def eval(self, environment, gene, date1, date2):
timeperiod = (gene.next_value(environment, date1, date2))
date1 = environment.shift_date(date1, -(timeperiod - 1), -1)
df = gene.next_value(environment, date1, date2)
res = df.apply(lambda x: pd.Series(
talib.TSF(x.values, timeperiod=timeperiod), index=df.index))
return res.iloc[timeperiod - 1:]
def test_TSF(self):
self.env.add_operator('linearreg', {
'operator': OperatorTSF,
})
string = 'linearreg(14, open)'
gene = self.env.parse_string(string)
self.assertRaises(IndexError, gene.eval, self.env, self.dates[12], self.dates[-1])
df = gene.eval(self.env, self.dates[13], self.dates[14])
ser0, ser1 = df.iloc[0], df.iloc[1]
o = self.env.get_data_value('open').values
res0, res1, res = [], [], []
for i in df.columns:
res0.append(talib.TSF(o[:14, i], timeperiod=14)[-1] == ser0[i])
res1.append(talib.TSF(o[1:14+1, i], timeperiod=14)[-1] == ser1[i])
res.append(talib.TSF(o[:14+1, i], timeperiod=14)[-1] == ser1[i])
self.assertTrue(all(res0) and all(res1) and all(res))
def TSF(close_ts, timeperiod=14):
import talib
close_np = close_ts.cpu().detach().numpy()
close_df = pd.DataFrame(close_np)
TSF = close_df.apply(lambda x: talib.TSF(x, timeperiod=14))
TSF_ts = torch.tensor(tsf.values, dtype=close_ts.dtype, device=close_ts.device)
return TSF_ts
def extract_features(data):
high = data['High']
low = data['Low']
close = data['Close']
volume = data['Volume']
open_ = data['Open']
data['ADX'] = ta.ADX(high, low, close, timeperiod=19)
data['CCI'] = ta.CCI(high, low, close, timeperiod=19)
data['CMO'] = ta.CMO(close, timeperiod=14)
data['MACD'], X, Y = ta.MACD(close, fastperiod=10, slowperiod=30, signalperiod=9)
data['MFI'] = ta.MFI(high, low, close, volume, timeperiod=19)
data['MOM'] = ta.MOM(close, timeperiod=9)
data['ROCR'] = ta.ROCR(close, timeperiod=12)
data['RSI'] = ta.RSI(close, timeperiod=19)
data['STOCHSLOWK'], data['STOCHSLOWD'] = ta.STOCH(high, low, close, fastk_period=5, slowk_period=3, slowk_matype=0, slowd_period=3, slowd_matype=0)
data['TRIX'] = ta.TRIX(close, timeperiod=30)
data['WILLR'] = ta.WILLR(high, low, close, timeperiod=14)
data['OBV'] = ta.OBV(close, volume)
data['TSF'] = ta.TSF(close, timeperiod=14)
data['NATR'] = ta.NATR(high, low, close)#, timeperiod=14)
data['ULTOSC'] = ta.ULTOSC(high, low, close)
data['AROONOSC'] = ta.AROONOSC(high, low, timeperiod=14)
data['BOP'] = ta.BOP(open_, high, low, close)
data['LINEARREG'] = ta.LINEARREG(close)
data['AP0'] = ta.APO(close, fastperiod=9, slowperiod=23, matype=1)
data['TEMA'] = ta.TRIMA(close, 29)
return data
def compTSF(self):
tsf = talib.TSF(self.close,timeperiod=self.lookback)
self.removeNullID(tsf)
self.rawFeatures['TSF'] = tsf
FEATURE_SIZE_DICT['TSF'] = 1
return
def update(self, data, N):
close = data[4]
self.clear()
self.series.attachAxis(self.chart.ax)
self.series.attachAxis(self.chart.ay)
tsf = talib.TSF(close, timeperiod=14)
firstNotNan = np.where(np.isnan(tsf))[0][-1] + 1
tsf[:firstNotNan] = tsf[firstNotNan]
for i, val in enumerate(tsf[-N:]):
self.series.append(i + 0.5, val)
def TSF(close, timeperiod=14):
''' Time Series Forecast 时间序列预测
分组: Statistic Functions 统计函数
简介: 一种历史资料延伸预测，也称历史引伸预测法。
是以时间数列所能反映的社会经济现象的发展过程和规律性，
进行引伸外推，预测其发展趋势的方法
real = TSF(close, timeperiod=14)
'''
return talib.TSF(close, timeperiod)
def __get_predictors(data):
open_list = np.asarray(data["open"].tolist())
close_list = np.asarray(data["close"].tolist())
high_list = np.asarray(data["high"].tolist())
low_list = np.asarray(data["low"].tolist())
volume_list = np.asarray(data["volume"].tolist())
adj_close = close_list
obv = talib.OBV(close_list, volume_list)
rsi6 = talib.RSI(close_list, timeperiod=6)
rsi12 = talib.RSI(close_list, timeperiod=12)
sma3 = talib.SMA(close_list, timeperiod=3)
ema6 = talib.EMA(close_list, timeperiod=6)
ema12 = talib.EMA(close_list, timeperiod=12)
atr14 = talib.ATR(high_list, low_list, close_list, timeperiod=14)
mfi14 = talib.MFI(high_list,
low_list,
close_list,
volume_list,
timeperiod=14)
adx14 = talib.ADX(high_list, low_list, close_list, timeperiod=14)
adx20 = talib.ADX(high_list, low_list, close_list, timeperiod=20)
mom1 = talib.MOM(close_list, timeperiod=1)
mom3 = talib.MOM(close_list, timeperiod=3)
cci12 = talib.CCI(high_list, low_list, close_list, timeperiod=14)
cci20 = talib.CCI(high_list, low_list, close_list, timeperiod=20)
rocr3 = talib.ROCR(close_list, timeperiod=3)
rocr12 = talib.ROCR(close_list, timeperiod=12)
macd, macd_sig, macd_hist = talib.MACD(close_list)
willr = talib.WILLR(high_list, low_list, close_list)
tsf10 = talib.TSF(close_list, timeperiod=10)
tsf20 = talib.TSF(close_list, timeperiod=20)
trix = talib.TRIX(close_list)
bbandupper, bbandmiddle, bbandlower = talib.BBANDS(close_list)
return [adj_close[-1], obv[-1], rsi6[-1], rsi12[-1], sma3[-1], ema6[-1], ema12[-1], atr14[-1], mfi14[-1], adx14[-1], adx20[-1], mom1[-1], mom3[-1], cci12[-1], cci20[-1], \
rocr3[-1], rocr12[-1], macd[-1], macd_sig[-1], macd_hist[-1], willr[-1], tsf10[-1], tsf20[-1], trix[-1], bbandupper[-1], bbandmiddle[-1], bbandlower[-1]]
def getStatFunctions(df):
high = df['High']
low = df['Low']
close = df['Close']
open = df['Open']
volume = df['Volume']
df['BETA'] = ta.BETA(high, low, timeperiod=5)
df['CORREL'] = ta.CORREL(high, low, timeperiod=30)
df['LINREG'] = ta.LINEARREG(close, timeperiod=14)
df['LINREGANGLE'] = ta.LINEARREG_ANGLE(close, timeperiod=14)
df['LINREGINTERCEPT'] = ta.LINEARREG_INTERCEPT(close, timeperiod=14)
df['LINREGSLOPE'] = ta.LINEARREG_SLOPE(close, timeperiod=14)
df['STDDEV'] = ta.STDDEV(close, timeperiod=5, nbdev=1)
df['TSF'] = ta.TSF(close, timeperiod=14)
df['VAR'] = ta.VAR(close, timeperiod=5, nbdev=1)
def tsf(client, symbol, range="6m", closecol="close", period=14, nbdev=1):
"""This will return a dataframe of standard deviation for the given symbol across
the given range
Args:
client (pyEX.Client): Client
symbol (string): Ticker
range (string): range to use, for pyEX.chart
closecol (string): column to use to calculate
period (int): period to calculate adx across
Returns:
DataFrame: result
"""
df = client.chartDF(symbol, range)
tsf = t.TSF(df[closecol].values.astype(float), period)
return pd.DataFrame({closecol: df[closecol].values, "tsf": tsf})
def tsf(candles: np.ndarray, period: int = 14, source_type: str = "close", sequential: bool = False) -> Union[
float, np.ndarray]:
"""
TSF - Time Series Forecast
:param candles: np.ndarray
:param period: int - default: 14
:param source_type: str - default: "close"
:param sequential: bool - default: False
:return: float | np.ndarray
"""
candles = slice_candles(candles, sequential)
source = get_candle_source(candles, source_type=source_type)
res = talib.TSF(source, timeperiod=period)
return res if sequential else res[-1]
def statistic_process(event):
print(event.widget.get())
statistic = event.widget.get()
upperband, middleband, lowerband = ta.BBANDS(close,
timeperiod=5,
nbdevup=2,
nbdevdn=2,
matype=0)
fig, axes = plt.subplots(2, 1, sharex=True)
ax1, ax2 = axes[0], axes[1]
axes[0].plot(close, 'rd-', markersize=3)
axes[0].plot(upperband, 'y-')
axes[0].plot(middleband, 'b-')
axes[0].plot(lowerband, 'y-')
axes[0].set_title(statistic, fontproperties='SimHei')
if statistic == '线性回归':
real = ta.LINEARREG(close, timeperiod=14)
axes[1].plot(real, 'r-')
elif statistic == '线性回归角度':
real = ta.LINEARREG_ANGLE(close, timeperiod=14)
axes[1].plot(real, 'r-')
elif statistic == '线性回归截距':
real = ta.LINEARREG_INTERCEPT(close, timeperiod=14)
axes[1].plot(real, 'r-')
elif statistic == '线性回归斜率':
real = ta.LINEARREG_SLOPE(close, timeperiod=14)
axes[1].plot(real, 'r-')
elif statistic == '标准差':
real = ta.STDDEV(close, timeperiod=5, nbdev=1)
axes[1].plot(real, 'r-')
elif statistic == '时间序列预测':
real = ta.TSF(close, timeperiod=14)
axes[1].plot(real, 'r-')
elif statistic == '方差':
real = ta.VAR(close, timeperiod=5, nbdev=1)
axes[1].plot(real, 'r-')
plt.show()
def tsf(candles: np.ndarray,
period: int = 14,
source_type: str = "close",
sequential: bool = False) -> Union[float, np.ndarray]:
"""
TSF - Time Series Forecast
:param candles: np.ndarray
:param period: int - default: 14
:param source_type: str - default: "close"
:param sequential: bool - default=False
:return: float | np.ndarray
"""
warmup_candles_num = get_config('env.data.warmup_candles_num', 240)
if not sequential and len(candles) > warmup_candles_num:
candles = candles[-warmup_candles_num:]
source = get_candle_source(candles, source_type=source_type)
res = talib.TSF(source, timeperiod=period)
return res if sequential else res[-1]
def Stat_Function(dataframe):
#Statistic Functions
#BETA - Beta
df[f'{ratio}_BETA'] = talib.BETA(High, Low, timeperiod=5)
#CORREL - Pearson's Correlation Coefficient (r)
df[f'{ratio}_CORREL'] = talib.CORREL(High, Low, timeperiod=30)
#LINEARREG - Linear Regression
df[f'{ratio}_LINEARREG'] = talib.LINEARREG(Close, timeperiod=14)
#LINEARREG_ANGLE - Linear Regression Angle
df[f'{ratio}_LINEARREG_ANGLE'] = talib.LINEARREG_ANGLE(Close, timeperiod=14)
#LINEARREG_INTERCEPT - Linear Regression Intercept
df[f'{ratio}_LINEARREG_INTERCEPT'] = talib.LINEARREG_INTERCEPT(Close, timeperiod=14)
#LINEARREG_SLOPE - Linear Regression Slope
df[f'{ratio}_LINEARREG_SLOPE'] = talib.LINEARREG_SLOPE(Close, timeperiod=14)
#STDDEV - Standard Deviation
df[f'{ratio}_STDDEV'] = talib.STDDEV(Close, timeperiod=5, nbdev=1)
#TSF - Time Series Forecast
df[f'{ratio}_TSF'] = talib.TSF(Close, timeperiod=14)
#VAR - Variance
df[f'{ratio}_VAR'] = talib.VAR(Close, timeperiod=5, nbdev=1)
return
def addFeatures(stock):
"""
Input pandas data frame, generate features for sock.
"""
df = stock
df['TSF'] = talib.TSF(np.asarray(df.AdjClose))
df['STDDEV'] = talib.STDDEV(np.asarray(df.AdjClose))
real = talib.ADOSC(np.asarray(df.High), np.asarray(df.Low), np.asarray(df.AdjClose), np.asarray(df.Volume.astype('double')))
df['ADOSC'] = real > 0
df['ADOSC'] = df['ADOSC'].astype(int)
df['ADX'] = talib.ADX(np.asarray(df.High), np.asarray(df.Low), np.asarray(df.AdjClose))
macd, macdsignal, macdhist = talib.MACD(np.asarray(df.AdjClose))
df['MACD'] = macd
df['MOM'] = talib.MOM(np.asarray(df.AdjClose))
df['MFI'] = talib.MFI(np.asarray(df.High), np.asarray(df.Low), np.asarray(df.AdjClose), np.asarray(df.Volume.astype('double')))
df['RSI'] = talib.RSI(np.asarray(df.AdjClose))
df['TRIX'] = talib.TRIX(np.asarray(df.AdjClose))
df['ATR'] = talib.ATR(np.asarray(df.High), np.asarray(df.Low), np.asarray(df.AdjClose))
#Add 9 lagged return
for i in range(1,10):
name = 'laggedReturn_' + str(i)
df[name] = df.AdjClose.pct_change(periods=i)
return df
def plot_timeseries(ax, data):
"""This function plots
######################## TIME SERIES FORCAST ###################################
The Time Series Forecast indicator displays the statistical trend of a
security's price over a specified time period. The trend is based on linear
regression analysis. Rather than plotting a straight linear regression
trendline, the Time Series Forecast plots the last point of multiple linear
regression trendlines. The resulting Time Series Forecast indicator is
sometimes referred to as the "moving linear regression" indicator or
the "regression oscillator." The interpretation of a Time Series Forecast
is identical to a moving average. However, the Time Series Forecast
indicator has two advantages over classic moving averages. Unlike a moving
average, a Time Series Forecast does not exhibit as much delay when
adjusting to price changes. Since the indicator is "fitting" itself
to the data rather than averaging them, the Time Series Forecast is more
responsive to price changes."""
