def t3(client, symbol, timeframe="6m", col="close", periods=None, vfactor=0):
"""This will return a dataframe of tripple exponential moving average
for the given symbol across the given timeframe
Args:
client (pyEX.Client); Client
symbol (string); Ticker
timeframe (string); timeframe to use, for pyEX.chart
col (string); column to use to calculate
periods (int); periods
vfactor (int); vfactor
Returns:
DataFrame: result
"""
if periods is None:
periods = [30]
periods = tolist(periods)
df = client.chartDF(symbol, timeframe)
build = {col: df[col].values}
for per in periods:
build["t3-{}".format(per)] = t.T3(df[col].values.astype(float),
per,
vfactor=vfactor)
return pd.DataFrame(build)
def add_T3(self, df, periods=[5, 10, 20, 30, 60, 120], vfactor=0):
for i in periods:
period = str(i)
df['T3_' + period] = ta.T3(df['close'],
timeperiod=i,
vfactor=vfactor)
return df
def calculations(self):
'''calculations'''
self.df['rsi'] = ta.RSI(self.df['close'], timeperiod=5)
self.df['apo'] = ta.APO(self.df['close'],
fastperiod=10,
slowperiod=5,
matype=0)
self.df['upperband'], self.df['middleband'], self.df[
'lowerband'] = ta.BBANDS(self.df['close'],
timeperiod=5,
nbdevup=2,
nbdevdn=2,
matype=0)
self.df['ema'] = ta.EMA(self.df['close'], timeperiod=5)
self.df['ma'] = ta.MA(self.df['close'], timeperiod=5, matype=0)
self.df['sma'] = ta.MA(self.df['close'], timeperiod=5)
self.df['t3'] = ta.T3(self.df['close'], timeperiod=5, vfactor=0)
self.df['wma'] = ta.WMA(self.df['close'], timeperiod=5)
self.df['aroonosc'] = ta.AROONOSC(self.df['high'],
self.df['low'],
timeperiod=5)
self.df['cci'] = ta.CCI(self.df['high'],
self.df['low'],
self.df['close'],
timeperiod=5)
self.df['cmo'] = ta.CMO(self.df['close'], timeperiod=14)
self.df['macd'], self.df['macdsignal'], self.df[
'macdhist'] = ta.MACDEXT(self.df['close'],
fastperiod=12,
fastmatype=0,
slowperiod=26,
slowmatype=0,
signalperiod=9,
signalmatype=0)
self.df['slowk'], self.df['slowd'] = ta.STOCH(self.df['high'],
self.df['low'],
self.df['close'],
fastk_period=5,
slowk_period=3,
slowk_matype=0,
slowd_period=3,
slowd_matype=0)
self.df['fastk'], self.df['fastd'] = ta.STOCHRSI(self.df['close'],
timeperiod=5,
fastk_period=5,
fastd_period=3,
fastd_matype=0)
self.df['ultosc'] = ta.ULTOSC(self.df['high'],
self.df['low'],
self.df['close'],
timeperiod1=7,
timeperiod2=14,
timeperiod3=28)
self.df['adosc'] = ta.ADOSC(self.df['high'],
self.df['low'],
self.df['close'],
self.df['volume'],
fastperiod=3,
slowperiod=10)
return self.df
def test_t3(self):
"""
Test T3 Moving Average.
"""
periods = 200
t3 = qufilab.t3(self.close, periods)
t3_talib = talib.T3(self.close, periods)
np.testing.assert_allclose(t3, t3_talib, rtol=self.tolerance)
def overlap_process(event):
print(event.widget.get())
overlap = 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(overlap, fontproperties="SimHei")
if overlap == '布林线':
pass
elif overlap == '双指数移动平均线':
real = ta.DEMA(close, timeperiod=30)
axes[1].plot(real, 'r-')
elif overlap == '指数移动平均线 ':
real = ta.EMA(close, timeperiod=30)
axes[1].plot(real, 'r-')
elif overlap == '希尔伯特变换——瞬时趋势线':
real = ta.HT_TRENDLINE(close)
axes[1].plot(real, 'r-')
elif overlap == '考夫曼自适应移动平均线':
real = ta.KAMA(close, timeperiod=30)
axes[1].plot(real, 'r-')
elif overlap == '移动平均线':
real = ta.MA(close, timeperiod=30, matype=0)
axes[1].plot(real, 'r-')
elif overlap == 'MESA自适应移动平均':
mama, fama = ta.MAMA(close, fastlimit=0, slowlimit=0)
axes[1].plot(mama, 'r-')
axes[1].plot(fama, 'g-')
elif overlap == '变周期移动平均线':
real = ta.MAVP(close, periods, minperiod=2, maxperiod=30, matype=0)
axes[1].plot(real, 'r-')
elif overlap == '简单移动平均线':
real = ta.SMA(close, timeperiod=30)
axes[1].plot(real, 'r-')
elif overlap == '三指数移动平均线(T3)':
real = ta.T3(close, timeperiod=5, vfactor=0)
axes[1].plot(real, 'r-')
elif overlap == '三指数移动平均线':
real = ta.TEMA(close, timeperiod=30)
axes[1].plot(real, 'r-')
elif overlap == '三角形加权法 ':
real = ta.TRIMA(close, timeperiod=30)
