Backtrader giving IndexError: array assignment index out of range - python

I am trying to run the following strategy:
def max_n(array, n):
return np.argpartition(array, -n)[-n:]
class CrossSectionalMR(bt.Strategy):
params = (
('num_positions', 100),
)
def __init__(self, temp):
self.inds = {}
for d in self.datas:
self.inds[d] = {}
self.inds[d]["pct"] = bt.indicators.PercentChange(d.close, period=1)
def prenext(self):
self.next()
def next(self):
available = list(filter(lambda d: len(d), self.datas)) # only look at data that existed yesterday
rets = np.zeros(len(available))
for i, d in enumerate(available):
rets[i] = self.inds[d]['pct'][0]
market_ret = np.mean(rets)
weights = -(rets - market_ret)
max_weights_index = max_n(np.abs(weights), self.params.num_positions)
max_weights = weights[max_weights_index]
weights = weights / np.sum(np.abs(max_weights))
for i, d in enumerate(available):
if i in max_weights_index:
self.order_target_percent(d, target=weights[i])
else:
self.order_target_percent(d, 0)
The full error is:
Traceback (most recent call last):
File "/home/poblivsig/Software/pycharm-2020.3.1/plugins/python/helpers/pydev/pydevd.py", line 1477, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "/home/poblivsig/Software/pycharm-2020.3.1/plugins/python/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/poblivsig/Dropbox/meanrev/main.py", line 190, in <module>
dd, cagr, sharpe = backtest(datas, CrossSectionalMR, plot=True, num_positions=100)
File "/home/poblivsig/Dropbox/meanrev/main.py", line 181, in backtest
results = cerebro.run()
File "/home/poblivsig/Dropbox/meanrev/venv/lib/python3.8/site-packages/backtrader/cerebro.py", line 1127, in run
runstrat = self.runstrategies(iterstrat)
File "/home/poblivsig/Dropbox/meanrev/venv/lib/python3.8/site-packages/backtrader/cerebro.py", line 1293, in runstrategies
self._runonce(runstrats)
File "/home/poblivsig/Dropbox/meanrev/venv/lib/python3.8/site-packages/backtrader/cerebro.py", line 1652, in _runonce
strat._once()
File "/home/poblivsig/Dropbox/meanrev/venv/lib/python3.8/site-packages/backtrader/lineiterator.py", line 297, in _once
indicator._once()
File "/home/poblivsig/Dropbox/meanrev/venv/lib/python3.8/site-packages/backtrader/lineiterator.py", line 297, in _once
indicator._once()
File "/home/poblivsig/Dropbox/meanrev/venv/lib/python3.8/site-packages/backtrader/linebuffer.py", line 630, in _once
self.oncestart(self._minperiod - 1, self._minperiod)
File "/home/poblivsig/Dropbox/meanrev/venv/lib/python3.8/site-packages/backtrader/lineroot.py", line 165, in oncestart
self.once(start, end)
File "/home/poblivsig/Dropbox/meanrev/venv/lib/python3.8/site-packages/backtrader/linebuffer.py", line 672, in once
dst[i] = src[i + ago]
IndexError: array assignment index out of range
python-BaseExceptio
Any help would be greatly appreciated.
I grab the data from Yahoo and store it in csv files which are then loaded up and added to Cerebro. Sometimes, the code cannot get the full list of the SPY, but I don't think that is the problem here.

