Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

error during SIGNAL run. dividing to ZERO #30

Open
cebbot opened this issue Jul 23, 2023 · 12 comments
Open

error during SIGNAL run. dividing to ZERO #30

cebbot opened this issue Jul 23, 2023 · 12 comments

Comments

@cebbot
Copy link

cebbot commented Jul 23, 2023

Dobriy Den Alexander,

I ınstalled all files. worked TRAINING SIGNAL also.
python -m scripts.features -c config.json after this comment giving ERROR. it is can not divide to ZERO with row 186, 182 etc.

how can ı work with this bot.

Have a nice day

@cebbot
Copy link
Author

cebbot commented Jul 23, 2023

PS C:\intelligent-trading-bot-master> python -m service.server -c config.json
Initializing server. Trade pair: BTCUSDT.
Finished health check (connection, server status etc.)
Finished initial data collection.
Scheduler started.
C:\intelligent-trading-bot-master\common\feature_generation_rolling_agg.py:159: RuntimeWarning: invalid value encountered in scalar divide
ratio = pos / b # in [0,1]
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:182: RuntimeWarning: invalid value encountered in scalar divide
slope = ssxym / ssxm
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:196: RuntimeWarning: invalid value encountered in sqrt
t = r * np.sqrt(df / ((1.0 - r + TINY)(1.0 + r + TINY)))
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:199: RuntimeWarning: invalid value encountered in scalar divide
slope_stderr = np.sqrt((1 - r**2) * ssym / ssxm / df)
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:182: RuntimeWarning: invalid value encountered in scalar divide
slope = ssxym / ssxm
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:196: RuntimeWarning: invalid value encountered in sqrt
t = r * np.sqrt(df / ((1.0 - r + TINY)
(1.0 + r + TINY)))
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:199: RuntimeWarning: invalid value encountered in scalar divide
slope_stderr = np.sqrt((1 - r**2) * ssym / ssxm / df)

@cebbot
Copy link
Author

cebbot commented Jul 23, 2023

FYI
Epoch 200, change: 0.00080476
max_iter reached after 60 seconds
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\sklearn\linear_model_sag.py:350: ConvergenceWarning: The max_iter was reached which means the coef_ did not converge
warnings.warn(
LABELS: 100%|██████████████████████████████████████████████████████████████████████████| 10/10 [08:16<00:00, 49.62s/it]
Models stored in path: C:\intelligent-trading-bot-master\data\btcusdt\MODELS
Metrics stored in path: C:\intelligent-trading-bot-master\data\btcusdt\prediction-metrics.txt
Storing output file...
Predictions stored in file: C:\intelligent-trading-bot-master\data\BTCUSDT\predictions. Length: 262618. Columns: 27
Finished training models in 0:08:58
PS C:\intelligent-trading-bot-master> python -m scripts.signals -c config.json

Loading predictions from input file: C:\intelligent-trading-bot-master\data\BTCUSDT\predictions.csv
Predictions loaded. Length: 262618. Width: 27
Metrics stored in path: C:\intelligent-trading-bot-master\data\btcusdt\signal-metrics.txt
Storing output file...
Signals stored in file: C:\intelligent-trading-bot-master\data\BTCUSDT\signals. Length: 262618. Columns: 24
Finished signal generation in 0:00:06
PS C:\intelligent-trading-bot-master> python -m scripts.train_signals -c config.json

Loading signals from input file: C:\intelligent-trading-bot-master\data\BTCUSDT\signals.csv
C:\intelligent-trading-bot-master\scripts\train_signals.py:96: DtypeWarning: Columns (20) have mixed types. Specify dtype option on import or set low_memory=False.
df = pd.read_csv(file_path, parse_dates=[time_column], nrows=P.in_nrows)
Signals loaded. Length: 262618. Width: 24
MODELS: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:01<00:00, 5.67it/s]
Simulation results stored in: C:\intelligent-trading-bot-master\data\btcusdt\signal_models.txt. Lines: 9.
Finished simulation in 0:00:02

@cebbot
Copy link
Author

cebbot commented Aug 5, 2023

I download all files from Github.
add my binance API
open C:\DATA_ITB\BTCUSDT
run all command on power shell
last command is not working properly
PS C:\intelligent-trading-bot-master> python -m service.server -c config.json
Initializing server. Trade pair: BTCUSDT.
Finished health check (connection, server status etc.)
Finished initial data collection.
Scheduler started.
C:\intelligent-trading-bot-master\common\feature_generation_rolling_agg.py:159: RuntimeWarning: invalid value encountered in scalar divide
ratio = pos / b # in [0,1]
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:182: RuntimeWarning: invalid value encountered in scalar divide
slope = ssxym / ssxm
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:196: RuntimeWarning: invalid value encountered in sqrt
t = r * np.sqrt(df / ((1.0 - r + TINY)(1.0 + r + TINY)))
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:199: RuntimeWarning: invalid value encountered in scalar divide
slope_stderr = np.sqrt((1 - r**2) * ssym / ssxm / df)
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:182: RuntimeWarning: invalid value encountered in scalar divide
slope = ssxym / ssxm
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:196: RuntimeWarning: invalid value encountered in sqrt
t = r * np.sqrt(df / ((1.0 - r + TINY)
(1.0 + r + TINY)))
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:199: RuntimeWarning: invalid value encountered in scalar divide
slope_stderr = np.sqrt((1 - r**2) * ssym / ssxm / df)
C:\intelligent-trading-bot-master\common\feature_generation_rolling_agg.py:159: RuntimeWarning: invalid value encountered in scalar divide
ratio = pos / b # in [0,1]

@asavinov
Copy link
Owner

asavinov commented Aug 6, 2023

Hi, as far as I understood you have division by zero in feature generation. There could be multiple reasons for that. If you provide more information about what features you generate then probably we find where is the problem. What is in your config?