axes[1].plot(real, 'r-')
elif overlap == '加权移动平均数':
real = ta.WMA(close, timeperiod=30)
axes[1].plot(real, 'r-')
plt.show()
def queryStock(self, stackCode):
# 连接数据库
resultTemp=[]
connection=Connection()
connect = pymysql.Connect(
host=connection.host,
port=connection.port,
user=connection.user,
passwd=connection.passwd,
db=connection.db,
charset=connection.charset
)
# 获取游标
cursor = connect.cursor()
# 查询数据
sql = "select * from (SELECT DISTINCT * FROM `"+stackCode+"` where tradestatus=1 and turn is not null order by date desc limit %i) as b order by date asc"
data = (self.window+80)
cursor.execute(sql % data)
fs = cursor.description
filelds = []
for field in fs:
filelds.append(field[0])
rs = cursor.fetchall()
result = pd.DataFrame(list(rs), columns=filelds)
# 关闭连接
cursor.close()
connect.close()
#二维数组
result=result.loc[:,['date','open','high','low','close','volume','turn','tradestatus'] ]
#计算三十日均线
result['M30']=talib.SMA(result['close'],30)
result['T30']=talib.T3(result['close'],timeperiod=30, vfactor=0)
result['tprice']=talib.TYPPRICE(result['high'],result['low'],result['close'])
# slowk, slowd = talib.STOCH(result['high'],result['low'],result['close'], fastk_period=9, slowk_period=3, slowk_matype=0, slowd_period=3, slowd_matype=0)
# slowj= list(map(lambda x,y: 3*x-2*y, slowk, slowd))
# result['k']=slowk
# result['d']=slowd
# result['j']=slowj
zsindex=ZSIndex()
# 主力线，散户线
zz, ss = zsindex.zsLine(result)
mm = zsindex.convertXQH(result)
result['z'] = zz
result['s'] = ss
result['m'] = mm
#神仙趋势线
result['h1']=talib.EMA(result['close'],6)
result['h2']=talib.EMA(result['h1'],18)
result['h3']=talib.EMA(result['close'],108)
maxPrice=talib.MAX(result['close'],data)[len(result)-1]
print(maxPrice)
result.date = range(0, len(result)) # 日期改变成序号
resultTemp.append(result)
resultTemp.append(maxPrice)
return resultTemp
def T3(close, timeperiod=5, vfactor=0):
''' Triple Exponential Moving Average (T3) 三重指数移动平均线
分组: Overlap Studies 重叠研究
简介: TRIX长线操作时采用本指标的讯号，长时间按照本指标讯号交易，
获利百分比大于损失百分比，利润相当可观。 比如日线MA5指5天内的收盘价除以5 。
分析和应用: http://www.iwencai.com/yike/detail/auid/6c22c15ccbf24e64?rid=80
real = T3(close, timeperiod=5, vfactor=0)
'''
return talib.T3(close, timeperiod, vfactor)
def add_T3(self, timeperiod=20, vfactor=0.7, type="line", color="secondary", **kwargs):
"""T3 Exponential Moving Average."""
if not self.has_close:
raise Exception()
utils.kwargs_check(kwargs, VALID_TA_KWARGS)
if "kind" in kwargs:
type = kwargs["kind"]
name = "T3({}, {})".format(str(timeperiod), str(vfactor))
self.pri[name] = dict(type=type, color=color)
self.ind[name] = talib.T3(self.df[self.cl].values, timeperiod, vfactor)
def t3(close, graph=False, **kwargs):
'''
T3 - Triple Exponential Moving Average (T3)
'''
result = talib.T3(close, **kwargs)
df = pd.concat([pd.DataFrame(close), pd.DataFrame(result)], axis=1)
df.columns = ['close', 't3']
if graph:
title = 'T3 - Triple Exponential Moving Average (T3)'
style = ['r-'] + ['--'] * (len(df.columns) - 1)
fname = '14_t3.png'
make_graph(title, df, style=style, fname=fname)
return df
def test_t3(self):
result = self.overlap.t3(self.close)
self.assertIsInstance(result, Series)
self.assertEqual(result.name, 'T3_10_0.7')
try:
expected = tal.T3(self.close, 10)
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 overlap(self): upper, middle, lower = talib.BBANDS(self.close,timeperiod=5,nbdevup=2,nbdevdn=2,matype=0) EMA = talib.EMA(self.close,self.period) HT_trendline = talib.HT_TRENDLINE(self.close) KAMA = talib.KAMA(self.close,self.period) MA = talib.MA(self.close,self.period,matype=0) mama, fama = talib.MAMA(self.close,fastlimit = 0.5,slowlimit = 0.05) mavp = talib.MAVP(self.close, minperiod = 5,maxperiod = 30,matype=0) midpoint = talib.MIDPOINT(self.close,self.period) midprice = talib.MIDPRICE(self.high,self.low,self.period) sar = talib.SAR(self.high,self.low,acceleration = 0, maximum = 0) sarext = talib.SAREXT(self.high,self.low,startvalue=0,offsetonreverse=0,accelerationinitlong=0, accelerationlong=0, accelerationmaxlong=0, accelerationinitshort=0, accelerationshort=0, accelerationmaxshort=0) sma = talib.SMA(self.close,self.period) t3 = talib.T3(self.close, self.period, vfactor = 0) tema = talib.TEMA(self.close,self.period) trima = talib.TRIMA(self.close,period) wma = talib.WMA(self.close, self.period)
