879e-01   1.24123106e-02
   2.01895699e-01   7.52164721e-02   2.45534279e-03   1.05829861e-06
   4.32550400e-01   1.03851606e-03   2.44527720e-02   1.07029840e-01]
the step is 285
total assets are 1.073199 BTC
Omega: [  0.00000000e+00   5.34362718e-03   5.51222451e-02   6.25956745e-04
   2.06300080e-01   4.89953347e-02   1.49612606e-03   1.55355283e-05
   5.95938861e-01   5.17086824e-04   3.73305976e-02   4.83145490e-02]
the step is 286
total assets are 1.085568 BTC
Omega: [  0.00000000e+00   2.48961151e-02   1.15973562e-01   8.63013491e-02
   3.91753227e-01   2.62561589e-01   4.70719812e-03   8.18253175e-05
   6.05605058e-02   1.16714614e-03   3.93071808e-02   1.26902992e-02]
the step is 287
total assets are 1.078626 BTC
Omega: [  0.00000000e+00   6.67942408e-03   1.81443710e-02   6.55498803e-01
   1.09826021e-01   1.34067729e-01   1.64414216e-02   1.97273039e-05
   5.02751097e-02   5.48439508e-04   6.60856068e-03   1.89055502e-03]
the step is 288
total assets are 1.081110 BTC
Omega: [  0.00000000e+00   2.68835016e-03   6.42250245e-03   8.11986506e-01
   4.74417508e-02   6.19635731e-02   2.54519284e-02   1.14492490e-04
   1.37106050e-02   4.13178699e-04   2.65649408e-02   3.24207684e-03]
the step is 289
total assets are 1.082318 BTC
Omega: [ 0.          0.00107081  0.00074802  0.73231071  0.01560375  0.05872371
  0.03936032  0.0007718   0.00917829  0.00312204  0.04791574  0.09119488]
the step is 290
total assets are 1.074109 BTC
Omega: [  0.00000000e+00   2.29251542e-04   1.84969278e-04   8.95684004e-01
   5.78459725e-03   2.62956806e-02   1.30469352e-02   5.38026739e-04
   2.72146543e-03   4.23921132e-03   1.91770755e-02   3.20989043e-02]
the step is 291
total assets are 1.075366 BTC
Omega: [  0.00000000e+00   1.35150083e-04   4.29669948e-04   9.29171622e-01
   2.41158321e-03   2.53016446e-02   8.75803456e-03   6.08062022e-04
   3.91821051e-03   7.08836177e-03   2.16135923e-02   5.64024027e-04]
the step is 292
total assets are 1.081871 BTC
Omega: [  0.00000000e+00   3.38047801e-04   1.98578881e-03   8.13814700e-01
   8.10597837e-03   5.10176122e-02   3.46294492e-02   3.45699070e-03
   2.05367571e-03   5.41350506e-02   2.90929228e-02   1.36986026e-03]
the step is 293
total assets are 1.074618 BTC
Omega: [  0.00000000e+00   6.69507644e-05   1.44611369e-03   8.57060134e-01
   3.17532290e-03   2.09120922e-02   2.21375078e-02   9.07125417e-04
   1.24603848e-03   8.51652920e-02   7.73243606e-03   1.50970300e-04]
the step is 294
total assets are 1.064207 BTC
All the Tasks are Over

where is the nonlinearity?

I'm trying to understand about the nonlinearity in your network (except for the final softmax): in the current version of net_config.json, you list the 3 layers of the network as one ConvLayer, one EIIEDense and one EIIE_Output_WithW. In neither of them there is an entry to specify the activation function, and the default one of conv_2d in TFLearn is 'linear', so are you using a nonlinearity between the layers?

Question about "algo" command line options

Hi there,

First of all i would like to thank you to have shared the code, it is a very good work, also the code is clear to understand.I had followed your first paper too and implemented a live trading agent but without lucky.
This paper seems more interesting, also takes into consideration the transaction fees.

It's my question: Can't i use algo option for selecting specific algo when the mode is train ? is it always train with all algos with train_all command ?
In main.py i think there is a typing error (options.train_floder) on line 58.

Thank you very much in advance.

