def add_indicators(data: pd.DataFrame) -> pd.DataFrame:
"""
This method creates technical indicators, based on the OHLC and volume bars
:param data: pandas DataFrame, containing open, high, low and close and
optional volume columns
:return: DataFrame with added technical indicators
"""
assert 'open' in data.columns, "open column not present or with different name"
assert 'high' in data.columns, "high column not present or with different name"
assert 'low' in data.columns, "low column not present or with different name"
assert 'close' in data.columns, "close column not present or with different name"
try:
data['RSI'] = ta.rsi(data["close"])
data['TSI'] = ta.tsi(data["close"])
data['UO'] = ta.uo(data["high"], data["low"], data["close"])
data['AO'] = ta.ao(data["high"], data["low"])
data['MACD_diff'] = ta.macd_diff(data["close"])
data['Vortex_pos'] = ta.vortex_indicator_pos(data["high"], data["low"], data["close"])
data['Vortex_neg'] = ta.vortex_indicator_neg(data["high"], data["low"], data["close"])
data['Vortex_diff'] = abs(data['Vortex_pos'] - data['Vortex_neg'])
data['Trix'] = ta.trix(data["close"])
data['Mass_index'] = ta.mass_index(data["high"], data["low"])
data['CCI'] = ta.cci(data["high"], data["low"], data["close"])
data['DPO'] = ta.dpo(data["close"])
data['KST'] = ta.kst(data["close"])
data['KST_sig'] = ta.kst_sig(data["close"])
data['KST_diff'] = (data['KST'] - data['KST_sig'])
data['Aroon_up'] = ta.aroon_up(data["close"])
data['Aroon_down'] = ta.aroon_down(data["close"])
data['Aroon_ind'] = (data['Aroon_up'] - data['Aroon_down'])
data['BBH'] = ta.bollinger_hband(data["close"])
data['BBL'] = ta.bollinger_lband(data["close"])
data['BBM'] = ta.bollinger_mavg(data["close"])
data['BBHI'] = ta.bollinger_hband_indicator(data["close"])
data['BBLI'] = ta.bollinger_lband_indicator(data["close"])
data['KCHI'] = ta.keltner_channel_hband_indicator(data["high"], data["low"], data["close"])
data['KCLI'] = ta.keltner_channel_lband_indicator(data["high"], data["low"], data["close"])
data['DCHI'] = ta.donchian_channel_hband_indicator(data["close"])
data['DCLI'] = ta.donchian_channel_lband_indicator(data["close"])
data['DR'] = ta.daily_return(data["close"])
data['DLR'] = ta.daily_log_return(data["close"])
if 'volume' in data.columns:
data['MFI'] = ta.money_flow_index(data["high"], data["low"], data["close"], data["volume"])
data['ADI'] = ta.acc_dist_index(data["high"], data["low"], data["close"], data["volume"])
data['OBV'] = ta.on_balance_volume(data["close"], data["volume"])
data['CMF'] = ta.chaikin_money_flow(data["high"], data["low"], data["close"], data["volume"])
data['FI'] = ta.force_index(data["close"], data["volume"])
data['EM'] = ta.ease_of_movement(data["high"], data["low"], data["close"], data["volume"])
data['VPT'] = ta.volume_price_trend(data["close"], data["volume"])
data['NVI'] = ta.negative_volume_index(data["close"], data["volume"])
data.fillna(method='bfill', inplace=True)
return data
except (AssertionError, Exception) as error:
raise IndicatorsError(error)
LOGGER.error(error)
def add_indicators(df):
df['RSI'] = ta.rsi(df["Close"])
df['MFI'] = ta.money_flow_index(df["High"], df["Low"], df["Close"],
df["Volume"])
df['TSI'] = ta.tsi(df["Close"])
df['UO'] = ta.uo(df["High"], df["Low"], df["Close"])
df['AO'] = ta.ao(df["High"], df["Low"])
df['MACD_diff'] = ta.macd_diff(df["Close"])
df['Vortex_pos'] = ta.vortex_indicator_pos(df["High"], df["Low"],
df["Close"])
df['Vortex_neg'] = ta.vortex_indicator_neg(df["High"], df["Low"],