def test_T3(self):
class MyT3(OperatorT3):
def __init__(self, name, **kwargs):
super(MyT3, self).__init__(100, name, **kwargs)
self.env.add_operator('t3', {
'operator': MyT3,
})
string = 't3(5, 0.7, open)'
gene = self.env.parse_string(string)
self.assertRaises(IndexError, gene.eval, self.env, self.dates[98], self.dates[-1])
ser = gene.eval(self.env, self.dates[99], self.dates[99]).iloc[0]
o = self.env.get_data_value('open').values
res = []
for i, val in ser.iteritems():
res.append(talib.T3(o[:100, i], 5, 0.7)[-1] == val)
self.assertTrue(all(res))
def t3(candles: np.ndarray,
period=5,
vfactor=0,
sequential=False) -> Union[float, np.ndarray]:
"""
T3 - Triple Exponential Moving Average (T3)
:param candles: np.ndarray
:param period: int - default: 5
:param vfactor: float - default: 0
:param sequential: bool - default=False
:return: float | np.ndarray
"""
if not sequential and len(candles) > 240:
candles = candles[-240:]
res = talib.T3(candles[:, 2], timeperiod=period, vfactor=vfactor)
return res if sequential else res[-1]
def handle_data(self, kl):
self.kl = kl #.copy()
self.data['t'] = kl['t']
if self.indicator == 'ma':
#MA_Type: 0=SMA, 1=EMA, 2=WMA, 3=DEMA, 4=TEMA, 5=TRIMA, 6=KAMA, 7=MAMA, 8=T3 (Default=SMA)
self.data[col_name] = ta.MA(kl['c'], **self.params)
elif self.indicator == 'wma':
self.data[col_name] = ta.WMA(kl['c'], **self.params)
elif self.indicator == 'sma':
self.data[col_name] = ta.SMA(kl['c'], **self.params)
elif self.indicator == 'ema':
self.data[col_name] = ta.EMA(kl['c'], **self.params)
elif self.indicator == 'dema':
self.data[col_name] = ta.DEMA(kl['c'], **self.params)
elif self.indicator == 'trima':
self.data[col_name] = ta.TRIMA(kl['c'], **self.params)
elif self.indicator == 'kama':
self.data[col_name] = ta.KAMA(kl['c'], **self.params)
elif self.indicator == 't3':
self.data[col_name] = ta.T3(kl['c'],
**self.params) ##, vfactor = 0)
def t3(candles: np.ndarray,
period: int = 5,
vfactor: float = 0,
source_type: str = "close",
sequential: bool = False) -> Union[float, np.ndarray]:
"""
T3 - Triple Exponential Moving Average (T3)
:param candles: np.ndarray
:param period: int - default: 5
:param vfactor: float - default: 0
: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.T3(source, timeperiod=period, vfactor=vfactor)
return res if sequential else res[-1]
def get_df(filename):
tech = pd.read_csv(filename,index_col=0)
dclose = np.array(tech.close)
volume = np.array(tech.volume)
tech['RSI'] = ta.RSI(np.array(tech.close))
tech['OBV'] = ta.OBV(np.array(tech.close),np.array(tech.volume))
tech['NATR'] = ta.NATR(np.array(tech.high),np.array(tech.low),np.array(tech.close))
tech['upper'],tech['middle'],tech['lower'] = ta.BBANDS(np.array(tech.close), timeperiod=10, nbdevup=2, nbdevdn=2, matype=0)
tech['DEMA'] = ta.DEMA(dclose, timeperiod=30)
tech['EMA'] = ta.EMA(dclose, timeperiod=30)
tech['HT_TRENDLINE'] = ta.HT_TRENDLINE(dclose)
tech['KAMA'] = ta.KAMA(dclose, timeperiod=30)
tech['MA'] = ta.MA(dclose, timeperiod=30, matype=0)
# tech['mama'], tech['fama'] = ta.MAMA(dclose, fastlimit=0, slowlimit=0)
tech['MIDPOINT'] = ta.MIDPOINT(dclose, timeperiod=14)
tech['SMA'] = ta.SMA(dclose, timeperiod=30)
tech['T3'] = ta.T3(dclose, timeperiod=5, vfactor=0)
tech['TEMA'] = ta.TEMA(dclose, timeperiod=30)
tech['TRIMA'] = ta.TRIMA(dclose, timeperiod=30)
tech['WMA'] = ta.WMA(dclose, timeperiod=30)
tech['APO'] = ta.APO(dclose, fastperiod=12, slowperiod=26, matype=0)
tech['CMO'] = ta.CMO(dclose, timeperiod=14)
tech['macd'], tech['macdsignal'], tech['macdhist'] = ta.MACD(dclose, fastperiod=12, slowperiod=26, signalperiod=9)
