def acceptCandle(self, candle):
'''
accepts a candle and updates current state of strategy to determine buy/sell
'''
self.addCandle(candle)
macd = MACD(self.candleDf['C'])
# print(macd.macd().iloc[-1], macd.macd_signal().iloc[-1], macd.macd_diff().iloc[-1], macd.macd().iloc[-1] - macd.macd_signal().iloc()[-1])
if macd.macd_diff().iloc[-1] >= 0 and macd.macd_diff().iloc[-2] < 0:
self.buy(0.05 * self.capital)
elif macd.macd_diff().iloc[-1] <= 0 and macd.macd_diff().iloc[-2] > 0:
self.sell()
def __init__(self):
dfr['EMA_12'] = EMAIndicator(close=dfr['close'], n=9,
fillna=True).ema_indicator()
dfr['EMA_26'] = EMAIndicator(close=dfr['close'], n=26,
fillna=True).ema_indicator()
MACD = MACD(close=dfr['close'])
dfr['MACD'] = dfr['EMA_12'] - dfr['EMA_26']
dfr['MACD2'] = MACD.macd()
dfr['MACD_Signal'] = EMAIndicator(close=dfr['MACD'],
n=9).ema_indicator()
dfr['MACD_Signal2'] = MACD.macd_signal()
dfr['MACD_HIST'] = dfr['MACD'] - dfr['MACD_Signal']
dfr['MACD_HIST2'] = MACD.macd_diff()
new_col = 'MACD_HIST_TYPE'
new_col2 = 'MACD_HIST_TYPE2'
nr = dfr.shape[0]
dfr[new_col] = np.empty(nr)
for k in range(1, nr):
i1 = dfr.index.values[k - 1]
i = dfr.index.values[k]
if dfr.loc[i, 'MACD_HIST'] > 0 and dfr.loc[i1, 'MACD_HIST'] < 0:
dfr.loc[i, new_col] = 1 # Cross over
dfr.loc[i, new_col2] = 1 # Cross over
if i not in long_asset_list.keys():
tlist = []
tlist.append(table_name)
long_asset_list[i] = tlist
elif dfr.loc[i, 'MACD_HIST'] > 0 and dfr.loc[
i, 'MACD_HIST'] > dfr.loc[i1, 'MACD_HIST']:
dfr.loc[i, new_col] = 2 # Col grow above
dfr.loc[i, new_col2] = 2 # Cross over
elif dfr.loc[i, 'MACD_HIST'] > 0 and dfr.loc[
i, 'MACD_HIST'] < dfr.loc[i1, 'MACD_HIST']:
dfr.loc[i, new_col] = 3 # Col fall above
dfr.loc[i, new_col2] = 3 # Cross over
elif dfr.loc[i, 'MACD_HIST'] < 0 and dfr.loc[i1,
'MACD_HIST'] > 0:
a = (i, table_name)
dfr.loc[i, new_col] = -1 # Cross over
dfr.loc[i, new_col2] = -1 # Cross over
if i not in short_asset_list.keys():
tlist = []
tlist.append(table_name)
short_asset_list[i] = tlist
else:
short_asset_list[i].append(table_name)
elif dfr.loc[i, 'MACD_HIST'] < 0 and dfr.loc[
i, 'MACD_HIST'] < dfr.loc[i1, 'MACD_HIST']:
dfr.loc[i, new_col] = -2 # Col fall above
dfr.loc[i, new_col2] = -2 # Cross over
elif dfr.loc[i, 'MACD_HIST'] < 0 and dfr.loc[
i, 'MACD_HIST'] > dfr.loc[i1, 'MACD_HIST']:
dfr.loc[i, new_col] = -3 # Cross under
dfr.loc[i, new_col2] = -3 # Cross over
else:
dfr.loc[i, new_col] = 0
dfr.loc[i, new_col2] = 0 # Cross over
def init(self, base_data):
base_data = base_data.sort_values("date")
macd = MACD(close=base_data["close"], n_slow=26, n_fast=12, n_sign=9)
base_data["macd_diff"] = macd.macd_diff()
base_data["macd_signal"] = macd.macd_signal()
base_data["fs_dif"] = base_data["macd_diff"] - base_data["macd_signal"]
base_data["bool_signal"] = base_data["fs_dif"].map(
lambda x: 1 if x > 0 else -1
)
base_data["bool_signal_shift1"] = base_data["bool_signal"].shift(1)
base_data["signal"] = 0
base_data.loc[
(
(base_data["bool_signal"] > 0)
& (base_data["bool_signal_shift1"] < 0)
),
"signal",
] = 1
base_data.loc[
(
(base_data["bool_signal"] < 0)
& (base_data["bool_signal_shift1"] > 0)
),
"signal",
] = -1
base_data.index = range(len(base_data))
return base_data
def get_MACD_Indicator(self, col='Close', fillna=False):
"""
get MACD Indicator
"""
stock_MACD = MACD(self.df[col], fillna=fillna)
self.df['MACD'] = stock_MACD.macd()
self.df['MACD_signal'] = stock_MACD.macd_signal()
self.df['MACD_diff'] = stock_MACD.macd_diff()
def acceptCandle(self, candle):
'''
accepts a candle and updates current state of strategy to determine buy/sell
'''
self.addCandle(candle)
macd = MACD(self.candleDf['C'], 20, 6, 5)
rsi = RSIIndicator(self.candleDf['C'], 8)
prevRsi = rsi.rsi().iloc[-2]
currentRsi = rsi.rsi().iloc[-1]
# print(macd.macd().iloc[-1], macd.macd_signal().iloc[-1], macd.macd_diff().iloc[-1], macd.macd().iloc[-1] - macd.macd_signal().iloc()[-1])
if macd.macd_diff().iloc[-1] >= 0 and macd.macd_diff().iloc[-2] < 0\
and currentRsi >= self.oversold and prevRsi < self.oversold:
self.buy(0.05 * self.capital)
elif macd.macd_diff().iloc[-1] <= 0 and macd.macd_diff().iloc[-2] > 0\
and currentRsi <= self.overbought and prevRsi > self.overbought:
self.sell()
def ta_macd(df):
"""
Moving Average Convergence Divergence (MACD) calculation.