Exception "Have to be online" raised when training offline

Command that generate the error:
python main.py --mode=train --processes=1

Condition:
data offline, using provided Data.db in database folder

Configuration file:
./pgportfolio/net_config.json , 'online' option set to 'False'

Error logs:
$ python main.py --mode=train --processes=1 hdf5 is not supported on this machine (please install/reinstall h5py for optimal experience) training at 1 started select coins offline from 2017-04-03 12:28 to 2017-05-03 12:28 Process Process-1: Traceback (most recent call last): File "/usr/lib/python3.5/multiprocessing/process.py", line 249, in _bootstrap self.run() File "/usr/lib/python3.5/multiprocessing/process.py", line 93, in run self._target(*self._args, **self._kwargs) File "/home/jon/PGPortfolio/pgportfolio/autotrain/training.py", line 33, in train_one return TraderTrainer(config, save_path=save_path, device=device).train_net(log_file_dir=log_file_dir, index=index) File "/home/jon/PGPortfolio/pgportfolio/learn/tradertrainer.py", line 55, in __init__ self._matrix = DataMatrices.create_from_config(config) File "/home/jon/PGPortfolio/pgportfolio/marketdata/datamatrices.py", line 110, in create_from_config portion_reversed=input_config["portion_reversed"], File "/home/jon/PGPortfolio/pgportfolio/marketdata/datamatrices.py", line 51, in __init__ features=type_list) File "/home/jon/PGPortfolio/pgportfolio/marketdata/globaldatamatrix.py", line 62, in get_global_panel self.update_data(start, end, coin) File "/home/jon/PGPortfolio/pgportfolio/marketdata/globaldatamatrix.py", line 180, in update_data raise Exception("Have to be online") Exception: Have to be online ^CTraceback (most recent call last): File "main.py", line 132, in <module> main() File "main.py", line 56, in main pgportfolio.autotrain.training.train_all(int(options.processes), options.device) File "/home/jon/PGPortfolio/pgportfolio/autotrain/training.py", line 74, in train_all time.sleep(5) KeyboardInterrupt
Exception raise:
Have to be online

Different asset classes and time index

Hi!

Thank you for your great work and for the original paper, which has been a great inspiration in choosing a thesis topic as a master's student. I have been working on changing the code to work on FX assets.

I have changed the globaldatamatrix.py and especially the get_global_panel function to match my daily OHLC FX data without data for volume (which would be hard to extrapolate accurately from even a number of FX datasets including volume).

However I have come up with a problem regarding the creation of the panel in get_global_panel: the time_index that is created at line 71 is far longer than my actual data is, producing an error at line 117:
panel.loc[feature, coin, serial_data.index] = serial_data.squeeze().

The error:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-41-7b90bc3eb543> in <module>()
     57                                             parse_dates=["date_norm"],
     58                                             index_col="date_norm")
---> 59             panel.loc[feature, coin, serial_data.index] = serial_data.squeeze()
     60             panel = panel_fillna(panel, 'both')
     61 finally:

~\Anaconda3\lib\site-packages\pandas\core\indexing.py in __setitem__(self, key, value)
    177             key = com._apply_if_callable(key, self.obj)
    178         indexer = self._get_setitem_indexer(key)
--> 179         self._setitem_with_indexer(indexer, value)
    180 
    181     def _has_valid_type(self, k, axis):

~\Anaconda3\lib\site-packages\pandas\core\indexing.py in _setitem_with_indexer(self, indexer, value)
    577 
    578                     if len(labels) != len(value):
--> 579                         raise ValueError('Must have equal len keys and value '
    580                                          'when setting with an iterable')
    581 

ValueError: Must have equal len keys and value when setting with an iterable

From what I have understood the problem is that the len(serial_data) is some 700 obs less than time_index. I have gathered my data with the following:

def preprocess(sym, data_source, startD, endD):
    try:
        df = web.DataReader(sym, data_source, startD, endD)[['Open','High','Low','Close']]
        df.fillna('ffill')
        df.index = df.index.astype(np.int64) // 10**9
        if sym[3] != '=':
            df[['Open','High','Low','Close']] = 1/df[['Open','High','Low','Close']]
        coin = pd.Series(data = [sym[0:3] for number in range(len(df))])
        df['Coin'] = coin.values
        cols = df.columns.tolist
        cols = ['Coin','Open','High','Low','Close']
        df = df[cols]
        outN = './Thesis/Data/FX/'+str(sym[0:3])+'.csv'
        df.to_csv(outN, sep=',', decimal='.')
    except:
        print('Error for: ' + sym)

for sym in symbols:
    preprocess(sym, data_source, startD, endD)

I then merge the csv's and import to .db using DB Browser such that they are in the same form as the original cryptocurrency database. Below is the version that I have edited from the globaldatamatrix.py. Do you have recommendations on how to continue? Thank you already in advance, I am relatively new to programming.