df["Close"])
df['Vortex_diff'] = abs(df['Vortex_pos'] - df['Vortex_neg'])
df['Trix'] = ta.trix(df["Close"])
df['Mass_index'] = ta.mass_index(df["High"], df["Low"])
df['CCI'] = ta.cci(df["High"], df["Low"], df["Close"])
df['DPO'] = ta.dpo(df["Close"])
df['KST'] = ta.kst(df["Close"])
df['KST_sig'] = ta.kst_sig(df["Close"])
df['KST_diff'] = (df['KST'] - df['KST_sig'])
df['Aroon_up'] = ta.aroon_up(df["Close"])
df['Aroon_down'] = ta.aroon_down(df["Close"])
df['Aroon_ind'] = (df['Aroon_up'] - df['Aroon_down'])
df['BBH'] = ta.bollinger_hband(df["Close"])
df['BBL'] = ta.bollinger_lband(df["Close"])
df['BBM'] = ta.bollinger_mavg(df["Close"])
df['BBHI'] = ta.bollinger_hband_indicator(df["Close"])
df['BBLI'] = ta.bollinger_lband_indicator(df["Close"])
df['KCHI'] = ta.keltner_channel_hband_indicator(df["High"], df["Low"],
df["Close"])
df['KCLI'] = ta.keltner_channel_lband_indicator(df["High"], df["Low"],
df["Close"])
df['DCHI'] = ta.donchian_channel_hband_indicator(df["Close"])
df['DCLI'] = ta.donchian_channel_lband_indicator(df["Close"])
df['ADI'] = ta.acc_dist_index(df["High"], df["Low"], df["Close"],
df["Volume"])
df['OBV'] = ta.on_balance_volume(df["Close"], df["Volume"])
df['CMF'] = ta.chaikin_money_flow(df["High"], df["Low"], df["Close"],
df["Volume"])
df['FI'] = ta.force_index(df["Close"], df["Volume"])
df['EM'] = ta.ease_of_movement(df["High"], df["Low"], df["Close"],
df["Volume"])
df['VPT'] = ta.volume_price_trend(df["Close"], df["Volume"])
df['NVI'] = ta.negative_volume_index(df["Close"], df["Volume"])
df['DR'] = ta.daily_return(df["Close"])
df['DLR'] = ta.daily_log_return(df["Close"])
df.fillna(method='bfill', inplace=True)
return df
def channel(self, df, period=50):
df.columns = map(str.lower, df.columns)
df.sort_index(inplace=True)
df = df.reset_index()
if ta.donchian_channel_hband_indicator(df.close, period)[0] == 1.0:
return 'long'
elif ta.donchian_channel_lband_indicator(df.close, period)[0] == 1.0:
return 'short'
return 'none'
def add_candle_indicators(df, l, ck, hk, lk, vk):
df[l + 'rsi'] = ta.rsi(df[ck])
df[l + 'mfi'] = ta.money_flow_index(df[hk], df[lk], df[ck], df[vk])
df[l + 'tsi'] = ta.tsi(df[ck])
df[l + 'uo'] = ta.uo(df[hk], df[lk], df[ck])
df[l + 'ao'] = ta.ao(df[hk], df[lk])
df[l + 'macd_diff'] = ta.macd_diff(df[ck])
df[l + 'vortex_pos'] = ta.vortex_indicator_pos(df[hk], df[lk], df[ck])
df[l + 'vortex_neg'] = ta.vortex_indicator_neg(df[hk], df[lk], df[ck])
df[l + 'vortex_diff'] = abs(df[l + 'vortex_pos'] - df[l + 'vortex_neg'])
df[l + 'trix'] = ta.trix(df[ck])
df[l + 'mass_index'] = ta.mass_index(df[hk], df[lk])
df[l + 'cci'] = ta.cci(df[hk], df[lk], df[ck])
df[l + 'dpo'] = ta.dpo(df[ck])
df[l + 'kst'] = ta.kst(df[ck])
df[l + 'kst_sig'] = ta.kst_sig(df[ck])
df[l + 'kst_diff'] = (df[l + 'kst'] - df[l + 'kst_sig'])
df[l + 'aroon_up'] = ta.aroon_up(df[ck])
df[l + 'aroon_down'] = ta.aroon_down(df[ck])
df[l + 'aroon_ind'] = (df[l + 'aroon_up'] - df[l + 'aroon_down'])
df[l + 'bbh'] = ta.bollinger_hband(df[ck])
df[l + 'bbl'] = ta.bollinger_lband(df[ck])
df[l + 'bbm'] = ta.bollinger_mavg(df[ck])
df[l + 'bbhi'] = ta.bollinger_hband_indicator(df[ck])
df[l + 'bbli'] = ta.bollinger_lband_indicator(df[ck])
df[l + 'kchi'] = ta.keltner_channel_hband_indicator(df[hk], df[lk], df[ck])
df[l + 'kcli'] = ta.keltner_channel_lband_indicator(df[hk], df[lk], df[ck])
df[l + 'dchi'] = ta.donchian_channel_hband_indicator(df[ck])
df[l + 'dcli'] = ta.donchian_channel_lband_indicator(df[ck])