time_series_ind = talib.TSF(data['Adj_Close'], timeperiod=14)
ax.plot(data["Date"],
time_series_ind,
label="TIME SERIES FORCAST",
color="sandybrown")
df['CORREL'] = ta.CORREL(np.array(df['High'].shift(1)),
np.array(df['Low'].shift(1)),
timeperiod=n)
df['LINEARREG'] = ta.LINEARREG(np.array(df['Adj Close'].shift(1)),
timeperiod=n)
df['LINEARREG_ANGLE'] = ta.LINEARREG_ANGLE(np.array(df['Adj Close'].shift(1)),
timeperiod=n)
df['LINEARREG_INTERCEPT'] = ta.LINEARREG_INTERCEPT(np.array(
df['Adj Close'].shift(1)),
timeperiod=n)
df['LINEARREG_SLOPE'] = ta.LINEARREG_SLOPE(np.array(df['Adj Close'].shift(1)),
timeperiod=n)
df['STDDEV'] = ta.STDDEV(np.array(df['Adj Close'].shift(1)),
timeperiod=n,
nbdev=1)
df['Time Series Forecast'] = ta.TSF(np.array(df['Adj Close'].shift(1)),
timeperiod=n)
df['VAR'] = ta.VAR(np.array(df['Adj Close'].shift(1)), timeperiod=n, nbdev=1)
# Overlap Studies Functions
df['upperband'], df['middleband'], df['lowerband'] = ta.BBANDS(np.array(
df['Adj Close'].shift(1)),
timeperiod=n,
nbdevup=2,
nbdevdn=2,
matype=0)
df['DEMA'] = ta.DEMA(np.array(df['Adj Close'].shift(1)), timeperiod=n)
df['EMA'] = ta.EMA(np.array(df['Adj Close'].shift(1)), timeperiod=n)
df['HT_TRENDLINE'] = ta.HT_TRENDLINE(np.array(df['Adj Close'].shift(1)))
df['KAMA'] = ta.KAMA(np.array(df['Adj Close'].shift(1)), timeperiod=n)
df['MA'] = ta.MA(np.array(df['Adj Close'].shift(1)), timeperiod=n, matype=0)
# df['mama'],df['fama'] = ta.MAMA(np.array(df['Adj Close'].shift(1)), fastlimit=0, slowlimit=0)
import talib as ta
from forex_python.converter import CurrencyRates
moving_averages_functions = {
'SMA': lambda close, time_p: ta.SMA(close, time_p),
'EMA': lambda close, time_p: ta.EMA(close, time_p),
'WMA': lambda close, time_p: ta.WMA(close, time_p),
'LINEAR_REG': lambda close, time_p: ta.LINEARREG(close, time_p),
'TRIMA': lambda close, time_p: ta.TRIMA(close, time_p),
'DEMA': lambda close, time_p: ta.DEMA(close, time_p),
'HT_TRENDLINE': lambda close, time_p: ta.HT_TRENDLINE(close, time_p),
'TSF': lambda close, time_p: ta.TSF(close, time_p)
}
def get_pip_value(symbol, account_currency):
first_symbol = symbol[0:3]
second_symbol = symbol[3:6]
c = CurrencyRates()
return c.convert(second_symbol, account_currency, c.convert(first_symbol, second_symbol, 1))
def get_tsf(self):
return talib.TSF(self.close_list)
def TSF(data, **kwargs):
_check_talib_presence()
prices = _extract_series(data)
return talib.TSF(prices, **kwargs)
def ta(name, price_h, price_l, price_c, price_v, price_o):
# function 'MAX'/'MAXINDEX'/'MIN'/'MININDEX'/'MINMAX'/'MINMAXINDEX'/'SUM' is missing
if name == 'AD':
return talib.AD(np.array(price_h), np.array(price_l),
np.array(price_c), np.asarray(price_v, dtype='float'))
if name == 'ADOSC':
return talib.ADOSC(np.array(price_h),
np.array(price_l),
np.array(price_c),
np.asarray(price_v, dtype='float'),
fastperiod=2,
slowperiod=10)
if name == 'ADX':
return talib.ADX(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'ADXR':
return talib.ADXR(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'APO':
return talib.APO(np.asarray(price_c, dtype='float'),
fastperiod=12,
slowperiod=26,
matype=0)
if name == 'AROON':
AROON_DWON, AROON2_UP = talib.AROON(np.array(price_h),
np.asarray(price_l, dtype='float'),
timeperiod=90)
return (AROON_DWON, AROON2_UP)
if name == 'AROONOSC':
return talib.AROONOSC(np.array(price_h),
np.asarray(price_l, dtype='float'),
timeperiod=14)
if name == 'ATR':
return talib.ATR(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'AVGPRICE':
return talib.AVGPRICE(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'BBANDS':
BBANDS1, BBANDS2, BBANDS3 = talib.BBANDS(np.asarray(price_c,
dtype='float'),
matype=MA_Type.T3)
return BBANDS1
if name == 'BETA':
return talib.BETA(np.array(price_h),
np.asarray(price_l, dtype='float'),
timeperiod=5)
if name == 'BOP':
return talib.BOP(np.array(price_o), np.array(price_h),
np.array(price_l), np.asarray(price_c, dtype='float'))
if name == 'CCI':
return talib.CCI(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'CDL2CROWS':
return talib.CDL2CROWS(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDL3BLACKCROWS':
return talib.CDL3BLACKCROWS(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDL3INSIDE':
return talib.CDL3INSIDE(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDL3LINESTRIKE':
return talib.CDL3LINESTRIKE(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDL3OUTSIDE':
return talib.CDL3OUTSIDE(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDL3STARSINSOUTH':
return talib.CDL3STARSINSOUTH(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDL3WHITESOLDIERS':
return talib.CDL3WHITESOLDIERS(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLABANDONEDBABY':
return talib.CDLABANDONEDBABY(np.array(price_o),
np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
penetration=0)
if name == 'CDLADVANCEBLOCK':
return talib.CDLADVANCEBLOCK(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLBELTHOLD':
return talib.CDLBELTHOLD(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLBREAKAWAY':
return talib.CDLBREAKAWAY(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLCLOSINGMARUBOZU':
return talib.CDLCLOSINGMARUBOZU(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLCONCEALBABYSWALL':
return talib.CDLCONCEALBABYSWALL(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLCOUNTERATTACK':
return talib.CDLCOUNTERATTACK(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLDARKCLOUDCOVER':
return talib.CDLDARKCLOUDCOVER(np.array(price_o),
np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
penetration=0)
if name == 'CDLDOJI':
return talib.CDLDOJI(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLDOJISTAR':
return talib.CDLDOJISTAR(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLDRAGONFLYDOJI':
return talib.CDLDRAGONFLYDOJI(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLENGULFING':
return talib.CDLENGULFING(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLEVENINGDOJISTAR':
return talib.CDLEVENINGDOJISTAR(np.array(price_o),
np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
penetration=0)
if name == 'CDLEVENINGSTAR':
return talib.CDLEVENINGSTAR(np.array(price_o),
np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
penetration=0)
if name == 'CDLGAPSIDESIDEWHITE':
return talib.CDLGAPSIDESIDEWHITE(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLGRAVESTONEDOJI':
return talib.CDLGRAVESTONEDOJI(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLHAMMER':
return talib.CDLHAMMER(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLHANGINGMAN':
return talib.CDLHANGINGMAN(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLHARAMI':
return talib.CDLHARAMI(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLHARAMICROSS':
return talib.CDLHARAMICROSS(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLHIGHWAVE':
return talib.CDLHIGHWAVE(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLHIKKAKE':
return talib.CDLHIKKAKE(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLHIKKAKEMOD':
return talib.CDLHIKKAKEMOD(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLHOMINGPIGEON':
return talib.CDLHOMINGPIGEON(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLIDENTICAL3CROWS':
return talib.CDLIDENTICAL3CROWS(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLINNECK':
return talib.CDLINNECK(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLINVERTEDHAMMER':
return talib.CDLINVERTEDHAMMER(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLKICKING':
return talib.CDLKICKING(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLKICKINGBYLENGTH':
return talib.CDLKICKINGBYLENGTH(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLLADDERBOTTOM':
return talib.CDLLADDERBOTTOM(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLLONGLEGGEDDOJI':
return talib.CDLLONGLEGGEDDOJI(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLLONGLINE':
return talib.CDLLONGLINE(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLMARUBOZU':
return talib.CDLMARUBOZU(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLMATCHINGLOW':
return talib.CDLMATCHINGLOW(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLMATHOLD':
return talib.CDLMATHOLD(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLMORNINGDOJISTAR':
return talib.CDLMORNINGDOJISTAR(np.array(price_o),
np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
penetration=0)
if name == 'CDLMORNINGSTAR':
return talib.CDLMORNINGSTAR(np.array(price_o),
np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
penetration=0)
if name == 'CDLONNECK':
return talib.CDLONNECK(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLPIERCING':
return talib.CDLPIERCING(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLRICKSHAWMAN':
return talib.CDLRICKSHAWMAN(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLRISEFALL3METHODS':
return talib.CDLRISEFALL3METHODS(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLSEPARATINGLINES':
return talib.CDLSEPARATINGLINES(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLSHOOTINGSTAR':
return talib.CDLSHOOTINGSTAR(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLSHORTLINE':
return talib.CDLSHORTLINE(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLSPINNINGTOP':
return talib.CDLSPINNINGTOP(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLSTALLEDPATTERN':
return talib.CDLSTALLEDPATTERN(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLSTICKSANDWICH':
return talib.CDLSTICKSANDWICH(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLTAKURI':
return talib.CDLTAKURI(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLTASUKIGAP':
return talib.CDLTASUKIGAP(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLTHRUSTING':
return talib.CDLTHRUSTING(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLTRISTAR':
return talib.CDLTRISTAR(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLUNIQUE3RIVER':
return talib.CDLUNIQUE3RIVER(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLUPSIDEGAP2CROWS':
return talib.CDLUPSIDEGAP2CROWS(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CDLXSIDEGAP3METHODS':
return talib.CDLXSIDEGAP3METHODS(np.array(price_o), np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'CMO':
return talib.CMO(np.asarray(price_c, dtype='float'), timeperiod=14)
if name == 'CORREL':
return talib.CORREL(np.array(price_h),
np.asarray(price_l, dtype='float'),
timeperiod=30)
if name == 'DEMA':
return talib.DEMA(np.asarray(price_c, dtype='float'), timeperiod=30)
if name == 'DX':
return talib.DX(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'EMA':
return talib.EMA(np.asarray(price_c, dtype='float'), timeperiod=30)
if name == 'HT_DCPERIOD':
return talib.HT_DCPERIOD(np.asarray(price_c, dtype='float'))
if name == 'HT_DCPHASE':
return talib.HT_DCPHASE(np.asarray(price_c, dtype='float'))
if name == 'HT_PHASOR':
HT_PHASOR1, HT_PHASOR2 = talib.HT_PHASOR(
np.asarray(price_c, dtype='float')
) # use HT_PHASOR1 for the indication of up and down
return HT_PHASOR1
if name == 'HT_SINE':
HT_SINE1, HT_SINE2 = talib.HT_SINE(np.asarray(price_c, dtype='float'))
return HT_SINE1
if name == 'HT_TRENDLINE':
return talib.HT_TRENDLINE(np.asarray(price_c, dtype='float'))
if name == 'HT_TRENDMODE':
return talib.HT_TRENDMODE(np.asarray(price_c, dtype='float'))
if name == 'KAMA':
return talib.KAMA(np.asarray(price_c, dtype='float'), timeperiod=30)
if name == 'LINEARREG':
return talib.LINEARREG(np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'LINEARREG_ANGLE':
return talib.LINEARREG_ANGLE(np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'LINEARREG_INTERCEPT':
return talib.LINEARREG_INTERCEPT(np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'LINEARREG_SLOPE':
return talib.LINEARREG_SLOPE(np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'MA':
return talib.MA(np.asarray(price_c, dtype='float'),
timeperiod=30,
matype=0)
if name == 'MACD':
MACD1, MACD2, MACD3 = talib.MACD(np.asarray(price_c, dtype='float'),
fastperiod=12,
slowperiod=26,
signalperiod=9)
return MACD1
if nam == 'MACDEXT':
return talib.MACDEXT(np.asarray(price_c, dtype='float'),
fastperiod=12,
fastmatype=0,
slowperiod=26,
slowmatype=0,
signalperiod=9,
signalmatype=0)
if name == 'MACDFIX':
MACDFIX1, MACDFIX2, MACDFIX3 = talib.MACDFIX(np.asarray(price_c,
dtype='float'),
signalperiod=9)
return MACDFIX1
if name == 'MAMA':
MAMA1, MAMA2 = talib.MAMA(np.asarray(price_c, dtype='float'),
fastlimit=0,
slowlimit=0)
return MAMA1
if name == 'MEDPRICE':
return talib.MEDPRICE(np.array(price_h),