from __future__ import division
from __future__ import absolute_import
from __future__ import print_function

from pgportfolio.marketdata.coinlist import CoinList
import numpy as np
import pandas as pd
from pgportfolio.tools.data import panel_fillna
from pgportfolio.constants import *
import sqlite3
from datetime import datetime
import logging


class HistoryManager:
    # if offline ,the coin_list could be None
    # NOTE: return of the sqlite results is a list of tuples, each tuple is a row
    def __init__(self, coin_number, end, volume_average_days=1, volume_forward=0, online=True):
        self.initialize_db()
        self.__storage_period = FIVE_MINUTES  # keep this as 300
        self._coin_number = coin_number
        self._online = online
        if self._online:
            self._coin_list = CoinList(end, volume_average_days, volume_forward)
        self.__volume_forward = volume_forward
        self.__volume_average_days = volume_average_days
        self.__coins = None

    @property
    def coins(self):
        return self.__coins

    def initialize_db(self):
        with sqlite3.connect(DATABASE_DIR) as connection:
            cursor = connection.cursor()
            cursor.execute('CREATE TABLE IF NOT EXISTS History (date INTEGER,'
                           ' coin TEXT, high REAL, low REAL,'
                           ' open REAL, close REAL, volume REAL, '
                           ' quoteVolume REAL, weightedAverage REAL,'
                           'PRIMARY KEY (date, coin));')
            connection.commit()

    def get_global_data_matrix(self, start, end, period=86400, features=('close',)):
        """
        :return a numpy ndarray whose axis is [feature, coin, time]
        """
        return self.get_global_panel(start, end, period, features).values

    def get_global_panel(self, start, end, period=86400, features=('close',)):
        """
        :param start/end: linux timestamp in seconds
        :param period: time interval of each data access point
        :param features: tuple or list of the feature names
        :return a panel, [feature, coin, time]
        """
        start = int(start - (start%period))
        end = int(end - (end%period))
        coins = self.select_coins(start=start,
                                  end=end)
        self.__coins = coins
        for coin in coins:
            self.update_data(start, end, coin)

        if len(coins)!=self._coin_number:
            raise ValueError("the length of selected coins %d is not equal to expected %d"
                             % (len(coins), self._coin_number))

        logging.info("feature type list is %s" % str(features))
        self.__checkperiod(period)

        time_index = pd.to_datetime(list(range(start, end+1, period)),unit='s')
        panel = pd.Panel(items=features, major_axis=coins, minor_axis=time_index, dtype=np.float32)

        connection = sqlite3.connect(DATABASE_DIR)
        try:
            for row_number, coin in enumerate(coins):
                for feature in features:
                    # NOTE: transform the start date to end date
                    if feature == "close":
                        sql = ("SELECT date+{period} AS date_norm, close FROM History WHERE"
                               " date_norm>={start} and date_norm<={end}" 
                               " and date_norm%{period}=0 and coin=\"{coin}\"".format(
                               start=start, end=end, period=period, coin=coin))
                    elif feature == "open":
                        sql = ("SELECT date+{period} AS date_norm, open FROM History WHERE"
                               " date_norm>={start} and date_norm<={end}" 
                               " and date_norm%{period}=0 and coin=\"{coin}\"".format(
                               start=start, end=end, period=period, coin=coin))
                    elif feature == "volume":
                        sql = ("SELECT date_norm, SUM(volume)"+
                               " FROM (SELECT date+{period}-(date%{period}) "
                               "AS date_norm, volume, coin FROM History)"
                               " WHERE date_norm>={start} and date_norm<={end} and coin=\"{coin}\""
                               " GROUP BY date_norm".format(
                                    period=period,start=start,end=end,coin=coin))
                    elif feature == "high":
                        sql = ("SELECT date_norm, MAX(high)" +
                               " FROM (SELECT date+{period}-(date%{period})"
                               " AS date_norm, high, coin FROM History)"
                               " WHERE date_norm>={start} and date_norm<={end} and coin=\"{coin}\""
                               " GROUP BY date_norm".format(
                                    period=period,start=start,end=end,coin=coin))
                    elif feature == "low":
                        sql = ("SELECT date_norm, MIN(low)" +
                                " FROM (SELECT date+{period}-(date%{period})"
                                " AS date_norm, low, coin FROM History)"
                                " WHERE date_norm>={start} and date_norm<={end} and coin=\"{coin}\""
                                " GROUP BY date_norm".format(
                                    period=period,start=start,end=end,coin=coin))
                    else:
                        msg = ("The feature %s is not supported" % feature)
                        logging.error(msg)
                        raise ValueError(msg)
                    serial_data = pd.read_sql_query(sql, con=connection,
                                                    parse_dates=["date_norm"],
                                                    index_col="date_norm")
                    panel.loc[feature, coin, serial_data.index] = serial_data.squeeze()
                    panel = panel_fillna(panel, "both")
        finally:
            connection.commit()
            connection.close()
        return panel