:param df: pandas dataframe
:return: pandas dataframe
"""
temp_df = df.copy()
temp = MACD(close=temp_df["Close"], fillna=False)
# temp = MACD(close=temp_df["Close"], window_slow=26, window_fast=12, window_sign=9, fillna=True)
temp_df["macd"] = temp.macd()
temp_df["macd_diff"] = temp.macd_diff()
temp_df["macd_signal"] = temp.macd_signal()
return temp_df
def action(self, indicator):
# Derive the action based on past data
# action: 1 means buy, -1 means sell, 0 means do nothing
close = indicator['c']
macd = MACD(close=close,
n_slow=self.parameters['ema26'],
n_fast=self.parameters['ema12'],
n_sign=self.parameters['ema9'])
indicator['trend_macd'] = macd.macd()
indicator['trend_macd_signal'] = macd.macd_signal()
indicator['trend_macd_diff'] = macd.macd_diff()
indicator['trend_macd_diff_prev'] = indicator['trend_macd_diff'].shift(1)
indicator['action'] = (np.sign(indicator['trend_macd_diff']) \
- np.sign(indicator['trend_macd_diff_prev'])) / 2
def get_macd(config, company):
close_prices = company.prices
dataframe = company.technical_indicators
window_slow = 26
signal = 9
window_fast = 12
macd = MACD(company.prices, window_slow, window_fast, signal)
dataframe['MACD'] = macd.macd()
dataframe['MACD_Histogram'] = macd.macd_diff()
dataframe['MACD_Signal'] = macd.macd_signal()
generate_buy_sell_signals(
lambda x, dataframe: dataframe['MACD'].values[x] < dataframe[
'MACD_Signal'].iloc[x], lambda x, dataframe: dataframe['MACD'].
values[x] > dataframe['MACD_Signal'].iloc[x], dataframe, 'MACD')
return dataframe
def action(self, indicator):
# Derive the action based on past data
# action: 1 means buy, -1 means sell, 0 means do nothing
close = indicator["c"]
macd = MACD(
close=close,
n_slow=self.parameters["ema26"],
n_fast=self.parameters["ema12"],
n_sign=self.parameters["ema9"],
)
indicator["trend_macd"] = macd.macd()
indicator["trend_macd_signal"] = macd.macd_signal()
indicator["trend_macd_diff"] = macd.macd_diff()
indicator["trend_macd_diff_prev"] = indicator["trend_macd_diff"].shift(
1)
indicator["action"] = (np.sign(indicator["trend_macd_diff"]) -
np.sign(indicator["trend_macd_diff_prev"])) / 2
def get_signal(self, input_df, ticker, run_id):
df = input_df.copy()
indicator_macd = MACD(
close=df["Close"],
window_slow=self.indicator["window_slow"],
window_fast=self.indicator["window_fast"],
window_sign=self.indicator["window_sign"],
fillna=self.indicator["fillna"],
)
# Add Bollinger Bands features
df["macd"] = indicator_macd.macd()
df["macd_signal"] = indicator_macd.macd_signal()
df["macd_diff"] = indicator_macd.macd_diff()
previous_row = df.iloc[-2]
row = df.iloc[-1]
if (row.macd_diff.item() < 0) and (previous_row.macd_diff.item() > 0):
sell_signal = {
"ticker": ticker,
"datetime": row.Date,
"indicator": self.name,
"param": self.param,
"reason": "MACD Downward Crossover",
"image": self.draw_image(df, ticker, run_id),
}
else:
sell_signal = None
if (previous_row.macd_diff.item() < 0) and (row.macd_diff.item() > 0):
buy_signal = {
"ticker": ticker,
"datetime": row.Date,
"indicator": self.name,
"param": self.param,
"reason": "MACD Upward Crossover",
"image": self.draw_image(df, ticker, run_id),
}
else:
buy_signal = None
return buy_signal, sell_signal
def create_trade_sign(self, stock_price: pd.DataFrame) -> pd.DataFrame:
stock_price = stock_price.sort_values("date")
macd = MACD(close=stock_price["close"], n_slow=26, n_fast=12, n_sign=9)
stock_price["macd_diff"] = macd.macd_diff()
stock_price["macd_signal"] = macd.macd_signal()
stock_price["fs_dif"] = (stock_price["macd_diff"] -
stock_price["macd_signal"])
stock_price["bool_signal"] = stock_price["fs_dif"].map(
lambda x: 1 if x > 0 else -1)
stock_price["bool_signal_shift1"] = stock_price["bool_signal"].shift(1)
stock_price["signal"] = 0
stock_price.loc[((stock_price["bool_signal"] > 0)
& (stock_price["bool_signal_shift1"] < 0)),
"signal", ] = 1
stock_price.loc[((stock_price["bool_signal"] < 0)
& (stock_price["bool_signal_shift1"] > 0)),
"signal", ] = -1
stock_price.index = range(len(stock_price))
return stock_price
def create_trade_sign(self, stock_price: pd.DataFrame) -> pd.DataFrame:
stock_price = stock_price.sort_values("date")
macd = MACD(close=stock_price["close"], n_slow=26, n_fast=12, n_sign=9)
stock_price["DIF"] = macd.macd_diff()
stock_price["MACD"] = macd.macd_signal()
stock_price["OSC"] = stock_price["DIF"] - stock_price["MACD"]
stock_price["OSC_signal"] = stock_price["OSC"].map(lambda x: 1
if x > 0 else -1)
stock_price["OSC_signal_yesterday"] = stock_price["OSC_signal"].shift(
1)
stock_price["signal"] = 0
stock_price.loc[((stock_price["OSC_signal"] > 0)
& (stock_price["OSC_signal_yesterday"] < 0)),
"signal", ] = 1 # 下而上穿過
stock_price.loc[((stock_price["OSC_signal"] < 0)
& (stock_price["OSC_signal_yesterday"] > 0)),
"signal", ] = -1 # 上而下穿過
stock_price.index = range(len(stock_price))
return stock_price
def add_trend_indicators(data: pd.DataFrame) -> pd.DataFrame:
"""Adds the trend indicators.
