def addEvidence(self, symbol = "IBM", \
sd=dt.datetime(2008,1,1), \
ed=dt.datetime(2009,1,1), \
sv = 10000):
# add your code to do learning here
# example usage of the old backward compatible util function
syms = [symbol]
dates = pd.date_range(sd, ed)
prices_all = ut.get_data(syms, dates) # automatically adds SPY
prices = prices_all[syms] # only portfolio symbols
prices_SPY = prices_all['SPY'] # only SPY, for comparison later
if self.verbose: print prices
# example use with new colname
volume_all = ut.get_data(syms, dates,
colname="Volume") # automatically adds SPY
volume = volume_all[syms] # only portfolio symbols
volume_SPY = volume_all['SPY'] # only SPY, for comparison later
if self.verbose: print volume
bb_val, upper, lower, rm, rs = get_bb(prices)
sma = get_sma(prices)
mom = get_momentum(prices)
x_train = np.zeros(shape=(len(prices), 7))
for i in range(20, len(prices) - self.N):
x_train[i][0] = bb_val[i]
x_train[i][1] = upper[i]
x_train[i][2] = lower[i]
x_train[i][3] = rm[i]
x_train[i][4] = rs[i]
x_train[i][5] = sma[i]
x_train[i][6] = mom[i]
x_train = pd.DataFrame(x_train)
x_train = x_train[:-self.N]
x_train.fillna(0, inplace=True)
x_train = x_train.values
y = []
for i in range(0, len(prices) - self.N):
if (prices.ix[i + self.N, symbol] /
prices.ix[i, symbol]) > 1.0009 + self.impact:
y.append(1)
elif (prices.ix[i + self.N, symbol] /
prices.ix[i, symbol]) < 0.9991 - self.impact:
y.append(-1)
else:
y.append(0)
y_train = np.array(y)
#print y_train
self.learner.addEvidence(x_train, y_train)
def testPolicy(symbol, sd, ed, sv):
symbols = ['JPM']
dates = pd.date_range(sd, ed)
benchmark = get_data(symbols, dates, addSPY=False).dropna()
prices = benchmark['JPM'].values
trades = pd.DataFrame(data=np.zeros(len(prices)),
index=benchmark.index,
columns=['JPM'])
print benchmark
sma = get_sma(benchmark)
mom = get_momentum(benchmark)
bbval, upper, lower, rolling_m, rolling_s = get_bb(benchmark)
holding = 0
benchmark = pd.DataFrame({'Date': dt.datetime(2008, 1, 2), 'JPM': [1000]})
benchmark.set_index("Date", inplace=True)
for i in range(12, len(prices)):
if sma[i] < 0.95 and bbval[i] < 0:
trades['JPM'].iloc[i] = 1000 - holding
holding = 1000
elif sma[i] > 1.05 and bbval[i] > 1:
trades['JPM'].iloc[i] = -holding - 1000
holding = -1000
return trades, benchmark
def check_signal(stock):
sleep(3)
#set indicators
ema_co_long = 50
ema_co_short = 25
cci_length = 20
ppo_length_short = 12
ppo_length_long = 26
atr_length = 14
min_ppo_change = 0.2
min_cci_change = 20
#get stock data
stock_data = get_stock_data(stock)
if (stock_data["open"][0] <= 0) and (stock_data["close"][0] <= 0):
return
#get indicator values
cci = get_cci(stock_data, cci_length)
ema_short = get_ema(stock_data, ema_co_short)
ema_long = get_sma(stock_data, ema_co_long)
ppo = get_ppo(stock_data, ppo_length_short, ppo_length_long)
atr = get_atr(stock_data, atr_length)
cci_reversal = False
#check trend with ema crossover
if ema_short[0] > ema_long[0]:
#Kommt CCI aus Short-Trend und ist jetzt neutral/long?
