def eom(df, number):
h = df.high
l = df.low
v = df.volume
eom = tav.ease_of_movement(h, l, v, n=number)
df['ease'] = eom
return df
def test_ease_of_movement(self):
target = 'EMV'
result = ease_of_movement(high=self._df['High'],
low=self._df['Low'],
volume=self._df['Volume'],
n=14,
fillna=False)
pd.testing.assert_series_equal(self._df[target].tail(),
result.tail(),
check_names=False)
def EOM(df, intervals):
"""
Ease of Movement
Key Takeaways from Reference: https://www.investopedia.com/terms/e/easeofmovement.asp
- This indicator calculates how easily a price can move up or down.
- The calculation subtracts yesterday's average price from today's average price and divides the difference by volume.
- This generates a volume-weighted momentum indicator.
"""
from tqdm.auto import tqdm
from ta.volume import ease_of_movement
for interval in tqdm(intervals):
df['eom_' + str(interval)] = ease_of_movement(df['high'],
df['low'],
df['volume'],
n=interval,
fillna=True)
def ease_mov(datos, start, end = '', window = 10):
'''
ENTRADA
datos: Pandas dataframe que contiene al menos una columna de fechas (DATE) y otra
columna numérica
start, end: strings en formato 'YYYY-MM-DD' representando la fecha de inicio
y la fecha final respectivamente
window: Entero que representa la ventan de tiempo a utilizar
SALIDA
resultado: Dataframe datos con una columna extra conteniendo la información
del indicador
'''
#Localiza la fecha de inicio y revisa si hay suficiente información
indiceInicio=datos[datos['Date']==start].index[0]
if window > indiceInicio + 1:
print 'No hay suficiente historia para esta fecha'
return datos
#Último índice
if end=='':
lastIndex=datos.shape[0] - 1
else:
lastIndex=datos[datos['Date']==end].index[0]
#calcula el indicador
indicador = ease_of_movement(datos['High'], datos['Low'], datos['Adj Close'], datos['Volume'], window)
#agrega la nueva columna
resultado = deepcopy(datos)
resName = 'Ease-Mov-' + str(window)
resultado[resName] = indicador
#Filtra a partir del índice correspondiente a la fecha start
resultado=resultado.iloc[indiceInicio:lastIndex+1,:]
resultado=resultado.reset_index(drop=True)
#añade metadatos
resultado.tipo = 'ease-mov'
resultado.resName = resName
return resultado
def engineer_data_over_single_interval(df: pd.DataFrame,
indicators: list,
ticker: str = "",
rsi_n: int = 14,
cmo_n: int = 7,
macd_fast: int = 12,
macd_slow: int = 26,
macd_sign: int = 9,
roc_n: int = 12,
cci_n: int = 20,
dpo_n: int = 20,
cmf_n: int = 20,
adx_n: int = 14,
mass_index_low: int = 9,
mass_index_high: int = 25,
trix_n: int = 15,
stochastic_oscillator_n: int = 14,
stochastic_oscillator_sma_n: int = 3,
ultimate_oscillator_short_n: int = 7,
ultimate_oscillator_medium_n: int = 14,
ultimate_oscillator_long_n: int = 28,
ao_short_n: int = 5,
ao_long_n: int = 34,
kama_n: int = 10,
tsi_high_n: int = 25,
tsi_low_n: int = 13,
eom_n: int = 14,
force_index_n: int = 13,
ichimoku_low_n: int = 9,
ichimoku_medium_n: int = 26):
from ta.momentum import rsi, wr, roc, ao, stoch, uo, kama, tsi
from ta.trend import macd, macd_signal, cci, dpo, adx, mass_index, trix, ichimoku_a
from ta.volume import chaikin_money_flow, acc_dist_index, ease_of_movement, force_index
# Momentum Indicators
if Indicators.RELATIVE_STOCK_INDEX in indicators:
Logger.console_log(message="Calculating " +
Indicators.RELATIVE_STOCK_INDEX.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.RELATIVE_STOCK_INDEX.value] = rsi(close=df['close'],
n=rsi_n)
if Indicators.WILLIAMS_PERCENT_RANGE in indicators:
Logger.console_log(message="Calculating " +
Indicators.WILLIAMS_PERCENT_RANGE.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.WILLIAMS_PERCENT_RANGE.value] = wr(
df['high'], df['low'], df['close'])
if Indicators.CHANDE_MOMENTUM_OSCILLATOR in indicators:
Logger.console_log(message="Calculating " +
Indicators.CHANDE_MOMENTUM_OSCILLATOR.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.CHANDE_MOMENTUM_OSCILLATOR.