    # select top coin_number of coins by volume from start to end
    def select_coins(self, start, end):
        if not self._online:
            logging.info("select coins offline from %s to %s" % (datetime.fromtimestamp(start).strftime('%Y-%m-%d %H:%M'),
                                                                    datetime.fromtimestamp(end).strftime('%Y-%m-%d %H:%M')))
            connection = sqlite3.connect(DATABASE_DIR)
            try:
                cursor=connection.cursor()
                cursor.execute('SELECT coin FROM History WHERE'
                               ' date>=? and date<=? GROUP BY coin',
                               (int(start), int(end)))
                coins_tuples = cursor.fetchall()

                if len(coins_tuples)!=self._coin_number:
                    logging.error("the sqlite error happend")
            finally:
                connection.commit()
                connection.close()
            coins = []
            for tuple in coins_tuples:
                coins.append(tuple[0])
        else:
            coins = list(self._coin_list.topNVolume(n=self._coin_number).index)
        logging.debug("Selected coins are: "+str(coins))
        return coins

    def __checkperiod(self, period):
        if period == FIVE_MINUTES:
            return
        elif period == FIFTEEN_MINUTES:
            return
        elif period == HALF_HOUR:
            return
        elif period == TWO_HOUR:
            return
        elif period == FOUR_HOUR:
            return
        elif period == DAY:
            return
        else:
            raise ValueError('peroid has to be 5min, 15min, 30min, 2hr, 4hr, or a day')

    # add new history data into the database
    def update_data(self, start, end, coin):
        connection = sqlite3.connect(DATABASE_DIR)
        try:
            cursor = connection.cursor()
            min_date = cursor.execute('SELECT MIN(date) FROM History WHERE coin=?;', (coin,)).fetchall()[0][0]
            max_date = cursor.execute('SELECT MAX(date) FROM History WHERE coin=?;', (coin,)).fetchall()[0][0]

            if min_date==None or max_date==None:
                self.__fill_data(start, end, coin, cursor)
            else:
                if max_date+10*self.__storage_period<end:
                    if not self._online:
                        raise Exception("Have to be online")
                    self.__fill_data(max_date + self.__storage_period, end, coin, cursor)
                if min_date>start and self._online:
                    self.__fill_data(start, min_date - self.__storage_period-1, coin, cursor)

            # if there is no data
        finally:
            connection.commit()
            connection.close()

    def __fill_data(self, start, end, coin, cursor):
        chart = self._coin_list.get_chart_until_success(
            pair=self._coin_list.allActiveCoins.at[coin, 'pair'],
            start=start,
            end=end,
            period=self.__storage_period)
        logging.info("fill %s data from %s to %s"%(coin, datetime.fromtimestamp(start).strftime('%Y-%m-%d %H:%M'),
                                            datetime.fromtimestamp(end).strftime('%Y-%m-%d %H:%M')))
        for c in chart:
            if c["date"] > 0:
                if c['weightedAverage'] == 0:
                    weightedAverage = c['close']
                else:
                    weightedAverage = c['weightedAverage']

                #NOTE here the USDT is in reversed order
                if 'reversed_' in coin:
                    cursor.execute('INSERT INTO History VALUES (?,?,?,?,?,?,?,?,?)',
                        (c['date'],coin,1.0/c['low'],1.0/c['high'],1.0/c['open'],
                        1.0/c['close'],c['quoteVolume'],c['volume'],
                        1.0/weightedAverage))
                else:
                    cursor.execute('INSERT INTO History VALUES (?,?,?,?,?,?,?,?,?)',
                                   (c['date'],coin,c['high'],c['low'],c['open'],
                                    c['close'],c['volume'],c['quoteVolume'],
                                    weightedAverage))

Portfolio memory question

Hello!