np.asarray(price_l, dtype='float'))
if name == 'MINUS_DI':
return talib.MINUS_DI(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'MINUS_DM':
return talib.MINUS_DM(np.array(price_h),
np.asarray(price_l, dtype='float'),
timeperiod=14)
if name == 'MOM':
return talib.MOM(np.asarray(price_c, dtype='float'), timeperiod=10)
if name == 'NATR':
return talib.NATR(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'OBV':
return talib.OBV(np.array(price_c), np.asarray(price_v, dtype='float'))
if name == 'PLUS_DI':
return talib.PLUS_DI(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'PLUS_DM':
return talib.PLUS_DM(np.array(price_h),
np.asarray(price_l, dtype='float'),
timeperiod=14)
if name == 'PPO':
return talib.PPO(np.asarray(price_c, dtype='float'),
fastperiod=12,
slowperiod=26,
matype=0)
if name == 'ROC':
return talib.ROC(np.asarray(price_c, dtype='float'), timeperiod=10)
if name == 'ROCP':
return talib.ROCP(np.asarray(price_c, dtype='float'), timeperiod=10)
if name == 'ROCR100':
return talib.ROCR100(np.asarray(price_c, dtype='float'), timeperiod=10)
if name == 'RSI':
return talib.RSI(np.asarray(price_c, dtype='float'), timeperiod=14)
if name == 'SAR':
return talib.SAR(np.array(price_h),
np.asarray(price_l, dtype='float'),
acceleration=0,
maximum=0)
if name == 'SAREXT':
return talib.SAREXT(np.array(price_h),
np.asarray(price_l, dtype='float'),
startvalue=0,
offsetonreverse=0,
accelerationinitlong=0,
accelerationlong=0,
accelerationmaxlong=0,
accelerationinitshort=0,
accelerationshort=0,
accelerationmaxshort=0)
if name == 'SMA':
return talib.SMA(np.asarray(price_c, dtype='float'), timeperiod=30)
if name == 'STDDEV':
return talib.STDDEV(np.asarray(price_c, dtype='float'),
timeperiod=5,
nbdev=1)
if name == 'STOCH':
STOCH1, STOCH2 = talib.STOCH(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
fastk_period=5,
slowk_period=3,
slowk_matype=0,
slowd_period=3,
slowd_matype=0)
return STOCH1
if name == 'STOCHF':
STOCHF1, STOCHF2 = talib.STOCHF(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
fastk_period=5,
fastd_period=3,
fastd_matype=0)
return STOCHF1
if name == 'STOCHRSI':
STOCHRSI1, STOCHRSI2 = talib.STOCHRSI(np.asarray(price_c,
dtype='float'),
timeperiod=14,
fastk_period=5,
fastd_period=3,
fastd_matype=0)
return STOCHRSI1
if name == 'T3':
return talib.T3(np.asarray(price_c, dtype='float'),
timeperiod=5,
vfactor=0)
if name == 'TEMA':
return talib.TEMA(np.asarray(price_c, dtype='float'), timeperiod=30)
if name == 'TRANGE':
return talib.TRANGE(np.array(price_h), np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'TRIMA':
return talib.TRIMA(np.asarray(price_c, dtype='float'), timeperiod=30)
if name == 'TRIX':
return talib.TRIX(np.asarray(price_c, dtype='float'), timeperiod=30)
if name == 'TSF':
return talib.TSF(np.asarray(price_c, dtype='float'), timeperiod=14)
if name == 'TYPPRICE':
return talib.TYPPRICE(np.array(price_h), np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'ULTOSC':
return talib.ULTOSC(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
timeperiod1=7,
timeperiod2=14,
timeperiod3=28)
if name == 'VAR':
return talib.VAR(np.asarray(price_c, dtype='float'),
timeperiod=5,
nbdev=1)
if name == 'WCLPRICE':
return talib.WCLPRICE(np.array(price_h), np.array(price_l),
np.asarray(price_c, dtype='float'))
if name == 'WILLR':
return talib.WILLR(np.array(price_h),
np.array(price_l),
np.asarray(price_c, dtype='float'),
timeperiod=14)
if name == 'WMA':
return talib.WMA(np.asarray(price_c, dtype='float'), timeperiod=30)
def get_talib_stock_daily(
stock_code,
s,
e,
append_ori_close=False,
norms=['volume', 'amount', 'ht_dcphase', 'obv', 'adosc', 'ad', 'cci']):
"""获取经过talib处理后的股票日线数据"""
stock_data = QA.QA_fetch_stock_day_adv(stock_code, s, e)
stock_df = stock_data.to_qfq().data
if append_ori_close:
stock_df['o_close'] = stock_data.data['close']
# stock_df['high_qfq'] = stock_data.to_qfq().data['high']
# stock_df['low_hfq'] = stock_data.to_hfq().data['low']
close = np.array(stock_df['close'])
high = np.array(stock_df['high'])
low = np.array(stock_df['low'])
_open = np.array(stock_df['open'])
_volume = np.array(stock_df['volume'])
stock_df['dema'] = talib.DEMA(close)
stock_df['ema'] = talib.EMA(close)
stock_df['ht_tradeline'] = talib.HT_TRENDLINE(close)
stock_df['kama'] = talib.KAMA(close)
stock_df['ma'] = talib.MA(close)
stock_df['mama'], stock_df['fama'] = talib.MAMA(close)
# MAVP
stock_df['midpoint'] = talib.MIDPOINT(close)
stock_df['midprice'] = talib.MIDPRICE(high, low)
stock_df['sar'] = talib.SAR(high, low)
stock_df['sarext'] = talib.SAREXT(high, low)
stock_df['sma'] = talib.SMA(close)
stock_df['t3'] = talib.T3(close)
stock_df['tema'] = talib.TEMA(close)
stock_df['trima'] = talib.TRIMA(close)
stock_df['wma'] = talib.WMA(close)
stock_df['adx'] = talib.ADX(high, low, close)
stock_df['adxr'] = talib.ADXR(high, low, close)
stock_df['apo'] = talib.APO(close)
stock_df['aroondown'], stock_df['aroonup'] = talib.AROON(high, low)
stock_df['aroonosc'] = talib.AROONOSC(high, low)
stock_df['bop'] = talib.BOP(_open, high, low, close)
stock_df['cci'] = talib.CCI(high, low, close)
stock_df['cmo'] = talib.CMO(close)
stock_df['dx'] = talib.DX(high, low, close)
# MACD
stock_df['macd'], stock_df['macdsignal'], stock_df[
'macdhist'] = talib.MACDEXT(close)
# MACDFIX
stock_df['mfi'] = talib.MFI(high, low, close, _volume)
stock_df['minus_di'] = talib.MINUS_DI(high, low, close)
stock_df['minus_dm'] = talib.MINUS_DM(high, low)
stock_df['mom'] = talib.MOM(close)
stock_df['plus_di'] = talib.PLUS_DI(high, low, close)
stock_df['plus_dm'] = talib.PLUS_DM(high, low)
stock_df['ppo'] = talib.PPO(close)
stock_df['roc'] = talib.ROC(close)
stock_df['rocp'] = talib.ROCP(close)
stock_df['rocr'] = talib.ROCR(close)
stock_df['rocr100'] = talib.ROCR100(close)
stock_df['rsi'] = talib.RSI(close)
stock_df['slowk'], stock_df['slowd'] = talib.STOCH(high, low, close)
stock_df['fastk'], stock_df['fastd'] = talib.STOCHF(high, low, close)
# STOCHRSI - Stochastic Relative Strength Index
stock_df['trix'] = talib.TRIX(close)
stock_df['ultosc'] = talib.ULTOSC(high, low, close)
stock_df['willr'] = talib.WILLR(high, low, close)
stock_df['ad'] = talib.AD(high, low, close, _volume)
stock_df['adosc'] = talib.ADOSC(high, low, close, _volume)
stock_df['obv'] = talib.OBV(close, _volume)
stock_df['ht_dcperiod'] = talib.HT_DCPERIOD(close)
stock_df['ht_dcphase'] = talib.HT_DCPHASE(close)
stock_df['inphase'], stock_df['quadrature'] = talib.HT_PHASOR(close)
stock_df['sine'], stock_df['leadsine'] = talib.HT_PHASOR(close)
stock_df['ht_trendmode'] = talib.HT_TRENDMODE(close)
stock_df['avgprice'] = talib.AVGPRICE(_open, high, low, close)
stock_df['medprice'] = talib.MEDPRICE(high, low)
stock_df['typprice'] = talib.TYPPRICE(high, low, close)
stock_df['wclprice'] = talib.WCLPRICE(high, low, close)
stock_df['atr'] = talib.ATR(high, low, close)
stock_df['natr'] = talib.NATR(high, low, close)
stock_df['trange'] = talib.TRANGE(high, low, close)
stock_df['beta'] = talib.BETA(high, low)
stock_df['correl'] = talib.CORREL(high, low)
stock_df['linearreg'] = talib.LINEARREG(close)
stock_df['linearreg_angle'] = talib.LINEARREG_ANGLE(close)
stock_df['linearreg_intercept'] = talib.LINEARREG_INTERCEPT(close)
stock_df['linearreg_slope'] = talib.LINEARREG_SLOPE(close)
stock_df['stddev'] = talib.STDDEV(close)
stock_df['tsf'] = talib.TSF(close)
stock_df['var'] = talib.VAR(close)
stock_df = stock_df.reset_index().set_index('date')
if norms:
x = stock_df[norms].values # returns a numpy array
x_scaled = MinMaxScaler().fit_transform(x)
stock_df = stock_df.drop(columns=norms).join(
pd.DataFrame(x_scaled, columns=norms, index=stock_df.index))
# stock_df = stock_df.drop(columns=['code', 'open', 'high', 'low'])
stock_df = stock_df.dropna()
stock_df = stock_df.drop(columns=['code'])
return stock_df
def get_datasets(asset, currency, granularity, datapoints):
"""Fetch the API and precess the desired pair
Arguments:
asset {str} -- First pair
currency {str} -- Second pair
granularity {str ['day', 'hour']} -- Granularity
datapoints {int [100 - 2000]} -- [description]
Returns:
pandas.Dataframe -- The OHLCV and indicators dataframe
"""
df_train_path = 'datasets/bot_train_{}_{}_{}.csv'.format(
asset + currency, datapoints, granularity)
df_rollout_path = 'datasets/bot_rollout_{}_{}_{}.csv'.format(
asset + currency, datapoints, granularity)
emojis = [
':moneybag:', ':yen:', ':dollar:', ':pound:', ':euro:',
':credit_card:', ':money_with_wings:', ':gem:'
]
if not os.path.exists(df_rollout_path):
headers = {
'User-Agent':
'Mozilla/5.0',
'authorization':
'Apikey 3d7d3e9e6006669ac00584978342451c95c3c78421268ff7aeef69995f9a09ce'
}
# OHLC
# url = 'https://min-api.cryptocompare.com/data/histo{}?fsym={}&tsym={}&e=Binance&limit={}'.format(granularity, asset, currency, datapoints)
url = 'https://min-api.cryptocompare.com/data/histo{}?fsym={}&tsym={}&limit={}'.format(
granularity, asset, currency, datapoints)
# print(emoji.emojize(':dizzy: :large_blue_diamond: :gem: :bar_chart: :crystal_ball: :chart_with_downwards_trend: :chart_with_upwards_trend: :large_orange_diamond: loading...', use_aliases=True))
print(
colored(
emoji.emojize('> ' + random.choice(emojis) + ' downloading ' +
asset + '/' + currency,
use_aliases=True), 'green'))
# print(colored('> downloading ' + asset + '/' + currency, 'green'))
response = requests.get(url, headers=headers)
json_response = response.json()
status = json_response['Response']
if status == "Error":
print(colored('=== {} ==='.format(json_response['Message']),
'red'))
raise AssertionError()
result = json_response['Data']
df = pd.DataFrame(result)
print(df.tail())
df['Date'] = pd.to_datetime(df['time'], utc=True, unit='s')
df.drop('time', axis=1, inplace=True)
# indicators
# https://github.com/mrjbq7/ta-lib/blob/master/docs/func.md
open_price, high, low, close = np.array(df['open']), np.array(
df['high']), np.array(df['low']), np.array(df['close'])
volume = np.array(df['volumefrom'])
# cycle indicators
df.loc[:, 'HT_DCPERIOD'] = talib.HT_DCPERIOD(close)
df.loc[:, 'HT_DCPHASE'] = talib.HT_DCPHASE(close)
df.loc[:,
'HT_PHASOR_inphase'], df.loc[:,
'HT_PHASOR_quadrature'] = talib.HT_PHASOR(
close)
df.loc[:, 'HT_SINE_sine'], df.loc[:,
'HT_SINE_leadsine'] = talib.HT_SINE(
close)
df.loc[:, 'HT_TRENDMODE'] = talib.HT_TRENDMODE(close)
# momemtum indicators
df.loc[:, 'ADX'] = talib.ADX(high, low, close, timeperiod=12)
df.loc[:, 'ADXR'] = talib.ADXR(high, low, close, timeperiod=13)
df.loc[:, 'APO'] = talib.APO(close,
fastperiod=5,
slowperiod=10,
matype=0)
df.loc[:,
'AROON_down'], df.loc[:,
'AROON_up'] = talib.AROON(high,
low,
timeperiod=15)
df.loc[:, 'AROONOSC'] = talib.AROONOSC(high, low, timeperiod=13)
df.loc[:, 'BOP'] = talib.BOP(open_price, high, low, close)
df.loc[:, 'CCI'] = talib.CCI(high, low, close, timeperiod=13)
df.loc[:, 'CMO'] = talib.CMO(close, timeperiod=14)
df.loc[:, 'DX'] = talib.DX(high, low, close, timeperiod=10)
df['MACD'], df['MACD_signal'], df['MACD_hist'] = talib.MACD(
close, fastperiod=5, slowperiod=10, signalperiod=20)
df.loc[:, 'MFI'] = talib.MFI(high, low, close, volume, timeperiod=12)
df.loc[:, 'MINUS_DI'] = talib.MINUS_DI(high, low, close, timeperiod=10)
df.loc[:, 'MINUS_DM'] = talib.MINUS_DM(high, low, timeperiod=14)
df.loc[:, 'MOM'] = talib.MOM(close, timeperiod=20)
df.loc[:, 'PPO'] = talib.PPO(close,
fastperiod=17,
slowperiod=35,
matype=2)
df.loc[:, 'ROC'] = talib.ROC(close, timeperiod=12)
df.loc[:, 'RSI'] = talib.RSI(close, timeperiod=25)
df.loc[:, 'STOCH_k'], df.loc[:,
'STOCH_d'] = talib.STOCH(high,
low,
close,
fastk_period=35,
slowk_period=12,
slowk_matype=0,
slowd_period=7,
slowd_matype=0)
df.loc[:,
'STOCHF_k'], df.loc[:,
'STOCHF_d'] = talib.STOCHF(high,
low,
close,
fastk_period=28,
fastd_period=14,
fastd_matype=0)
df.loc[:, 'STOCHRSI_K'], df.loc[:, 'STOCHRSI_D'] = talib.STOCHRSI(
close,
timeperiod=35,
fastk_period=12,
fastd_period=10,
fastd_matype=1)
df.loc[:, 'TRIX'] = talib.TRIX(close, timeperiod=30)
df.loc[:, 'ULTOSC'] = talib.ULTOSC(high,
low,
close,
timeperiod1=14,
timeperiod2=28,
timeperiod3=35)
df.loc[:, 'WILLR'] = talib.WILLR(high, low, close, timeperiod=35)
# overlap studies
df.loc[:,
'BBANDS_upper'], df.loc[:,
'BBANDS_middle'], df.loc[:,
'BBANDS_lower'] = talib.BBANDS(
close,
timeperiod=
12,
nbdevup=2,
nbdevdn=2,
matype=0)
df.loc[:, 'DEMA'] = talib.DEMA(close, timeperiod=30)
df.loc[:, 'EMA'] = talib.EMA(close, timeperiod=7)
df.loc[:, 'HT_TRENDLINE'] = talib.HT_TRENDLINE(close)
df.loc[:, 'KAMA'] = talib.KAMA(close, timeperiod=5)
df.loc[:, 'MA'] = talib.MA(close, timeperiod=5, matype=0)