df[l + 'adi'] = ta.acc_dist_index(df[hk], df[lk], df[ck], df[vk])
df[l + 'obv'] = ta.on_balance_volume(df[ck], df[vk])
df[l + 'cmf'] = ta.chaikin_money_flow(df[hk], df[lk], df[ck], df[vk])
df[l + 'fi'] = ta.force_index(df[ck], df[vk])
df[l + 'em'] = ta.ease_of_movement(df[hk], df[lk], df[ck], df[vk])
df[l + 'vpt'] = ta.volume_price_trend(df[ck], df[vk])
df[l + 'nvi'] = ta.negative_volume_index(df[ck], df[vk])
df[l + 'dr'] = ta.daily_return(df[ck])
df[l + 'dlr'] = ta.daily_log_return(df[ck])
df[l + 'ma50'] = df[ck].rolling(window=50).mean()
df[l + 'ma100'] = df[ck].rolling(window=100).mean()
df[l + '26ema'] = df[[ck]].ewm(span=26).mean()
df[l + '12ema'] = df[[ck]].ewm(span=12).mean()
df[l + 'macd'] = (df[l + '12ema'] - df[l + '26ema'])
df[l + '100sd'] = df[[ck]].rolling(100).std()
df[l + 'upper_band'] = df[l + 'ma100'] + (df[l + '100sd'] * 2)
df[l + 'lower_band'] = df[l + 'ma100'] - (df[l + '100sd'] * 2)
df[l + 'ema'] = df[ck].ewm(com=0.5).mean()
df[l + 'momentum'] = df[ck] - 1
return df
def dch():
dch = ta.donchian_channel_hband(close, n=20, fillna=False)
dchi = ta.donchian_channel_hband_indicator(close, n=20, fillna=False)
dcl = ta.donchian_channel_lband(close, n=20, fillna=False)
dcli = ta.donchian_channel_lband_indicator(close, n=20, fillna=False)
if close[-1] == dch[-1]:
vot_status_dc = "DCH Signals is: Strong Sell"
elif dch[-1] > close[-1] > dch[-1] - 2:
vot_status_dc = "DCH Signals is: Sell"
elif dcl[-1] == close[-1]:
vot_status_dc = "DCH Signals is: Strong Buy"
elif dcl[-1] < close[-1] <= dcl[-1] + 2:
vot_status_dc = "DCH Signals is: Buy"
else:
vot_status_dc = "DCH Signals is: Hold"
return vot_status_dc
def add_indicators(df):
df['RSI'] = ta.rsi(df["Close"])
df['TSI'] = ta.tsi(df["Close"])
df['UO'] = ta.uo(df["High"], df["Low"], df["Close"])
df['AO'] = ta.ao(df["High"], df["Low"])
df['MACD_diff'] = ta.macd_diff(df["Close"])
df['Vortex_pos'] = ta.vortex_indicator_pos(df["High"], df["Low"],
df["Close"])
df['Vortex_neg'] = ta.vortex_indicator_neg(df["High"], df["Low"],
df["Close"])
df['Vortex_diff'] = abs(df['Vortex_pos'] - df['Vortex_neg'])
df['Trix'] = ta.trix(df["Close"])
df['Mass_index'] = ta.mass_index(df["High"], df["Low"])
df['CCI'] = ta.cci(df["High"], df["Low"], df["Close"])
df['DPO'] = ta.dpo(df["Close"])
df['KST'] = ta.kst(df["Close"])
df['KST_sig'] = ta.kst_sig(df["Close"])
df['KST_diff'] = (df['KST'] - df['KST_sig'])
df['Aroon_up'] = ta.aroon_up(df["Close"])
df['Aroon_down'] = ta.aroon_down(df["Close"])
df['Aroon_ind'] = (df['Aroon_up'] - df['Aroon_down'])
df['BBH'] = ta.bollinger_hband(df["Close"])
df['BBL'] = ta.bollinger_lband(df["Close"])
df['BBM'] = ta.bollinger_mavg(df["Close"])
df['BBHI'] = ta.bollinger_hband_indicator(df["Close"])
df['BBLI'] = ta.bollinger_lband_indicator(df["Close"])
df['KCHI'] = ta.keltner_channel_hband_indicator(df["High"], df["Low"],
df["Close"])
df['KCLI'] = ta.keltner_channel_lband_indicator(df["High"], df["Low"],
df["Close"])
df['DCHI'] = ta.donchian_channel_hband_indicator(df["Close"])
df['DCLI'] = ta.donchian_channel_lband_indicator(df["Close"])
df['DR'] = ta.daily_return(df["Close"])
df['DLR'] = ta.daily_log_return(df["Close"])
df.fillna(method='bfill', inplace=True)
return df
ta_df['KCL'] = ta.keltner_channel_lband(
df["High"],
df["Low"],
df["Close"])
ta_df['KCHI'] = ta.keltner_channel_hband_indicator(df["High"],
df["Low"],
df["Close"])
ta_df['KCLI'] = ta.keltner_channel_lband_indicator(df["High"],
df["Low"],
df["Close"])
ta_df['DCH'] = ta.donchian_channel_hband(
df["Close"])