During training

The previous portfolio weights are inserted as an extra feature map before the scoring layer, for the agent to minimize transaction cost

As I understand we store portfolio values which are outputs of network, but may be it would be better if we insert rebalanced previous portfolio weights, i.e. previous portfolios in the end of period?

w_t-1_rebalanced = rebalanced(network.output_t-1)
w_t = network.output_t(w_t-1_rebalanced)

Thanks

Stock Application

Hello, I am interested in applying this solution to stock markets instead of cryptocurrencies. I Have a csv file containing the Open High Low Close of each one of my stocks. Let's say I Have 5 stocks for example.
I would like to know how should I proceed in order to adapt this solution to the stock market instead.

Really nice project.
Thank you

new live data config settings

Hello,
I have been trying to code the live trader, but 1 issue facing me is how to get live poloniex data while using the classes already implemented, of course i can hardcode 'generate_history_matrix' of the trader class to create the [3,11,31] data every tick manually but i am asking for the right way of doing it using the config settings since i didn't understand it.

i mean how to automate pulling the live data in sync. with the database.
Sorry for too much questions.
Regards

Long/short equity

First off, thanks for publishing the paper as well as the code, it will help me a lot.

Now for the question. As I understand the layer before softmax offers sort of 'ranking' of coins, where higher rank can be interpreted as higher possibility of price rise.

I planned on editing the code to use this layer as ranking for long/short equity strategy which hedges more against the market movements. I would test it on this years' data since a lot of things happened and would compare it against the current 'long only' method that is provided in the paper.

I do not need any technical help yet, but from the theoretical perspective what are your thoughts on this, since you probably have more insight on what your network is capable of? Or have you tried similar things so far?

ForwardTest class

Hi, thank you for your excellent work, this is very interesting stuff.

I am eager to test this on the live market, but having trouble moving from backtesting to forwardtesting. Any chance that an update with a ForwardTest class is on the way, or that you could advise on how to implement it? I understand it roughly, i.e. the generate_history_matrix( ) function needs to update the datamatrix with the newest market data (with "online" = True in the config file), and return that. And the trade_by_strategy( ) clearly needs a slight rewriting compared to BackTest as we don't know the future price. Any help on how to correctly return the newest market data would be appreciated.

Sharpe ratio as loss function

Hello all!

I wonder if you've tried to use Sharpe ratio directly to optimize portfolio selection? With controlling both mean and variance parts it seems to allow control risk management of portfolio selection and minimize drawdawn?

Although I saw in literature that risk sensitive policy is less effective than risk neutral one I want to hear your opinion.

Thanks!

better portfolio reallocation

The current portfolio reallocation step is divided into two parts: selling the necessary assets to convert them into BTC, and then buying the new assets. I'm wondering if it would be possible to adopt a more clever strategy.

For example, if the current portfolio is [0,1,0] and the desired one is [0,0,1], we need to pay 0.025% of fees for selling and another 0.025% for buying. But wouldn't it be more efficient to exchange the second and third assets directly, without going through BTC and so pay only 0.025% once?

how to get time index from __get_matrix_X()

This is not really an issue, but I'd like to find a way to reliably find the time indices of the values extracted from the database with self.get_submatrix(index) and __pack_samples(self, indexs). I understand that the time indices can be accessed with timeindices = self.__global_data.minor_axis, but how to do this inside the two previously mentioned methods?
What I'm trying to do is basically find out to which time index each of these 'X' matrices belongs to:

    def __get_matrix_X(self):
        return self.__test_set["X"][self._steps]

Extending the data into the past

Hi,

If a currency doesn't have enough data before a certain point in time, how do you extend it? With constant values? if so how do you pick the value?

I think I understood that you use the oldest non-NaN value, but some currencies have a crazy initial spike before settling very close to zero, so I'm not sure that's what you actually do.

y(t) = close(t)/close(t-1) or y(t) = close(t)/open(t)?

Thanks for putting the code up. Can I ask for a minor clarification?

In the paper it said you have y(t) = close(t)/open(t) but in the code there is y(t) = close(t)/close(t-1)

The paper also divides the batch X by the open(t) (X=M/open(t)) but in the code it doesn't look like it's divided/scaled (X=M)?

Heres the code I'm talking about. I think the shape of M is (batch, features, coins, times) where features are ["close", "high", "low", "open"].

Have these things changed since the paper or am I misunderstanding something?

Thanks!

Selecting prices for online operations

What is your experience with actual online trades? If I use the closing price, most of the orders end up not being executed because by the time I issue the buy/sell order, the price has already changed.

I tried mitigating this problem by training the agent with higher fee rates and offsetting that extra fee to a worse price for me (so that the order will most certainly be executed), but the agent can't get a return > 1 even with 0.30% of fees instead of 0.25%.

