from pybrain.structure.modules import LSTMLayer, SigmoidLayer, LinearLayer, TanhLayer, SoftmaxLayer from pybrain.tools.validation import testOnSequenceData from pybrain.structure.modules.neuronlayer import NeuronLayer from pybrain.tools.xml.networkwriter import NetworkWriter from pybrain.tools.xml.networkreader import NetworkReader random.seed(42) def ir(p, i, data): # p-days, i=current day a = np.sum([n['adj_close'] for n in data[i:i+p]]) / p c = data[i]['adj_close'] return ((a - c) / c) # prepare date symbol = '^HSI' yahoo_data = YahooHistorical() yahoo_data.open(os.path.join(os.path.dirname(__file__), 'data/' + symbol + '.csv')) training_set = np.array([n for n in yahoo_data.data if n['date'] >= date(2007, 1, 1) and n['date'] <= date(2013, 12, 31)]) test_set = np.array([n for n in yahoo_data.data if n['date'] >= date(2014, 1, 1) and n['date'] <= date(2015, 12, 31)]) rsi = yahoo_data.relative_strength(n=14) (sma13, sma7, macd) = yahoo_data.moving_average_convergence(7, 13) # 7 days and 13 days moving average and MACD test_label = [] training_label = [n['date'] for n in training_set] training_list = np.array([n['adj_close'] for n in training_set]) training_target = np.zeros(len(training_list)) test_list = np.array([n['adj_close'] for n in test_set]) test_target = np.zeros(len(test_list)) test_target[list(argrelextrema(test_list, np.greater)[0])] = 1 test_target[list(argrelextrema(test_list, np.less)[0])] = -1 training_target[list(argrelextrema(training_list, np.greater)[0])] = 1 training_target[list(argrelextrema(training_list, np.less)[0])] = -1
# Decimal Scaling
# replace nan with first non-nan
nan = np.isnan(data)
nnan = np.where(~nan)[0][0]
data[:nnan] = data[nnan]
if mean == None:
mean = np.mean(data)
if std == None:
std = np.std(data)
return (data - mean) / std, mean, std
if __name__=="__main__":
# prepare date
symbol = "0005.HK"
stock_data = YahooHistorical()
stock_data.open(os.path.join(os.path.dirname(__file__), "data/" + symbol + ".csv"))
dataset = stock_data.get()
date = np.array([n['date'] for n in dataset])
close_prices = np.array([n['adj_close'] for n in dataset])
low_prices = np.array([n['low'] for n in dataset])
high_prices = np.array([n['high'] for n in dataset])
volumes = np.array([n['vol'] for n in dataset])
prices, mean, std = normalize(close_prices)
low_prices, mean, std = normalize(low_prices, mean, std)
high_prices, mean, std = normalize(high_prices, mean, std)
emax = list(argrelextrema(prices, np.greater)[0])
emin = list(argrelextrema(prices, np.less)[0])
sma13, mean, std = normalize(talib.SMA(close_prices, 13), mean, std) # 50-day SMA
sma50, mean, std = normalize(talib.SMA(close_prices, 50), mean, std) # 50-day SMA
sma100, mean, std = normalize(talib.SMA(close_prices, 100), mean, std) # 100-day SMA
from sys import stdout
import numpy as np
import matplotlib.pyplot as plt
from scipy.signal import argrelextrema
def normalize(data, mean=None, std=None):
if mean == None:
mean = np.mean(data)
if std == None:
std = np.std(data)
x = (data - mean) / std
return x, mean, std
# prepare date
symbol = '^HSI'
yahoo_data = YahooHistorical(data_from=date(2014, 1, 1), data_to=date(2015, 12, 31))
yahoo_data.open(os.path.join(os.path.dirname(__file__), 'data/' + symbol + '.csv'))
training_set = yahoo_data.get()
test_set = training_set[200:]
rsi = yahoo_data.relative_strength(n=14)
(sma13, sma7, macd) = yahoo_data.moving_average_convergence(7, 13) # 7 days and 13 days moving average
label = np.array([n['date'] for n in test_set])