tech['MOM'] = ta.MOM(dclose, timeperiod=10)
tech['PPO'] = ta.PPO(dclose, fastperiod=12, slowperiod=26, matype=0)
tech['ROC'] = ta.ROC(dclose, timeperiod=10)
tech['ROCR'] = ta.ROCR(dclose, timeperiod=10)
tech['ROCP'] = ta.ROCP(dclose, timeperiod=10)
tech['ROCR100'] = ta.ROCR100(dclose, timeperiod=10)
tech['RSI'] = ta.RSI(dclose, timeperiod=14)
tech['fastk'], tech['fastd'] = ta.STOCHRSI(dclose, timeperiod=14, fastk_period=5, fastd_period=3, fastd_matype=0)
tech['TRIX'] = ta.TRIX(dclose, timeperiod=30)
tech['OBV'] = ta.OBV(dclose,volume)
tech['HT_DCPHASE'] = ta.HT_DCPHASE(dclose)
tech['inphase'], tech['quadrature'] = ta.HT_PHASOR(dclose)
tech['sine'], tech['leadsine'] = ta.HT_SINE(dclose)
tech['HT_TRENDMODE'] = ta.HT_TRENDMODE(dclose)
df = tech.fillna(method='bfill')
return df
def getOverlapFunctions(df):
high = df['High']
low = df['Low']
close = df['Close']
open = df['Open']
volume = df['Volume']
df['UPPERBB'],df['MIDDLEBB'],df['LOWERBB'] = ta.BBANDS(close, timeperiod=5, nbdevup=2, nbdevdn=2, matype=0)
df['DEMA'] = ta.DEMA(close,timeperiod=30)
df['EMA'] = ta.EMA(close, timeperiod=30)
df['HT_TREND'] = ta.HT_TRENDLINE(close)
df['KAMA'] = ta.KAMA(close, timeperiod=30)
df['MA'] = ta.MA(close, timeperiod=30, matype=0)
#df['MAMA'],df['FAMA'] = ta.MAMA(close, fastlimit=0, slowlimit=0)
#df['MAVP'] = ta.MAVP(close, periods, minperiod=2, maxperiod=30, matype=0)
df['MIDPOINT'] = ta.MIDPOINT(close, timeperiod=14)
df['MIDPRICE'] = ta.MIDPRICE(high, low, timeperiod=14)
df['SAR'] = ta.SAR(high, low, acceleration=0, maximum=0)
df['SAREXT'] = ta.SAREXT(high, low, startvalue=0, offsetonreverse=0, accelerationinitlong=0, accelerationlong=0, accelerationmaxlong=0, accelerationinitshort=0, accelerationshort=0, accelerationmaxshort=0)
df['SMA'] = ta.SMA(close, timeperiod=30)
df['T3'] = ta.T3(close, timeperiod=5, vfactor=0)
df['TEMA'] = ta.TEMA(close, timeperiod=30)
df['TRIMA'] = ta.TRIMA(close, timeperiod=30)
df['WMA'] = ta.WMA(close, timeperiod=30)
def t3(candles: np.ndarray,
period: int = 5,
vfactor: float = 0,
source_type: str = "close",
sequential: bool = False) -> Union[float, np.ndarray]:
"""
T3 - Triple Exponential Moving Average (T3)
:param candles: np.ndarray
:param period: int - default: 5
:param vfactor: float - default: 0
: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.T3(source, timeperiod=period, vfactor=vfactor)
return res if sequential else res[-1]
def Set_indicators(data, period):
"""
:param data: dataframe containing ohlcv prices and indexed with date
:param period: period used to calculate indicators
:return: dataframe of Technical indicators of specefic timeframe
"""
df = pd.DataFrame(index=data.index)
df["mom" + str(period)] = talib.MOM(data[USED_CLOSE_PRICE],
timeperiod=period)
#change it later
df["slowk" + str(period)], df["slowd" + str(period)] = talib.STOCH(
data["High"],
data["Low"],
data[USED_CLOSE_PRICE],
fastk_period=period,
slowk_period=period,
slowk_matype=0,
slowd_period=period,
slowd_matype=0)
#WILLR
df["willr" + str(period)] = talib.WILLR(data["High"],
data["Low"],
data[USED_CLOSE_PRICE],
timeperiod=period)
#MACDFIX - Moving Average Convergence/Divergence Fix 12/26
df["macd" + str(period)], df["macdsignal" +
str(period)], df["macdhist" +
str(period)] = talib.MACDFIX(
data[USED_CLOSE_PRICE],
signalperiod=period)
#CCI
df["cci" + str(period)] = talib.CCI(data["High"],
data["Low"],
data[USED_CLOSE_PRICE],
timeperiod=period)
#Bollinger Bands
df["upperband" +
str(period)], df["middleband" +
str(period)], df["lowerband" +
str(period)] = talib.BBANDS(
data[USED_CLOSE_PRICE],
timeperiod=period,
nbdevup=2,
nbdevdn=2,
matype=0)
#HIGH SMA
df["smaHigh" + str(period)] = talib.SMA(data["High"], timeperiod=period)
# SMA Adj Prices
df["sma" + str(period)] = talib.SMA(data[USED_CLOSE_PRICE],
timeperiod=period)
df["smaHighLow" + str(period)] = talib.SMA(talib.MEDPRICE(
data["High"], data["Low"]),
timeperiod=period)