About training period and backtest period

Hi
I am new to this project and try to do some deeper investigation for this framwork.
How could I set specific period for both training and backtesting, such as using 2010/01/01-2013/12/31 to train a model, and backtesting it (online training) from 2014/02/01 to 2014/12/31?
Thanks a lot!

Backtest trade by strategy, check fees vs coin value update

In BackTest, "omega" seems to be the vector wT storing the recommended new portfolio distribution at each step, "_last_omega" the latest/previous portfolio screenhost wT-1. So the system assumes to be able to sell at each step all the current coins of the portfolio and buy all "omega" reco, or at least the delta between omega & last_omega. This strong hypothesis (slippage/liquidity) is in your paper but shouldn't it check at least whether any coin qty adjustment would not cost more transaction fees than the expected value adjustment ?

working config

Im trying reproduce result plotted in User Guide (10^2), but with default config getting much worse results. Which config was used in example?
Thanks!

reversed_USDT vs BTC

Hello,

In the code, i don't understand what is the difference between reversed_USDT and the cash (BTC).

I supposed (USDT_BTC) which is actually BTC/USD is a mapping to just holding some weight in BTC

Am i wrong ?

training time

How long does it take to properly train the agent, on your machines? (I have a laptop without a GPU)

'./train_package/train_summary.csv' was not produced.

As the user guide,
First,I trained the mode:python main.py --mode=train --processes=1
Second, I run a back-test: python main.py --mode=backtest --algo=1
It seems successed.
Third, I run a plot. It failed. The programm need a file './train_package/train_summary.csv'.
But the file was not produced by the train or back-test process.
Progaram out put detail:

..............

the step is 2775
the raw omega is [ 0.00000000e+00 1.67575441e-02 8.37479383e-02 6.0264140
4e-01
2.47207396e-02 4.36192416e-02 1.71170235e-02 1.87526122e-01
2.03962550e-02 8.20985821e-04 2.59831552e-07 2.65252125e-03]
the portfolio change this period is : 1.0040169427478371
a new experience, indexed by 35024, was appended
total assets are 2.016892 BTC

(TensorFlow) D:\work\benew\backTest\PGPortfolio-master>python main.py --mode=plo
t --algos=1 --labels=crp,olmar,nnagent
D:\work\benew\backTest\PGPortfolio-master\pgportfolio\resultprocess\plot.py:164:
FutureWarning: from_csv is deprecated. Please use read_csv(...) instead. Note t
hat some of the default arguments are different, so please refer to the document
ation for from_csv when changing your function calls
dataframe = pd.DataFrame.from_csv("./train_package/train_summary.csv")
Traceback (most recent call last):
File "main.py", line 132, in
main()
File "main.py", line 97, in main
plot.plot_backtest(load_config(), algos, labels)
File "D:\work\benew\backTest\PGPortfolio-master\pgportfolio\resultprocess\plot
.py", line 52, in plot_backtest
results.append(np.cumprod(_load_from_summary(algo, config)))
File "D:\work\benew\backTest\PGPortfolio-master\pgportfolio\resultprocess\plot
.py", line 164, in _load_from_summary
dataframe = pd.DataFrame.from_csv("./train_package/train_summary.csv")
File "C:\ProgramData\Anaconda3\envs\TensorFlow\lib\site-packages\pandas\core\f
rame.py", line 1361, in from_csv
infer_datetime_format=infer_datetime_format)
File "C:\ProgramData\Anaconda3\envs\TensorFlow\lib\site-packages\pandas\io\par
sers.py", line 705, in parser_f
return _read(filepath_or_buffer, kwds)
File "C:\ProgramData\Anaconda3\envs\TensorFlow\lib\site-packages\pandas\io\par
sers.py", line 445, in _read
parser = TextFileReader(filepath_or_buffer, **kwds)
File "C:\ProgramData\Anaconda3\envs\TensorFlow\lib\site-packages\pandas\io\par
sers.py", line 814, in init
self._make_engine(self.engine)
File "C:\ProgramData\Anaconda3\envs\TensorFlow\lib\site-packages\pandas\io\par
sers.py", line 1045, in _make_engine
self._engine = CParserWrapper(self.f, **self.options)
File "C:\ProgramData\Anaconda3\envs\TensorFlow\lib\site-packages\pandas\io\par
sers.py", line 1684, in init
self._reader = parsers.TextReader(src, **kwds)
File "pandas_libs\parsers.pyx", line 391, in pandas._libs.parsers.TextReader.
cinit
File "pandas_libs\parsers.pyx", line 710, in pandas._libs.parsers.TextReader.
_setup_parser_source
FileNotFoundError: File b'./train_package/train_summary.csv' does not exist

Backtest when fast_train=false raises error

Greetings!
First of all, thank you for the amazing work! I find it a very elegant method and the paper is great at describing it.