Related

xlwings recently stopped getting live data from excel via Range

I was running a script to get data from excel for over a year using the Xlwings range command like so...
list=Range('A1:D10').value
Suddenly, it stopper working. I had changed nothing in the code nor the system, other than maybe installing another network card.
This is the error when trying to use the Range assignment now.
Traceback (most recent call last):
File "G:\python32\fetcher.py", line 61, in <module>
listFull = getComData()
File "G:\python32\fetcher.py", line 38, in getComData
listFull=Range('A4:H184').value
File "G:\python32\lib\site-packages\xlwings\main.py", line 1490, in __init__
impl = apps.active.range(cell1).impl
File "G:\python32\lib\site-packages\xlwings\main.py", line 439, in range
return Range(impl=self.impl.range(cell1, cell2))
File "G:\python32\lib\site-packages\xlwings\_xlwindows.py", line 457, in range
xl1 = self.xl.Range(arg1)
File "G:\python32\lib\site-packages\xlwings\_xlwindows.py", line 341, in xl
self._xl = get_xl_app_from_hwnd(self._hwnd)
File "G:\python32\lib\site-packages\xlwings\_xlwindows.py", line 251, in get_xl_app_from_hwnd
disp = COMRetryObjectWrapper(Dispatch(p))
File "G:\python32\lib\site-packages\win32com\client\__init__.py", line 96, in Dispatch
return __WrapDispatch(dispatch, userName, resultCLSID, typeinfo, clsctx=clsctx)
File "G:\python32\lib\site-packages\win32com\client\__init__.py", line 37, in __WrapDispatch
klass = gencache.GetClassForCLSID(resultCLSID)
File "G:\python32\lib\site-packages\win32com\client\gencache.py", line 180, in GetClassForCLSID
mod = GetModuleForCLSID(clsid)
File "G:\python32\lib\site-packages\win32com\client\gencache.py", line 223, in GetModuleForCLSID
mod = GetModuleForTypelib(typelibCLSID, lcid, major, minor)
File "G:\python32\lib\site-packages\win32com\client\gencache.py", line 259, in GetModuleForTypelib
mod = _GetModule(modName)
File "G:\python32\lib\site-packages\win32com\client\gencache.py", line 622, in _GetModule
mod = __import__(mod_name)
ValueError: source code string cannot contain null bytes