ta_df['DCL'] = ta.donchian_channel_lband(
df["Close"])
ta_df['DCHI'] = ta.donchian_channel_hband_indicator(df["Close"])
ta_df['DCLI'] = ta.donchian_channel_lband_indicator(df["Close"])
ta_df['ADI'] = ta.acc_dist_index(df["High"],
df["Low"],
df["Close"],
df["Volume BTC"])
ta_df['OBV'] = ta.on_balance_volume(df["Close"],
df["Volume BTC"])
ta_df['OBVM'] = ta.on_balance_volume_mean(
df["Close"],
df["Volume BTC"])
ta_df['CMF'] = ta.chaikin_money_flow(df["High"],
df["Low"],
df["Close"],
df["Volume BTC"])
ta_df['FI'] = ta.force_index(df["Close"],
def get_data(context, data_, window):
# Crear ventana de datos.
h1 = data_.history(
context.symbols,
context.row_features,
bar_count=window,
frequency=str(context.bar_period) + "T",
)
h1 = h1.swapaxes(2, 0)
norm_data = []
close_prices = []
for i, asset in enumerate(context.assets):
data = h1.iloc[i]
close = h1.iloc[i].close
if context.include_ha:
ha = heikenashi(data)
data = pd.concat((data, ha), axis=1)
for period in [3, 6, 8, 10, 15, 20]:
data["rsi" + str(period)] = ta.rsi(data.close,
n=period,
fillna=True)
data["stoch" + str(period)] = ta.stoch(data.high,
data.low,
data.close,
n=period,
fillna=True)
data["stoch_signal" + str(period)] = ta.stoch_signal(
high=data.high,
low=data.low,
close=data.close,
n=period,
d_n=3,
fillna=True)
data["dpo" + str(period)] = ta.dpo(close=data.close,
n=period,
fillna=True)
data["atr" + str(period)] = ta.average_true_range(high=data.high,
low=data.low,
close=data.close,
n=period,
fillna=True)
for period in [6, 7, 8, 9, 10]:
data["williams" + str(period)] = ta.wr(high=data.high,
low=data.low,
close=data.close,
lbp=period,
fillna=True)
for period in [12, 13, 14, 15]:
data["proc" + str(period)] = ta.trix(close=data.close,
n=period,
fillna=True)
data["macd_diff"] = ta.macd_diff(close=data.close,
n_fast=15,
n_slow=30,
n_sign=9,
fillna=True)
data["macd_signal"] = ta.macd_signal(close=data.close,
n_fast=15,
n_slow=30,
n_sign=9,
fillna=True)
data["bb_high_indicator"] = ta.bollinger_hband_indicator(
close=data.close, n=15, ndev=2, fillna=True)
data["bb_low_indicator"] = ta.bollinger_lband_indicator(
close=data.close, n=15, ndev=2, fillna=True)
data["dc_high_indicator"] = ta.donchian_channel_hband_indicator(
close=data.close, n=20, fillna=True)
data["dc_low_indicator"] = ta.donchian_channel_lband_indicator(
close=data.close, n=20, fillna=True)
data["ichimoku_a"] = ta.ichimoku_a(high=data.high,
low=data.low,
n1=9,
n2=26,
fillna=True)
data.fillna(method="bfill")
# Normalizar los valores
for feature in data.columns:
norm_feature = preprocessing.normalize(
data[feature].values.reshape(-1, 1), axis=0)
data[feature] = pd.DataFrame(data=norm_feature,
index=data.index,
columns=[feature])
norm_data.append(data.values)
close_prices.append(close)
context.features = data.columns
return np.array(norm_data), np.array(close_prices)
price['Volume'],
fillna=True)
X['negative_volume_index'] = ta.negative_volume_index(price['Adj. Close'],
price['Volume'],
fillna=True)
X['average_true_range'] = ta.average_true_range(price['High'],
price['Low'],
price['Adj. Close'],
n=14,
fillna=True)
# X['KCU'] = ta.keltner_channel_hband_indicator(price['High'], price['Low'], price['Adj. Close'], n=10, fillna=True)
X['keltner_channel_lband_indicator'] = ta.keltner_channel_lband_indicator(
price['High'], price['Low'], price['Adj. Close'], n=10, fillna=True)
X['donchian_channel_hband_indicator'] = ta.donchian_channel_hband_indicator(
price['Adj. Close'], n=20, fillna=True)
X['donchian_channel_lband_indicator'] = ta.donchian_channel_lband_indicator(