#DEMA - Double Exponential Moving Average
df["DEMA" + str(period)] = talib.DEMA(data[USED_CLOSE_PRICE],
timeperiod=period)
#EMA - Exponential Moving Average
df["EMA" + str(period)] = talib.EMA(data[USED_CLOSE_PRICE],
timeperiod=period)
#HT_TRENDLINE - Hilbert Transform - Instantaneous Trendline
df["HT_TRENDLINE" + str(period)] = talib.HT_TRENDLINE(
data[USED_CLOSE_PRICE])
#KAMA - Kaufman Adaptive Moving Average
df["KAMA" + str(period)] = talib.KAMA(data[USED_CLOSE_PRICE],
timeperiod=period)
#T3 - Triple Exponential Moving Average (T3)
df["T3-" + str(period)] = talib.T3(data[USED_CLOSE_PRICE],
timeperiod=period,
vfactor=0)
#TEMA - Triple Exponential Moving Average
df["TEMA" + str(period)] = talib.TEMA(data[USED_CLOSE_PRICE],
timeperiod=period)
#TRIMA - Triangular Moving Average
df["TRIMA" + str(period)] = talib.TRIMA(data[USED_CLOSE_PRICE],
timeperiod=period)
#WMA - Weighted Moving Average
df["TRIMA" + str(period)] = talib.WMA(data[USED_CLOSE_PRICE],
timeperiod=period)
##########
#ADX - Average Directional Movement Index
df["ADX" + str(period)] = talib.ADX(data["High"],
data["Low"],
data[USED_CLOSE_PRICE],
timeperiod=period)
#ADXR - Average Directional Movement Index Rating
df["ADXR" + str(period)] = talib.ADXR(data["High"],
data["Low"],
data[USED_CLOSE_PRICE],
timeperiod=period)
#AROON - Aroon
df["aroondown" + str(period)], df["aroonup" + str(period)] = talib.AROON(
data["High"], data["Low"], timeperiod=period)
#AROONOSC - Aroon Oscillator
df["aroondown" + str(period)] = talib.AROONOSC(data["High"],
data["Low"],
timeperiod=period)
#CMO - Chande Momentum Oscillator
df["CMO" + str(period)] = talib.CMO(data[USED_CLOSE_PRICE],
timeperiod=period)
#DX - Directional Movement Index
df["DX" + str(period)] = talib.DX(data["High"],
data["Low"],
data[USED_CLOSE_PRICE],
timeperiod=period)
#MINUS_DI - Minus Directional Indicator
df["MINUS_DI" + str(period)] = talib.MINUS_DI(data["High"],
data["Low"],
data[USED_CLOSE_PRICE],
timeperiod=period)
#MINUS_DM - Minus Directional Movement
df["MINUS_DM" + str(period)] = talib.MINUS_DM(data["High"],
data["Low"],
timeperiod=period)
#PLUS_DI - Plus Directional Indicator
df["PLUS_DI" + str(period)] = talib.PLUS_DI(data["High"],
data["Low"],
data[USED_CLOSE_PRICE],
timeperiod=period)
#PLUS_DM - Plus Directional Movement
df["PLUS_DM" + str(period)] = talib.PLUS_DM(data["High"],
data["Low"],
timeperiod=period)
#ROC - Rate of change : ((price/prevPrice)-1)*100
df["roc" + str(period)] = talib.ROC(data[USED_CLOSE_PRICE],
timeperiod=period)
#ROCP - Rate of change Percentage: (price-prevPrice)/prevPrice
df["ROCP" + str(period)] = talib.ROCP(data[USED_CLOSE_PRICE],
timeperiod=period)
#ROCR - Rate of change ratio: (price/prevPrice)
df["ROCR" + str(period)] = talib.ROCR(data[USED_CLOSE_PRICE],
timeperiod=period)
#ROCR100 - Rate of change ratio 100 scale: (price/prevPrice)*100
df["ROCR100-" + str(period)] = talib.ROCR100(data[USED_CLOSE_PRICE],
timeperiod=period)
#RSI - Relative Strength Index
df["RSI-" + str(period)] = talib.RSI(data[USED_CLOSE_PRICE],
timeperiod=period)
#TRIX - 1-day Rate-Of-Change (ROC) of a Triple Smooth EMA
df["TRIX" + str(period)] = talib.TRIX(data[USED_CLOSE_PRICE],
timeperiod=period)
#MFI - Money Flow Index
df["MFI" + str(period)] = talib.MFI(data["High"],
data["Low"],
data[USED_CLOSE_PRICE],
data["Volume"],
timeperiod=period)
#ADOSC - Chaikin A/D Oscillator set periods later please
df["ADOSC" + str(period)] = talib.ADOSC(data["High"],
data["Low"],
data[USED_CLOSE_PRICE],
data["Volume"],
fastperiod=np.round(period / 3),
slowperiod=period)
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 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_T3(close, timeperiod=5, vfactor=0.7):
'''00386,3,1'''
return talib.T3(close, timeperiod, vfactor)
def handle_overlap_studies(args, kax, klines_df, close_times, display_count):
all_name = ""
if args.ABANDS: # ATR BANDS
name = 'ABANDS'
real = talib.ATR(klines_df["high"],
klines_df["low"],