Autoencoder in Chainer issue

I am trying to train Autoencoder by Chainer in python and wrote below code. But it does not work. Why??
class Autoencoder(Chain):
def __init__(self):
super().__init__()
with self.init_scope():
self.l1 = L.Linear(3,2)
self.l2 = L.Linear(2,3)
def __call__(self,x):
h1 = self.l1(x)
h2 = self.l2(h1)
return h2
class Dataset(dataset.DatasetMixin):
def __init__(self,number_of_data, show_initial = False):
noise_level = 1
self.data = np.zeros((number_of_data,3),dtype = np.float32)
OA_vector = np.array([3,2,1])
OB_vector = np.array([2,-1,1])
t = np.random.uniform(-0.5,0.5,number_of_data)
s = np.random.uniform(-0.5,0.5,number_of_data)
for i in range(0,number_of_data):
noise = np.random.uniform(-noise_level, noise_level,3)
self.data[i] = t[i]*OA_vector + s[i]*OB_vector + noise
def __len__(self):
return self.data.shape[0]
def get_example(self,idx):
return self.data[idx]
if __name__ == "__main__":
n_epoch = 5
batch_size = 100
number_of_data = 1000 #データ数
train_data = Dataset(number_of_data,False)
model = Autoencoder()
optimizer = optimizers.SGD(lr=0.05).setup(model)
train_iter = iterators.SerialIterator(train_data,batch_size)
updater = training.StandardUpdater(train_iter,optimizer,device=0)
trainer = training.Trainer(updater,(n_epoch,"epoch"),out="result")
trainer.run()
I am using Chainer. And the Dataset makes 3 dimensitonal vectors. The number of the vectors is "number_of_data".
Should I do that without using trainer?
I don't understand where problem is.
EDIT
When we run above code with device=0, we have error like below.
Exception in main training loop: Unsupported type <class 'NoneType'>
Traceback (most recent call last):
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 308, in run
update()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 149, in update
self.update_core()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 164, in update_core
optimizer.update(loss_func, in_arrays)
File "/home/****/.local/lib/python3.5/site-packages/chainer/optimizer.py", line 655, in update
loss.backward(loss_scale=self._loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 966, in backward
self._backward_main(retain_grad, loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 1095, in _backward_main
target_input_indexes, out_grad, in_grad)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 548, in backward_accumulate
gxs = self.backward(target_input_indexes, grad_outputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 73, in backward
return ReLUGrad2(y).apply((gy,))
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 258, in apply
outputs = self.forward(in_data)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 368, in forward
return self.forward_cpu(inputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 97, in forward_cpu
y = (self.b > 0) * inputs[0]
File "cupy/core/core.pyx", line 1310, in cupy.core.core.ndarray.__mul__
File "cupy/core/elementwise.pxi", line 753, in cupy.core.core.ufunc.__call__
File "cupy/core/elementwise.pxi", line 68, in cupy.core.core._preprocess_args
Will finalize trainer extensions and updater before reraising the exception.
Traceback (most recent call last):
File "AC.py", line 70, in <module>
trainer.run()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 322, in run
six.reraise(*sys.exc_info())
File "/home/****/.local/lib/python3.5/site-packages/six.py", line 693, in reraise
raise value
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 308, in run
update()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 149, in update
self.update_core()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 164, in update_core
optimizer.update(loss_func, in_arrays)
File "/home/****/.local/lib/python3.5/site-packages/chainer/optimizer.py", line 655, in update
loss.backward(loss_scale=self._loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 966, in backward
self._backward_main(retain_grad, loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 1095, in _backward_main
target_input_indexes, out_grad, in_grad)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 548, in backward_accumulate
gxs = self.backward(target_input_indexes, grad_outputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 73, in backward
return ReLUGrad2(y).apply((gy,))
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 258, in apply
outputs = self.forward(in_data)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 368, in forward
return self.forward_cpu(inputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 97, in forward_cpu
y = (self.b > 0) * inputs[0]
File "cupy/core/core.pyx", line 1310, in cupy.core.core.ndarray.__mul__
File "cupy/core/elementwise.pxi", line 753, in cupy.core.core.ufunc.__call__
File "cupy/core/elementwise.pxi", line 68, in cupy.core.core._preprocess_args
TypeError: Unsupported type <class 'NoneType'>
When we run above code with device=-1, we have error like below.
Exception in main training loop: unsupported operand type(s) for *: 'bool' and 'NoneType'
Traceback (most recent call last):
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 308, in run
update()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 149, in update
self.update_core()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 164, in update_core
optimizer.update(loss_func, in_arrays)
File "/home/****/.local/lib/python3.5/site-packages/chainer/optimizer.py", line 655, in update
loss.backward(loss_scale=self._loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 966, in backward
self._backward_main(retain_grad, loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 1095, in _backward_main
target_input_indexes, out_grad, in_grad)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 548, in backward_accumulate
gxs = self.backward(target_input_indexes, grad_outputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 73, in backward
return ReLUGrad2(y).apply((gy,))
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 258, in apply
outputs = self.forward(in_data)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 368, in forward
return self.forward_cpu(inputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 97, in forward_cpu
y = (self.b > 0) * inputs[0]
Will finalize trainer extensions and updater before reraising the exception.
Traceback (most recent call last):
File "AC.py", line 70, in <module>
trainer.run()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 322, in run
six.reraise(*sys.exc_info())
File "/home/****/.local/lib/python3.5/site-packages/six.py", line 693, in reraise
raise value
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 308, in run
update()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 149, in update
self.update_core()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 164, in update_core
optimizer.update(loss_func, in_arrays)
File "/home/****/.local/lib/python3.5/site-packages/chainer/optimizer.py", line 655, in update
loss.backward(loss_scale=self._loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 966, in backward
self._backward_main(retain_grad, loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 1095, in _backward_main
target_input_indexes, out_grad, in_grad)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 548, in backward_accumulate
gxs = self.backward(target_input_indexes, grad_outputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 73, in backward
return ReLUGrad2(y).apply((gy,))
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 258, in apply
outputs = self.forward(in_data)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 368, in forward
return self.forward_cpu(inputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 97, in forward_cpu
y = (self.b > 0) * inputs[0]
TypeError: unsupported operand type(s) for *: 'bool' and 'NoneType'

I think the model need to return loss in __call__ method.
Sample modification is as follows:
class Autoencoder(Chain):
def __init__(self):
super().__init__()
with self.init_scope():
self.l1 = L.Linear(3,2)
self.l2 = L.Linear(2,3)
def forward(self,x):
h1 = self.l1(x)
h2 = self.l2(h1)
return h2
def __call__(self,x):
h = self.forward(x)
# Instead of h, __call__ should return loss.
loss = F.mean_squared_error(h, x)
return loss

Theano: MissingInputError

this is a semplification of the original code that i'm trying to fix. I have invented a problem that reflects what the original code does and which gives me the same error but is written in a minimal form:
class Test(object):
def __init__(self):
self.rate=0.01
def start(self, x, y):
W_val=40.89
W=theano.shared(value=W_val, borrow=True)
z=T.mean(x*W/y)
gz=T.grad(z, W)
updates=[(W, W-self.rate*gz)]
fz=theano.function([], z, updates=updates)
for i in range(100):
out=fz()
self.out=out
return out
x_set=np.random.rand(10)
y_set=np.random.randint(low=0, high=5, size=10, dtype=int)
batch_size=2
x = T.dvector('x')
y = T.ivector('y')
index = T.lscalar()
test = Test()
cost=test.start(x,y)
train = theano.function(
inputs=[index],
outputs=cost,
givens={
x: x_set[index * batch_size: (index + 1) * batch_size],
y: y_set[index * batch_size: (index + 1) * batch_size]
}
)
for i in range(5):
result=train(i)
print(result)
This is the TraceBack:
Traceback (most recent call last):
File "functions.py", line 33, in <module>
cost=test.start(x,y)
File "functions.py", line 18, in start
fz=theano.function([], z, updates=updates)
File "C:\Program Files\Anaconda3\lib\site-packages\theano\compile\function.py", line 320, in function
output_keys=output_keys)
File "C:\Program Files\Anaconda3\lib\site-packages\theano\compile\pfunc.py", line 479, in pfunc
output_keys=output_keys)
File "C:\Program Files\Anaconda3\lib\site-packages\theano\compile\function_module.py", line 1776, in orig_function
output_keys=output_keys).create(
File "C:\Program Files\Anaconda3\lib\site-packages\theano\compile\function_module.py", line 1428, in __init__
accept_inplace)
File "C:\Program Files\Anaconda3\lib\site-packages\theano\compile\function_module.py", line 177, in std_fgraph
update_mapping=update_mapping)
File "C:\Program Files\Anaconda3\lib\site-packages\theano\gof\fg.py", line 171, in __init__
self.__import_r__(output, reason="init")
File "C:\Program Files\Anaconda3\lib\site-packages\theano\gof\fg.py", line 360, in __import_r__
self.__import__(variable.owner, reason=reason)
File "C:\Program Files\Anaconda3\lib\site-packages\theano\gof\fg.py", line 465, in __import__
detailed_err_msg)
theano.gof.fg.MissingInputError: A variable that is an input to the graph was neither provided as an input to the function nor given a value. A chain of variables leading from this input to an output is [x, Elemwise{mul,no_inplace}.0, Elemwise{true_div,no_inplace}.0, Sum{acc_dtype=float64}.0, mean]. This chain may not be unique
Backtrace when the variable is created:
File "functions.py", line 28, in <module>
x = T.dvector('x')
I do not know where to slam my head again...
Thanks

S3 the read operation timed out while reading commoncrawl data

In order to read few files from common crawl I have written this script
import warc
import boto
for line in sys.stdin:
line = line.strip()
#Connect to AWS and read a dataset
conn = boto.connect_s3(anon=True, host='s3.amazonaws.com')
pds = conn.get_bucket('commoncrawl')
k = Key(pds)
k.key = line
f = warc.WARCFile(fileobj=GzipStreamFile(k))
skipped_doc = 0
for num, record in enumerate(f):
# analysis code
Where each line is the key of warc files. When I run this script to analyze 5 files, I got this exception
Traceback (most recent call last):
File "./warc_mapper_full.py", line 42, in <module>
for num, record in enumerate(f):
File "/usr/lib/python2.7/site-packages/warc/warc.py", line 393, in __iter__
record = self.read_record()
File "/usr/lib/python2.7/site-packages/warc/warc.py", line 364, in read_record
self.finish_reading_current_record()
File "/usr/lib/python2.7/site-packages/warc/warc.py", line 358, in finish_reading_current_record
self.current_payload.read()
File "/usr/lib/python2.7/site-packages/warc/utils.py", line 59, in read
return self._read(self.length)
File "/usr/lib/python2.7/site-packages/warc/utils.py", line 69, in _read
content = self.buf + self.fileobj.read(size)
File "/home/hpcnl/Documents/kics/current_work/aws/tasks/warc-analysis/src/gzipstream/gzipstream/gzipstreamfile.py", line 67, in read
result = super(GzipStreamFile, self).read(*args, **kwargs)
File "/home/hpcnl/Documents/kics/current_work/aws/tasks/warc-analysis/src/gzipstream/gzipstream/gzipstreamfile.py", line 48, in readinto
data = self.read(len(b))
File "/home/hpcnl/Documents/kics/current_work/aws/tasks/warc-analysis/src/gzipstream/gzipstream/gzipstreamfile.py", line 38, in read
raw = self.stream.read(io.DEFAULT_BUFFER_SIZE)
File "/usr/lib/python2.7/site-packages/boto/s3/key.py", line 400, in read
data = self.resp.read(size)
File "/usr/lib/python2.7/site-packages/boto/connection.py", line 413, in read
return http_client.HTTPResponse.read(self, amt)
File "/usr/lib64/python2.7/httplib.py", line 602, in read
s = self.fp.read(amt)
File "/usr/lib64/python2.7/socket.py", line 380, in read
data = self._sock.recv(left)
File "/usr/lib64/python2.7/ssl.py", line 736, in recv
return self.read(buflen)
File "/usr/lib64/python2.7/ssl.py", line 630, in read
v = self._sslobj.read(len or 1024)
ssl.SSLError: ('The read operation timed out',)
I run it many times. Above exception happened every time. Where is the problem ?

ipython parallel load balanced view failing randomly

Here's my code:
from IPython.parallel import Client
from sklearn.datasets import load_digits
def mytask(data, labels, id):
# ...
pass
engines = Client()
bview = engines.load_balanced_view()
bview.block = False
digits = load_digits()
X, y = digits.data, digits.target
job = bview.apply(mytask, X, y, 1)
while not job.ready(): # line 242
time.sleep(2)
print job.result
Occasionally with the same input my code fails with this:
Traceback (most recent call last):
File "task.py", line 242, in <module>
while not job.ready():
File "/usr/lib/python2.7/dist-packages/IPython/parallel/client/asyncresult.py", line 111, in ready
self.wait(0)
File "/usr/lib/python2.7/dist-packages/IPython/parallel/client/asyncresult.py", line 121, in wait
self._ready = self._client.wait(self.msg_ids, timeout)
File "/usr/lib/python2.7/dist-packages/IPython/parallel/client/client.py", line 844, in wait
self.spin()
File "/usr/lib/python2.7/dist-packages/IPython/parallel/client/client.py", line 799, in spin
self._flush_results(self._task_socket)
File "/usr/lib/python2.7/dist-packages/IPython/parallel/client/client.py", line 692, in _flush_results
handler(msg)
File "/usr/lib/python2.7/dist-packages/IPython/parallel/client/client.py", line 657, in _handle_apply_reply
self.results[msg_id] = util.unserialize_object(msg['buffers'])[0]
File "/usr/lib/python2.7/dist-packages/IPython/parallel/util.py", line 262, in unserialize_object
return uncanSequence(map(unserialize, sobj)), bufs
File "/usr/lib/python2.7/dist-packages/IPython/utils/newserialized.py", line 177, in unserialize
return UnSerializeIt(serialized).getObject()
File "/usr/lib/python2.7/dist-packages/IPython/utils/newserialized.py", line 161, in getObject
result = numpy.frombuffer(buf, dtype = self.serialized.metadata['dtype'])
ValueError: offset must be non-negative and smaller than buffer lenth (0)
This seems to be unconnected to my code. I'm not sure what's going wrong.

Categories