I think I've encountered an issue while doing backtest with the flag fast_train=false in the settings.
It looks like the function _evaluate(), at line 80 of tradertrainer.py, is called with the argument set_name='validation', but is not able to handle such input.
Is it something which is still to be developed?

Thank you!

Portfolio weights (real time)

First, congratulations on the great work!

I would like to know how to access the date frame of updated weights every 30 minutes for trades in real time. Currently I have some models in R, already operating online, but I do not have much knowledge in Python. Anyone would like to collaborate? All the methods of access to the exchanges and the launching of orders are already developed.

yukie

Question about reward function and `__pack_samples`

I'm having trouble reconciling what I read in the paper and what I read in the code.

The reward function in a single period in the paper (Eq. (10)) is \log(\mu_t y_t \cdot w_{t-1}). But in the code, it seems that the reward is instead \log(mu_t y_{t+1} \cdot w_{t}). Am I correct?

Because __pack_samples (in datamatrices.py) makes the price tensor X using M[..., :-1] and the relative price vector y using M[...,-1]/M[...,-2], so y is one period ahead of X.

Automatic hyperparameter optimization

I think it would be interesting to extend the code with hyperparameter optimization like Bayesian Optimisation. Would you be interested in integrating that with your codebase?

features besides ohlc

I'm not familiar with reinforcement learning so this might be a newbie question.
In other areas of data science, feature engineering can significantly affect the performance. As for quantitative trading, indicators (generated from ohlc data) like MACD usually can improve the performance of models. I would like to know did you use only ohlc prices for features on purpose (maybe it's not necessary in case of reinforcement learning) or is this considered as future work?

Experience related to selected coins.

Hello,

I noticed something while backtesting, the model new experience index is not following the previous backtesting if the selected coins is different.

does that mean that model experience gained is only related to the coins it's trained on ?

Not an issue but suggestion for data

Hi yaojiang,
As you know, google Captcha not work in China, so the data in poloniex.com I cannot download successfully. Could you upload those data for a while?

Issue about train_summary.csv

Hi, I am following your instruction on user_guide.md. You mention the file named train_summary and train_summary.csv from time to time which I think store the results of training. However, I could not find in your project where you generate such a file. Neither could I generate one by following your instruction. Look forward to your answer. Thank you so much!

Eq. (16)

Surely you meant 1 - [current equation]?
As it is now, if there were no change in the portfolio vector, mu_guess would be zero, which is a terrible guess (mu_t is 1). Also in the case in which there are no fees (c=0), you'd guess 0.

Using prices directly as opposed to price relative vector?

I was looking through the code and I noticed, if I understand correctly, that the inputs to the neural network are the prices directly and not the price relative vector defined in eq(1) of the paper. Is this intentional? Did I misread the code?

I guess it doesn't matter too much since, relative to BTC, prices of all other assets are < 1, but was curious if this was on purpose.

Here's the code I am looking at, where the price relative vector is passed to traditional agents but not to the neural network.

def generate_history_matrix(self):
        inputs = self.__get_matrix_X()
        if self._agent_type == "traditional":
            inputs = np.concatenate([np.ones([1, 1, inputs.shape[2]]), inputs], axis=1)
            inputs = inputs[:, :, 1:] / inputs[:, :, :-1]
        return inputs

data interval

It seems to be hard coded 5 minute interval for data. Can it be configured for 1 minute or 1 hour / day by using other data sources?
Thanks!

Price norm_method

Greetings!

Thank you for posting your incredible work!

if I understood you correctly - then the normalization of prices in the current code is not used
"norm_method": "relative", / "absolute"
I did not find where the function "pricenorm3d" is called
the percentage of price increment/decrements is used as a result - y
Is it so that the "RAW" price values are used - X?

How does the network summarize price data for the past periods when prices differed by an order of magnitude?
or is it done intentionally to take only the closest experience when prices were on the same scale?

I apologize if this is an obvious question, and also for my English

thank you

online training

Hello

Thanks for the wonderful work, i read your paper and almost studied most of the code. However, i don't get the concept of append_experience and agent train in the rolling_train method
I have some questions if i may ask
1- what is the format of the saved experience and how does it affect the model ?
2- how is that different from training the model directly using self._agent.train() ?
3- is the experience mentioned here the same as the mini-batches mentioned in the paper for online learning section 5.3 for example ?

thanks in advance
Sarah Ahmed

Trading agent

Hello great team,

is there a trading agent already built to trade live using the saved trained model ?

I would be interested to help either by building or by improving existing.

Regards,

Weight sharing in CNN

Hi everyone! First of all, thanks for the article and for sharing the code, you made a great job!

Now the question. In article it's said:

Apart from weight-sharing among receptive fields in a feature map, which is a usual CNN characteristic, parameters are also shared between rows in an EIIE configuration.

But I couldn't find realization of this feature in code :( Can you help, or this idea was deprecated?

Thanks!

Bad performing example for NNAgent

Hi,

thank you for making your framework publically available.
I was playing with it recently and I while testing it on different timeframes and coin setups I stumbled upon a set of input data where NNAgent performs worse than UBAH, CRP, BEST algos. I thought you, or people visiting your repo, might be interested in examining it. I might even be interesting to include it (or some other input sets you have) in the next version of your paper to demonstrate where it isn't performing.

This is the json config file I used:

{
  "layers":
  [
    {"filter_shape": [1, 2], "filter_number": 3, "type": "ConvLayer"},
    {"filter_number":10, "type": "EIIE_Dense", "regularizer": "L2", "weight_decay": 5e-9},
    {"type": "EIIE_Output_WithW","regularizer": "L2", "weight_decay": 5e-8}
  ],
  "training":{
    "steps":80000,
    "learning_rate":0.00028,
    "batch_size":109,
    "buffer_biased":5e-5,
    "snap_shot":false,
    "fast_train":true,
    "training_method":"Adam",
    "loss_function":"loss_function6"
  },

  "input":{
    "window_size":31,
    "coin_number":4,
    "global_period":1800,
    "feature_number":3,
    "test_portion":0.08,
    "online":false,
    "start_date":"2017/03/17",
    "end_date":"2018/02/02",
    "volume_average_days":30,
    "coins": ["ETH", "LTC", "reversed_USDT", "BCH"]
  },

  "trading":{
    "trading_consumption":0.0025,
    "rolling_training_steps":85,
    "learning_rate":0.00028,
    "buffer_biased":5e-5
  }
}

The difference is in the period times and me enforcing using explicit set of assets to trade (custom change I made in the code).
This is the chart I get:
result

By the way - your implementation of UBAH is using hardcoded number of assets.

Downloading data

Hi!

First of all, thank you for your code.

I ran into an error when I wanted to download the data online when training.

An error at "Poloniex.py" occurs with:
urllib.error.URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:749)>

I have already used a global VPN whose server is in LA. And everything works fine when I download data with python main.py --mode=download_data.

So I think it is not a problem with the connection to Poloniex (although I am in China).

Could anyone help me with this issue? Thanks

Mac OS X support

First of all, I'd like to thank you for your work! I was able to run the code in Windows, the only minor issue was to install some modules for python 3.5, had to find some unofficial wheels.
However, I couldn't make it run on MacOS X, it's crashing due to an unknown error (¨python quit unexpectedly¨). I know this is not officially supported, but I'd like to know if you have any hints on what might be the issue...
Here's what I already tried:
-Deleted .DS_Store files from all subdirectories (so that it passes the if not str.isdigit(dir): condition)
-Tried different python versions and clean environments
It fails to executeTraderTrainer(config, save_path=save_path, device=device).train_net(log_file_dir=log_file_dir, index=index). The log file is created but remains empty... Do you think this has something to do with pathname issues in OS X or the python modules?

Four undefined names

flake8 testing of https://github.com/ZhengyaoJiang/PGPortfolio on Python 3.6.3

$ flake8 . --count --select=E901,E999,F821,F822,F823 --show-source --statistics

./pgportfolio/tdagent/tdagent.py:110:24: F821 undefined name 'x'
        x_0 = np.zeros(x.size)
                       ^

./pgportfolio/tdagent/tdagent.py:114:37: F821 undefined name 'x'
        bnds = [(0., max_leverage)]*x.size
                                    ^

./pgportfolio/tdagent/tdagent.py:119:21: F821 undefined name 'x'
                x = x + np.random.randn(1)[0] * 1e-5
                    ^

./pgportfolio/tools/configprocess.py:81:28: F821 undefined name 'unicode'
    elif isinstance(input, unicode):
                           ^

4     F821 undefined name 'x'

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.