Parameters
----------
data : pd.DataFrame
A dataframe with daily stock values. Must include: open, high,
low, close and volume. It should also be sorted in a descending
manner.
Returns
-------
pd.DataFrame
The input dataframe with the indicators added.
"""
adx = ADXIndicator(data['high'], data['low'], data['close'])
ema = EMAIndicator(data['close'])
ema_200 = EMAIndicator(data['close'], n=200)
ichimoku = IchimokuIndicator(data['high'], data['low'])
macd = MACD(data['close'])
sma = SMAIndicator(data['close'], n=14)
sma_200 = SMAIndicator(data['close'], n=200)
data.loc[:, 'adx'] = adx.adx()
data.loc[:, 'adx_pos'] = adx.adx_pos()
data.loc[:, 'adx_neg'] = adx.adx_neg()
data.loc[:, 'ema'] = ema.ema_indicator()
data.loc[:, 'ema_200'] = ema_200.ema_indicator()
data.loc[:, 'ichimoku_a'] = ichimoku.ichimoku_a()
data.loc[:, 'ichimoku_b'] = ichimoku.ichimoku_b()
data.loc[:, 'ichimoku_base_line'] = ichimoku.ichimoku_base_line()
data.loc[:, 'ichimoku_conversion_line'] = (
ichimoku.ichimoku_conversion_line())
data.loc[:, 'macd'] = macd.macd()
data.loc[:, 'macd_diff'] = macd.macd_diff()
data.loc[:, 'macd_signal'] = macd.macd_signal()
data.loc[:, 'sma'] = sma.sma_indicator()
data.loc[:, 'sma_200'] = sma_200.sma_indicator()
return data
def macd(df):
indicator_macd = MACD(close=df["Close"])
df['macd'] = indicator_macd.macd()
df['macd_diff'] = indicator_macd.macd_diff()
df['macd_signal'] = indicator_macd.macd_signal()
def _macd(self, df, close):
macd = MACD(close=close)
df['macd'] = macd.macd()
df['macd_signal'] = macd.macd_signal()
df['macd_diff'] = macd.macd_diff()
def handle(self, *args, **options):
# import pdb
# pdb.set_trace()
if not options['update']:
NSETechnical.objects.all().delete()
symbols = Symbol.objects.all()
for symbol in symbols:
nse_history_data = NSEHistoricalData.objects.filter(
symbol__symbol_name=symbol).order_by('timestamp')
if not nse_history_data:
continue
nse_technical = pd.DataFrame(
list(
nse_history_data.values('timestamp', 'open', 'high', 'low',
'close', 'total_traded_quantity')))
'''
Moving average convergence divergence
'''
indicator_macd = MACD(close=nse_technical['close'],
window_slow=26,
window_fast=12,
window_sign=9,
fillna=False)
nse_technical["trend_macd"] = indicator_macd.macd()
nse_technical["trend_macd_signal"] = indicator_macd.macd_signal()
nse_technical["trend_macd_diff"] = indicator_macd.macd_diff()
'''
Simple Moving Average
'''
nse_technical["trend_sma_fast"] = SMAIndicator(
close=nse_technical['close'], window=12,
fillna=False).sma_indicator()
nse_technical["trend_sma_slow"] = SMAIndicator(
close=nse_technical['close'], window=26,
fillna=False).sma_indicator()
'''
Exponential Moving Average
'''
nse_technical["trend_ema_fast"] = EMAIndicator(
close=nse_technical['close'], window=12,
fillna=False).ema_indicator()
nse_technical["trend_ema_slow"] = EMAIndicator(
close=nse_technical['close'], window=26,
fillna=False).ema_indicator()
'''
Ichimoku Indicator
'''
indicator_ichi = IchimokuIndicator(
high=nse_technical['high'],
low=nse_technical['low'],
window1=9,
window2=26,
window3=52,
visual=False,
fillna=False,
)
nse_technical[
"trend_ichimoku_conv"] = indicator_ichi.ichimoku_conversion_line(
)
nse_technical[
"trend_ichimoku_base"] = indicator_ichi.ichimoku_base_line()
nse_technical["trend_ichimoku_a"] = indicator_ichi.ichimoku_a()
nse_technical["trend_ichimoku_b"] = indicator_ichi.ichimoku_b()
indicator_ichi_visual = IchimokuIndicator(
high=nse_technical['high'],
low=nse_technical['low'],
window1=9,
window2=26,
window3=52,
visual=True,
fillna=False,
)
nse_technical[
"trend_visual_ichimoku_a"] = indicator_ichi_visual.ichimoku_a(
)
nse_technical[
"trend_visual_ichimoku_b"] = indicator_ichi_visual.ichimoku_b(
)
'''
Bollinger Band
'''
indicator_bb = BollingerBands(close=nse_technical['close'],
window=20,
window_dev=2,
fillna=False)
nse_technical["volatility_bbm"] = indicator_bb.bollinger_mavg()
nse_technical["volatility_bbh"] = indicator_bb.bollinger_hband()