for i in range(1,3):
if (cci[0] > -100) and (cci[i] < -100):
cci_reversal = True
print("CCI Reversal")
break
#wenn CCI im Longtrend oder Reversal aus -100
if (cci[0] >= 100) or (cci_reversal):
#Wenn PPO und CCI steigen (mindestens um X) + PPO/CCI-Momentum -> PPO/CCI steigt stärker als am Vortag
if ((ppo[0]-ppo[1]) >= min_ppo_change) and (ppo[0]-ppo[1] > ppo[1]-ppo[2]) and ((cci[0]-cci[1]) >= min_cci_change) and (cci[0]-cci[1] > cci[1]-cci[2]):
print("--------------------!!!--------------------")
print("GO LONG "+stock+" at "+str(stock_data["close"][0]))
print("Stop Loss 2D Low - 1 ATR: "+str(min(stock_data["low"][0], stock_data["low"][1], stock_data["low"][2])-atr[0]))
print("Stop Loss 2 ATR: "+str(stock_data["low"][0]-(2*atr[0])))
print("--------------------!!!--------------------")
elif ((ppo[0]-ppo[1]) >= min_ppo_change*0.7) and (ppo[0]-ppo[1] > ppo[1]-ppo[2]) and ((cci[0]-cci[1]) >= min_cci_change*0.7) and (cci[0]-cci[1] > cci[1]-cci[2]):
print("--------------------!!!--------------------")
print(stock+": about to show LONG signal")
print("--------------------!!!--------------------")
else:
print(stock+": kein Signal")
elif ema_short[0] < ema_long[0]:
#Kommt CCI aus Long-Trend und ist jetzt neutral/short?
for i in range(1,3):
if (cci[0] < 100) and (cci[i] > 100):
cci_reversal = True
print("CCI Reversal")
break
#wenn CCI im Shorttrend oder Reversal aus 100
if (cci[0] <= -100) or (cci_reversal):
#Wenn PPO und CCI fallen (mindestens um X) + PPO-Momentum -> PPO fällt stärker als am Vortag
if ((ppo[1]-ppo[0]) >= min_ppo_change) and (ppo[1]-ppo[0] > ppo[2]-ppo[1]) and ((cci[1]-cci[0]) >= min_cci_change) and (cci[1]-cci[0] > cci[2]-cci[1]):
print("--------------------!!!--------------------")
print("GO SHORT "+stock+" at "+str(stock_data["close"][0]))
print("Stop Loss 2D High - 1 ATR: "+str(max(stock_data["high"][0], stock_data["high"][1], stock_data["high"][2])+atr[0]))
print("Stop Loss 2 ATR: "+str(stock_data["high"][0]+(2*atr[0])))
print("--------------------!!!--------------------")
elif ((ppo[1]-ppo[0]) >= min_ppo_change*0.7) and (ppo[1]-ppo[0] > ppo[2]-ppo[1]) and ((cci[1]-cci[0]) >= min_cci_change*0.7) and (cci[1]-cci[0] > cci[2]-cci[1]):
print("--------------------!!!--------------------")
print(stock+": about to show SHORT signal")
print("--------------------!!!--------------------")
else:
print(stock+": kein Signal")
def showvalues():