price['Adj. Close'], n=20, fillna=True)
X['macd_signal'] = ta.macd_signal(price['Adj. Close'],
n_fast=12,
n_slow=26,
n_sign=9,
fillna=True)
X['adx_pos'] = ta.adx_pos(price['High'],
price['Low'],
price['Adj. Close'],
n=14,
fillna=True)
X['adx_neg'] = ta.adx_neg(price['High'],
price['Low'],
price['Adj. Close'],
n=14,
fillna=True)
def get_trayectory(self, t_intervals):
"""
:param t_intervals: número de intervalos en cada trayectoria
:return: Datos con características de la trayectoria sintética y precios de cierre en bruto de al misma
"""
trayectories = []
closes = []
p = True
for i, asset in enumerate(self.context.assets):
synthetic_return = np.exp(
self.drift[i] + self.stdev[i] * norm.ppf(np.random.rand((t_intervals * self.frequency) + self.frequency, 1)))
initial_close = self.close[i, -1]
synthetic_close = np.zeros_like(synthetic_return)
synthetic_close[0] = initial_close
for t in range(1, synthetic_return.shape[0]):
synthetic_close[t] = synthetic_close[t - 1] * synthetic_return[t]
OHLC = []
for t in range(synthetic_return.shape[0]):
if t % self.frequency == 0 and t > 0:
open = synthetic_close[t - self.frequency]
high = np.max(synthetic_close[t - self.frequency: t])
low = np.min(synthetic_close[t - self.frequency: t])
close = synthetic_close[t]
OHLC.append([open, high, close, low])
data = pd.DataFrame(data=OHLC, columns=["open", "high", "low", "close"])
close = data.close
if self.context.include_ha:
ha = heikenashi(data)
data = pd.concat((data, ha), axis=1)
for period in [3, 6, 8, 10, 15, 20]:
data["rsi" + str(period)] = ta.rsi(data.close, n=period, fillna=True)
data["stoch" + str(period)] = ta.stoch(data.high, data.low, data.close, n=period, fillna=True)
data["stoch_signal" + str(period)] = ta.stoch_signal(high=data.high,
low=data.low,
close=data.close,
n=period,
d_n=3,
fillna=True)
data["dpo" + str(period)] = ta.dpo(close=data.close,
n=period,
fillna=True)
data["atr" + str(period)] = ta.average_true_range(high=data.high,
low=data.low,
close=data.close,
n=period,
fillna=True)
for period in [6, 7, 8, 9, 10]:
data["williams" + str(period)] = ta.wr(high=data.high,
low=data.low,
close=data.close,
lbp=period,
fillna=True)
for period in [12, 13, 14, 15]:
data["proc" + str(period)] = ta.trix(close=data.close,
n=period,
fillna=True)
data["macd_diff"] = ta.macd_diff(close=data.close,
n_fast=15,
n_slow=30,
n_sign=9,
fillna=True)
data["macd_signal"] = ta.macd_signal(close=data.close,
n_fast=15,
n_slow=30,
n_sign=9,
fillna=True)
data["bb_high_indicator"] = ta.bollinger_hband_indicator(close=data.close,
n=15,
ndev=2,
fillna=True)
data["bb_low_indicator"] = ta.bollinger_lband_indicator(close=data.close,
n=15,
ndev=2,
fillna=True)
data["dc_high_indicator"] = ta.donchian_channel_hband_indicator(close=data.close,
n=20,
fillna=True)
data["dc_low_indicator"] = ta.donchian_channel_lband_indicator(close=data.close,
n=20,
fillna=True)
data["ichimoku_a"] = ta.ichimoku_a(high=data.high,
low=data.low,
n1=9,
n2=26,
fillna=True)
data.fillna(method="bfill")
# Normalizar los valores
for feature in data.columns:
norm_feature = preprocessing.normalize(data[feature].values.reshape(-1, 1), axis=0)
data[feature] = pd.DataFrame(data=norm_feature, index=data.index, columns=[feature])
self.assets = data.columns
trayectories.append(data.values)
closes.append(close)
return np.array(trayectories), np.array(closes)
def add_technical_indicators(df):
"""
Args:
df (pd.DataFrame): The processed dataframe returned by `process_data`.
