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.LINEARREG(x.values, timeperiod=timeperiod), index=df.index))
return res.iloc[timeperiod - 1:]
def genTA(data, y, t): #t is timeperiod
indicators = {}
y_ind = copy.deepcopy(y)
for ticker in data:
## Overlap
indicators[ticker] = ta.SMA(data[ticker].iloc[:,3], timeperiod=t).to_frame()
indicators[ticker]['EMA'] = ta.EMA(data[ticker].iloc[:,3], timeperiod=t)
indicators[ticker]['BBAND_Upper'], indicators[ticker]['BBAND_Middle' ], indicators[ticker]['BBAND_Lower' ] = ta.BBANDS(data[ticker].iloc[:,3], timeperiod=t, nbdevup=2, nbdevdn=2, matype=0)
indicators[ticker]['HT_TRENDLINE'] = ta.HT_TRENDLINE(data[ticker].iloc[:,3])
indicators[ticker]['SAR'] = ta.SAR(data[ticker].iloc[:,1], data[ticker].iloc[:,2], acceleration=0, maximum=0)
#rename SMA column
indicators[ticker].rename(columns={indicators[ticker].columns[0]: "SMA"}, inplace=True)
## Momentum
indicators[ticker]['RSI'] = ta.RSI(data[ticker].iloc[:,3], timeperiod=(t-1))
indicators[ticker]['MOM'] = ta.MOM(data[ticker].iloc[:,3], timeperiod=(t-1))
indicators[ticker]['ROC'] = ta.ROC(data[ticker].iloc[:,3], timeperiod=(t-1))
indicators[ticker]['ROCP']= ta.ROCP(data[ticker].iloc[:,3],timeperiod=(t-1))
indicators[ticker]['STOCH_SLOWK'], indicators[ticker]['STOCH_SLOWD'] = ta.STOCH(data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3], fastk_period=t, slowk_period=int(.6*t), slowk_matype=0, slowd_period=int(.6*t), slowd_matype=0)
indicators[ticker]['MACD'], indicators[ticker]['MACDSIGNAL'], indicators[ticker]['MACDHIST'] = ta.MACD(data[ticker].iloc[:,3], fastperiod=t,slowperiod=2*t,signalperiod=int(.7*t))
## Volume
indicators[ticker]['OBV'] = ta.OBV(data[ticker].iloc[:,3], data[ticker].iloc[:,4])
indicators[ticker]['AD'] = ta.AD(data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3], data[ticker].iloc[:,4])
indicators[ticker]['ADOSC'] = ta.ADOSC(data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3], data[ticker].iloc[:,4], fastperiod=int(.3*t), slowperiod=t)
## Cycle
indicators[ticker]['HT_DCPERIOD'] = ta.HT_DCPERIOD(data[ticker].iloc[:,3])
indicators[ticker]['HT_TRENDMODE']= ta.HT_TRENDMODE(data[ticker].iloc[:,3])
## Price
indicators[ticker]['AVGPRICE'] = ta.AVGPRICE(data[ticker].iloc[:,0], data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
indicators[ticker]['TYPPRICE'] = ta.TYPPRICE(data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
## Volatility
indicators[ticker]['ATR'] = ta.ATR(data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3], timeperiod=(t-1))
## Statistics
indicators[ticker]['BETA'] = ta.BETA(data[ticker].iloc[:,1], data[ticker].iloc[:,2], timeperiod=(t-1))
indicators[ticker]['LINEARREG'] = ta.LINEARREG(data[ticker].iloc[:,3], timeperiod=t)
indicators[ticker]['VAR'] = ta.VAR(data[ticker].iloc[:,3], timeperiod=t, nbdev=1)
## Math Transform
indicators[ticker]['EXP'] = ta.EXP(data[ticker].iloc[:,3])
indicators[ticker]['LN'] = ta.LN(data[ticker].iloc[:,3])
## Patterns (returns integers - but norming might not really do anything but wondering if they should be normed)
indicators[ticker]['CDLENGULFING'] = ta.CDLENGULFING(data[ticker].iloc[:,0], data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
indicators[ticker]['CDLDOJI'] = ta.CDLDOJI(data[ticker].iloc[:,0], data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
indicators[ticker]['CDLHAMMER'] = ta.CDLHAMMER(data[ticker].iloc[:,0], data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