nse_technical["volatility_bbl"] = indicator_bb.bollinger_lband()
nse_technical["volatility_bbw"] = indicator_bb.bollinger_wband()
nse_technical["volatility_bbp"] = indicator_bb.bollinger_pband()
nse_technical[
"volatility_bbhi"] = indicator_bb.bollinger_hband_indicator()
nse_technical[
"volatility_bbli"] = indicator_bb.bollinger_lband_indicator()
'''
Accumulation Distribution Index
'''
nse_technical["volume_adi"] = AccDistIndexIndicator(
high=nse_technical['high'],
low=nse_technical['low'],
close=nse_technical['close'],
volume=nse_technical['total_traded_quantity'],
fillna=False).acc_dist_index()
'''
Money Flow Index
'''
nse_technical["volume_mfi"] = MFIIndicator(
high=nse_technical['high'],
low=nse_technical['low'],
close=nse_technical['close'],
volume=nse_technical['total_traded_quantity'],
window=14,
fillna=False,
).money_flow_index()
'''
Relative Strength Index (RSI)
'''
nse_technical["momentum_rsi"] = RSIIndicator(
close=nse_technical['close'], window=14, fillna=False).rsi()
'''
Stoch RSI (StochRSI)
'''
indicator_srsi = StochRSIIndicator(close=nse_technical['close'],
window=14,
smooth1=3,
smooth2=3,
fillna=False)
nse_technical["momentum_stoch_rsi"] = indicator_srsi.stochrsi()
nse_technical["momentum_stoch_rsi_k"] = indicator_srsi.stochrsi_k()
nse_technical["momentum_stoch_rsi_d"] = indicator_srsi.stochrsi_d()
nse_technical.replace({np.nan: None}, inplace=True)
nse_technical.replace([np.inf, -np.inf], None, inplace=True)
list_to_create = []
list_to_update = []
for index in range(len(nse_history_data) - 1, -1, -1):
data = nse_history_data[index]
if data.technicals:
break
technical = NSETechnical(
nse_historical_data=data,
trend_macd=nse_technical['trend_macd'][index],
trend_macd_signal=nse_technical['trend_macd_signal']
[index],
trend_macd_diff=nse_technical['trend_macd_diff'][index],
trend_sma_fast=nse_technical['trend_sma_fast'][index],
trend_sma_slow=nse_technical['trend_sma_slow'][index],
trend_ema_fast=nse_technical['trend_ema_fast'][index],
trend_ema_slow=nse_technical['trend_ema_slow'][index],
trend_ichimoku_conv=nse_technical['trend_ichimoku_conv']
[index],
trend_ichimoku_base=nse_technical['trend_ichimoku_base']
[index],
trend_ichimoku_a=nse_technical['trend_ichimoku_a'][index],
trend_ichimoku_b=nse_technical['trend_ichimoku_b'][index],
trend_visual_ichimoku_a=nse_technical[
'trend_visual_ichimoku_a'][index],
trend_visual_ichimoku_b=nse_technical[
'trend_visual_ichimoku_b'][index],
volatility_bbm=nse_technical['volatility_bbm'][index],
volatility_bbh=nse_technical['volatility_bbh'][index],
volatility_bbl=nse_technical['volatility_bbl'][index],
volatility_bbw=nse_technical['volatility_bbw'][index],
volatility_bbp=nse_technical['volatility_bbp'][index],
volatility_bbhi=nse_technical['volatility_bbhi'][index],
volatility_bbli=nse_technical['volatility_bbli'][index],
volume_adi=nse_technical['volume_adi'][index],
volume_mfi=nse_technical['volume_mfi'][index],
momentum_rsi=nse_technical['momentum_rsi'][index],
momentum_stoch_rsi=nse_technical['momentum_stoch_rsi']
[index],
momentum_stoch_rsi_k=nse_technical['momentum_stoch_rsi_k']
[index],
momentum_stoch_rsi_d=nse_technical['momentum_stoch_rsi_d']
[index])
data.technicals = True
list_to_update.append(data)
list_to_create.append(technical)
NSETechnical.objects.bulk_create(list_to_create)
NSEHistoricalData.objects.bulk_update(list_to_update,
['technicals'])
print(f"Technicals updated for {symbol}")
def add_trend_ta(
df: pd.DataFrame,
high: str,
low: str,
close: str,
fillna: bool = False,
colprefix: str = "",
vectorized: bool = False,
) -> pd.DataFrame:
"""Add trend technical analysis features to dataframe.
Args:
df (pandas.core.frame.DataFrame): Dataframe base.
high (str): Name of 'high' column.
low (str): Name of 'low' column.
close (str): Name of 'close' column.
fillna(bool): if True, fill nan values.
colprefix(str): Prefix column names inserted
vectorized(bool): if True, use only vectorized functions indicators
Returns:
pandas.core.frame.DataFrame: Dataframe with new features.