klines_df["close"],
timeperiod=14)
emas = talib.EMA(klines_df["close"], timeperiod=26)
kax.plot(close_times, emas[-display_count:], "b--", label=name)
#cs = ['y', 'c', 'm', 'k']
for idx, n in enumerate(args.ABANDS):
"""
if idx >= len(cs):
break
c = cs[idx]
"""
c = 'y'
cl = c + '--'
n = int(n)
kax.plot(close_times, (emas + n * real)[-display_count:],
cl,
label=name + ' upperband')
kax.plot(close_times, (emas - n * real)[-display_count:],
cl,
label=name + ' lowerband')
if args.BANDS: # BANDS
name = 'BANDS'
emas = talib.EMA(klines_df["close"], timeperiod=26)
kax.plot(close_times, emas[-display_count:], "b--", label=name)
r = args.BANDS
kax.plot(close_times, (1 + r) * emas[-display_count:],
'y--',
label=name + ' upperband')
kax.plot(close_times, (1 - r) * emas[-display_count:],
'y--',
label=name + ' lowerband')
# talib
os_key = 'BBANDS'
if args.BBANDS:
upperband, middleband, lowerband = talib.BBANDS(klines_df["close"],
timeperiod=5,
nbdevup=2,
nbdevdn=2,
matype=0)
kax.plot(close_times,
upperband[-display_count:],
"y",
label=os_key + ' upperband')
kax.plot(close_times,
middleband[-display_count:],
"b",
label=os_key + ' middleband')
kax.plot(close_times,
lowerband[-display_count:],
"y",
label=os_key + ' lowerband')
os_key = 'DEMA'
if args.DEMA:
real = talib.DEMA(klines_df["close"], timeperiod=args.DEMA)
kax.plot(close_times, real[-display_count:], "y", label=os_key)
if args.EMA:
name = 'EMA'
all_name += " %s%s" % (name, args.EMA)
for idx, e_p in enumerate(args.EMA):
if idx >= len(plot_colors):
break
e_p = int(e_p)
emas = talib.EMA(klines_df["close"], timeperiod=e_p)
kax.plot(close_times,
emas[-display_count:],
plot_colors[idx] + '--',
label="%sEMA" % (e_p))
os_key = 'HT_TRENDLINE'
if args.HT_TRENDLINE:
real = talib.HT_TRENDLINE(klines_df["close"])
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'KAMA'
if args.KAMA:
real = talib.KAMA(klines_df["close"], timeperiod=args.KAMA)
kax.plot(close_times, real[-display_count:], "y", label=os_key)
if args.MA:
name = 'MA'
all_name += " %s%s" % (name, args.MA)
for idx, e_p in enumerate(args.MA):
if idx >= len(plot_colors):
break
e_p = int(e_p)
emas = talib.MA(klines_df["close"], timeperiod=e_p)
kax.plot(close_times,
emas[-display_count:],
plot_colors[idx],
label="%sMA" % (e_p))
os_key = 'MAMA'
if args.MAMA:
mama, fama = talib.MAMA(klines_df["close"], fastlimit=0, slowlimit=0)
kax.plot(close_times, mama[-display_count:], "b", label=os_key)
kax.plot(close_times, fama[-display_count:], "c", label=os_key)
os_key = 'MIDPOINT'
if args.MIDPOINT:
real = talib.MIDPOINT(klines_df["close"], timeperiod=args.MIDPOINT)
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'MIDPRICE'
if args.MIDPRICE:
real = talib.MIDPRICE(klines_df["high"],
klines_df["low"],
timeperiod=args.MIDPRICE)
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'SAR'
if args.SAR:
real = talib.SAR(klines_df["high"],
klines_df["low"],
acceleration=0,
maximum=0)
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'SAREXT'
if args.SAREXT:
real = talib.SAREXT(klines_df["high"],
klines_df["low"],
startvalue=0,
offsetonreverse=0,
accelerationinitlong=0,
accelerationlong=0,
accelerationmaxlong=0,
accelerationinitshort=0,
accelerationshort=0,
accelerationmaxshort=0)
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'SMA'
if args.SMA:
real = talib.SMA(klines_df["close"], timeperiod=args.SMA)
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'T3'
if args.T3:
real = talib.T3(klines_df["close"], timeperiod=args.T3, vfactor=0)
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'TEMA'
if args.TEMA:
real = talib.TEMA(klines_df["close"], timeperiod=args.TEMA)
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'TRIMA'
if args.TRIMA:
real = talib.TRIMA(klines_df["close"], timeperiod=args.TRIMA)
kax.plot(close_times, real[-display_count:], "y", label=os_key)
os_key = 'WMA'
if args.WMA:
real = talib.WMA(klines_df["close"], timeperiod=args.WMA)