indicators[ticker]['CDLHANGINGMAN']= ta.CDLHANGINGMAN(data[ticker].iloc[:,0], data[ticker].iloc[:,1], data[ticker].iloc[:,2], data[ticker].iloc[:,3])
#drop 'nan' values
indicators[ticker].drop(indicators[ticker].index[np.arange(0,63)], inplace=True)
y_ind[ticker].drop(y_ind[ticker].index[np.arange(0,63)], inplace=True)
#Normalize Features
indicators_norm = normData(indicators)
return indicators_norm, indicators, y_ind
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 test_LINEARREG(self):
self.env.add_operator('linearreg', {
'operator': OperatorLINEARREG,
})
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.LINEARREG(o[:14, i], timeperiod=14)[-1] == ser0[i])
res1.append(talib.LINEARREG(o[1:14+1, i], timeperiod=14)[-1] == ser1[i])
res.append(talib.LINEARREG(o[:14+1, i], timeperiod=14)[-1] == ser1[i])
self.assertTrue(all(res0) and all(res1) and all(res))
def cfo(candles: np.ndarray,
period: int = 14,
scalar: float = 100,
source_type: str = "close",
sequential: bool = False) -> Union[float, np.ndarray]:
"""
CFO - Chande Forcast Oscillator
: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)
cfo = scalar * (source - talib.LINEARREG(source, timeperiod=period))
cfo /= source
if sequential:
return cfo
else:
return None if np.isnan(cfo[-1]) else cfo[-1]
def lineareg_band(data, nATR=14, nlookback=20, scale=1):
"""
布林带和线性回归ATR通道共振指标系统
Source: https://cn.tradingview.com/script/jNWOuOMb-Colored-Linear-regression-band/
Translator: 阿财（Rgveda@github）（4910163#qq.com）
Parameters
----------
nlookback = defval = 20, minval = 1
Number of Lookback
scale = defval=1,
scale of ATR
nATR = defval = 14,
ATR Parameter
"""
#Linear Regression Curve
lrc = talib.LINEARREG(data.close, timeperiod=nlookback)
# ATR band
lrc_u = lrc + scale * talib.ATR(
data.high, data.low, data.close, timeperiod=nATR)
lrc_l = lrc - scale * talib.ATR(
data.high, data.low, data.close, timeperiod=nATR)
# direction
color_reg = np.where(lrc > lrc.shift(1), 1,
np.where(lrc < lrc.shift(1), -1, 0))
return lrc, lrc_u, lrc_l, color_reg
def cfo(candles: np.ndarray,
period: int = 14,
scalar: float = 100,
source_type: str = "close",
sequential: bool = False) -> Union[float, np.ndarray]:
"""
CFO - Chande Forcast Oscillator
: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)
cfo = scalar * (source - talib.LINEARREG(source, timeperiod=period))
cfo /= source
if sequential:
return cfo
else:
return None if np.isnan(cfo[-1]) else cfo[-1]
def maCross(self,am,paraDict):
regPeriod = paraDict["regPeriod"]
fastPeriod = paraDict["fastPeriod"]
slowPeriod = paraDict["slowPeriod"]
prediction = ta.LINEARREG(am.close, regPeriod)
residual = (am.close - prediction) / am.close
resSma = ta.MA(residual, fastPeriod)
resLma = ta.MA(residual, slowPeriod)
residualUp = resSma[-1] > resLma[-1] and resSma[-2]<= resLma[-2]
residualDn = resSma[-1] < resLma[-1] and resSma[-2]>= resLma[-2]
maCrossSignal = 0
if residualUp:
maCrossSignal = 1
elif residualDn:
maCrossSignal = -1
else:
resSignal = 0
return maCrossSignal, resSma, resLma
def choose():
print("I'm working......选股策略")
# 股票列表
engine = create_engine('postgresql://*****:*****@47.93.193.128:5432/xiaoan')
# stock_basics = ts.get_stock_basics()
temp_stock_basics = pd.read_sql_query('select * from stock_basics_all',con = engine)
stock_basics = pd.DataFrame(temp_stock_basics)
data = pd.DataFrame(stock_basics)
data = data[(data['pe']<40)] # pe,市盈率
data = data[(data['pb']<10)] # pd,市净率
data = data[(data['npr']>10)] # npr,净利润率(%)
data = data[(data['roe']>10)] # roe,净资产收益率