df.loc[:, 'MIDPOINT'] = talib.MIDPOINT(close, timeperiod=20)
df.loc[:, 'WMA'] = talib.WMA(close, timeperiod=15)
df.loc[:, 'SMA'] = talib.SMA(close)
# pattern recoginition
df.loc[:, 'CDL2CROWS'] = talib.CDL2CROWS(open_price, high, low, close)
df.loc[:, 'CDL3BLACKCROWS'] = talib.CDL3BLACKCROWS(
open_price, high, low, close)
df.loc[:, 'CDL3INSIDE'] = talib.CDL3INSIDE(open_price, high, low,
close)
df.loc[:, 'CDL3LINESTRIKE'] = talib.CDL3LINESTRIKE(
open_price, high, low, close)
# price transform
df.loc[:, 'WCLPRICE'] = talib.WCLPRICE(high, low, close)
# statistic funcitons
df.loc[:, 'BETA'] = talib.BETA(high, low, timeperiod=20)
df.loc[:, 'CORREL'] = talib.CORREL(high, low, timeperiod=20)
df.loc[:, 'STDDEV'] = talib.STDDEV(close, timeperiod=20, nbdev=1)
df.loc[:, 'TSF'] = talib.TSF(close, timeperiod=20)
df.loc[:, 'VAR'] = talib.VAR(close, timeperiod=20, nbdev=1)
# volatility indicators
df.loc[:, 'ATR'] = talib.ATR(high, low, close, timeperiod=7)
df.loc[:, 'NATR'] = talib.NATR(high, low, close, timeperiod=20)
df.loc[:, 'TRANGE'] = talib.TRANGE(high, low, close)
# volume indicators
df.loc[:, 'AD'] = talib.AD(high, low, close, volume)
df.loc[:, 'ADOSC'] = talib.ADOSC(high,
low,
close,
volume,
fastperiod=10,
slowperiod=20)
df.loc[:, 'OBV'] = talib.OBV(close, volume)
# df.fillna(df.mean(), inplace=True)
df.dropna(inplace=True)
df.set_index('Date', inplace=True)
print(colored('> caching' + asset + '/' + currency + ':)', 'cyan'))
train_size = round(
len(df) *
DF_TRAIN_SIZE) # 75% to train -> test with different value
df_train = df[:train_size]
df_rollout = df[train_size:]
df_train.to_csv(df_train_path)
df_rollout.to_csv(df_rollout_path)
df_train = pd.read_csv(
df_train_path) # re-read to avoid indexing issue w/ Ray
df_rollout = pd.read_csv(df_rollout_path)
else:
print(
colored(
emoji.emojize('> ' + random.choice(emojis) + ' feching ' +
asset + '/' + currency + ' from cache',
use_aliases=True), 'magenta'))
# print(colored('> feching ' + asset + '/' + currency + ' from cache :)', 'magenta'))
df_train = pd.read_csv(df_train_path)
df_rollout = pd.read_csv(df_rollout_path)
# df_train.set_index('Date', inplace=True)
# df_rollout.set_index('Date', inplace=True)
return df_train, df_rollout
def main():
ohlcv = api_ohlcv('20191017')
open, high, low, close, volume, timestamp = [], [], [], [], [], []
for i in ohlcv:
open.append(int(i[0]))
high.append(int(i[1]))
low.append(int(i[2]))
close.append(int(i[3]))
volume.append(float(i[4]))
time_str = str(i[5])
timestamp.append(
datetime.fromtimestamp(int(
time_str[:10])).strftime('%Y/%m/%d %H:%M:%M'))
date_time_index = pd.to_datetime(
timestamp) # convert to DateTimeIndex type
df = pd.DataFrame(
{
'open': open,
'high': high,
'low': low,
'close': close,
'volume': volume
},
index=date_time_index)
# df.index += pd.offsets.Hour(9) # adjustment for JST if required
print(df.shape)
print(df.columns)
# pct_change
f = lambda x: 1 if x > 0.0001 else -1 if x < -0.0001 else 0 if -0.0001 <= x <= 0.0001 else np.nan
y = df.rename(columns={
'close': 'y'
}).loc[:, 'y'].pct_change(1).shift(-1).fillna(0)
X = df.copy()
y_ = pd.DataFrame(y.map(f), columns=['y'])
y = df.rename(columns={'close': 'y'}).loc[:, 'y'].pct_change(1).fillna(0)
df_ = pd.concat([X, y_], axis=1)
# check the shape
print(
'----------------------------------------------------------------------------------------'
)
print('X shape: (%i,%i)' % X.shape)
print('y shape: (%i,%i)' % y_.shape)
print(
'----------------------------------------------------------------------------------------'
)
print(y_.groupby('y').size())
print('y=1 up, y=0 stay, y=-1 down')
print(
'----------------------------------------------------------------------------------------'
)
# feature calculation
open = pd.Series(df['open'])
high = pd.Series(df['high'])
low = pd.Series(df['low'])
close = pd.Series(df['close'])
volume = pd.Series(df['volume'])
# pct_change for new column
X['diff'] = y
# Exponential Moving Average
ema = talib.EMA(close, timeperiod=3)
ema = ema.fillna(ema.mean())
# Momentum
momentum = talib.MOM(close, timeperiod=5)
momentum = momentum.fillna(momentum.mean())
# RSI
rsi = talib.RSI(close, timeperiod=14)
rsi = rsi.fillna(rsi.mean())
# ADX
adx = talib.ADX(high, low, close, timeperiod=14)
adx = adx.fillna(adx.mean())
# ADX change
adx_change = adx.pct_change(1).shift(-1)
adx_change = adx_change.fillna(adx_change.mean())
# AD
ad = talib.AD(high, low, close, volume)
ad = ad.fillna(ad.mean())
X_ = pd.concat([X, ema, momentum, rsi, adx_change, ad],
axis=1).drop(['open', 'high', 'low', 'close'], axis=1)
X_.columns = ['volume', 'diff', 'ema', 'momentum', 'rsi', 'adx', 'ad']
X_.join(y_).head(10)
# default parameter models
X_train, X_test, y_train, y_test = train_test_split(X_,
y_,
test_size=0.33,
random_state=42)
print('X_train shape: {}'.format(X_train.shape))
print('X_test shape: {}'.format(X_test.shape))
print('y_train shape: {}'.format(y_train.shape))
print('y_test shape: {}'.format(y_test.shape))
pipe_knn = Pipeline([('scl', StandardScaler()),
('est', KNeighborsClassifier(n_neighbors=3))])
pipe_logistic = Pipeline([('scl', StandardScaler()),
('est',
LogisticRegression(solver='lbfgs',
multi_class='multinomial',
random_state=39))])
pipe_rf = Pipeline([('scl', StandardScaler()),
('est', RandomForestClassifier(random_state=39))])
pipe_gb = Pipeline([('scl', StandardScaler()),
('est', GradientBoostingClassifier(random_state=39))])
pipe_names = ['KNN', 'Logistic', 'RandomForest', 'GradientBoosting']
pipe_lines = [pipe_knn, pipe_logistic, pipe_rf, pipe_gb]
for (i, pipe) in enumerate(pipe_lines):
pipe.fit(X_train, y_train.values.ravel())
print(pipe)
print('%s: %.3f' %
(pipe_names[i] + ' Train Accuracy',
accuracy_score(y_train.values.ravel(), pipe.predict(X_train))))
print('%s: %.3f' %
(pipe_names[i] + ' Test Accuracy',
accuracy_score(y_test.values.ravel(), pipe.predict(X_test))))
print('%s: %.3f' % (pipe_names[i] + ' Train F1 Score',
f1_score(y_train.values.ravel(),
pipe.predict(X_train),
average='micro')))
print('%s: %.3f' % (pipe_names[i] + ' Test F1 Score',
f1_score(y_test.values.ravel(),
pipe.predict(X_test),
average='micro')))
for (i, pipe) in enumerate(pipe_lines):
predict = pipe.predict(X_test)
cm = confusion_matrix(y_test.values.ravel(),
predict,
labels=[-1, 0, 1])
print('{} Confusion Matrix'.format(pipe_names[i]))
print(cm)
## Overlap Studies Functions
# DEMA - Double Exponential Moving Average
dema = talib.DEMA(close, timeperiod=3)
dema = dema.fillna(dema.mean())
print('DEMA - Double Exponential Moving Average shape: {}'.format(
dema.shape))
# EMA - Exponential Moving Average
ema = talib.EMA(close, timeperiod=3)
ema = ema.fillna(ema.mean())
print('EMA - Exponential Moving Average shape: {}'.format(ema.shape))
# HT_TRENDLINE - Hilbert Transform - Instantaneous Trendline
hilbert = talib.HT_TRENDLINE(close)
hilbert = hilbert.fillna(hilbert.mean())
print(
'HT_TRENDLINE - Hilbert Transform - Instantaneous Trendline shape: {}'.
format(hilbert.shape))
# KAMA - Kaufman Adaptive Moving Average
kama = talib.KAMA(close, timeperiod=3)
kama = kama.fillna(kama.mean())
print('KAMA - Kaufman Adaptive Moving Average shape: {}'.format(
kama.shape))
# MA - Moving average
ma = talib.MA(close, timeperiod=3, matype=0)
ma = ma.fillna(ma.mean())
print('MA - Moving average shape: {}'.format(kama.shape))
# MIDPOINT - MidPoint over period
midpoint = talib.MIDPOINT(close, timeperiod=7)
midpoint = midpoint.fillna(midpoint.mean())
print('MIDPOINT - MidPoint over period shape: {}'.format(midpoint.shape))
# MIDPRICE - Midpoint Price over period
midprice = talib.MIDPRICE(high, low, timeperiod=7)
midprice = midprice.fillna(midprice.mean())
print('MIDPRICE - Midpoint Price over period shape: {}'.format(
midprice.shape))
# SAR - Parabolic SAR
sar = talib.SAR(high, low, acceleration=0, maximum=0)
sar = sar.fillna(sar.mean())
print('SAR - Parabolic SAR shape: {}'.format(sar.shape))
# SAREXT - Parabolic SAR - Extended
sarext = talib.SAREXT(high,
low,
startvalue=0,
offsetonreverse=0,
accelerationinitlong=0,
accelerationlong=0,
accelerationmaxlong=0,
accelerationinitshort=0,
accelerationshort=0,
accelerationmaxshort=0)
sarext = sarext.fillna(sarext.mean())
print('SAREXT - Parabolic SAR - Extended shape: {}'.format(sarext.shape))
# SMA - Simple Moving Average
sma = talib.SMA(close, timeperiod=3)
sma = sma.fillna(sma.mean())
print('SMA - Simple Moving Average shape: {}'.format(sma.shape))
# T3 - Triple Exponential Moving Average (T3)
t3 = talib.T3(close, timeperiod=5, vfactor=0)
t3 = t3.fillna(t3.mean())
print('T3 - Triple Exponential Moving Average shape: {}'.format(t3.shape))
# TEMA - Triple Exponential Moving Average
tema = talib.TEMA(close, timeperiod=3)
tema = tema.fillna(tema.mean())
print('TEMA - Triple Exponential Moving Average shape: {}'.format(
tema.shape))
# TRIMA - Triangular Moving Average
trima = talib.TRIMA(close, timeperiod=3)
trima = trima.fillna(trima.mean())
print('TRIMA - Triangular Moving Average shape: {}'.format(trima.shape))
# WMA - Weighted Moving Average
wma = talib.WMA(close, timeperiod=3)
wma = wma.fillna(wma.mean())
print('WMA - Weighted Moving Average shape: {}'.format(wma.shape))
## Momentum Indicator Functions
# ADX - Average Directional Movement Index
adx = talib.ADX(high, low, close, timeperiod=14)
adx = adx.fillna(adx.mean())
print('ADX - Average Directional Movement Index shape: {}'.format(
adx.shape))
# ADXR - Average Directional Movement Index Rating
adxr = talib.ADXR(high, low, close, timeperiod=7)
adxr = adxr.fillna(adxr.mean())
print('ADXR - Average Directional Movement Index Rating shape: {}'.format(
adxr.shape))
# APO - Absolute Price Oscillator
apo = talib.APO(close, fastperiod=12, slowperiod=26, matype=0)
apo = apo.fillna(apo.mean())
print('APO - Absolute Price Oscillator shape: {}'.format(apo.shape))
# AROONOSC - Aroon Oscillator
aroon = talib.AROONOSC(high, low, timeperiod=14)
aroon = aroon.fillna(aroon.mean())
print('AROONOSC - Aroon Oscillator shape: {}'.format(apo.shape))
# BOP - Balance Of Power
bop = talib.BOP(open, high, low, close)
bop = bop.fillna(bop.mean())
print('BOP - Balance Of Power shape: {}'.format(apo.shape))
# CCI - Commodity Channel Index
cci = talib.CCI(high, low, close, timeperiod=7)
cci = cci.fillna(cci.mean())
print('CCI - Commodity Channel Index shape: {}'.format(cci.shape))
# CMO - Chande Momentum Oscillator
cmo = talib.CMO(close, timeperiod=7)
cmo = cmo.fillna(cmo.mean())
print('CMO - Chande Momentum Oscillator shape: {}'.format(cmo.shape))
# DX - Directional Movement Index
dx = talib.DX(high, low, close, timeperiod=7)
dx = dx.fillna(dx.mean())
print('DX - Directional Movement Index shape: {}'.format(dx.shape))
# MFI - Money Flow Index
mfi = talib.MFI(high, low, close, volume, timeperiod=7)
mfi = mfi.fillna(mfi.mean())
print('MFI - Money Flow Index shape: {}'.format(mfi.shape))
# MINUS_DI - Minus Directional Indicator
minusdi = talib.MINUS_DI(high, low, close, timeperiod=14)
minusdi = minusdi.fillna(minusdi.mean())
print('MINUS_DI - Minus Directional Indicator shape: {}'.format(
minusdi.shape))
# MINUS_DM - Minus Directional Movement
minusdm = talib.MINUS_DM(high, low, timeperiod=14)
minusdm = minusdm.fillna(minusdm.mean())
print('MINUS_DM - Minus Directional Movement shape: {}'.format(
minusdm.shape))
# MOM - Momentum
mom = talib.MOM(close, timeperiod=5)
mom = mom.fillna(mom.mean())
print('MOM - Momentum shape: {}'.format(mom.shape))
# PLUS_DI - Plus Directional Indicator
plusdi = talib.PLUS_DI(high, low, close, timeperiod=14)
plusdi = plusdi.fillna(plusdi.mean())
print('PLUS_DI - Plus Directional Indicator shape: {}'.format(
plusdi.shape))
# PLUS_DM - Plus Directional Movement
plusdm = talib.PLUS_DM(high, low, timeperiod=14)
plusdm = plusdm.fillna(plusdm.mean())
print('PLUS_DM - Plus Directional Movement shape: {}'.format(plusdi.shape))
# PPO - Percentage Price Oscillator
ppo = talib.PPO(close, fastperiod=12, slowperiod=26, matype=0)
ppo = ppo.fillna(ppo.mean())
print('PPO - Percentage Price Oscillator shape: {}'.format(ppo.shape))
# ROC - Rate of change:((price/prevPrice)-1)*100
roc = talib.ROC(close, timeperiod=10)
roc = roc.fillna(roc.mean())
print('ROC - Rate of change : ((price/prevPrice)-1)*100 shape: {}'.format(
roc.shape))
# RSI - Relative Strength Index
rsi = talib.RSI(close, timeperiod=14)
rsi = rsi.fillna(rsi.mean())
print('RSI - Relative Strength Index shape: {}'.format(rsi.shape))
# TRIX - 1-day Rate-Of-Change (ROC) of a Triple Smooth EMA
trix = talib.TRIX(close, timeperiod=30)
trix = trix.fillna(trix.mean())
print('TRIX - 1-day Rate-Of-Change (ROC) of a Triple Smooth EMA shape: {}'.