"""
# MACD
indicator_macd = MACD(close=df[close],
window_slow=26,
window_fast=12,
window_sign=9,
fillna=fillna)
df[f"{colprefix}trend_macd"] = indicator_macd.macd()
df[f"{colprefix}trend_macd_signal"] = indicator_macd.macd_signal()
df[f"{colprefix}trend_macd_diff"] = indicator_macd.macd_diff()
# SMAs
df[f"{colprefix}trend_sma_fast"] = SMAIndicator(
close=df[close], window=12, fillna=fillna).sma_indicator()
df[f"{colprefix}trend_sma_slow"] = SMAIndicator(
close=df[close], window=26, fillna=fillna).sma_indicator()
# EMAs
df[f"{colprefix}trend_ema_fast"] = EMAIndicator(
close=df[close], window=12, fillna=fillna).ema_indicator()
df[f"{colprefix}trend_ema_slow"] = EMAIndicator(
close=df[close], window=26, fillna=fillna).ema_indicator()
# Vortex Indicator
indicator_vortex = VortexIndicator(high=df[high],
low=df[low],
close=df[close],
window=14,
fillna=fillna)
df[f"{colprefix}trend_vortex_ind_pos"] = indicator_vortex.vortex_indicator_pos(
)
df[f"{colprefix}trend_vortex_ind_neg"] = indicator_vortex.vortex_indicator_neg(
)
df[f"{colprefix}trend_vortex_ind_diff"] = indicator_vortex.vortex_indicator_diff(
)
# TRIX Indicator
df[f"{colprefix}trend_trix"] = TRIXIndicator(close=df[close],
window=15,
fillna=fillna).trix()
# Mass Index
df[f"{colprefix}trend_mass_index"] = MassIndex(high=df[high],
low=df[low],
window_fast=9,
window_slow=25,
fillna=fillna).mass_index()
# DPO Indicator
df[f"{colprefix}trend_dpo"] = DPOIndicator(close=df[close],
window=20,
fillna=fillna).dpo()
# KST Indicator
indicator_kst = KSTIndicator(
close=df[close],
roc1=10,
roc2=15,
roc3=20,
roc4=30,
window1=10,
window2=10,
window3=10,
window4=15,
nsig=9,
fillna=fillna,
)
df[f"{colprefix}trend_kst"] = indicator_kst.kst()
df[f"{colprefix}trend_kst_sig"] = indicator_kst.kst_sig()
df[f"{colprefix}trend_kst_diff"] = indicator_kst.kst_diff()
# Ichimoku Indicator
indicator_ichi = IchimokuIndicator(
high=df[high],
low=df[low],
window1=9,
window2=26,
window3=52,
visual=False,
fillna=fillna,
)
df[f"{colprefix}trend_ichimoku_conv"] = indicator_ichi.ichimoku_conversion_line(
)
df[f"{colprefix}trend_ichimoku_base"] = indicator_ichi.ichimoku_base_line()
df[f"{colprefix}trend_ichimoku_a"] = indicator_ichi.ichimoku_a()
df[f"{colprefix}trend_ichimoku_b"] = indicator_ichi.ichimoku_b()
# Schaff Trend Cycle (STC)
df[f"{colprefix}trend_stc"] = STCIndicator(
close=df[close],
window_slow=50,
window_fast=23,
cycle=10,
smooth1=3,
smooth2=3,
fillna=fillna,
).stc()
if not vectorized:
# Average Directional Movement Index (ADX)
indicator_adx = ADXIndicator(high=df[high],
low=df[low],
close=df[close],
window=14,
fillna=fillna)
df[f"{colprefix}trend_adx"] = indicator_adx.adx()
df[f"{colprefix}trend_adx_pos"] = indicator_adx.adx_pos()
df[f"{colprefix}trend_adx_neg"] = indicator_adx.adx_neg()
# CCI Indicator
df[f"{colprefix}trend_cci"] = CCIIndicator(
high=df[high],
low=df[low],
close=df[close],
window=20,
constant=0.015,
fillna=fillna,
).cci()
# Ichimoku Visual Indicator
indicator_ichi_visual = IchimokuIndicator(
high=df[high],
low=df[low],
window1=9,
window2=26,
window3=52,
visual=True,
fillna=fillna,
)
df[f"{colprefix}trend_visual_ichimoku_a"] = indicator_ichi_visual.ichimoku_a(
)
df[f"{colprefix}trend_visual_ichimoku_b"] = indicator_ichi_visual.ichimoku_b(
)
# Aroon Indicator
indicator_aroon = AroonIndicator(close=df[close],
window=25,
fillna=fillna)
df[f"{colprefix}trend_aroon_up"] = indicator_aroon.aroon_up()
df[f"{colprefix}trend_aroon_down"] = indicator_aroon.aroon_down()
df[f"{colprefix}trend_aroon_ind"] = indicator_aroon.aroon_indicator()
# PSAR Indicator
indicator_psar = PSARIndicator(
high=df[high],
low=df[low],
close=df[close],
step=0.02,
max_step=0.20,
fillna=fillna,
)
# df[f'{colprefix}trend_psar'] = indicator.psar()
df[f"{colprefix}trend_psar_up"] = indicator_psar.psar_up()
df[f"{colprefix}trend_psar_down"] = indicator_psar.psar_down()
df[f"{colprefix}trend_psar_up_indicator"] = indicator_psar.psar_up_indicator(
)
df[f"{colprefix}trend_psar_down_indicator"] = indicator_psar.psar_down_indicator(
)
return df
import pandas as pd
from ta.utils import dropna
import matplotlib.pyplot as plt
from ta.trend import MACD
import numpy as np
df = pd.read_csv('TSLA.csv', sep=',')
# clean NaN
df = dropna(df)
macd = MACD(close=df["Close"])
def normalize(col):
return (col - col.mean()) / col.std()
df["macd"] = normalize(macd.macd())
df["macd_signal"] = normalize(macd.macd_signal())
df["macd_diff"] = normalize(macd.macd_diff())
plt.plot(df.macd, label="MACD")
plt.plot(df.macd_signal, label="MACD signal")
plt.plot(df.macd_diff, label="MACD diff")
plt.title("TSLA MACD")
plt.show()
with open("TSLA_ta.csv", "w") as f:
f.write(df.to_csv())
def create_env(config):
df = load_csv('btc_usdt_m5_history.csv')
from ta.trend import (
MACD,
ADXIndicator,
AroonIndicator,
CCIIndicator,
DPOIndicator,
EMAIndicator,
IchimokuIndicator,
KSTIndicator,
MassIndex,
PSARIndicator,
SMAIndicator,