kax.plot(close_times, real[-display_count:], "y", label=os_key)
return all_name
acceleration=0,
maximum=0)
df['SAREXT'] = ta.SAREXT(np.array(df['High'].shift(1)),
np.array(df['Low'].shift(1)),
startvalue=0,
offsetonreverse=0,
accelerationinitlong=0,
accelerationlong=0,
accelerationmaxlong=0,
accelerationinitshort=0,
accelerationshort=0,
accelerationmaxshort=0)
df['SMA'] = ta.SMA(np.array(df['Adj Close'].shift(1)), timeperiod=n)
df['T3'] = ta.T3(np.array(df['Adj Close'].shift(1)), timeperiod=n, vfactor=0)
df['TEMA'] = ta.TEMA(np.array(df['Adj Close'].shift(1)), timeperiod=n)
df['TRIMA'] = ta.TRIMA(np.array(df['Adj Close'].shift(1)), timeperiod=n)
df['WMA'] = ta.WMA(np.array(df['Adj Close'].shift(1)), timeperiod=n)
df['20d_ma'] = df['Adj Close'].shift(1).rolling(window=20).mean()
df['50d_ma'] = df['Adj Close'].shift(1).rolling(window=50).mean()
df['Bol_upper'] = df['Adj Close'].shift(1).rolling(
window=20).mean() + 2 * df['Adj Close'].shift(1).rolling(window=20).std()
df['Bol_lower'] = df['Adj Close'].shift(1).rolling(
window=20).mean() - 2 * df['Adj Close'].shift(1).rolling(window=20).std()
df['Bol_BW'] = ((df['Bol_upper'] - df['Bol_lower']) / df['20d_ma']) * 100
df['Bol_BW_200MA'] = df['Bol_BW'].shift(1).rolling(window=50).mean()
df['Bol_BW_200MA'] = df['Bol_BW_200MA'].fillna(method='backfill')
# df['20d_ewma'] = df['Adj Close'].shift(1).ewm(span=20).mean()
# df['50d_ewma'] = df['Adj Close'].shift(1).ewm(span=50).mean()
def talib_T3(DataFrame, N=5, vfactor=0):
res = talib.T3(DataFrame.close.values, timeperiod=N, vfactor=vfactor)
return pd.DataFrame({'T3': res}, index=DataFrame.index)
def T3(raw_df, timeperiod=5, vfactor=0):
# extract necessary data from raw dataframe (close)
return ta.T3(raw_df.Close.values, timeperiod, vfactor)
df[col + '_fastd'] = slowd
df[col + '_WILLR'] = tl.WILLR(high, low, close)
aroondown, aroonup = tl.AROON(high, low)
df[col + '_aroondown'] = aroondown
df[col + '_aroonup'] = aroonup
#miss true strength index
df[col + '_SMA'] = tl.SMA(close)
df[col + '_EMA'] = tl.EMA(close)
macd, macdsignal, macdhist = tl.MACD(close)
df[col + '_macd'] = macd
df[col + '_macdsignal'] = macdsignal
df[col + '_macdhist'] = macdhist
df[col + '_ADX'] = tl.ADX(high, low, close)
#MACD,ADX are Momentum indicators
df[col + '_T3'] = tl.T3(close)
df[col + '_OBV'] = tl.OBV(close, volume)
df[col + '_MFI'] = tl.MFI(high, low, close, volume)
#MFI are Momentum indicators
df[col + '_ADOSC'] = tl.ADOSC(high, low, close, volume)
upperband, middleband, lowerband = tl.BBANDS(close)
df[col + '_upperband'] = upperband
df[col + '_middleband'] = middleband
df[col + '_lowerband'] = lowerband
df[col + '_ATR'] = tl.ATR(high, low, close)
window = 3
ret = df[col + '_returns']
df['Y1'] = (ret < 0).replace(True, 1)
closeprice = criptomoeda_close.iloc[-1]
cci = talib.CCI(criptomoeda_maxima,
criptomoeda_minima,
criptomoeda_close,
timeperiod=14)
atr = talib.ATR(criptomoeda_maxima,
criptomoeda_minima,
criptomoeda_close,
timeperiod=14)
midpoint = talib.MIDPOINT(criptomoeda_close, timeperiod=30)
sma6 = talib.SMA(criptomoeda_close, timeperiod=6)
sma9 = talib.SMA(criptomoeda_close, timeperiod=9)
real = talib.T3(criptomoeda_close, timeperiod=14)
print('Close Price: $%.2f' % (closeprice))
# Média movel de 14 dias do Fechamento
criptomoeda_fechamento_mediamovel = criptomoeda['c'].rolling(30).mean()
# Média movel de 30 dias do Fechamento
criptomoeda_fechamento_mediamovel100 = criptomoeda['c'].rolling(100).mean()
#======== Importar biblioteca SKLEARN
import numpy as np
from sklearn import linear_model
from sklearn.metrics import mean_squared_error, r2_score
from matplotlib import rcParams
#=========
criptomoeda_regressao = criptomoeda_abertura
#========= Treinar X
criptomoeda_X_train = criptomoeda_abertura
criptomoeda_X_test = criptomoeda_abertura
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 showK(self, code, result, isShow, savePath):
savePath = savePath.strip() + "\\temp"