format(trix.shape))
# ULTOSC - Ultimate Oscillator
ultosc = talib.ULTOSC(high,
low,
close,
timeperiod1=7,
timeperiod2=14,
timeperiod3=28)
ultosc = ultosc.fillna(ultosc.mean())
print('ULTOSC - Ultimate Oscillator shape: {}'.format(ultosc.shape))
# WILLR - Williams'%R
willr = talib.WILLR(high, low, close, timeperiod=7)
willr = willr.fillna(willr.mean())
print("WILLR - Williams'%R shape: {}".format(willr.shape))
## Volume Indicator Functions
# AD - Chaikin A/D Line
ad = talib.AD(high, low, close, volume)
ad = ad.fillna(ad.mean())
print('AD - Chaikin A/D Line shape: {}'.format(ad.shape))
# ADOSC - Chaikin A/D Oscillator
adosc = talib.ADOSC(high, low, close, volume, fastperiod=3, slowperiod=10)
adosc = adosc.fillna(adosc.mean())
print('ADOSC - Chaikin A/D Oscillator shape: {}'.format(adosc.shape))
# OBV - On Balance Volume
obv = talib.OBV(close, volume)
obv = obv.fillna(obv.mean())
print('OBV - On Balance Volume shape: {}'.format(obv.shape))
## Volatility Indicator Functions
# ATR - Average True Range
atr = talib.ATR(high, low, close, timeperiod=7)
atr = atr.fillna(atr.mean())
print('ATR - Average True Range shape: {}'.format(atr.shape))
# NATR - Normalized Average True Range
natr = talib.NATR(high, low, close, timeperiod=7)
natr = natr.fillna(natr.mean())
print('NATR - Normalized Average True Range shape: {}'.format(natr.shape))
# TRANGE - True Range
trange = talib.TRANGE(high, low, close)
trange = trange.fillna(trange.mean())
print('TRANGE - True Range shape: {}'.format(natr.shape))
## Price Transform Functions
# AVGPRICE - Average Price
avg = talib.AVGPRICE(open, high, low, close)
avg = avg.fillna(avg.mean())
print('AVGPRICE - Average Price shape: {}'.format(natr.shape))
# MEDPRICE - Median Price
medprice = talib.MEDPRICE(high, low)
medprice = medprice.fillna(medprice.mean())
print('MEDPRICE - Median Price shape: {}'.format(medprice.shape))
# TYPPRICE - Typical Price
typ = talib.TYPPRICE(high, low, close)
typ = typ.fillna(typ.mean())
print('TYPPRICE - Typical Price shape: {}'.format(typ.shape))
# WCLPRICE - Weighted Close Price
wcl = talib.WCLPRICE(high, low, close)
wcl = wcl.fillna(wcl.mean())
print('WCLPRICE - Weighted Close Price shape: {}'.format(wcl.shape))
## Cycle Indicator Functions
# HT_DCPERIOD - Hilbert Transform - Dominant Cycle Period
dcperiod = talib.HT_DCPERIOD(close)
dcperiod = dcperiod.fillna(dcperiod.mean())
print('HT_DCPERIOD - Hilbert Transform - Dominant Cycle Period shape: {}'.
format(dcperiod.shape))
# HT_DCPHASE - Hilbert Transform - Dominant Cycle Phase
dcphase = talib.HT_DCPHASE(close)
dcphase = dcphase.fillna(dcphase.mean())
print('HT_DCPHASE - Hilbert Transform - Dominant Cycle Phase shape: {}'.
format(dcperiod.shape))
## Statistic Functions
# BETA - Beta
beta = talib.BETA(high, low, timeperiod=3)
beta = beta.fillna(beta.mean())
print('BETA - Beta shape: {}'.format(beta.shape))
# CORREL - Pearson's Correlation Coefficient(r)
correl = talib.CORREL(high, low, timeperiod=30)
correl = correl.fillna(correl.mean())
print("CORREL - Pearson's Correlation Coefficient(r) shape: {}".format(
beta.shape))
# LINEARREG - Linear Regression
linreg = talib.LINEARREG(close, timeperiod=7)
linreg = linreg.fillna(linreg.mean())
print("LINEARREG - Linear Regression shape: {}".format(linreg.shape))
# STDDEV - Standard Deviation
stddev = talib.STDDEV(close, timeperiod=5, nbdev=1)
stddev = stddev.fillna(stddev.mean())
print("STDDEV - Standard Deviation shape: {}".format(stddev.shape))
# TSF - Time Series Forecast
tsf = talib.TSF(close, timeperiod=7)
tsf = tsf.fillna(tsf.mean())
print("TSF - Time Series Forecast shape: {}".format(tsf.shape))
# VAR - Variance
var = talib.VAR(close, timeperiod=5, nbdev=1)
var = var.fillna(var.mean())
print("VAR - Variance shape: {}".format(var.shape))
## Feature DataFrame
X_full = pd.concat([
X, dema, ema, hilbert, kama, ma, midpoint, midprice, sar, sarext, sma,
t3, tema, trima, wma, adx, adxr, apo, aroon, bop, cci, cmo, mfi,
minusdi, minusdm, mom, plusdi, plusdm, ppo, roc, rsi, trix, ultosc,
willr, ad, adosc, obv, atr, natr, trange, avg, medprice, typ, wcl,
dcperiod, dcphase, beta, correl, linreg, stddev, tsf, var
],
axis=1).drop(['open', 'high', 'low', 'close'], axis=1)
X_full.columns = [
'volume', 'diff', 'dema', 'ema', 'hilbert', 'kama', 'ma', 'midpoint',
'midprice', 'sar', 'sarext', 'sma', 't3', 'tema', 'trima', 'wma',
'adx', 'adxr', 'apo', 'aroon', 'bop', 'cci', 'cmo', 'mfi', 'minusdi',
'minusdm', 'mom', 'plusdi', 'plusdm', 'ppo', 'roc', 'rsi', 'trix',
'ultosc', 'willr', 'ad', 'adosc', 'obv', 'atr', 'natr', 'trange',
'avg', 'medprice', 'typ', 'wcl', 'dcperiod', 'dcphase', 'beta',
'correl', 'linreg', 'stddev', 'tsf', 'var'
]
X_full.join(y_).head(10)
# full feature models
X_train_full, X_test_full, y_train_full, y_test_full = train_test_split(
X_full, y_, test_size=0.33, random_state=42)
print('X_train shape: {}'.format(X_train_full.shape))
print('X_test shape: {}'.format(X_test_full.shape))
print('y_train shape: {}'.format(y_train_full.shape))
print('y_test shape: {}'.format(y_test_full.shape))
pipe_knn_full = Pipeline([('scl', StandardScaler()),
('est', KNeighborsClassifier(n_neighbors=3))])
pipe_logistic_full = Pipeline([
('scl', StandardScaler()),
('est',
LogisticRegression(solver='lbfgs',
multi_class='multinomial',
random_state=39))
])
pipe_rf_full = Pipeline([('scl', StandardScaler()),
('est', RandomForestClassifier(random_state=39))])
pipe_gb_full = Pipeline([('scl', StandardScaler()),
('est',
GradientBoostingClassifier(random_state=39))])
pipe_names = ['KNN', 'Logistic', 'RandomForest', 'GradientBoosting']
pipe_lines_full = [
pipe_knn_full, pipe_logistic_full, pipe_rf_full, pipe_gb_full
]
for (i, pipe) in enumerate(pipe_lines_full):
pipe.fit(X_train_full, y_train_full.values.ravel())
print(pipe)
print('%s: %.3f' % (pipe_names[i] + ' Train Accuracy',
accuracy_score(y_train_full.values.ravel(),
pipe.predict(X_train_full))))
print('%s: %.3f' % (pipe_names[i] + ' Test Accuracy',
accuracy_score(y_test_full.values.ravel(),
pipe.predict(X_test_full))))
print('%s: %.3f' % (pipe_names[i] + ' Train F1 Score',
f1_score(y_train_full.values.ravel(),
pipe.predict(X_train_full),
average='micro')))
print('%s: %.3f' % (pipe_names[i] + ' Test F1 Score',
f1_score(y_test_full.values.ravel(),
pipe.predict(X_test_full),
average='micro')))
# Univariate Statistics
select = SelectPercentile(percentile=25)
select.fit(X_train_full, y_train_full.values.ravel())
X_train_selected = select.transform(X_train_full)
X_test_selected = select.transform(X_test_full)
# GradientBoost Classifier
print(
'--------------------------Without Univariate Statistics-------------------------------------'
)
pipe_gb = Pipeline([('scl', StandardScaler()),
('est', GradientBoostingClassifier(random_state=39))])
pipe_gb.fit(X_train_full, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full),
average='micro')))
# GradientBoost Cllassifier with Univariate Statistics
print(
'---------------------------With Univariate Statistics--------------------------------------'
)
pipe_gb_percentile = Pipeline([
('scl', StandardScaler()),
('est', GradientBoostingClassifier(random_state=39))
])
pipe_gb_percentile.fit(X_train_selected, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb_percentile.predict(X_train_selected))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb_percentile.predict(X_test_selected))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb_percentile.predict(X_train_selected),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb_percentile.predict(X_test_selected),
average='micro')))
# Model-based Selection
select = SelectFromModel(RandomForestClassifier(n_estimators=100,
random_state=42),
threshold="1.25*mean")
select.fit(X_train_full, y_train_full.values.ravel())
X_train_model = select.transform(X_train_full)
X_test_model = select.transform(X_test_full)
# GradientBoost Classifier
print(
'--------------------------Without Model-based Selection--------------------------------------'
)
pipe_gb = Pipeline([('scl', StandardScaler()),
('est', GradientBoostingClassifier(random_state=39))])
pipe_gb.fit(X_train_full, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full),
average='micro')))
# GradientBoost Classifier with Model-based Selection
print(
'----------------------------With Model-based Selection--------------------------------------'
)
pipe_gb_model = Pipeline([('scl', StandardScaler()),
('est',
GradientBoostingClassifier(random_state=39))])
pipe_gb_model.fit(X_train_model, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb_model.predict(X_train_model))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb_model.predict(X_test_model))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb_model.predict(X_train_model),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb_model.predict(X_test_model),
average='micro')))
# Recursive Feature Elimination
select = RFE(RandomForestClassifier(n_estimators=100, random_state=42),
n_features_to_select=15)
select.fit(X_train_full, y_train_full.values.ravel())
X_train_rfe = select.transform(X_train_full)
X_test_rfe = select.transform(X_test_full)
# GradientBoost Classifier
print(
'--------------------------Without Recursive Feature Elimination-------------------------------------'
)
pipe_gb = Pipeline([('scl', StandardScaler()),
('est', GradientBoostingClassifier(random_state=39))])
pipe_gb.fit(X_train_full, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb.predict(X_train_full),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb.predict(X_test_full),
average='micro')))
# GradientBoost Classifier with Recursive Feature Elimination
print(
'----------------------------With Recursive Feature Elimination--------------------------------------'
)
pipe_gb_rfe = Pipeline([('scl', StandardScaler()),
('est',
GradientBoostingClassifier(random_state=39))])
pipe_gb_rfe.fit(X_train_rfe, y_train_full.values.ravel())
print('Train Accuracy: {:.3f}'.format(
accuracy_score(y_train_full.values.ravel(),
pipe_gb_rfe.predict(X_train_rfe))))
print('Test Accuracy: {:.3f}'.format(
accuracy_score(y_test_full.values.ravel(),
pipe_gb_rfe.predict(X_test_rfe))))
print('Train F1 Score: {:.3f}'.format(
f1_score(y_train_full.values.ravel(),
pipe_gb_rfe.predict(X_train_rfe),
average='micro')))
print('Test F1 Score: {:.3f}'.format(
f1_score(y_test_full.values.ravel(),
pipe_gb_rfe.predict(X_test_rfe),
average='micro')))
cv = cross_val_score(pipe_gb,
X_,
y_.values.ravel(),
cv=StratifiedKFold(n_splits=10,
shuffle=True,
random_state=39))
print('Cross validation with StratifiedKFold scores: {}'.format(cv))
print('Cross Validation with StatifiedKFold mean: {}'.format(cv.mean()))
# GridSearch
n_features = len(df.columns)
param_grid = {
'learning_rate': [0.01, 0.1, 1, 10],
'n_estimators': [1, 10, 100, 200, 300],
'max_depth': [1, 2, 3, 4, 5]
}
stratifiedcv = StratifiedKFold(n_splits=10, shuffle=True, random_state=39)
X_train, X_test, y_train, y_test = train_test_split(X_,
y_,
test_size=0.33,
random_state=42)
grid_search = GridSearchCV(GradientBoostingClassifier(),
param_grid,
cv=stratifiedcv)
grid_search.fit(X_train, y_train.values.ravel())
print('GridSearch Train Accuracy: {:.3f}'.format(
accuracy_score(y_train.values.ravel(), grid_search.predict(X_train))))
print('GridSearch Test Accuracy: {:.3f}'.format(
accuracy_score(y_test.values.ravel(), grid_search.predict(X_test))))
print('GridSearch Train F1 Score: {:.3f}'.format(
f1_score(y_train.values.ravel(),
grid_search.predict(X_train),
average='micro')))
print('GridSearch Test F1 Score: {:.3f}'.format(
f1_score(y_test.values.ravel(),
grid_search.predict(X_test),
average='micro')))
# GridSearch results
print("Best params:\n{}".format(grid_search.best_params_))
print("Best cross-validation score: {:.2f}".format(
grid_search.best_score_))
results = pd.DataFrame(grid_search.cv_results_)
corr_params = results.drop(results.columns[[
0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 20
]],
axis=1)
corr_params.head()
# GridSearch in nested
cv_gb = cross_val_score(grid_search,
X_,
y_.values.ravel(),
cv=StratifiedKFold(n_splits=3,
shuffle=True,
random_state=39))
print('Grid Search with nested cross validation scores: {}'.format(cv_gb))
print('Grid Search with nested cross validation mean: {}'.format(
cv_gb.mean()))
def TALIB_TSF(close, timeperiod=14):
'''00391,2,1'''
return talib.TSF(close, timeperiod)
def add_ta_features(df, ta_settings):
"""Add technial analysis features from typical financial dataset that
typically include columns such as "open", "high", "low", "price" and
"volume".
http://mrjbq7.github.io/ta-lib/
Args:
df(pandas.DataFrame): original DataFrame.
ta_settings(dict): configuration.
Returns:
pandas.DataFrame: DataFrame with new features included.
"""
open = df['open']
high = df['high']
low = df['low']
close = df['price']
volume = df['volume']
if ta_settings['overlap']:
df['ta_overlap_bbands_upper'], df['ta_overlap_bbands_middle'], df[
'ta_overlap_bbands_lower'] = ta.BBANDS(close,
timeperiod=5,
nbdevup=2,
nbdevdn=2,
matype=0)
df['ta_overlap_dema'] = ta.DEMA(
close, timeperiod=15) # NOTE: Changed to avoid a lot of Nan values
df['ta_overlap_ema'] = ta.EMA(close, timeperiod=30)
df['ta_overlap_kama'] = ta.KAMA(close, timeperiod=30)
df['ta_overlap_ma'] = ta.MA(close, timeperiod=30, matype=0)
df['ta_overlap_mama_mama'], df['ta_overlap_mama_fama'] = ta.MAMA(close)
period = np.random.randint(10, 20, size=len(close)).astype(float)
df['ta_overlap_mavp'] = ta.MAVP(close,
period,
minperiod=2,
maxperiod=30,
matype=0)
df['ta_overlap_midpoint'] = ta.MIDPOINT(close, timeperiod=14)
df['ta_overlap_midprice'] = ta.MIDPRICE(high, low, timeperiod=14)
df['ta_overlap_sar'] = ta.SAR(high, low, acceleration=0, maximum=0)
df['ta_overlap_sarext'] = ta.SAREXT(high,
low,
startvalue=0,
offsetonreverse=0,
accelerationinitlong=0,
accelerationlong=0,
accelerationmaxlong=0,
accelerationinitshort=0,
accelerationshort=0,
accelerationmaxshort=0)
df['ta_overlap_sma'] = ta.SMA(close, timeperiod=30)
df['ta_overlap_t3'] = ta.T3(close, timeperiod=5, vfactor=0)
df['ta_overlap_tema'] = ta.TEMA(
close, timeperiod=12) # NOTE: Changed to avoid a lot of Nan values
df['ta_overlap_trima'] = ta.TRIMA(close, timeperiod=30)
df['ta_overlap_wma'] = ta.WMA(close, timeperiod=30)
# NOTE: Commented to avoid a lot of Nan values
# df['ta_overlap_ht_trendline'] = ta.HT_TRENDLINE(close)
if ta_settings['momentum']:
df['ta_momentum_adx'] = ta.ADX(high, low, close, timeperiod=14)
df['ta_momentum_adxr'] = ta.ADXR(high, low, close, timeperiod=14)
df['ta_momentum_apo'] = ta.APO(close,
fastperiod=12,
slowperiod=26,
matype=0)
df['ta_momentum_aroondown'], df['ta_momentum_aroonup'] = ta.AROON(
high, low, timeperiod=14)
df['ta_momentum_aroonosc'] = ta.AROONOSC(high, low, timeperiod=14)
df['ta_momentum_bop'] = ta.BOP(open, high, low, close)
df['ta_momentum_cci'] = ta.CCI(high, low, close, timeperiod=14)
df['ta_momentum_cmo'] = ta.CMO(close, timeperiod=14)
df['ta_momentum_dx'] = ta.DX(high, low, close, timeperiod=14)
df['ta_momentum_macd_macd'], df['ta_momentum_macd_signal'], df[
'ta_momentum_macd_hist'] = ta.MACD(close,
fastperiod=12,
slowperiod=26,
signalperiod=9)
df['ta_momentum_macdext_macd'], df['ta_momentum_macdext_signal'], df[
'ta_momentum_macdext_hist'] = ta.MACDEXT(close,
fastperiod=12,
fastmatype=0,
slowperiod=26,
slowmatype=0,
signalperiod=9,
signalmatype=0)
df['ta_momentum_macdfix_macd'], df['ta_momentum_macdfix_signal'], df[
'ta_momentum_macdfix_hist'] = ta.MACDFIX(close, signalperiod=9)
df['ta_momentum_mfi'] = ta.MFI(high, low, close, volume, timeperiod=14)
df['ta_momentum_minus_di'] = ta.MINUS_DI(high,
low,
close,
timeperiod=14)
df['ta_momentum_minus_dm'] = ta.MINUS_DM(high, low, timeperiod=14)
df['ta_momentum_mom'] = ta.MOM(close, timeperiod=10)
df['ta_momentum_plus_di'] = ta.PLUS_DI(high, low, close, timeperiod=14)
df['ta_momentum_plus_dm'] = ta.PLUS_DM(high, low, timeperiod=14)
df['ta_momentum_ppo'] = ta.PPO(close,
fastperiod=12,
slowperiod=26,
matype=0)
df['ta_momentum_roc'] = ta.ROC(close, timeperiod=10)
df['ta_momentum_rocp'] = ta.ROCP(close, timeperiod=10)
df['ta_momentum_rocr'] = ta.ROCR(close, timeperiod=10)
df['ta_momentum_rocr100'] = ta.ROCR100(close, timeperiod=10)
df['ta_momentum_rsi'] = ta.RSI(close, timeperiod=14)
df['ta_momentum_slowk'], df['ta_momentum_slowd'] = ta.STOCH(
high,
low,
close,
fastk_period=5,
slowk_period=3,
slowk_matype=0,
slowd_period=3,
slowd_matype=0)
df['ta_momentum_fastk'], df['ta_momentum_fastd'] = ta.STOCHF(
high, low, close, fastk_period=5, fastd_period=3, fastd_matype=0)
df['ta_momentum_fastk'], df['ta_momentum_fastd'] = ta.STOCHRSI(
close,
timeperiod=14,
fastk_period=5,
fastd_period=3,
fastd_matype=0)
df['ta_momentum_trix'] = ta.TRIX(
close, timeperiod=12) # NOTE: Changed to avoid a lot of Nan values
df['ta_momentum_ultosc'] = ta.ULTOSC(high,
low,
close,
timeperiod1=7,
timeperiod2=14,
timeperiod3=28)
df['ta_momentum_willr'] = ta.WILLR(high, low, close, timeperiod=14)
if ta_settings['volume']:
df['ta_volume_ad'] = ta.AD(high, low, close, volume)
df['ta_volume_adosc'] = ta.ADOSC(high,
low,
close,
volume,
fastperiod=3,
slowperiod=10)
df['ta_volume_obv'] = ta.OBV(close, volume)
if ta_settings['volatility']:
df['ta_volatility_atr'] = ta.ATR(high, low, close, timeperiod=14)
df['ta_volatility_natr'] = ta.NATR(high, low, close, timeperiod=14)
df['ta_volatility_trange'] = ta.TRANGE(high, low, close)
if ta_settings['price']:
df['ta_price_avgprice'] = ta.AVGPRICE(open, high, low, close)
df['ta_price_medprice'] = ta.MEDPRICE(high, low)
df['ta_price_typprice'] = ta.TYPPRICE(high, low, close)
df['ta_price_wclprice'] = ta.WCLPRICE(high, low, close)
if ta_settings['cycle']:
df['ta_cycle_ht_dcperiod'] = ta.HT_DCPERIOD(close)
df['ta_cycle_ht_phasor_inphase'], df[
'ta_cycle_ht_phasor_quadrature'] = ta.HT_PHASOR(close)
df['ta_cycle_ht_trendmode'] = ta.HT_TRENDMODE(close)
# NOTE: Commented to avoid a lot of Nan values
# df['ta_cycle_ht_dcphase'] = ta.HT_DCPHASE(close)
# df['ta_cycle_ht_sine_sine'], df['ta_cycle_ht_sine_leadsine'] = ta.HT_SINE(close)
if ta_settings['pattern']:
df['ta_pattern_cdl2crows'] = ta.CDL2CROWS(open, high, low, close)
df['ta_pattern_cdl3blackrows'] = ta.CDL3BLACKCROWS(
open, high, low, close)
df['ta_pattern_cdl3inside'] = ta.CDL3INSIDE(open, high, low, close)
df['ta_pattern_cdl3linestrike'] = ta.CDL3LINESTRIKE(
open, high, low, close)
df['ta_pattern_cdl3outside'] = ta.CDL3OUTSIDE(open, high, low, close)
df['ta_pattern_cdl3starsinsouth'] = ta.CDL3STARSINSOUTH(
open, high, low, close)
df['ta_pattern_cdl3whitesoldiers'] = ta.CDL3WHITESOLDIERS(
open, high, low, close)
df['ta_pattern_cdlabandonedbaby'] = ta.CDLABANDONEDBABY(open,
high,
low,
close,
penetration=0)
df['ta_pattern_cdladvanceblock'] = ta.CDLADVANCEBLOCK(
open, high, low, close)
df['ta_pattern_cdlbelthold'] = ta.CDLBELTHOLD(open, high, low, close)
df['ta_pattern_cdlbreakaway'] = ta.CDLBREAKAWAY(open, high, low, close)
df['ta_pattern_cdlclosingmarubozu'] = ta.CDLCLOSINGMARUBOZU(
open, high, low, close)
df['ta_pattern_cdlconcealbabyswall'] = ta.CDLCONCEALBABYSWALL(
open, high, low, close)
df['ta_pattern_cdlcounterattack'] = ta.CDLCOUNTERATTACK(
open, high, low, close)
df['ta_pattern_cdldarkcloudcover'] = ta.CDLDARKCLOUDCOVER(
open, high, low, close, penetration=0)
df['ta_pattern_cdldoji'] = ta.CDLDOJI(open, high, low, close)
df['ta_pattern_cdldojistar'] = ta.CDLDOJISTAR(open, high, low, close)
df['ta_pattern_cdldragonflydoji'] = ta.CDLDRAGONFLYDOJI(
open, high, low, close)
df['ta_pattern_cdlengulfing'] = ta.CDLENGULFING(open, high, low, close)
df['ta_pattern_cdleveningdojistar'] = ta.CDLEVENINGDOJISTAR(
open, high, low, close, penetration=0)
df['ta_pattern_cdleveningstar'] = ta.CDLEVENINGSTAR(open,
high,
low,
close,
penetration=0)
df['ta_pattern_cdlgapsidesidewhite'] = ta.CDLGAPSIDESIDEWHITE(
open, high, low, close)
df['ta_pattern_cdlgravestonedoji'] = ta.CDLGRAVESTONEDOJI(
open, high, low, close)
df['ta_pattern_cdlhammer'] = ta.CDLHAMMER(open, high, low, close)
df['ta_pattern_cdlhangingman'] = ta.CDLHANGINGMAN(
open, high, low, close)
df['ta_pattern_cdlharami'] = ta.CDLHARAMI(open, high, low, close)
df['ta_pattern_cdlharamicross'] = ta.CDLHARAMICROSS(
open, high, low, close)
df['ta_pattern_cdlhighwave'] = ta.CDLHIGHWAVE(open, high, low, close)
df['ta_pattern_cdlhikkake'] = ta.CDLHIKKAKE(open, high, low, close)
df['ta_pattern_cdlhikkakemod'] = ta.CDLHIKKAKEMOD(
open, high, low, close)
df['ta_pattern_cdlhomingpigeon'] = ta.CDLHOMINGPIGEON(
open, high, low, close)
df['ta_pattern_cdlidentical3crows'] = ta.CDLIDENTICAL3CROWS(
open, high, low, close)
df['ta_pattern_cdlinneck'] = ta.CDLINNECK(open, high, low, close)
df['ta_pattern_cdlinvertedhammer'] = ta.CDLINVERTEDHAMMER(
open, high, low, close)
df['ta_pattern_cdlkicking'] = ta.CDLKICKING(open, high, low, close)
df['ta_pattern_cdlkickingbylength'] = ta.CDLKICKINGBYLENGTH(
open, high, low, close)
df['ta_pattern_cdlladderbottom'] = ta.CDLLADDERBOTTOM(
open, high, low, close)
df['ta_pattern_cdllongleggeddoji'] = ta.CDLLONGLEGGEDDOJI(
open, high, low, close)
df['ta_pattern_cdllongline'] = ta.CDLLONGLINE(open, high, low, close)
df['ta_pattern_cdlmarubozu'] = ta.CDLMARUBOZU(open, high, low, close)
df['ta_pattern_cdlmatchinglow'] = ta.CDLMATCHINGLOW(
open, high, low, close)
df['ta_pattern_cdlmathold'] = ta.CDLMATHOLD(open,
high,
low,
close,
penetration=0)
df['ta_pattern_cdlmorningdojistar'] = ta.CDLMORNINGDOJISTAR(
open, high, low, close, penetration=0)
df['ta_pattern_cdlmorningstar'] = ta.CDLMORNINGSTAR(open,
high,
low,
close,
penetration=0)
df['ta_pattern_cdllonneck'] = ta.CDLONNECK(open, high, low, close)
df['ta_pattern_cdlpiercing'] = ta.CDLPIERCING(open, high, low, close)
df['ta_pattern_cdlrickshawman'] = ta.CDLRICKSHAWMAN(
open, high, low, close)
df['ta_pattern_cdlrisefall3methods'] = ta.CDLRISEFALL3METHODS(
open, high, low, close)
df['ta_pattern_cdlseparatinglines'] = ta.CDLSEPARATINGLINES(
open, high, low, close)
df['ta_pattern_cdlshootingstar'] = ta.CDLSHOOTINGSTAR(
open, high, low, close)
df['ta_pattern_cdlshortline'] = ta.CDLSHORTLINE(open, high, low, close)
df['ta_pattern_cdlspinningtop'] = ta.CDLSPINNINGTOP(
open, high, low, close)
df['ta_pattern_cdlstalledpattern'] = ta.CDLSTALLEDPATTERN(
open, high, low, close)
df['ta_pattern_cdlsticksandwich'] = ta.CDLSTICKSANDWICH(
open, high, low, close)
df['ta_pattern_cdltakuri'] = ta.CDLTAKURI(open, high, low, close)
df['ta_pattern_cdltasukigap'] = ta.CDLTASUKIGAP(open, high, low, close)
df['ta_pattern_cdlthrusting'] = ta.CDLTHRUSTING(open, high, low, close)
df['ta_pattern_cdltristar'] = ta.CDLTRISTAR(open, high, low, close)
df['ta_pattern_cdlunique3river'] = ta.CDLUNIQUE3RIVER(
open, high, low, close)
df['ta_pattern_cdlupsidegap2crows'] = ta.CDLUPSIDEGAP2CROWS(
open, high, low, close)
df['ta_pattern_cdlxsidegap3methods'] = ta.CDLXSIDEGAP3METHODS(
open, high, low, close)
if ta_settings['statistic']:
df['ta_statistic_beta'] = ta.BETA(high, low, timeperiod=5)
df['ta_statistic_correl'] = ta.CORREL(high, low, timeperiod=30)
df['ta_statistic_linearreg'] = ta.LINEARREG(close, timeperiod=14)
df['ta_statistic_linearreg_angle'] = ta.LINEARREG_ANGLE(close,
timeperiod=14)
df['ta_statistic_linearreg_intercept'] = ta.LINEARREG_INTERCEPT(
close, timeperiod=14)
df['ta_statistic_linearreg_slope'] = ta.LINEARREG_SLOPE(close,
timeperiod=14)
df['ta_statistic_stddev'] = ta.STDDEV(close, timeperiod=5, nbdev=1)
df['ta_statistic_tsf'] = ta.TSF(close, timeperiod=14)
df['ta_statistic_var'] = ta.VAR(close, timeperiod=5, nbdev=1)
if ta_settings['math_transforms']:
df['ta_math_transforms_atan'] = ta.ATAN(close)
df['ta_math_transforms_ceil'] = ta.CEIL(close)
df['ta_math_transforms_cos'] = ta.COS(close)
df['ta_math_transforms_floor'] = ta.FLOOR(close)
df['ta_math_transforms_ln'] = ta.LN(close)
df['ta_math_transforms_log10'] = ta.LOG10(close)
df['ta_math_transforms_sin'] = ta.SIN(close)
df['ta_math_transforms_sqrt'] = ta.SQRT(close)
df['ta_math_transforms_tan'] = ta.TAN(close)
if ta_settings['math_operators']:
df['ta_math_operators_add'] = ta.ADD(high, low)
df['ta_math_operators_div'] = ta.DIV(high, low)
df['ta_math_operators_min'], df['ta_math_operators_max'] = ta.MINMAX(
close, timeperiod=30)
df['ta_math_operators_minidx'], df[
'ta_math_operators_maxidx'] = ta.MINMAXINDEX(close, timeperiod=30)
