pisimo/bitcoinforecast

Predict bitcoin price with deep learning

bitcoinforecast's Issues

Can't get response from https://api.coinmarketcap.com/v1/ticker/bitcoin/

Can't get response from https://api.coinmarketcap.com/v1/ticker/bitcoin/

Grabber pull issue

I have a Problem
When i Run the grabber after a while i get a "Too many request" from "https://blockchain.info/ticker", i think there a to many requests

from where I can download the latest csv for input to your program. Kindly help.

Data Source

Data source dataset.csv Where to get updates

Error while running the program

File "network.py", line 117, in
net.fit(data[:el],labels[:el],epochs=epochs,batch_size=300)
File "/usr/local/lib/python3.5/dist-packages/keras/models.py", line 965, in fit
validation_steps=validation_steps)
File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 1593, in fit
batch_size=batch_size)
File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 1426, in _standardize_user_data
exception_prefix='input')
File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 70, in _standardize_input_data
data = [np.expand_dims(x, 1) if x is not None and x.ndim == 1 else x for x in data]
File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 70, in
data = [np.expand_dims(x, 1) if x is not None and x.ndim == 1 else x for x in data]
AttributeError: 'list' object has no attribute 'ndim'

Question?

What's the purpose of running grabber 2/3 days to get the new data when I can just fetch it all in a second?

Could you explain your point of view please?

thanks mate

Why is the price deviation calculated so much?

Starting main loop...
[23:08:22] Actual:4644.28$ Last Prediction:0$ Next 9m:1087.96$
[23:08:27] Actual:4644.28$ Last Prediction:1087.96$ Next 9m:1087.96$
[23:08:31] Actual:4644.28$ Last Prediction:1087.96$ Next 9m:1087.96$
[23:08:36] Actual:4644.28$ Last Prediction:1087.96$ Next 9m:1087.96$
[23:08:40] Actual:4644.28$ Last Prediction:1087.96$ Next 9m:1087.96$
[23:08:45] Actual:4644.28$ Last Prediction:1087.96$ Next 9m:1087.96$
[23:08:49] Actual:4644.28$ Last Prediction:1087.96$ Next 9m:1087.96$
[23:08:55] Actual:4644.28$ Last Prediction:1087.96$ Next 9m:1087.96$
[23:08:59] Actual:4644.28$ Last Prediction:1087.96$ Next 9m:1087.96$

Image

number_of_training_iterations

-iterations number_of_training_iterations
How many fill?

AttributeError: 'list' object has no attribute 'ndim'

Hi,

I'm total AI newbie trying to run your piece of code, but i'm getting error. Any hint about that ?

python3 network.py -train dataset.csv -iterations 100 15:10:20 Using TensorFlow backend. /home/jfburdet/tmp/BitcoinForecast/venv3/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) Namespace(finetune=None, iterations=100, model=None, run=None, train='dataset.csv') Building net..done! Loading data...1022 chunk loaded! training... Traceback (most recent call last): File "network.py", line 117, in <module> net.fit(data[:el],labels[:el],epochs=epochs,batch_size=300) File "/home/jfburdet/tmp/BitcoinForecast/venv3/lib/python3.6/site-packages/keras/models.py", line 965, in fit validation_steps=validation_steps) File "/home/jfburdet/tmp/BitcoinForecast/venv3/lib/python3.6/site-packages/keras/engine/training.py", line 1593, in fit batch_size=batch_size) File "/home/jfburdet/tmp/BitcoinForecast/venv3/lib/python3.6/site-packages/keras/engine/training.py", line 1426, in _standardize_user_data exception_prefix='input') File "/home/jfburdet/tmp/BitcoinForecast/venv3/lib/python3.6/site-packages/keras/engine/training.py", line 70, in _standardize_input_data data = [np.expand_dims(x, 1) if x is not None and x.ndim == 1 else x for x in data] File "/home/jfburdet/tmp/BitcoinForecast/venv3/lib/python3.6/site-packages/keras/engine/training.py", line 70, in <listcomp> data = [np.expand_dims(x, 1) if x is not None and x.ndim == 1 else x for x in data] AttributeError: 'list' object has no attribute 'ndim'

data.keys() will change order of data

It must be corrected!
python dictionary can't keep order.
grabber.py
util.py

Predicted Price

I seem to get the same predicted price every-time whether I retrain the model or not.

Mistake util.py

I think, you have mistake in util.py.
line 15: shoud be "return data[:-2],label[2:]"

dataset.csv

Can I have dataset.csv format?

grabber.py create dataset time

9 minutes, 1024 records. It takes 153.6 days
How, long, will, it, take, to, retrain!!

change 9min to (15min or 30min)?

You can choose your own configuration time
How do I change the code?

grabber option to grab old data

Hello,

I found your project very interesting and was wondering if you could add a script to grab data from the past to train the model with.

Thanks

help me run this

how do i run this, i have no clue, i tried running the commands with python3 butit just returns errors, i have installed all libraries but cant, please help