@cebbot
Copy link
Author

cebbot commented Aug 6, 2023

Hi Alexander,
I am happy to get answer my question. Thank you !
I want to explain shortly what ı did.
1- I am using Win 10 Home
2-I installed Python 3.11 (64bit)
3-I am using config.json which you put in github config-sample-v0.6.dev.json.
4-I add only my binance API key and secret.
5- open folder C:\DATA_ITB\BTCUSDT
6- using all below command at power shell in C:\intelligent-trading-bot-master
pip install -r requirements.txt
python -m scripts.download_binance -c config.json
python -m scripts.merge -c config.json
python -m scripts.features -c config.json
python -m scripts.labels -c config.json
python -m scripts.train -c config.json
python -m scripts.signals -c config.json
python -m scripts.train_signals -c config.json
python -m service.server -c config.json

all abowe command working properly except 'python -m service.server -c config.json'.
7-after latst command can see below warning:
PS C:\intelligent-trading-bot-master> python -m service.server -c config.json
Initializing server. Trade pair: BTCUSDT.
Finished health check (connection, server status etc.)
Finished initial data collection.
Scheduler started.
C:\intelligent-trading-bot-master\common\feature_generation_rolling_agg.py:159: RuntimeWarning: invalid value encountered in scalar divide
ratio = pos / b # in [0,1]
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:182: RuntimeWarning: invalid value encountered in scalar divide
slope = ssxym / ssxm
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:196: RuntimeWarning: invalid value encountered in sqrt
t = r * np.sqrt(df / ((1.0 - r + TINY)(1.0 + r + TINY)))
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:199: RuntimeWarning: invalid value encountered in scalar divide
slope_stderr = np.sqrt((1 - r2) * ssym / ssxm / df)
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:182: RuntimeWarning: invalid value encountered in scalar divide
slope = ssxym / ssxm
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:196: RuntimeWarning: invalid value encountered in sqrt
t = r * np.sqrt(df / ((1.0 - r + TINY)(1.0 + r + TINY)))
C:\Users\PC2\AppData\Local\Programs\Python\Python311\Lib\site-packages\scipy\stats_stats_mstats_common.py:199: RuntimeWarning: invalid value encountered in scalar divide
slope_stderr = np.sqrt((1 - r
2) * ssym / ssxm / df)
C:\intelligent-trading-bot-master\common\feature_generation_rolling_agg.py:159: RuntimeWarning: invalid value encountered in scalar divide
ratio = pos / b # in [0,1]

image
image

some files very large in C:\DATA_ITB\BTCUSDT folder, I can send link if you want.
other all files dowloaded from github.

Please, text me where is my mistake

Thank you in advance,

Cebrail

@asavinov
Copy link
Owner

asavinov commented Aug 7, 2023

Is it the latest version? If not then could you please update your installation and execute all steps again. The reason is that I did many fixes and now it should run without problems.

@cebbot
Copy link
Author

cebbot commented Aug 7, 2023

I cannot install TA-LIB propely.
trying to install to python on Win 10 based OS.
ı will text to you when I am installing this library.
Thanks agin

@cebbot
Copy link
Author

cebbot commented Aug 12, 2023

Hello Alexander,

it is STARTED to work. :)

now I am trying it at Binance.

I will text you result of bot.

Thank you for your help!

image

@cebbot
Copy link
Author

cebbot commented Sep 7, 2023

  Hello Alexander,

Still Ta-lib has some problem


build\lib.win-amd64-cpython-39\talib_ta_lib.cp39-win_amd64.pyd : fatal error LNK1120: 339 ‡”z\x81mlenmemiŸ d\x8dŸlar
error: command 'C:\Program Files (x86)\Microsoft Visual Studio\2022\BuildTools\VC\Tools\MSVC\14.37.32822\bin\HostX86\x64\link.exe' failed with exit code 1120
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for ta-lib
Failed to build ta-lib
ERROR: Could not build wheels for ta-lib, which is required to install pyproject.toml-based projects
PS C:\intelligent-trading-bot-master>

@asavinov
Copy link
Owner

You can install it using conda conda install -c conda-forge ta-lib which includes Windows binary library.

If you do not want to use conda for your porject then just do it one time (install miniconda and then ta-ib), get the binary from this installation, and copy this lib to your normal environment (without conda). It did not try it but it should work.

@cebbot
Copy link
Author

cebbot commented Sep 11, 2023

Hello Alexander,
I install now Ananconda. ı used powershell as administrator.
image
still can not install ta-lib.
good night

@asavinov
Copy link
Owner

asavinov commented Sep 15, 2023

It seems that the package is not available for Python 3.11. Try Python 3.10:

conda create -n itb python=3.10
conda activate itb
conda install -c conda-forge ta-lib

Then start python and execute line by line:

import talib
import numpy as np
talib.SMA(np.array([1.0,2,3,4,5]), 2)

If it prints something then it works.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants