I define a class as follows. But I can only run myStrategy once. If I change the parameters and run myStrategy again, nothing changes. I hope to use the same strategy many times with different stocks and parameters.
"""
from pyalgotrade import strategy
from pyalgotrade.barfeed import quandlfeed
from pyalgotrade.technical import atr
from pyalgotrade.technical import highlow
from pyalgotrade.technical import ma
class turtleStrategy(strategy.BacktestingStrategy):
def __init__(self, feed, instrument, period):
strategy.BacktestingStrategy.__init__(self,feed,1000000)
#super(turtleStrategy, self).__init__(feed,1000000)
self.__instrument = instrument
self.__period = period
self.__position = None
barsDs = feed[instrument]
self.__atr = atr.ATR(barsDs,period)
self.__closePrice = feed[instrument].getCloseDataSeries()
self.__hband = highlow.High(self.__closePrice,period)
self.__lband = highlow.Low(self.__closePrice,period)
def onBars(self,bars):
try:
high = self.__hband.getDataSeries()[-2]
low = self.__lband.getDataSeries()[-2]
except:
return
price = bars[self.__instrument].getClose()
if self.__position is None:
if price > high:
shares = int(self.getBroker().getCash() / price)
self.marketOrder(self.__instrument,shares)
elif price < low:
self.marketOrder(self.__instrument,self.getBroker().getShares())
rdat = "...\\FREE.csv"
instrument = "FREE"
period = 20
feed = quandlfeed.Feed()
feed.addBarsFromCSV(instrument,rdat)
myStrategy = turtleStrategy(feed,instrument,period)
"""
If you just want to change the period, you can try this:
rdat = "...\\FREE.csv"
instrument = "FREE"
feed = quandlfeed.Feed()
feed.addBarsFromCSV(instrument,rdat)
for period in [20, 30, 40]:
feed.reset()
myStrategy = turtleStrategy(feed, instrument, period)
If you also want to change the instrument/feed, then you need to do everything again, not just reset the feed.
Related
I am having trouble in making things work with a Custom ParallelEnv I wrote by using PettingZoo. I am using SuperSuit's ss.pettingzoo_env_to_vec_env_v1(env) as a wrapper to Vectorize the environment and make it work with Stable-Baseline3 and documented here.
You can find attached a summary of the most relevant part of the code:
from typing import Optional
from gym import spaces
import random
import numpy as np
from pettingzoo import ParallelEnv
from pettingzoo.utils.conversions import parallel_wrapper_fn
import supersuit as ss
from gym.utils import EzPickle, seeding
def env(**kwargs):
env_ = parallel_env(**kwargs)
env_ = ss.pettingzoo_env_to_vec_env_v1(env_)
#env_ = ss.concat_vec_envs_v1(env_, 1)
return env_
petting_zoo = env
class parallel_env(ParallelEnv, EzPickle):
metadata = {'render_modes': ['ansi'], "name": "PlayerEnv-Multi-v0"}
def __init__(self, n_agents: int = 20, new_step_api: bool = True) -> None:
EzPickle.__init__(
self,
n_agents,
new_step_api
)
self._episode_ended = False
self.n_agents = n_agents
self.possible_agents = [
f"player_{idx}" for idx in range(n_agents)]
self.agents = self.possible_agents[:]
self.agent_name_mapping = dict(
zip(self.possible_agents, list(range(len(self.possible_agents))))
)
self.observation_spaces = spaces.Dict(
{agent: spaces.Box(shape=(len(self.agents),),
dtype=np.float64, low=0.0, high=1.0) for agent in self.possible_agents}
)
self.action_spaces = spaces.Dict(
{agent: spaces.Discrete(4) for agent in self.possible_agents}
)
self.current_step = 0
def seed(self, seed=None):
self.np_random, seed = seeding.np_random(seed)
def observation_space(self, agent):
return self.observation_spaces[agent]
def action_space(self, agent):
return self.action_spaces[agent]
def __calculate_observation(self, agent_id: int) -> np.ndarray:
return self.observation_space(agent_id).sample()
def __calculate_observations(self) -> np.ndarray:
observations = {
agent: self.__calculate_observation(
agent_id=agent)
for agent in self.agents
}
return observations
def observe(self, agent):
return self.__calculate_observation(agent_id=agent)
def step(self, actions):
if self._episode_ended:
return self.reset()
observations = self.__calculate_observations()
rewards = random.sample(range(100), self.n_agents)
self.current_step += 1
self._episode_ended = self.current_step >= 100
infos = {agent: {} for agent in self.agents}
dones = {agent: self._episode_ended for agent in self.agents}
rewards = {
self.agents[i]: rewards[i]
for i in range(len(self.agents))
}
if self._episode_ended:
self.agents = {} # To satisfy `set(par_env.agents) == live_agents`
return observations, rewards, dones, infos
def reset(self,
seed: Optional[int] = None,
return_info: bool = False,
options: Optional[dict] = None,):
self.agents = self.possible_agents[:]
self._episode_ended = False
self.current_step = 0
observations = self.__calculate_observations()
return observations
def render(self, mode="human"):
# TODO: IMPLEMENT
print("TO BE IMPLEMENTED")
def close(self):
pass
Unfortunately when I try to test with the following main procedure:
from stable_baselines3 import DQN, PPO
from stable_baselines3.common.env_checker import check_env
from dummy_env import dummy
from pettingzoo.test import parallel_api_test
if __name__ == '__main__':
# Testing the parallel algorithm alone
env_parallel = dummy.parallel_env()
parallel_api_test(env_parallel) # This works!
# Testing the environment with the wrapper
env = dummy.petting_zoo()
# ERROR: AssertionError: The observation returned by the `reset()` method does not match the given observation space
check_env(env)
# Model initialization
model = PPO("MlpPolicy", env, verbose=1)
# ERROR: ValueError: could not broadcast input array from shape (20,20) into shape (20,)
model.learn(total_timesteps=10_000)
I get the following error:
AssertionError: The observation returned by the `reset()` method does not match the given observation space
If I skip check_env() I get the following one:
ValueError: could not broadcast input array from shape (20,20) into shape (20,)
It seems like that ss.pettingzoo_env_to_vec_env_v1(env) is capable of splitting the parallel environment in multiple vectorized ones, but not for the reset() function.
Does anyone know how to fix this problem?
Plese find the Github Repository to reproduce the problem.
You should double check the reset() function in PettingZoo. It will return None instead of an observation like GYM
Thanks to discussion I had in the issue section of the SuperSuit repository, I am able to post the solution to the problem. Thanks to jjshoots!
First of all it is necessary to have the latest SuperSuit version. In order to get that I needed to install Stable-Baseline3 using the instructions here to make it work with gym 0.24+.
After that, taking the code in the question as example, it is necessary to substitute
def env(**kwargs):
env_ = parallel_env(**kwargs)
env_ = ss.pettingzoo_env_to_vec_env_v1(env_)
#env_ = ss.concat_vec_envs_v1(env_, 1)
return env_
with
def env(**kwargs):
env_ = parallel_env(**kwargs)
env_ = ss.pettingzoo_env_to_vec_env_v1(env_)
env_ = ss.concat_vec_envs_v1(env_, 1, base_class="stable_baselines3")
return env_
The outcomes are:
Outcome 1: leaving the line with check_env(env) I got an error AssertionError: Your environment must inherit from the gym.Env class cf https://github.com/openai/gym/blob/master/gym/core.py
Outcome 2: removing the line with check_env(env), the agent starts training successfully!
In the end, I think that the argument base_class="stable_baselines3" made the difference.
Only the small problem on check_env remains to be reported, but I think it can be considered as trivial if the training works.
I saw a Kaggle kernel on PyTorch and run it with the same img_size, batch_size, etc. and created another PyTorch-lightning kernel with exact same values but my lightning model runs out of memory after about 1.5 epochs (each epoch contains 8750 steps) on the first fold whereas the native PyTorch model runs for whole 5 folds. Is there any way to improve the code or release memory? I could have tried to delete the models or do some garbage collection but if it doesn't complete even the first fold I can't delete the models and things.
def run_fold(fold):
df_train = train[train['fold'] != fold]
df_valid = train[train['fold'] == fold]
train_dataset = G2NetDataset(df_train, get_train_aug())
valid_dataset = G2NetDataset(df_valid, get_test_aug())
train_dl = DataLoader(train_dataset,
batch_size = config.batch_size,
num_workers = config.num_workers,
shuffle = True,
drop_last = True,
pin_memory = True)
valid_dl = DataLoader(valid_dataset,
batch_size = config.batch_size,
num_workers = config.num_workers,
shuffle = False,
drop_last = False,
pin_memory = True)
model = Classifier()
logger = pl.loggers.WandbLogger(project='G2Net', name=f'fold: {fold}')
trainer = pl.Trainer(gpus = 1,
max_epochs = config.epochs,
fast_dev_run = config.debug,
logger = logger,
log_every_n_steps=10)
trainer.fit(model, train_dl, valid_dl)
result = trainer.test(test_dataloaders = valid_dl)
wandb.run.finish()
return result
def main():
if config.train:
results = []
for fold in range(config.n_fold):
result = run_fold(fold)
results.append(result)
return results
results = main()
I cannot say much without looking at your model class, but couple possible issues that I encountered were metric and loss evaluation for logging.
For example, stuff like
pl.metrics.Accuracy(compute_on_step=False)
requires and explicit call of .compute()
def training_epoch_end(self, outputs):
loss = sum([out['loss'] for out in outputs])/len(outputs)
self.log_dict({'train_loss' : loss.detach(),
'train_accuracy' : self.train_metric.compute()})
at the epoch end.
In Order to explain it simply: I have 53 Oil Producing wells measurements, each well has been measured each day for 6 years, we recorded multiple variables (Pressure, water production, gas production...etc), and our main component(The one we want to study and forecast) is the Oil production rate. How can I Use all the data to train my model of LSTM/GRU knowing that the Oil wells are independent and that the measurments have been done in the same time for each one?
The knowledge that "the measurments have been done in the same time for each [well]" is not necessary if you want to assume that the wells are independent. (Why do you think that that knowledge is useful?)
So if the wells are considered independent, treat them as individual samples. Split them into a training set, validation set, and test set, as usual. Train a usual LSTM or GRU on the training set.
By the way, you might want to use the attention mechanism instead of recurrent networks. It is easier to train and usually yields comparable results.
Even convolutional networks might be good enough. See methods like WaveNet if you suspect long-range correlations.
These well measurements sound like specific and independent events. I work in the finance sector. We always look at different stocks, and each stocks specific time neries using LSTM, but not 10 stocks mashed up together. Here's some code to analyze a specific stock. Modify the code to suit your needs.
from pandas_datareader import data as wb
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.pylab import rcParams
from sklearn.preprocessing import MinMaxScaler
start = '2019-06-30'
end = '2020-06-30'
tickers = ['GOOG']
thelen = len(tickers)
price_data = []
for ticker in tickers:
prices = wb.DataReader(ticker, start = start, end = end, data_source='yahoo')[['Open','Adj Close']]
price_data.append(prices.assign(ticker=ticker)[['ticker', 'Open', 'Adj Close']])
#names = np.reshape(price_data, (len(price_data), 1))
df = pd.concat(price_data)
df.reset_index(inplace=True)
for col in df.columns:
print(col)
#used for setting the output figure size
rcParams['figure.figsize'] = 20,10
#to normalize the given input data
scaler = MinMaxScaler(feature_range=(0, 1))
#to read input data set (place the file name inside ' ') as shown below
df['Adj Close'].plot()
plt.legend(loc=2)
plt.xlabel('Date')
plt.ylabel('Price')
plt.show()
ntrain = 80
df_train = df.head(int(len(df)*(ntrain/100)))
ntest = -80
df_test = df.tail(int(len(df)*(ntest/100)))
#importing the packages
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense, Dropout, LSTM
#dataframe creation
seriesdata = df.sort_index(ascending=True, axis=0)
new_seriesdata = pd.DataFrame(index=range(0,len(df)),columns=['Date','Adj Close'])
length_of_data=len(seriesdata)
for i in range(0,length_of_data):
new_seriesdata['Date'][i] = seriesdata['Date'][i]
new_seriesdata['Adj Close'][i] = seriesdata['Adj Close'][i]
#setting the index again
new_seriesdata.index = new_seriesdata.Date
new_seriesdata.drop('Date', axis=1, inplace=True)
#creating train and test sets this comprises the entire data’s present in the dataset
myseriesdataset = new_seriesdata.values
totrain = myseriesdataset[0:255,:]
tovalid = myseriesdataset[255:,:]
#converting dataset into x_train and y_train
scalerdata = MinMaxScaler(feature_range=(0, 1))
scale_data = scalerdata.fit_transform(myseriesdataset)
x_totrain, y_totrain = [], []
length_of_totrain=len(totrain)
for i in range(60,length_of_totrain):
x_totrain.append(scale_data[i-60:i,0])
y_totrain.append(scale_data[i,0])
x_totrain, y_totrain = np.array(x_totrain), np.array(y_totrain)
x_totrain = np.reshape(x_totrain, (x_totrain.shape[0],x_totrain.shape[1],1))
#LSTM neural network
lstm_model = Sequential()
lstm_model.add(LSTM(units=50, return_sequences=True, input_shape=(x_totrain.shape[1],1)))
lstm_model.add(LSTM(units=50))
lstm_model.add(Dense(1))
lstm_model.compile(loss='mean_squared_error', optimizer='adadelta')
lstm_model.fit(x_totrain, y_totrain, epochs=10, batch_size=1, verbose=2)
#predicting next data stock price
myinputs = new_seriesdata[len(new_seriesdata) - (len(tovalid)+1) - 60:].values
myinputs = myinputs.reshape(-1,1)
myinputs = scalerdata.transform(myinputs)
tostore_test_result = []
for i in range(60,myinputs.shape[0]):
tostore_test_result.append(myinputs[i-60:i,0])
tostore_test_result = np.array(tostore_test_result)
tostore_test_result = np.reshape(tostore_test_result,(tostore_test_result.shape[0],tostore_test_result.shape[1],1))
myclosing_priceresult = lstm_model.predict(tostore_test_result)
myclosing_priceresult = scalerdata.inverse_transform(myclosing_priceresult)
totrain = df_train
tovalid = df_test
#predicting next data stock price
myinputs = new_seriesdata[len(new_seriesdata) - (len(tovalid)+1) - 60:].values
# Printing the next day’s predicted stock price.
print(len(tostore_test_result));
print(myclosing_priceresult);
Final result:
1
[[1396.532]]
I'm pretty new to PyBullet and physics engines in general. My first step is trying to get one object to move towards another.
import pybullet as p
import time
import pybullet_data
DURATION = 10000
physicsClient = p.connect(p.GUI)#or p.DIRECT for non-graphical version
p.setAdditionalSearchPath(pybullet_data.getDataPath()) #optionally
print("data path: %s " % pybullet_data.getDataPath())
p.setGravity(0,0,-10)
planeId = p.loadURDF("plane.urdf")
cubeStartPos = [0,0,1]
cubeStartOrientation = p.getQuaternionFromEuler([0,0,0])
boxId = p.loadURDF("r2d2.urdf",cubeStartPos, cubeStartOrientation)
gemId = p.loadURDF("duck_vhacd.urdf", [2,2,1], p.getQuaternionFromEuler([0,0,0]) )
for i in range (DURATION):
p.stepSimulation()
time.sleep(1./240.)
gemPos, gemOrn = p.getBasePositionAndOrientation(gemId)
cubePos, cubeOrn = p.getBasePositionAndOrientation(boxId)
oid, lk, frac, pos, norm = p.rayTest(cubePos, gemPos)[0]
#rt = p.rayTest(cubePos, gemPos)
#print("rayTest: %s" % rt[0][1])
print("rayTest: Norm: ")
print(norm)
p.applyExternalForce(objectUniqueId=boxId, linkIndex=-1, forceObj=pos
,posObj=gemPos, flags=p.WORLD_FRAME)
print(cubePos,cubeOrn)
p.disconnect()
But this just gets R2 to wiggle a bit. How do I do this?