data = data[(data['rev']>0)] # rev,收入同比(%)
# data = data[(data['profits_yoy'].isnull()) | (data['profits_yoy']>10)]
data = data[(data['profit']>0)] # profit,利润同比(%)
data.to_sql('my_stocks',engine,index=True,if_exists='replace')
data = pd.read_sql_query('select * from my_stocks',con = engine)
data = pd.DataFrame(read_sql_query)
get_k_data = ts.get_k_data('000651', start='1990-12-19')
ma5 = ta.MA(get_k_data['close'].values, timeperiod=5, matype=0)
ma10 = ta.MA(get_k_data['close'].values, timeperiod=10, matype=0)
ma20 = ta.MA(get_k_data['close'].values, timeperiod=20, matype=0)
ma60 = ta.MA(get_k_data['close'].values, timeperiod=60, matype=0)
fig, axes = plt.subplots(1, 1, sharex=True, sharey=True)
# LINEARREG = ta.LINEARREG(get_k_data['close'].values, timeperiod=14)
real = ta.LINEARREG(get_k_data['close'].values, timeperiod=60)
get_k_data.set_index('date')
axes.plot(ma60[1300:2300], 'k-')
axes.plot(real[1300:2300], 'r-')
axes.plot(ma60, 'k-')
plt.subplots_adjust(wspace = 0, hspace = 0)
# get_k_data.plot(x='date', y='close')
# x=get_k_data.close
# y=get_k_data.close
# est=sm.OLS(y,x)
# est=est.fit()
# x_prime=np.linspace(x.close.min(), x.close.max(),100)
# x_prime=sm.add_constant(x_prime)
# y_hat=est.predict(x_prime)
# plt.scatter(x.close, y, alpha=0.3)
# plt.xlabel("Gross National Product")
# plt.ylabel("Total Employment")
# plt.plot(x_prime[:,1], y_hat, 'r', alpha=0.9)
# print(est.summary())
plt.show()
# send_mail(data, 'choose')
print("选股策略......done")
def update(self, data, N):
close = data[4]
self.clear()
self.series_fast.attachAxis(self.chart.ax)
self.series_fast.attachAxis(self.chart.ay)
self.series_slow.attachAxis(self.chart.ax)
self.series_slow.attachAxis(self.chart.ay)
regression_fast = talib.LINEARREG(close, timeperiod=11)
firstNotNan = np.where(np.isnan(regression_fast))[0][-1] + 1
regression_fast[:firstNotNan] = regression_fast[firstNotNan]
for i, val in enumerate(regression_fast[-N:]):
self.series_fast.append(i + 0.5, val)
regression_slow = talib.LINEARREG(close, timeperiod=23)
firstNotNan = np.where(np.isnan(regression_slow))[0][-1] + 1
regression_slow[:firstNotNan] = regression_slow[firstNotNan]
for i, val in enumerate(regression_slow[-N:]):
self.series_slow.append(i + 0.5, val)
def LINEARREG(close, timeperiod=14):
''' Linear Regression 线性回归
分组: Statistic Functions 统计函数
简介:
real = LINEARREG(close, timeperiod=14)
'''
return talib.LINEARREG(close, timeperiod)
def linreg(vm, args, kwargs):
source, length, _offset = _expand_args(args, kwargs,
(('source', Series, True),
('length', int, True),
('offset', int, True)))
try:
return series_np(ta.LINEARREG(source, length) + _offset, source)
except Exception as e:
if str(e) == 'inputs are all NaN':
return source.dup()
raise
def test_linreg(self):
result = self.overlap.linreg(self.close)
self.assertIsInstance(result, Series)
self.assertEqual(result.name, 'LR_14')
try:
expected = tal.LINEARREG(self.close)
pdt.assert_series_equal(result, expected, check_names=False)
except AssertionError as ae:
try:
corr = pandas_ta.utils.df_error_analysis(result, expected, col=CORRELATION)
self.assertGreater(corr, CORRELATION_THRESHOLD)
except Exception as ex:
error_analysis(result, CORRELATION, ex)
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 linearreg(client, symbol, timeframe="6m", closecol="close", period=14):
"""This will return a dataframe of linear regression for the given symbol across
the given timeframe
Args:
client (pyEX.Client): Client
symbol (string): Ticker