(training_prices, m, s) = normalize(np.array([n['adj_close'] for n in training_set]))
(prices, m, s) = normalize(np.array([n['adj_close'] for n in test_set]))
(tmax, tmin) = yahoo_data.trading_range_breakout(50)
(sma13, m, s) = normalize(sma13, m, s)
(sma7, m, s) = normalize(sma7, m, s)
(tmax, m, s) = normalize(tmax, m, s)
(tmin, m, s) = normalize(tmin, m, s)
(macd, m, s) = normalize(macd)
(rsi, m, s) = normalize(rsi)
import os
from data_prepare import YahooHistorical
from datetime import date, datetime
import numpy as np
from itertools import cycle
from sys import stdout
import matplotlib.pyplot as plt
from pybrain.supervised import RPropMinusTrainer, BackpropTrainer
from pybrain.datasets import SequentialDataSet
from pybrain.tools.shortcuts import buildNetwork
from pybrain.structure.modules import LSTMLayer, SigmoidLayer, LinearLayer, TanhLayer
from pybrain.tools.validation import testOnSequenceData
# prepare date
yahoo_data = YahooHistorical()
yahoo_data.open(os.path.join(os.path.dirname(__file__), 'data/^HSI.csv'))
dataset = yahoo_data.get()
# build network
net = buildNetwork(5, 25, 2, hiddenclass=LSTMLayer, outclass=SigmoidLayer, outputbias=False, recurrent=True)
net.randomize()
# build sequential dataset
train_ds = SequentialDataSet(5, 2)
for n, n1, m20 in zip(training_set, training_set[1:], sma20[-len(training_set):]):
i = [n['open'], n['high'], n['low'], n['adj_close'], m20]
d = (n1['adj_close'] - n['adj_close']) / n['adj_close']
o = [-1, -1]
if d > 0:
o[0] = abs(d)
__version__ = '0.1'
import os
from sys import stdout
import matplotlib.pyplot as plt
from data_prepare import YahooHistorical
from datetime import date, datetime
import numpy as np
from lib.features import Features
from pybrain.structure.modules import KohonenMap
import pickle
np.random.seed(42)
symbol1 = '0005.HK'
yahoo_data1 = YahooHistorical(data_from=date(2000, 1, 1), data_to=date(2015, 12, 31))
yahoo_data1.open(os.path.join(os.path.dirname(__file__), 'data/' + symbol1 + '.csv'))
data1 = yahoo_data1.get()
dataset1 = np.asarray([n['adj_close'] for n in data1])
p = 17 # 17-day
p = 5 # 5-day
nodes = 3
som = KohonenMap(p, nodes)
# som = pickle.load(open("pattern5.p", "rb"))
som.learningrate = 0.01
epochs = 1000
training_dataset = []
result = {}
# preparation
for i in xrange(p, len(dataset1)):
import pickle
np.random.seed(42)
def normalize(data, mean=None, std=None):
data = np.asarray(data)
if mean == None:
mean = np.mean(data)
if std == None:
std = np.std(data)
return (data - mean) / std, mean, std
symbol1 = "0005.HK"
yahoo_data = YahooHistorical(data_from=date(2000, 1, 1), data_to=date(2015, 12, 31))
yahoo_data.open(os.path.join(os.path.dirname(__file__), "data/" + symbol1 + ".csv"))
data = yahoo_data.get()
close_prices = np.array([n["adj_close"] for n in data])
# low_prices = np.array([n['low'] for n in data])
# high_prices = np.array([n['high'] for n in data])
# volumes = np.array([n['vol'] for n in data])
# prices, mean, std = normalize(close_prices)
# sma10, mean, std = normalize(talib.SMA(close_prices, 10), mean, std) # 10-day SMA
# sma50, mean, std = normalize(talib.SMA(close_prices, 50), mean, std) # 50-day SMA
# sma200, mean, std = normalize(talib.SMA(close_prices, 200), mean, std) # 200-day SMA
# macd_upper, macd_middle, macd_lower = talib.MACD(close_prices, 12, 26, 9)
# mfi = talib.MFI(high_prices, low_prices, close_prices, volumes) # Money Flow Index
# rsi = talib.RSI(close_prices)
training_input = []
training_output = []