First of all, if you are moving a robot, you should do something a little more complicated, by providing some commands to the joints of the robot. Here is an example
Now assuming that you are moving something less complicated by applying an external force, the simplest thing you can do is multiply a factor alpha with the difference between the two positions; this would be your force.
For your example this would be:
import numpy as np
import pybullet as p
import time
import pybullet_data
DURATION = 10000
ALPHA = 300
physicsClient = p.connect(p.GUI) # or p.DIRECT for non-graphical version
p.setAdditionalSearchPath(pybullet_data.getDataPath()) # optionally
print("data path: %s " % pybullet_data.getDataPath())
p.setGravity(0, 0, -10)
planeId = p.loadURDF("plane.urdf")
cubeStartPos = [0, 0, 1]
cubeStartOrientation = p.getQuaternionFromEuler([0, 0, 0])
boxId = p.loadURDF("r2d2.urdf", cubeStartPos, cubeStartOrientation)
gemId = p.loadURDF("duck_vhacd.urdf", [
2, 2, 1], p.getQuaternionFromEuler([0, 0, 0]))
for i in range(DURATION):
p.stepSimulation()
time.sleep(1./240.)
gemPos, gemOrn = p.getBasePositionAndOrientation(gemId)
boxPos, boxOrn = p.getBasePositionAndOrientation(boxId)
force = ALPHA * (np.array(gemPos) - np.array(boxPos))
p.applyExternalForce(objectUniqueId=boxId, linkIndex=-1,
forceObj=force, posObj=boxPos, flags=p.WORLD_FRAME)
print('Applied force magnitude = {}'.format(force))
print('Applied force vector = {}'.format(np.linalg.norm(force)))
p.disconnect()
I am overwriting the get_obj_list function. Following some parameters and a random function I would like to return an object related to the actual object that follows the parameters. This works fine. How can I return only this obj instead of a one-entry-list? Is there another function that better fits my purpose?
class SentenceRandomResource(ModelResource):
class Meta:
queryset = Sentence.objects.filter()
resource_name = 'sentence/random'
always_return_data = True
authorization = ReadOnlyAuthorization()
filtering = {'internal': ALL}
def obj_get_list(self, bundle, **kwargs):
if 'case' in bundle.request.GET.keys() and 'lemma' in bundle.request.GET.keys() :
if 'number' in bundle.request.GET.keys() :
words = Word.objects.filter(case = bundle.request.GET['case'], number = bundle.request.GET['number'], lemma = bundle.request.GET['lemma'])
else :
words = Word.objects.filter(case = bundle.request.GET['case'], lemma = bundle.request.GET['lemma'])
number_of_words = len(words)
if number_of_words > 0 :
random_index = int(random.random()*number_of_words)+0
random_word = words[random_index]
sentence = random_word.sentence
return [sentence]
else: ...
else: ...
Thanks to method prepend_url you may add some special functionality not included in RESTful principles.
import random
from tastypie.http import HttpBadRequest
class SentenceRandomResource(ModelResource):
class Meta:
queryset = Sentence.objects.filter()
resource_name = 'sentence/random'
always_return_data = True
authorization = ReadOnlyAuthorization()
filtering = {'internal': ALL}
def prepend_urls(self, *args, **kwargs):
name = 'get_one_random'
return [url(r"^(?P<resource_name>%s)/%s%s$" %
(self._meta.resource_name, name, trailing_slash()),
self.wrap_view(name), name="api_%s" % name)]
def get_one_random(self, request, **kwargs):
"""
Gets one random sentence of sentences with provided `case` and `lemma`
params.
"""
case = request.GET.get('case')
lemma = request.GET.get('lemma')
number = request.GET.get('number')
if case and lemma:
query_params = {'case': case, 'lemma': lemma}
if number is not None:
query_params['number'] = number
words = Word.objects.filter(**query_params)
word = random.choice(words)
return self.create_response(request, {'sentence': word.sentence.__dict__})
else:
return self.error_response(request, {'error': 'lemma and case are required.'},
response_class=HttpBadRequest)
Example use:
GET ..../sentence/random/get_one_random/?case=1&lemma=2
{'sentence': 'asdfasdf'}