df['ta_math_operators_mult'] = ta.MULT(high, low)
df['ta_math_operators_sub'] = ta.SUB(high, low)
df['ta_math_operators_sum'] = ta.SUM(close, timeperiod=30)
return df
def calculate(self, para):
self.t = self.inputdata[:, 0]
self.op = self.inputdata[:, 1]
self.high = self.inputdata[:, 2]
self.low = self.inputdata[:, 3]
self.close = self.inputdata[:, 4]
#adjusted close
self.close1 = self.inputdata[:, 5]
self.volume = self.inputdata[:, 6]
#Overlap study
#Overlap Studies
#Overlap Studies
if para is 'BBANDS': #Bollinger Bands
upperband, middleband, lowerband = ta.BBANDS(self.close,
timeperiod=self.tp,
nbdevup=2,
nbdevdn=2,
matype=0)
self.output = [upperband, middleband, lowerband]
elif para is 'DEMA': #Double Exponential Moving Average
self.output = ta.DEMA(self.close, timeperiod=self.tp)
elif para is 'EMA': #Exponential Moving Average
self.output = ta.EMA(self.close, timeperiod=self.tp)
elif para is 'HT_TRENDLINE': #Hilbert Transform - Instantaneous Trendline
self.output = ta.HT_TRENDLINE(self.close)
elif para is 'KAMA': #Kaufman Adaptive Moving Average
self.output = ta.KAMA(self.close, timeperiod=self.tp)
elif para is 'MA': #Moving average
self.output = ta.MA(self.close, timeperiod=self.tp, matype=0)
elif para is 'MAMA': #MESA Adaptive Moving Average
mama, fama = ta.MAMA(self.close, fastlimit=0, slowlimit=0)
elif para is 'MAVP': #Moving average with variable period
self.output = ta.MAVP(self.close,
periods=10,
minperiod=self.tp,
maxperiod=self.tp1,
matype=0)
elif para is 'MIDPOINT': #MidPoint over period
self.output = ta.MIDPOINT(self.close, timeperiod=self.tp)
elif para is 'MIDPRICE': #Midpoint Price over period
self.output = ta.MIDPRICE(self.high, self.low, timeperiod=self.tp)
elif para is 'SAR': #Parabolic SAR
self.output = ta.SAR(self.high,
self.low,
acceleration=0,
maximum=0)
elif para is 'SAREXT': #Parabolic SAR - Extended
self.output = ta.SAREXT(self.high,
self.low,
startvalue=0,
offsetonreverse=0,
accelerationinitlong=0,
accelerationlong=0,
accelerationmaxlong=0,
accelerationinitshort=0,
accelerationshort=0,
accelerationmaxshort=0)
elif para is 'SMA': #Simple Moving Average
self.output = ta.SMA(self.close, timeperiod=self.tp)
elif para is 'T3': #Triple Exponential Moving Average (T3)
self.output = ta.T3(self.close, timeperiod=self.tp, vfactor=0)
elif para is 'TEMA': #Triple Exponential Moving Average
self.output = ta.TEMA(self.close, timeperiod=self.tp)
elif para is 'TRIMA': #Triangular Moving Average
self.output = ta.TRIMA(self.close, timeperiod=self.tp)
elif para is 'WMA': #Weighted Moving Average
self.output = ta.WMA(self.close, timeperiod=self.tp)
#Momentum Indicators
elif para is 'ADX': #Average Directional Movement Index
self.output = ta.ADX(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'ADXR': #Average Directional Movement Index Rating
self.output = ta.ADXR(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'APO': #Absolute Price Oscillator
self.output = ta.APO(self.close,
fastperiod=12,
slowperiod=26,
matype=0)
elif para is 'AROON': #Aroon
aroondown, aroonup = ta.AROON(self.high,
self.low,
timeperiod=self.tp)
self.output = [aroondown, aroonup]
elif para is 'AROONOSC': #Aroon Oscillator
self.output = ta.AROONOSC(self.high, self.low, timeperiod=self.tp)
elif para is 'BOP': #Balance Of Power
self.output = ta.BOP(self.op, self.high, self.low, self.close)
elif para is 'CCI': #Commodity Channel Index
self.output = ta.CCI(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'CMO': #Chande Momentum Oscillator
self.output = ta.CMO(self.close, timeperiod=self.tp)
elif para is 'DX': #Directional Movement Index
self.output = ta.DX(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'MACD': #Moving Average Convergence/Divergence
macd, macdsignal, macdhist = ta.MACD(self.close,
fastperiod=12,
slowperiod=26,
signalperiod=9)
self.output = [macd, macdsignal, macdhist]
elif para is 'MACDEXT': #MACD with controllable MA type
macd, macdsignal, macdhist = ta.MACDEXT(self.close,
fastperiod=12,
fastmatype=0,
slowperiod=26,
slowmatype=0,
signalperiod=9,
signalmatype=0)
self.output = [macd, macdsignal, macdhist]
elif para is 'MACDFIX': #Moving Average Convergence/Divergence Fix 12/26
macd, macdsignal, macdhist = ta.MACDFIX(self.close, signalperiod=9)
self.output = [macd, macdsignal, macdhist]
elif para is 'MFI': #Money Flow Index
self.output = ta.MFI(self.high,
self.low,
self.close,
self.volume,
timeperiod=self.tp)
elif para is 'MINUS_DI': #Minus Directional Indicator
self.output = ta.MINUS_DI(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'MINUS_DM': #Minus Directional Movement
self.output = ta.MINUS_DM(self.high, self.low, timeperiod=self.tp)
elif para is 'MOM': #Momentum
self.output = ta.MOM(self.close, timeperiod=10)
elif para is 'PLUS_DI': #Plus Directional Indicator
self.output = ta.PLUS_DI(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'PLUS_DM': #Plus Directional Movement
self.output = ta.PLUS_DM(self.high, self.low, timeperiod=self.tp)
elif para is 'PPO': #Percentage Price Oscillator
self.output = ta.PPO(self.close,
fastperiod=12,
slowperiod=26,
matype=0)
elif para is 'ROC': #Rate of change : ((price/prevPrice)-1)*100
self.output = ta.ROC(self.close, timeperiod=10)
elif para is 'ROCP': #Rate of change Percentage: (price-prevPrice)/prevPrice
self.output = ta.ROCP(self.close, timeperiod=10)
elif para is 'ROCR': #Rate of change ratio: (price/prevPrice)
self.output = ta.ROCR(self.close, timeperiod=10)
elif para is 'ROCR100': #Rate of change ratio 100 scale: (price/prevPrice)*100
self.output = ta.ROCR100(self.close, timeperiod=10)
elif para is 'RSI': #Relative Strength Index
self.output = ta.RSI(self.close, timeperiod=self.tp)
elif para is 'STOCH': #Stochastic
slowk, slowd = ta.STOCH(self.high,
self.low,
self.close,
fastk_period=5,
slowk_period=3,
slowk_matype=0,
slowd_period=3,
slowd_matype=0)
self.output = [slowk, slowd]
elif para is 'STOCHF': #Stochastic Fast
fastk, fastd = ta.STOCHF(self.high,
self.low,
self.close,
fastk_period=5,
fastd_period=3,
fastd_matype=0)
self.output = [fastk, fastd]
elif para is 'STOCHRSI': #Stochastic Relative Strength Index
fastk, fastd = ta.STOCHRSI(self.close,
timeperiod=self.tp,
fastk_period=5,
fastd_period=3,
fastd_matype=0)
self.output = [fastk, fastd]
elif para is 'TRIX': #1-day Rate-Of-Change (ROC) of a Triple Smooth EMA
self.output = ta.TRIX(self.close, timeperiod=self.tp)
elif para is 'ULTOSC': #Ultimate Oscillator
self.output = ta.ULTOSC(self.high,
self.low,
self.close,
timeperiod1=self.tp,
timeperiod2=self.tp1,
timeperiod3=self.tp2)
elif para is 'WILLR': #Williams' %R
self.output = ta.WILLR(self.high,
self.low,
self.close,
timeperiod=self.tp)
# Volume Indicators : #
elif para is 'AD': #Chaikin A/D Line
self.output = ta.AD(self.high, self.low, self.close, self.volume)
elif para is 'ADOSC': #Chaikin A/D Oscillator
self.output = ta.ADOSC(self.high,
self.low,
self.close,
self.volume,
fastperiod=3,
slowperiod=10)
elif para is 'OBV': #On Balance Volume
self.output = ta.OBV(self.close, self.volume)
# Volatility Indicators: #
elif para is 'ATR': #Average True Range
self.output = ta.ATR(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'NATR': #Normalized Average True Range
self.output = ta.NATR(self.high,
self.low,
self.close,
timeperiod=self.tp)
elif para is 'TRANGE': #True Range
self.output = ta.TRANGE(self.high, self.low, self.close)
#Price Transform : #
elif para is 'AVGPRICE': #Average Price
self.output = ta.AVGPRICE(self.op, self.high, self.low, self.close)
elif para is 'MEDPRICE': #Median Price
self.output = ta.MEDPRICE(self.high, self.low)
elif para is 'TYPPRICE': #Typical Price
self.output = ta.TYPPRICE(self.high, self.low, self.close)
elif para is 'WCLPRICE': #Weighted Close Price
self.output = ta.WCLPRICE(self.high, self.low, self.close)
#Cycle Indicators : #
elif para is 'HT_DCPERIOD': #Hilbert Transform - Dominant Cycle Period
self.output = ta.HT_DCPERIOD(self.close)
elif para is 'HT_DCPHASE': #Hilbert Transform - Dominant Cycle Phase
self.output = ta.HT_DCPHASE(self.close)
elif para is 'HT_PHASOR': #Hilbert Transform - Phasor Components
inphase, quadrature = ta.HT_PHASOR(self.close)
self.output = [inphase, quadrature]
elif para is 'HT_SINE': #Hilbert Transform - SineWave #2
sine, leadsine = ta.HT_SINE(self.close)
self.output = [sine, leadsine]
elif para is 'HT_TRENDMODE': #Hilbert Transform - Trend vs Cycle Mode
self.integer = ta.HT_TRENDMODE(self.close)
#Pattern Recognition : #
elif para is 'CDL2CROWS': #Two Crows
self.integer = ta.CDL2CROWS(self.op, self.high, self.low,
self.close)
elif para is 'CDL3BLACKCROWS': #Three Black Crows
self.integer = ta.CDL3BLACKCROWS(self.op, self.high, self.low,
self.close)
elif para is 'CDL3INSIDE': #Three Inside Up/Down
self.integer = ta.CDL3INSIDE(self.op, self.high, self.low,
self.close)
elif para is 'CDL3LINESTRIKE': #Three-Line Strike
self.integer = ta.CDL3LINESTRIKE(self.op, self.high, self.low,
self.close)
elif para is 'CDL3OUTSIDE': #Three Outside Up/Down
self.integer = ta.CDL3OUTSIDE(self.op, self.high, self.low,
self.close)
elif para is 'CDL3STARSINSOUTH': #Three Stars In The South
self.integer = ta.CDL3STARSINSOUTH(self.op, self.high, self.low,
self.close)
elif para is 'CDL3WHITESOLDIERS': #Three Advancing White Soldiers
self.integer = ta.CDL3WHITESOLDIERS(self.op, self.high, self.low,
self.close)
elif para is 'CDLABANDONEDBABY': #Abandoned Baby
self.integer = ta.CDLABANDONEDBABY(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLBELTHOLD': #Belt-hold
self.integer = ta.CDLBELTHOLD(self.op, self.high, self.low,
self.close)
elif para is 'CDLBREAKAWAY': #Breakaway
self.integer = ta.CDLBREAKAWAY(self.op, self.high, self.low,
self.close)
elif para is 'CDLCLOSINGMARUBOZU': #Closing Marubozu
self.integer = ta.CDLCLOSINGMARUBOZU(self.op, self.high, self.low,
self.close)
elif para is 'CDLCONCEALBABYSWALL': #Concealing Baby Swallow
self.integer = ta.CDLCONCEALBABYSWALL(self.op, self.high, self.low,
self.close)
elif para is 'CDLCOUNTERATTACK': #Counterattack
self.integer = ta.CDLCOUNTERATTACK(self.op, self.high, self.low,
self.close)
elif para is 'CDLDARKCLOUDCOVER': #Dark Cloud Cover
self.integer = ta.CDLDARKCLOUDCOVER(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLDOJI': #Doji
self.integer = ta.CDLDOJI(self.op, self.high, self.low, self.close)
elif para is 'CDLDOJISTAR': #Doji Star
self.integer = ta.CDLDOJISTAR(self.op, self.high, self.low,
self.close)
elif para is 'CDLDRAGONFLYDOJI': #Dragonfly Doji
self.integer = ta.CDLDRAGONFLYDOJI(self.op, self.high, self.low,
self.close)
elif para is 'CDLENGULFING': #Engulfing Pattern
self.integer = ta.CDLENGULFING(self.op, self.high, self.low,
self.close)
elif para is 'CDLEVENINGDOJISTAR': #Evening Doji Star
self.integer = ta.CDLEVENINGDOJISTAR(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLEVENINGSTAR': #Evening Star
self.integer = ta.CDLEVENINGSTAR(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLGAPSIDESIDEWHITE': #Up/Down-gap side-by-side white lines
self.integer = ta.CDLGAPSIDESIDEWHITE(self.op, self.high, self.low,
self.close)
elif para is 'CDLGRAVESTONEDOJI': #Gravestone Doji
self.integer = ta.CDLGRAVESTONEDOJI(self.op, self.high, self.low,
self.close)
elif para is 'CDLHAMMER': #Hammer
self.integer = ta.CDLHAMMER(self.op, self.high, self.low,
self.close)
elif para is 'CDLHANGINGMAN': #Hanging Man
self.integer = ta.CDLHANGINGMAN(self.op, self.high, self.low,
self.close)
elif para is 'CDLHARAMI': #Harami Pattern
self.integer = ta.CDLHARAMI(self.op, self.high, self.low,
self.close)
elif para is 'CDLHARAMICROSS': #Harami Cross Pattern