STCIndicator,
TRIXIndicator,
VortexIndicator,
)
colprefix = ""
# MACD
indicator_macd = MACD(close=df['close'],
window_slow=26,
window_fast=12,
window_sign=9,
fillna=True)
df[f"{colprefix}trend_macd"] = indicator_macd.macd()
df[f"{colprefix}trend_macd_signal"] = indicator_macd.macd_signal()
df[f"{colprefix}trend_macd_diff"] = indicator_macd.macd_diff()
#df = ta.add_trend_ta(df,'high', 'low', 'close', fillna=True)
#df = ta.add_volume_ta(df,'high', 'low', 'close', 'volume', fillna=True)
#df = ta.add_volume_ta(df, 'high', 'low', 'close', 'volume', fillna=True)
#df = ta.add_volatility_ta(df, 'high', 'low', 'close', fillna=True)
price_history = df[['date', 'open', 'high', 'low', 'close',
'volume']] # chart data
df.drop(columns=['date', 'open', 'high', 'low', 'close', 'volume'],
inplace=True)
print(df.head(5))
with NameSpace("bitfinex"):
streams = [
Stream.source(df[c].tolist(), dtype="float").rename(c)
for c in df.columns
]
feed_ta_features = DataFeed(streams)
price_list = price_history['close'].tolist()
p = Stream.source(price_list, dtype="float").rename("USD-BTC")
bitfinex = Exchange("bitfinex", service=execute_order)(p)
cash = Wallet(bitfinex, 10000 * USD)
asset = Wallet(bitfinex, 0 * BTC)
portfolio = Portfolio(USD, [cash, asset])
reward_scheme = default.rewards.SimpleProfit(window_size=1)
#action_scheme = default.actions.BSHEX(
# cash=cash,
# asset=asset
#).attach(reward_scheme)
action_scheme = default.actions.SimpleOrders(trade_sizes=3)
renderer_feed_ptc = DataFeed([
Stream.source(list(price_history["date"])).rename("date"),
Stream.source(list(price_history["open"]),
dtype="float").rename("open"),
Stream.source(list(price_history["high"]),
dtype="float").rename("high"),
Stream.source(list(price_history["low"]), dtype="float").rename("low"),
Stream.source(list(price_history["close"]),
dtype="float").rename("close"),
Stream.source(list(price_history["volume"]),
dtype="float").rename("volume")
])
env = default.create(
feed=feed_ta_features,
portfolio=portfolio,
#renderer=PositionChangeChart(),
renderer=default.renderers.PlotlyTradingChart(),
action_scheme=action_scheme,
reward_scheme=reward_scheme,
renderer_feed=renderer_feed_ptc,
window_size=config["window_size"],
max_allowed_loss=0.1)
return env
#%%画K线主图
datacent = go.Datacent()
if datacent.qihuo_connectSer():
qihuocount = list(range(len(cf.cfqihuo)))
df = datacent.qihuoK(cflen)
df = tdx_tools.SuperTrend(
df,
period=cf.st_period_fast,
multiplier=cf.st_mult_fast,
)
df = tdx_tools.StochRSI(df, m=14, p=7)
dfmacd = MACD(df['close'], n_slow=10, n_fast=5, n_sign=89)
df["macd"] = dfmacd.macd()
df['diff'] = dfmacd.macd_diff()
df['macd_signal'] = dfmacd.macd_signal()
df = df.iloc[100:]
weekday_quotes = [
tuple([i] + list(quote[1:]))
for i, quote in enumerate(df.values, )
]
fig = plt.figure(figsize=(1000 / 72, 500 / 72),
facecolor='#CCCCCC',
edgecolor='#CCCCCC')
df = df.reset_index()
df = actionOrder(df)
indicator_ema15 = EMAIndicator(close=df['cls'], window=15)
indicator_ema30 = EMAIndicator(close=df['cls'], window=30)
indicator_ema35 = EMAIndicator(close=df['cls'], window=35)
indicator_ema40 = EMAIndicator(close=df['cls'], window=40)
indicator_ema45 = EMAIndicator(close=df['cls'], window=45)
indicator_ema50 = EMAIndicator(close=df['cls'], window=50)
indicator_ema60 = EMAIndicator(close=df['cls'], window=60)
# Add Bollinger Band high indicator
df['bb_bbhi'] = indicator_bb.bollinger_hband_indicator()
# Add Bollinger Band low indicator
df['bb_bbli'] = indicator_bb.bollinger_lband_indicator()
#df['macd'] = indicator_macd.macd()
df['macd'] = indicator_macd.macd_diff()
#df['macd_signal'] = indicator_macd.macd_signal()
df['obv'] = indicator_obv.on_balance_volume()
df['vol_sma20'] = indicator_vol_sma20.sma_indicator()
df['ema03'] = indicator_ema03.ema_indicator()
df['ema05'] = indicator_ema05.ema_indicator()
df['ema08'] = indicator_ema08.ema_indicator()
df['ema10'] = indicator_ema10.ema_indicator()
df['ema12'] = indicator_ema12.ema_indicator()
df['ema15'] = indicator_ema15.ema_indicator()
df['ema30'] = indicator_ema30.ema_indicator()
df['ema35'] = indicator_ema35.ema_indicator()
df['ema40'] = indicator_ema40.ema_indicator()
def __init__(self, symbols):
# data = json.loads(symbols)
# df_stock = pd.json_normalize(symbols)
# df_stock = pd.read_csv(fn,names = ['sym']).drop_duplicates()
df_stock = pd.DataFrame(symbols)
ls_stock = df_stock['sym'].to_list()
df_stock = df_stock.reset_index()
df_stock.columns = ['sort', 'sym']
df_stock.head()
# In[3]:
start = dt.date.today() + relativedelta(days=-150)
end = dt.date.today() + relativedelta(days=-0)
ls_tickers = ls_stock
ls_df = []
for ticker in ls_tickers:
try:
df = web.DataReader(ticker, 'yahoo', start, end)
except Exception as e:
print(str(e))
continue
df['sym'] = ticker
ls_df.append(df.copy())
df_price = pd.concat(ls_df).reset_index()
df_price.columns = [
'dte', 'hgh', 'low', 'opn', 'cls', 'vol', 'cls_adj', 'sym'