Returns:
pd.DataFrame: The updated dataframe with the technical indicators inside.
Acknowledgements:
- Thanks for Adam King for this compilation of technical indicators!
The original file and code can be found here:
https://github.com/notadamking/RLTrader/blob/e5b83b1571f9fcfa6a67a2a810222f1f1751996c/util/indicators.py
"""
# Add momentum indicators
df["AO"] = ta.ao(df["High"], df["Low"])
df["MFI"] = ta.money_flow_index(df["High"], df["Low"], df["Close"],
df["Volume"])
df["RSI"] = ta.rsi(df["Close"])
df["TSI"] = ta.tsi(df["Close"])
df["UO"] = ta.uo(df["High"], df["Low"], df["Close"])
# Add trend indicators
df["Aroon_up"] = ta.aroon_up(df["Close"])
df["Aroon_down"] = ta.aroon_down(df["Close"])
df["Aroon_ind"] = (df["Aroon_up"] - df["Aroon_down"])
df["CCI"] = ta.cci(df["High"], df["Low"], df["Close"])
df["DPO"] = ta.dpo(df["Close"])
df["KST"] = ta.kst(df["Close"])
df["KST_sig"] = ta.kst_sig(df["Close"])
df["KST_diff"] = (df["KST"] - df["KST_sig"])
df["MACD_diff"] = ta.macd_diff(df["Close"])
df["Mass_index"] = ta.mass_index(df["High"], df["Low"])
df["Trix"] = ta.trix(df["Close"])
df["Vortex_pos"] = ta.vortex_indicator_pos(df["High"], df["Low"],
df["Close"])
df["Vortex_neg"] = ta.vortex_indicator_neg(df["High"], df["Low"],
df["Close"])
df["Vortex_diff"] = abs(df["Vortex_pos"] - df["Vortex_neg"])
# Add volatility indicators
df["BBH"] = ta.bollinger_hband(df["Close"])
df["BBL"] = ta.bollinger_lband(df["Close"])
df["BBM"] = ta.bollinger_mavg(df["Close"])
df["BBHI"] = ta.bollinger_hband_indicator(df["Close"])
df["BBLI"] = ta.bollinger_lband_indicator(df["Close"])
df["KCHI"] = ta.keltner_channel_hband_indicator(df["High"], df["Low"],
df["Close"])
df["KCLI"] = ta.keltner_channel_lband_indicator(df["High"], df["Low"],
df["Close"])
df["DCHI"] = ta.donchian_channel_hband_indicator(df["Close"])
df["DCLI"] = ta.donchian_channel_lband_indicator(df["Close"])
# Volume indicators
df["ADI"] = ta.acc_dist_index(df["High"], df["Low"], df["Close"],
df["Volume"])
df["CMF"] = ta.chaikin_money_flow(df["High"], df["Low"], df["Close"],
df["Volume"])
df["EM"] = ta.ease_of_movement(df["High"], df["Low"], df["Close"],
df["Volume"])
df["FI"] = ta.force_index(df["Close"], df["Volume"])
df["NVI"] = ta.negative_volume_index(df["Close"], df["Volume"])
df["OBV"] = ta.on_balance_volume(df["Close"], df["Volume"])
df["VPT"] = ta.volume_price_trend(df["Close"], df["Volume"])
# Add miscellaneous indicators
df["DR"] = ta.daily_return(df["Close"])
df["DLR"] = ta.daily_log_return(df["Close"])
# Fill in NaN values
df.fillna(method="bfill", inplace=True) # First try `bfill`
df.fillna(value=0,
inplace=True) # Then replace the rest of the NANs with 0s
return df