timeframe (string): timeframe 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, timeframe)
linearreg = t.LINEARREG(df[closecol].values, period)
return pd.DataFrame({closecol: df[closecol].values, "lineearreg": linearreg})
def get_technicals_of_series(self, indivations):
result = indivations
result = np.vstack((result, ta.SMA(indivations, timeperiod=5)))
result = np.vstack((result, ta.SMA(indivations, timeperiod=14)))
result = np.vstack((result, ta.BBANDS(indivations)))
result = np.vstack((result, ta.MAMA(indivations)))
result = np.vstack((result, ta.APO(indivations)))
result = np.vstack((result, ta.CMO(indivations)))
result = np.vstack((result, ta.MACD(indivations)))
result = np.vstack((result, ta.MOM(indivations)))
result = np.vstack((result, ta.ROC(indivations)))
result = np.vstack((result, ta.RSI(indivations)))
result = np.vstack((result, ta.HT_TRENDMODE(indivations)))
result = np.vstack((result, ta.LINEARREG(indivations)))
result = result[:, ~np.isnan(result).any(axis=0)]
result = result.T
print(np.shape(result))
return result
def linearreg(candles: np.ndarray, period: int = 14, source_type: str = "close", sequential: bool = False) -> Union[
float, np.ndarray]:
"""
LINEARREG - Linear Regression
: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.LINEARREG(source, timeperiod=period)
return res if sequential else res[-1]
def getSignalPos(self):
"""计算指标数据"""
# 指标计算
am = self.am
prediction = ta.LINEARREG(am.close, self.regPeriod)
residual = (am.close - prediction)
residualSma = ta.MA(residual, self.residualSmaPeriod)
residualLma = ta.MA(residual, self.residualLmaPeriod)
residualUp = residualSma[-1] > residualLma[-1]
residualDn = residualSma[-1] < residualLma[-1]
# 进出场逻辑
if (residualUp):
return 1
if (residualDn):
return -1
return 0
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 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 linearreg(candles: np.ndarray,
period: int = 14,
source_type: str = "close",
sequential: bool = False) -> Union[float, np.ndarray]:
"""
LINEARREG - Linear Regression
: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.LINEARREG(source, timeperiod=period)
return res if sequential else res[-1]
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)
def TALIB_LINEARREG(close, timeperiod=14):
'''00348,2,1'''
return talib.LINEARREG(close, timeperiod)
df['ATR2'] = abs(
np.array(df['High'].shift(1)) - np.array(df['Adj Close'].shift(1)))
df['ATR3'] = abs(
np.array(df['Low'].shift(1)) - np.array(df['Adj Close'].shift(1)))
df['AverageTrueRange'] = df[['ATR1', 'ATR2', 'ATR3']].max(axis=1)
# df['EMA']=pd.Series(pd.ewma(df['Adj Close'], span = n, min_periods = n - 1))
# Statistic Functions
df['Beta'] = ta.BETA(np.array(df['High'].shift(1)),
np.array(df['Low'].shift(1)),
timeperiod=n)
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
def calc_features(df):
open = df['op']
high = df['hi']
low = df['lo']
close = df['cl']
volume = df['volume']
orig_columns = df.columns
hilo = (df['hi'] + df['lo']) / 2
df['BBANDS_upperband'], df['BBANDS_middleband'], df[
'BBANDS_lowerband'] = talib.BBANDS(close,
timeperiod=5,
nbdevup=2,
nbdevdn=2,
matype=0)
df['BBANDS_upperband'] -= hilo
df['BBANDS_middleband'] -= hilo
df['BBANDS_lowerband'] -= hilo
df['DEMA'] = talib.DEMA(close, timeperiod=30) - hilo
df['EMA'] = talib.EMA(close, timeperiod=30) - hilo
df['HT_TRENDLINE'] = talib.HT_TRENDLINE(close) - hilo
df['KAMA'] = talib.KAMA(close, timeperiod=30) - hilo
df['MA'] = talib.MA(close, timeperiod=30, matype=0) - hilo