]
df_price.sort_values(['sym', 'dte'], inplace=True)
df_price = df_price[['dte', 'sym', 'hgh', 'low', 'cls', 'vol']].copy()
df_price['curr'] = end
df_price['curr'] = pd.to_datetime(df_price['curr'])
df_price['dte'] = pd.to_datetime(df_price['dte'])
df_price['ndays'] = (df_price['curr'] - df_price['dte']).dt.days
df_price['ndays'] = df_price.groupby(['sym'])['ndays'].rank()
df_price[df_price['sym'] == 'SPY'].head()
# In[4]:
ls_df = []
ls_tickers = ls_stock
for ticker in ls_tickers:
#df = dropna(df_price[df_price['sym']==ticker])
df = df_price[df_price['sym'] == ticker].copy()
indicator_bb = BollingerBands(close=df['cls'],
window=20,
window_dev=2)
indicator_macd = MACD(close=df['cls'],
window_fast=12,
window_slow=26,
window_sign=9)
indicator_rsi14 = RSIIndicator(close=df['cls'], window=14)
indicator_cci20 = cci(high=df['hgh'],
low=df['low'],
close=df['cls'],
window=20,
constant=0.015)
indicator_obv = OnBalanceVolumeIndicator(close=df['cls'],
volume=df['vol'],
fillna=True)
indicator_vol_sma20 = SMAIndicator(close=df['vol'], window=20)
indicator_ema03 = EMAIndicator(close=df['cls'], window=3)
indicator_ema05 = EMAIndicator(close=df['cls'], window=5)
indicator_ema08 = EMAIndicator(close=df['cls'], window=8)
indicator_ema10 = EMAIndicator(close=df['cls'], window=10)
indicator_ema12 = EMAIndicator(close=df['cls'], window=12)
indicator_ema15 = EMAIndicator(close=df['cls'], window=15)
indicator_ema30 = EMAIndicator(close=df['cls'], window=30)
indicator_ema35 = EMAIndicator(close=df['cls'], window=35)
indicator_ema40 = EMAIndicator(close=df['cls'], window=40)
indicator_ema45 = EMAIndicator(close=df['cls'], window=45)
indicator_ema50 = EMAIndicator(close=df['cls'], window=50)
indicator_ema60 = EMAIndicator(close=df['cls'], window=60)
# Add Bollinger Band high indicator
df['bb_bbhi'] = indicator_bb.bollinger_hband_indicator()
# Add Bollinger Band low indicator
df['bb_bbli'] = indicator_bb.bollinger_lband_indicator()
#df['macd'] = indicator_macd.macd()
df['macd'] = indicator_macd.macd_diff()
#df['macd_signal'] = indicator_macd.macd_signal()
df['obv'] = indicator_obv.on_balance_volume()
df['vol_sma20'] = indicator_vol_sma20.sma_indicator()
df['ema03'] = indicator_ema03.ema_indicator()
df['ema05'] = indicator_ema05.ema_indicator()
df['ema08'] = indicator_ema08.ema_indicator()
df['ema10'] = indicator_ema10.ema_indicator()
df['ema12'] = indicator_ema12.ema_indicator()
df['ema15'] = indicator_ema15.ema_indicator()
df['ema30'] = indicator_ema30.ema_indicator()
df['ema35'] = indicator_ema35.ema_indicator()
df['ema40'] = indicator_ema40.ema_indicator()
df['ema45'] = indicator_ema45.ema_indicator()
df['ema50'] = indicator_ema50.ema_indicator()
df['ema60'] = indicator_ema60.ema_indicator()
df['rsi14'] = indicator_rsi14.rsi()
df['cci20'] = indicator_cci20
ls_df.append(df.copy())
df = pd.concat(ls_df)
df['score_vol_sma20'] = df[['vol',
'vol_sma20']].apply(lambda x: x[0] / x[1],
axis=1)
df['emash_min'] = df[[
'ema03', 'ema05', 'ema08', 'ema10', 'ema12', 'ema15'
]].min(axis=1)
df['emash_max'] = df[[
'ema03', 'ema05', 'ema08', 'ema10', 'ema12', 'ema15'
]].max(axis=1)
df['emash_avg'] = df[[
'ema03', 'ema05', 'ema08', 'ema10', 'ema12', 'ema15'
]].mean(axis=1)
#df['score_short'] = df[['cls','emash_min','emash_max','emash_min']].apply(lambda x: 100 * (x[0]-x[1])/(x[2]-x[3]),axis=1)
df['emalg_min'] = df[[
'ema30', 'ema35', 'ema40', 'ema45', 'ema50', 'ema60'
]].min(axis=1)
df['emalg_max'] = df[[
'ema30', 'ema35', 'ema40', 'ema45', 'ema50', 'ema60'
]].max(axis=1)
df['emalg_avg'] = df[[
'ema30', 'ema35', 'ema40', 'ema45', 'ema50', 'ema60'
]].mean(axis=1)
#df['score_long'] = df[['cls','emalg_min','emalg_max','emalg_min']].apply(lambda x: 100 * (x[0]-x[1])/(x[2]-x[3]),axis=1)
df['ema_min'] = df[[
'ema03', 'ema05', 'ema08', 'ema10', 'ema12', 'ema15', 'ema30',
'ema35', 'ema40', 'ema45', 'ema50', 'ema60'
]].min(axis=1)
df['ema_max'] = df[[
'ema03', 'ema05', 'ema08', 'ema10', 'ema12', 'ema15', 'ema30',
'ema35', 'ema40', 'ema45', 'ema50', 'ema60'
]].max(axis=1)
df['score_ovlp_ema'] = df[[
'emash_min', 'emalg_max', 'ema_max', 'ema_min'
]].apply(lambda x: 100 * (x[0] - x[1]) / (x[2] - x[3]), axis=1)
df = pd.merge(df_stock, df, on=['sym'],
how='inner').sort_values(['sort', 'ndays'])
decimals = pd.Series([1, 0, 0, 2, 0, 0, 2, 0, 0, 0, 0],
index=[
'cls', 'ndays', 'vol', 'score_vol_sma20',
'bb_bbhi', 'bb_bbli', 'macd', 'obv', 'rsi14',
'cci20', 'score_ovlp_ema'
])
cols = [
'ndays', 'dte', 'sort', 'sym', 'cls', 'vol', 'score_vol_sma20',
'bb_bbhi', 'bb_bbli', 'macd', 'obv', 'rsi14', 'cci20',
'score_ovlp_ema'
]
df = df[df['ndays'] <= 10][cols].round(decimals).copy()
print(df['score_ovlp_ema'].min(), df['score_ovlp_ema'].max())
df[df['sym'] == 'QQQ'].head(50)
self.df = df
def add_trend_ta(df: pd.DataFrame,
high: str,
low: str,
close: str,
fillna: bool = False,
colprefix: str = ""):
"""Add trend technical analysis features to dataframe.