self.integer = ta.CDLHARAMICROSS(self.op, self.high, self.low,
self.close)
elif para is 'CDLHIGHWAVE': #High-Wave Candle
self.integer = ta.CDLHIGHWAVE(self.op, self.high, self.low,
self.close)
elif para is 'CDLHIKKAKE': #Hikkake Pattern
self.integer = ta.CDLHIKKAKE(self.op, self.high, self.low,
self.close)
elif para is 'CDLHIKKAKEMOD': #Modified Hikkake Pattern
self.integer = ta.CDLHIKKAKEMOD(self.op, self.high, self.low,
self.close)
elif para is 'CDLHOMINGPIGEON': #Homing Pigeon
self.integer = ta.CDLHOMINGPIGEON(self.op, self.high, self.low,
self.close)
elif para is 'CDLIDENTICAL3CROWS': #Identical Three Crows
self.integer = ta.CDLIDENTICAL3CROWS(self.op, self.high, self.low,
self.close)
elif para is 'CDLINNECK': #In-Neck Pattern
self.integer = ta.CDLINNECK(self.op, self.high, self.low,
self.close)
elif para is 'CDLINVERTEDHAMMER': #Inverted Hammer
self.integer = ta.CDLINVERTEDHAMMER(self.op, self.high, self.low,
self.close)
elif para is 'CDLKICKING': #Kicking
self.integer = ta.CDLKICKING(self.op, self.high, self.low,
self.close)
elif para is 'CDLKICKINGBYLENGTH': #Kicking - bull/bear determined by the longer marubozu
self.integer = ta.CDLKICKINGBYLENGTH(self.op, self.high, self.low,
self.close)
elif para is 'CDLLADDERBOTTOM': #Ladder Bottom
self.integer = ta.CDLLADDERBOTTOM(self.op, self.high, self.low,
self.close)
elif para is 'CDLLONGLEGGEDDOJI': #Long Legged Doji
self.integer = ta.CDLLONGLEGGEDDOJI(self.op, self.high, self.low,
self.close)
elif para is 'CDLLONGLINE': #Long Line Candle
self.integer = ta.CDLLONGLINE(self.op, self.high, self.low,
self.close)
elif para is 'CDLMARUBOZU': #Marubozu
self.integer = ta.CDLMARUBOZU(self.op, self.high, self.low,
self.close)
elif para is 'CDLMATCHINGLOW': #Matching Low
self.integer = ta.CDLMATCHINGLOW(self.op, self.high, self.low,
self.close)
elif para is 'CDLMATHOLD': #Mat Hold
self.integer = ta.CDLMATHOLD(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLMORNINGDOJISTAR': #Morning Doji Star
self.integer = ta.CDLMORNINGDOJISTAR(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLMORNINGSTAR': #Morning Star
self.integer = ta.CDLMORNINGSTAR(self.op,
self.high,
self.low,
self.close,
penetration=0)
elif para is 'CDLONNECK': #On-Neck Pattern
self.integer = ta.CDLONNECK(self.op, self.high, self.low,
self.close)
elif para is 'CDLPIERCING': #Piercing Pattern
self.integer = ta.CDLPIERCING(self.op, self.high, self.low,
self.close)
elif para is 'CDLRICKSHAWMAN': #Rickshaw Man
self.integer = ta.CDLRICKSHAWMAN(self.op, self.high, self.low,
self.close)
elif para is 'CDLRISEFALL3METHODS': #Rising/Falling Three Methods
self.integer = ta.CDLRISEFALL3METHODS(self.op, self.high, self.low,
self.close)
elif para is 'CDLSEPARATINGLINES': #Separating Lines
self.integer = ta.CDLSEPARATINGLINES(self.op, self.high, self.low,
self.close)
elif para is 'CDLSHOOTINGSTAR': #Shooting Star
self.integer = ta.CDLSHOOTINGSTAR(self.op, self.high, self.low,
self.close)
elif para is 'CDLSHORTLINE': #Short Line Candle
self.integer = ta.CDLSHORTLINE(self.op, self.high, self.low,
self.close)
elif para is 'CDLSPINNINGTOP': #Spinning Top
self.integer = ta.CDLSPINNINGTOP(self.op, self.high, self.low,
self.close)
elif para is 'CDLSTALLEDPATTERN': #Stalled Pattern
self.integer = ta.CDLSTALLEDPATTERN(self.op, self.high, self.low,
self.close)
elif para is 'CDLSTICKSANDWICH': #Stick Sandwich
self.integer = ta.CDLSTICKSANDWICH(self.op, self.high, self.low,
self.close)
elif para is 'CDLTAKURI': #Takuri (Dragonfly Doji with very long lower shadow)
self.integer = ta.CDLTAKURI(self.op, self.high, self.low,
self.close)
elif para is 'CDLTASUKIGAP': #Tasuki Gap
self.integer = ta.CDLTASUKIGAP(self.op, self.high, self.low,
self.close)
elif para is 'CDLTHRUSTING': #Thrusting Pattern
self.integer = ta.CDLTHRUSTING(self.op, self.high, self.low,
self.close)
elif para is 'CDLTRISTAR': #Tristar Pattern
self.integer = ta.CDLTRISTAR(self.op, self.high, self.low,
self.close)
elif para is 'CDLUNIQUE3RIVER': #Unique 3 River
self.integer = ta.CDLUNIQUE3RIVER(self.op, self.high, self.low,
self.close)
elif para is 'CDLUPSIDEGAP2CROWS': #Upside Gap Two Crows
self.integer = ta.CDLUPSIDEGAP2CROWS(self.op, self.high, self.low,
self.close)
elif para is 'CDLXSIDEGAP3METHODS': #Upside/Downside Gap Three Methods
self.integer = ta.CDLXSIDEGAP3METHODS(self.op, self.high, self.low,
self.close)
#Statistic Functions : #
elif para is 'BETA': #Beta
self.output = ta.BETA(self.high, self.low, timeperiod=5)
elif para is 'CORREL': #Pearson's Correlation Coefficient (r)
self.output = ta.CORREL(self.high, self.low, timeperiod=self.tp)
elif para is 'LINEARREG': #Linear Regression
self.output = ta.LINEARREG(self.close, timeperiod=self.tp)
elif para is 'LINEARREG_ANGLE': #Linear Regression Angle
self.output = ta.LINEARREG_ANGLE(self.close, timeperiod=self.tp)
elif para is 'LINEARREG_INTERCEPT': #Linear Regression Intercept
self.output = ta.LINEARREG_INTERCEPT(self.close,
timeperiod=self.tp)
elif para is 'LINEARREG_SLOPE': #Linear Regression Slope
self.output = ta.LINEARREG_SLOPE(self.close, timeperiod=self.tp)
elif para is 'STDDEV': #Standard Deviation
self.output = ta.STDDEV(self.close, timeperiod=5, nbdev=1)
elif para is 'TSF': #Time Series Forecast
self.output = ta.TSF(self.close, timeperiod=self.tp)
elif para is 'VAR': #Variance
self.output = ta.VAR(self.close, timeperiod=5, nbdev=1)
else:
print('You issued command:' + para)
#获取交易数据用于示例分析
import tushare as ts
def get_data(code,start='2015-01-01'):
df=ts.get_k_data(code,start)
df.index=pd.to_datetime(df.date)
df=df.sort_index()
return df
#获取上证指数收盘价、最高、最低价格
df=get_data('sh')[['open','close','high','low']]
#收盘价对时间t的线性回归预测值
df['linearreg']=ta.LINEARREG(df.close, timeperiod=14)
#时间序列预测值
df['tsf']=ta.TSF(df.close, timeperiod=14)
#画图
df.loc['2018-08-01':,['close','linearreg','tsf']].plot(figsize=(12,6))
plt.show()
df['beta']=ta.BETA(df.high,df.low,timeperiod=5)
df['correl']=ta.CORREL(df.high, df.low, timeperiod=30)
df['stdev']=ta.STDDEV(df.close, timeperiod=5, nbdev=1)
#将上述函数计算得到的结果进行可视化
df[['close','beta','correl','stdev']].plot(figsize=(12,8),
subplots = True,layout=(2, 2))
plt.subplots_adjust(wspace=0,hspace=0.2)
plt.show()
def get_factors(index,
Open,
Close,
High,
Low,
Volume,
rolling=26,
drop=False,
normalization=True):
tmp = pd.DataFrame()
tmp['tradeTime'] = index
# 累积/派发线（Accumulation / Distribution Line，该指标将每日的成交量通过价格加权累计，
# 用以计算成交量的动量。属于趋势型因子
tmp['AD'] = talib.AD(High, Low, Close, Volume)
# 佳庆指标（Chaikin Oscillator），该指标基于AD曲线的指数移动均线而计算得到。属于趋势型因子
tmp['ADOSC'] = talib.ADOSC(High,
Low,
Close,
Volume,
fastperiod=3,
slowperiod=10)
# 平均动向指数，DMI因子的构成部分。属于趋势型因子
tmp['ADX'] = talib.ADX(High, Low, Close, timeperiod=14)
# 相对平均动向指数，DMI因子的构成部分。属于趋势型因子
tmp['ADXR'] = talib.ADXR(High, Low, Close, timeperiod=14)
# 绝对价格振荡指数
tmp['APO'] = talib.APO(Close, fastperiod=12, slowperiod=26)
# Aroon通过计算自价格达到近期最高值和最低值以来所经过的期间数，帮助投资者预测证券价格从趋势到区域区域或反转的变化，
# Aroon指标分为Aroon、AroonUp和AroonDown3个具体指标。属于趋势型因子
tmp['AROONDown'], tmp['AROONUp'] = talib.AROON(High, Low, timeperiod=14)
tmp['AROONOSC'] = talib.AROONOSC(High, Low, timeperiod=14)
# 均幅指标（Average TRUE Ranger），取一定时间周期内的股价波动幅度的移动平均值，
# 是显示市场变化率的指标，主要用于研判买卖时机。属于超买超卖型因子。
tmp['ATR14'] = talib.ATR(High, Low, Close, timeperiod=14)
tmp['ATR6'] = talib.ATR(High, Low, Close, timeperiod=6)
# 布林带
tmp['Boll_Up'], tmp['Boll_Mid'], tmp['Boll_Down'] = talib.BBANDS(
Close, timeperiod=20, nbdevup=2, nbdevdn=2, matype=0)
# 均势指标
tmp['BOP'] = talib.BOP(Open, High, Low, Close)
# 5日顺势指标（Commodity Channel Index），专门测量股价是否已超出常态分布范围。属于超买超卖型因子。
tmp['CCI5'] = talib.CCI(High, Low, Close, timeperiod=5)
tmp['CCI10'] = talib.CCI(High, Low, Close, timeperiod=10)
tmp['CCI20'] = talib.CCI(High, Low, Close, timeperiod=20)
tmp['CCI88'] = talib.CCI(High, Low, Close, timeperiod=88)
# 钱德动量摆动指标（Chande Momentum Osciliator），与其他动量指标摆动指标如相对强弱指标（RSI）和随机指标（KDJ）不同，
# 钱德动量指标在计算公式的分子中采用上涨日和下跌日的数据。属于超买超卖型因子
tmp['CMO_Close'] = talib.CMO(Close, timeperiod=14)
tmp['CMO_Open'] = talib.CMO(Close, timeperiod=14)
# DEMA双指数移动平均线
tmp['DEMA6'] = talib.DEMA(Close, timeperiod=6)
tmp['DEMA12'] = talib.DEMA(Close, timeperiod=12)
tmp['DEMA26'] = talib.DEMA(Close, timeperiod=26)
# DX 动向指数
tmp['DX'] = talib.DX(High, Low, Close, timeperiod=14)
# EMA 指数移动平均线
tmp['EMA6'] = talib.EMA(Close, timeperiod=6)
tmp['EMA12'] = talib.EMA(Close, timeperiod=12)
tmp['EMA26'] = talib.EMA(Close, timeperiod=26)
# KAMA 适应性移动平均线
tmp['KAMA'] = talib.KAMA(Close, timeperiod=30)
# MACD
tmp['MACD_DIF'], tmp['MACD_DEA'], tmp['MACD_bar'] = talib.MACD(
Close, fastperiod=12, slowperiod=24, signalperiod=9)
# 中位数价格 不知道是什么意思
tmp['MEDPRICE'] = talib.MEDPRICE(High, Low)
# 负向指标 负向运动
tmp['MiNUS_DI'] = talib.MINUS_DI(High, Low, Close, timeperiod=14)
tmp['MiNUS_DM'] = talib.MINUS_DM(High, Low, timeperiod=14)
# 动量指标（Momentom Index），动量指数以分析股价波动的速度为目的，研究股价在波动过程中各种加速，
# 减速，惯性作用以及股价由静到动或由动转静的现象。属于趋势型因子
tmp['MOM'] = talib.MOM(Close, timeperiod=10)
# 归一化平均值范围
tmp['NATR'] = talib.NATR(High, Low, Close, timeperiod=14)
# OBV 能量潮指标（On Balance Volume，OBV），以股市的成交量变化来衡量股市的推动力，
# 从而研判股价的走势。属于成交量型因子
tmp['OBV'] = talib.OBV(Close, Volume)
# PLUS_DI 更向指示器
tmp['PLUS_DI'] = talib.PLUS_DI(High, Low, Close, timeperiod=14)
tmp['PLUS_DM'] = talib.PLUS_DM(High, Low, timeperiod=14)
# PPO 价格振荡百分比
tmp['PPO'] = talib.PPO(Close, fastperiod=6, slowperiod=26, matype=0)
# ROC 6日变动速率（Price Rate of Change），以当日的收盘价和N天前的收盘价比较，
# 通过计算股价某一段时间内收盘价变动的比例，应用价格的移动比较来测量价位动量。属于超买超卖型因子。
tmp['ROC6'] = talib.ROC(Close, timeperiod=6)
tmp['ROC20'] = talib.ROC(Close, timeperiod=20)
# 12日量变动速率指标（Volume Rate of Change），以今天的成交量和N天前的成交量比较，
# 通过计算某一段时间内成交量变动的幅度，应用成交量的移动比较来测量成交量运动趋向，
# 达到事先探测成交量供需的强弱，进而分析成交量的发展趋势及其将来是否有转势的意愿，
# 属于成交量的反趋向指标。属于成交量型因子
tmp['VROC6'] = talib.ROC(Volume, timeperiod=6)
tmp['VROC20'] = talib.ROC(Volume, timeperiod=20)
# ROC 6日变动速率（Price Rate of Change），以当日的收盘价和N天前的收盘价比较，
# 通过计算股价某一段时间内收盘价变动的比例，应用价格的移动比较来测量价位动量。属于超买超卖型因子。
tmp['ROCP6'] = talib.ROCP(Close, timeperiod=6)
tmp['ROCP20'] = talib.ROCP(Close, timeperiod=20)
# 12日量变动速率指标（Volume Rate of Change），以今天的成交量和N天前的成交量比较，
# 通过计算某一段时间内成交量变动的幅度，应用成交量的移动比较来测量成交量运动趋向，
# 达到事先探测成交量供需的强弱，进而分析成交量的发展趋势及其将来是否有转势的意愿，
# 属于成交量的反趋向指标。属于成交量型因子
tmp['VROCP6'] = talib.ROCP(Volume, timeperiod=6)
tmp['VROCP20'] = talib.ROCP(Volume, timeperiod=20)
# RSI
tmp['RSI'] = talib.RSI(Close, timeperiod=14)
# SAR 抛物线转向
tmp['SAR'] = talib.SAR(High, Low, acceleration=0.02, maximum=0.2)
# TEMA
tmp['TEMA6'] = talib.TEMA(Close, timeperiod=6)
tmp['TEMA12'] = talib.TEMA(Close, timeperiod=12)
tmp['TEMA26'] = talib.TEMA(Close, timeperiod=26)
# TRANGE 真实范围
tmp['TRANGE'] = talib.TRANGE(High, Low, Close)
# TYPPRICE 典型价格
tmp['TYPPRICE'] = talib.TYPPRICE(High, Low, Close)
# TSF 时间序列预测
tmp['TSF'] = talib.TSF(Close, timeperiod=14)
# ULTOSC 极限振子
tmp['ULTOSC'] = talib.ULTOSC(High,
Low,
Close,
timeperiod1=7,
timeperiod2=14,
timeperiod3=28)
# 威廉指标
tmp['WILLR'] = talib.WILLR(High, Low, Close, timeperiod=14)
# 标准化
if normalization:
factors_list = tmp.columns.tolist()[1:]
if rolling >= 26:
for i in factors_list:
tmp[i] = (tmp[i] - tmp[i].rolling(window=rolling, center=False).mean()) \
/ tmp[i].rolling(window=rolling, center=False).std()
elif rolling < 26 & rolling > 0:
print('Recommended rolling range greater than 26')
elif rolling <= 0:
for i in factors_list:
tmp[i] = (tmp[i] - tmp[i].mean()) / tmp[i].std()
if drop:
tmp.dropna(inplace=True)
tmp.set_index('tradeTime', inplace=True)
return tmp
def talib_041(self):
data_TSF = copy.deepcopy(self.close)
for symbol in symbols:
data_TSF[symbol] = ta.TSF(self.close[symbol].values, timeperiod=14)
return data_TSF