# Specify the start and end dates for this period.
start_d = dt.date(2008, 1, 1)
#end_d = dt.datetime(2018, 10, 30)
yesterday = dt.date.today() - dt.timedelta(1)
# Get portfolio values from Yahoo
symbol = request.form['symbol']
portf_value = fetchOnlineData(start_d, yesterday, symbol)
# ****Stock prices chart****
plot_prices = plot_stock_prices(portf_value.index,
portf_value['Adj Close'], symbol)
# ****Momentum chart****
# Normalize the prices Dataframe
normed = pd.DataFrame()
normed['Adj Close'] = portf_value['Adj Close'].values / portf_value[
'Adj Close'].iloc[0]
# Compute momentum
sym_mom = get_momentum(normed['Adj Close'], window=10)
# Create momentum chart
plot_mom = plot_momentum(portf_value.index, normed['Adj Close'], sym_mom,
"Momentum Indicator", (12, 8))
# ****Bollinger Bands****
# Compute rolling mean
rm_JPM = get_rolling_mean(portf_value['Adj Close'], window=10)
# Compute rolling standard deviation
rstd_JPM = get_rolling_std(portf_value['Adj Close'], window=10)
# Compute upper and lower bands
upper_band, lower_band = get_bollinger_bands(rm_JPM, rstd_JPM)
# Plot raw symbol values, rolling mean and Bollinger Bands
dates = pd.date_range(start_d, yesterday)
plot_boll = plot_bollinger(dates,
portf_value.index,
portf_value['Adj Close'],
symbol,
upper_band,
lower_band,
rm_JPM,
num_std=1,
title="Bollinger Indicator",
fig_size=(12, 6))
# ****Simple moving average (SMA)****
# Compute SMA
sma_JPM, q = get_sma(normed['Adj Close'], window=10)
# Plot symbol values, SMA and SMA quality
plot_sma = plot_sma_indicator(dates, portf_value.index,
normed['Adj Close'], symbol, sma_JPM, q,
"Simple Moving Average (SMA)")
# ****Relative Strength Index (RSI)****
# Compute RSI
rsi_value = get_RSI(portf_value['Adj Close'])
# Plot RSI
plot_rsi = plot_rsi_indicator(dates,
portf_value.index,
portf_value['Adj Close'],
symbol,
rsi_value,
window=14,
title="RSI Indicator",
fig_size=(12, 6))
# Session variables
session['start_val'] = request.form['start_val']
session['symbol'] = request.form['symbol']
session['start_d'] = start_d.strftime('%Y/%m/%d')
session['num_shares'] = request.form['num_shares']
session['commission'] = request.form['commission']
session['impact'] = request.form['impact']
return render_template(
# name of template
"stockpriceschart.html",
# now we pass in our variables into the template
start_val=request.form['start_val'],
symbol=request.form['symbol'],
commission=request.form['commission'],
impact=request.form['impact'],
num_shares=request.form['num_shares'],
start_date=start_d,
end_date=yesterday,
tables=[portf_value.to_html(classes=symbol)],
titles=['na', 'Stock Prices '],
div_placeholder_stock_prices=Markup(plot_prices),
div_placeholder_momentum=Markup(plot_mom),
div_placeholder_bollinger=Markup(plot_boll),
div_placeholder_sma=Markup(plot_sma),
div_placeholder_rsi=Markup(plot_rsi))
def testPolicy(self, symbol = "IBM", \
sd=dt.datetime(2009,1,1), \
ed=dt.datetime(2010,1,1), \
sv = 10000):
# here we build a fake set of trades
# your code should return the same sort of data
dates = pd.date_range(sd, ed)
prices_all = ut.get_data([symbol], dates) # automatically adds SPY
prices = prices_all[[
symbol,
]] # only portfolio symbols
trades_SPY = prices_all['SPY'] # only SPY, for comparison later
bb_val, upper, lower, rm, rs = get_bb(prices)
sma = get_sma(prices)
mom = get_momentum(prices)
x_test = np.zeros(shape=(len(prices), 7))
for i in range(20, len(prices) - self.N):
x_test[i][0] = bb_val[i]
x_test[i][1] = upper[i]
x_test[i][2] = lower[i]
x_test[i][3] = rm[i]
x_test[i][4] = rs[i]
x_test[i][5] = sma[i]
x_test[i][6] = mom[i]
x_test = pd.DataFrame(x_test)
x_test = x_test[:-self.N]
x_test = x_test.values
y_test = self.learner.query(x_test)
trades = pd.DataFrame(0, columns=prices.columns, index=prices.index)
flag = 0
for i in range(0, len(prices) - self.N):
if y_test[i] == 1:
if flag == 0:
flag = 1000
trades[symbol].iloc[i] = 1000
elif flag == -1000:
flag = 1000
trades.iloc[i, 0] = 2000
if y_test[i] == -1:
if flag == 0:
flag = -1000
trades[symbol].iloc[i] = -1000
elif flag == 1000:
flag = -1000
trades[symbol].iloc[i] = -2000
# trades.values[:,:] = 0 # set them all to nothing
# trades.values[0,:] = 1000 # add a BUY at the start
# trades.values[40,:] = -1000 # add a SELL
# trades.values[41,:] = 1000 # add a BUY
# trades.values[60,:] = -2000 # go short from long
# trades.values[61,:] = 2000 # go long from short
# trades.values[-1,:] = -1000 #exit on the last day
# if self.verbose: print type(trades) # it better be a DataFrame!
# if self.verbose: print trades
# if self.verbose: print prices_all
return trades
def check_signal(stock):
stock_data = {}
output = []
sum = 50000
#get stock data
stock_data = get_stock_data_wotd(stock)
if (stock_data[0]["open"] <= 0) and (stock_data[0]["close"] <= 0):
output.append(stock + ' ZERO VALUES!')
return output
sma_length = 50
cci_length = 100
hma_1_length = 12
hma_2_length = 25
hma_3_length = 100
atr_1_length = 14
atr_2_length = 1
#get indicator values
sma = get_sma(stock_data, sma_length)
atr_1 = get_atr(stock_data, atr_1_length)
atr_2 = get_atr(stock_data, atr_2_length)
hma_1 = get_hma(stock_data, hma_1_length)
hma_2 = get_hma(stock_data, hma_2_length)
hma_3 = get_hma(stock_data, hma_3_length)
cci = get_cci(stock_data, cci_length)
# Alle Listen so lange machen, wie die kürzeste, damit von hinten durchiteriert werden kann
min_length = min(len(hma_3), len(hma_2), len(hma_1), len(sma), len(atr_1),
len(atr_2), len(cci))
sma = sma[:min_length]
atr_1 = atr_1[:min_length]
atr_2 = atr_2[:min_length]
hma_1 = hma_1[:min_length]
hma_2 = hma_2[:min_length]
hma_3 = hma_3[:min_length]
cci = cci[:min_length]
#stock_data = stock_data[:min_length]
'''
print(sma[0])
print(atr_1[0])
print(atr_2[0])
print(hma_1[0])
print(hma_2[0])
print(hma_3[0])
print(cci[0])
'''
if ((cci[0] > 100) and ((hma_1[0] - hma_1[1]) > 0)
and ((hma_2[0] - hma_2[1]) > 0) and ((hma_3[0] - hma_3[1]) > 0)
and ((sma[0] - sma[1]) > 0) and ((hma_1[0] - hma_1[1]) >
(hma_1[1] - hma_1[2]))):
output.append("!!!!!!!!!!" + stock + "!!!!!!!!!!")
vol_avg = 0
for i in range(14):
vol_avg += stock_data[i]["volume"]
vol_avg = vol_avg / 14
if ((stock_data[0]["volume"] * atr_2[0] > vol_avg * atr_1[0])
and (stock_data[0]["close"] > stock_data[0]["open"])
and (stock_data[0]["close"] > stock_data[1]["close"])):
trade = {"EK": 0, "Anzahl": 0, "SL": 0, "TP": 0}
trade["EK"] = stock_data[0]["close"]
trade["Anzahl"] = round((0.005 * sum) / (2.5 * atr_1[0]))
trade["SL"] = stock_data[0]["close"] - (2.5 * atr_1[0])
trade["TP"] = stock_data[0]["close"] + (2.5 * atr_1[0])
output.append("Buy " + str(trade["Anzahl"]) + " Stück für " +
str(trade["EK"]))
output.append("ATR = " + str(atr_1[0]))
output.append("Stop Loss 2.5 ATR: " + str(trade["SL"]))
output.append("Take Profit 2.5 ATR: " + str(trade["TP"]))
if len(output) == 0:
output.append("----------" + stock + "----------")
return output