Args:
df (pandas.core.frame.DataFrame): Dataframe base.
high (str): Name of 'high' column.
low (str): Name of 'low' column.
close (str): Name of 'close' column.
fillna(bool): if True, fill nan values.
colprefix(str): Prefix column names inserted
Returns:
pandas.core.frame.DataFrame: Dataframe with new features.
"""
# MACD
indicator_macd = MACD(close=df[close],
n_fast=12,
n_slow=26,
n_sign=9,
fillna=fillna)
df[f'{colprefix}trend_macd'] = indicator_macd.macd()
df[f'{colprefix}trend_macd_signal'] = indicator_macd.macd_signal()
df[f'{colprefix}trend_macd_diff'] = indicator_macd.macd_diff()
# EMAs
df[f'{colprefix}trend_ema_fast'] = EMAIndicator(
close=df[close], n=12, fillna=fillna).ema_indicator()
df[f'{colprefix}trend_ema_slow'] = EMAIndicator(
close=df[close], n=26, fillna=fillna).ema_indicator()
# Average Directional Movement Index (ADX)
indicator = ADXIndicator(high=df[high],
low=df[low],
close=df[close],
n=14,
fillna=fillna)
df[f'{colprefix}trend_adx'] = indicator.adx()
df[f'{colprefix}trend_adx_pos'] = indicator.adx_pos()
df[f'{colprefix}trend_adx_neg'] = indicator.adx_neg()
# Vortex Indicator
indicator = VortexIndicator(high=df[high],
low=df[low],
close=df[close],
n=14,
fillna=fillna)
df[f'{colprefix}trend_vortex_ind_pos'] = indicator.vortex_indicator_pos()
df[f'{colprefix}trend_vortex_ind_neg'] = indicator.vortex_indicator_neg()
df[f'{colprefix}trend_vortex_ind_diff'] = indicator.vortex_indicator_diff()
# TRIX Indicator
indicator = TRIXIndicator(close=df[close], n=15, fillna=fillna)
df[f'{colprefix}trend_trix'] = indicator.trix()
# Mass Index
indicator = MassIndex(high=df[high],
low=df[low],
n=9,
n2=25,
fillna=fillna)
df[f'{colprefix}trend_mass_index'] = indicator.mass_index()
# CCI Indicator
indicator = CCIIndicator(high=df[high],
low=df[low],
close=df[close],
n=20,
c=0.015,
fillna=fillna)
df[f'{colprefix}trend_cci'] = indicator.cci()
# DPO Indicator
indicator = DPOIndicator(close=df[close], n=20, fillna=fillna)
df[f'{colprefix}trend_dpo'] = indicator.dpo()
# KST Indicator
indicator = KSTIndicator(close=df[close],
r1=10,
r2=15,
r3=20,
r4=30,
n1=10,
n2=10,
n3=10,
n4=15,
nsig=9,
fillna=fillna)
df[f'{colprefix}trend_kst'] = indicator.kst()
df[f'{colprefix}trend_kst_sig'] = indicator.kst_sig()
df[f'{colprefix}trend_kst_diff'] = indicator.kst_diff()
# Ichimoku Indicator
indicator = IchimokuIndicator(high=df[high],
low=df[low],
n1=9,
n2=26,
n3=52,
visual=False,
fillna=fillna)
df[f'{colprefix}trend_ichimoku_a'] = indicator.ichimoku_a()
df[f'{colprefix}trend_ichimoku_b'] = indicator.ichimoku_b()
indicator = IchimokuIndicator(high=df[high],
low=df[low],
n1=9,
n2=26,
n3=52,
visual=True,
fillna=fillna)
df[f'{colprefix}trend_visual_ichimoku_a'] = indicator.ichimoku_a()
df[f'{colprefix}trend_visual_ichimoku_b'] = indicator.ichimoku_b()
# Aroon Indicator
indicator = AroonIndicator(close=df[close], n=25, fillna=fillna)
df[f'{colprefix}trend_aroon_up'] = indicator.aroon_up()
df[f'{colprefix}trend_aroon_down'] = indicator.aroon_down()
df[f'{colprefix}trend_aroon_ind'] = indicator.aroon_indicator()
# PSAR Indicator
indicator = PSARIndicator(high=df[high],
low=df[low],
close=df[close],
step=0.02,
max_step=0.20,
fillna=fillna)
df[f'{colprefix}trend_psar'] = indicator.psar()
df[f'{colprefix}trend_psar_up'] = indicator.psar_up()
df[f'{colprefix}trend_psar_down'] = indicator.psar_down()
df[f'{colprefix}trend_psar_up_indicator'] = indicator.psar_up_indicator()
df[f'{colprefix}trend_psar_down_indicator'] = indicator.psar_down_indicator(
)
return df