df['MIDPOINT'] = talib.MIDPOINT(close, timeperiod=14) - hilo
df['SMA'] = talib.SMA(close, timeperiod=30) - hilo
df['T3'] = talib.T3(close, timeperiod=5, vfactor=0) - hilo
df['TEMA'] = talib.TEMA(close, timeperiod=30) - hilo
df['TRIMA'] = talib.TRIMA(close, timeperiod=30) - hilo
df['WMA'] = talib.WMA(close, timeperiod=30) - hilo
df['ADX'] = talib.ADX(high, low, close, timeperiod=14)
df['ADXR'] = talib.ADXR(high, low, close, timeperiod=14)
df['APO'] = talib.APO(close, fastperiod=12, slowperiod=26, matype=0)
df['AROON_aroondown'], df['AROON_aroonup'] = talib.AROON(high,
low,
timeperiod=14)
df['AROONOSC'] = talib.AROONOSC(high, low, timeperiod=14)
df['BOP'] = talib.BOP(open, high, low, close)
df['CCI'] = talib.CCI(high, low, close, timeperiod=14)
df['DX'] = talib.DX(high, low, close, timeperiod=14)
df['MACD_macd'], df['MACD_macdsignal'], df['MACD_macdhist'] = talib.MACD(
close, fastperiod=12, slowperiod=26, signalperiod=9)
# skip MACDEXT MACDFIX たぶん同じなので
df['MFI'] = talib.MFI(high, low, close, volume, timeperiod=14)
df['MINUS_DI'] = talib.MINUS_DI(high, low, close, timeperiod=14)
df['MINUS_DM'] = talib.MINUS_DM(high, low, timeperiod=14)
df['MOM'] = talib.MOM(close, timeperiod=10)
df['PLUS_DI'] = talib.PLUS_DI(high, low, close, timeperiod=14)
df['PLUS_DM'] = talib.PLUS_DM(high, low, timeperiod=14)
df['RSI'] = talib.RSI(close, timeperiod=14)
df['STOCH_slowk'], df['STOCH_slowd'] = talib.STOCH(high,
low,
close,
fastk_period=5,
slowk_period=3,
slowk_matype=0,
slowd_period=3,
slowd_matype=0)
df['STOCHF_fastk'], df['STOCHF_fastd'] = talib.STOCHF(high,
low,
close,
fastk_period=5,
fastd_period=3,
fastd_matype=0)
df['STOCHRSI_fastk'], df['STOCHRSI_fastd'] = talib.STOCHRSI(close,
timeperiod=14,
fastk_period=5,
fastd_period=3,
fastd_matype=0)
df['TRIX'] = talib.TRIX(close, timeperiod=30)
df['ULTOSC'] = talib.ULTOSC(high,
low,
close,
timeperiod1=7,
timeperiod2=14,
timeperiod3=28)
df['WILLR'] = talib.WILLR(high, low, close, timeperiod=14)
df['AD'] = talib.AD(high, low, close, volume)
df['ADOSC'] = talib.ADOSC(high,
low,
close,
volume,
fastperiod=3,
slowperiod=10)
df['OBV'] = talib.OBV(close, volume)
df['ATR'] = talib.ATR(high, low, close, timeperiod=14)
df['NATR'] = talib.NATR(high, low, close, timeperiod=14)
df['TRANGE'] = talib.TRANGE(high, low, close)
df['HT_DCPERIOD'] = talib.HT_DCPERIOD(close)
df['HT_DCPHASE'] = talib.HT_DCPHASE(close)
df['HT_PHASOR_inphase'], df['HT_PHASOR_quadrature'] = talib.HT_PHASOR(
close)
df['HT_SINE_sine'], df['HT_SINE_leadsine'] = talib.HT_SINE(close)
df['HT_TRENDMODE'] = talib.HT_TRENDMODE(close)
df['BETA'] = talib.BETA(high, low, timeperiod=5)
df['CORREL'] = talib.CORREL(high, low, timeperiod=30)
df['LINEARREG'] = talib.LINEARREG(close, timeperiod=14) - close
df['LINEARREG_ANGLE'] = talib.LINEARREG_ANGLE(close, timeperiod=14)
df['LINEARREG_INTERCEPT'] = talib.LINEARREG_INTERCEPT(
close, timeperiod=14) - close
df['LINEARREG_SLOPE'] = talib.LINEARREG_SLOPE(close, timeperiod=14)
df['STDDEV'] = talib.STDDEV(close, timeperiod=5, nbdev=1)
return df
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 LINEARREG(Series, N=14):
res = talib.LINEARREG(Series.values, N)
return pd.Series(res, index=Series.index)
def LINEARREG(data, **kwargs):
_check_talib_presence()
prices = _extract_series(data)
return talib.LINEARREG(prices, **kwargs)
def LINEARREG(Series, timeperiod=14):
res = talib.LINEARREG(Series.values, timeperiod)
return pd.Series(res, index=Series.index)
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))