self.savePath = savePath.rstrip("\\")
self.isShow = isShow
self.code = code
t3Price = talib.T3(result['close'], timeperiod=30, vfactor=0)
self.date_tickers = result.date.values
result.date = range(0, len(result)) # 日期改变成序号
self.matix = result.values # 转换成绘制蜡烛图需要的数据格式(date, open, close, high, low, volume)
xdates = self.matix[:, 0] # X轴数据(这里用的天数索引)
if isShow:
# 设置外观效果
plt.rc('font', family='Microsoft YaHei') # 用中文字体，防止中文显示不出来
plt.rc('figure', fc='k') # 绘图对象背景图
plt.rc('text', c='#800000') # 文本颜色
plt.rc(
'axes',
axisbelow=True,
xmargin=0,
fc='k',
ec='#800000',
lw=1.5,
labelcolor='#800000',
unicode_minus=False) # 坐标轴属性(置底，左边无空隙，背景色，边框色，线宽，文本颜色，中文负号修正)
plt.rc('xtick', c='#d43221') # x轴刻度文字颜色
plt.rc('ytick', c='#d43221') # y轴刻度文字颜色
plt.rc('grid', c='#800000', alpha=0.9, ls=':',
lw=0.8) # 网格属性(颜色，透明值，线条样式，线宽)
plt.rc('lines', lw=0.8) # 全局线宽
fig = plt.figure(figsize=(16, 8))
left, width = 0.05, 0.9
self.ax1 = fig.add_axes([left, 0.5, width,
0.48]) # left, bottom, width, height
self.ax2 = fig.add_axes([left, 0.4, width, 0.1],
sharex=self.ax1) # 共享ax1轴
self.ax3 = fig.add_axes([left, 0.3, width, 0.09],
sharex=self.ax1) # 共享ax1轴
self.ax4 = fig.add_axes([left, 0.2, width, 0.09],
sharex=self.ax1) # 共享ax1轴
self.ax5 = fig.add_axes([left, 0.1, width, 0.09],
sharex=self.ax1) # 共享ax1轴
plt.setp(self.ax1.get_xticklabels(),
visible=True) # 使x轴刻度文本不可见，因为共享，不需要显示
plt.setp(self.ax2.get_xticklabels(),
visible=True) # 使x轴刻度文本不可见，因为共享，不需要显示
self.ax1.xaxis.set_major_formatter(
ticker.FuncFormatter(self.format_date)) # 设置自定义x轴格式化日期函数
self.ax1.xaxis.set_major_locator(
ticker.MultipleLocator(max(int(len(result) / 15),
5))) # 横向最多排15个左右的日期，最少5个，防止日期太拥挤
# # 下面这一段代码，替换了上面注释的这个函数，因为上面的这个函数达不到同花顺的效果
opens, closes, highs, lows = self.matix[:,
1], self.matix[:,
4], self.matix[:,
2], self.matix[:,
3] # 取出ochl值
avg_dist_between_points = (xdates[-1] - xdates[0]) / float(
len(xdates)) # 计算每个日期之间的距离
delta = avg_dist_between_points / 4.0 # 用于K线实体(矩形)的偏移坐标计算
barVerts = [((date - delta, open), (date - delta, close),
(date + delta, close), (date + delta, open))
for date, open, close in zip(xdates, opens, closes)
] # 生成K线实体(矩形)的4个顶点坐标
rangeSegLow = [
((date, low), (date, min(open, close)))
for date, low, open, close in zip(xdates, lows, opens, closes)
] # 生成下影线顶点列表
rangeSegHigh = [((date, high), (date, max(open, close)))
for date, high, open, close in zip(
xdates, highs, opens, closes)] # 生成上影线顶点列表
rangeSegments = rangeSegLow + rangeSegHigh # 上下影线顶点列表
cmap = {
True: mcolors.to_rgba('#000000', 1.0),
False: mcolors.to_rgba('#54fcfc', 1.0)
} # K线实体(矩形)中间的背景色(True是上涨颜色，False是下跌颜色)
inner_colors = [
cmap[opn < cls] for opn, cls in zip(opens, closes)
] # K线实体(矩形)中间的背景色列表
cmap = {
True: mcolors.to_rgba('#ff3232', 1.0),
False: mcolors.to_rgba('#54fcfc', 1.0)
} # K线实体(矩形)边框线颜色(上下影线和后面的成交量颜色也共用)
updown_colors = [
cmap[opn < cls] for opn, cls in zip(opens, closes)
] # K线实体(矩形)边框线颜色(上下影线和后面的成交量颜色也共用)列表
#
self.ax1.add_collection(
LineCollection(rangeSegments,
colors=updown_colors,
linewidths=0.5,
antialiaseds=False))
# 生成上下影线的顶点数据(颜色，线宽，反锯齿，反锯齿关闭好像没效果)
self.ax1.add_collection(
PolyCollection(barVerts,
facecolors=inner_colors,
edgecolors=updown_colors,
antialiaseds=False,
linewidths=0.5))
# 生成多边形(矩形)顶点数据(背景填充色，边框色，反锯齿，线宽)
# 绘制均线
mav_colors = [
'#ffffff', '#d4ff07', '#ff80ff', '#00e600', '#02e2f4',
'#ffffb9', '#2a6848'
] # 均线循环颜色
mav_period = [5, 10, 20, 30, 60, 120, 180] # 定义要绘制的均线周期，可增减
n = len(result)
for i in range(len(mav_period)):
if n >= mav_period[i]:
mav_vals = result['close'].rolling(
mav_period[i]).mean().values
self.ax1.plot(xdates,
mav_vals,
c=mav_colors[i % len(mav_colors)],
label='MA' + str(mav_period[i]))
# 线性回归展示
# for item in erChengPrice:
# myX=item[0]
# myY=item[1]
# ax1.plot(myX, myY, color="yellow", linewidth=0.3)
self.ax1.plot(xdates, t3Price, label='t3price')
self.ax1.set_title(code) # 标题
self.ax1.grid(True) # 画网格
self.ax1.legend(loc='upper left') # 图例放置于右上角
self.ax1.xaxis_date() # 好像要不要效果一样？
return