value] = chande_momentum_oscillator(close_data=df['close'],
period=cmo_n)
if Indicators.RATE_OF_CHANGE in indicators:
Logger.console_log(message="Calculating " +
Indicators.RATE_OF_CHANGE.value + " for stock " +
ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.RATE_OF_CHANGE.value] = roc(close=df['close'], n=roc_n)
if Indicators.STOCHASTIC_OSCILLATOR in indicators:
Logger.console_log(message="Calculating " +
Indicators.STOCHASTIC_OSCILLATOR.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.STOCHASTIC_OSCILLATOR.value] = stoch(
high=df['high'],
low=df['low'],
close=df['close'],
n=stochastic_oscillator_n,
d_n=stochastic_oscillator_sma_n)
if Indicators.ULTIMATE_OSCILLATOR in indicators:
Logger.console_log(message="Calculating " +
Indicators.ULTIMATE_OSCILLATOR.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.ULTIMATE_OSCILLATOR.value] = uo(
high=df['high'],
low=df['low'],
close=df['close'],
s=ultimate_oscillator_short_n,
m=ultimate_oscillator_medium_n,
len=ultimate_oscillator_long_n)
if Indicators.AWESOME_OSCILLATOR in indicators:
Logger.console_log(message="Calculating " +
Indicators.AWESOME_OSCILLATOR.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.AWESOME_OSCILLATOR.value] = ao(high=df['high'],
low=df['low'],
s=ao_short_n,
len=ao_long_n)
if Indicators.KAUFMAN_ADAPTIVE_MOVING_AVERAGE in indicators:
Logger.console_log(message="Calculating " +
Indicators.KAUFMAN_ADAPTIVE_MOVING_AVERAGE.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.KAUFMAN_ADAPTIVE_MOVING_AVERAGE.value] = kama(
close=df['close'], n=kama_n)
if Indicators.TRUE_STRENGTH_INDEX in indicators:
Logger.console_log(message="Calculating " +
Indicators.TRUE_STRENGTH_INDEX.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.TRUE_STRENGTH_INDEX.value] = tsi(close=df['close'],
r=tsi_high_n,
s=tsi_low_n)
# Trend Indicator
if Indicators.MOVING_AVERAGE_CONVERGENCE_DIVERGENCE in indicators:
Logger.console_log(
message="Calculating " +
Indicators.MOVING_AVERAGE_CONVERGENCE_DIVERGENCE.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.MOVING_AVERAGE_CONVERGENCE_DIVERGENCE.value] = macd(close=df['close'],
n_slow=macd_slow,
n_fast=macd_fast) - \
macd_signal(close=df['close'],
n_slow=macd_slow,
n_fast=macd_fast,
n_sign=macd_sign)
if Indicators.COMMODITY_CHANNEL_INDEX in indicators:
Logger.console_log(message="Calculating " +
Indicators.COMMODITY_CHANNEL_INDEX.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.COMMODITY_CHANNEL_INDEX.value] = cci(high=df['high'],
low=df['low'],
close=df['close'],
n=cci_n)
if Indicators.DETRENDED_PRICE_OSCILLATOR in indicators:
Logger.console_log(message="Calculating " +
Indicators.DETRENDED_PRICE_OSCILLATOR.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.DETRENDED_PRICE_OSCILLATOR.value] = dpo(
close=df['close'], n=dpo_n)
if Indicators.AVERAGE_DIRECTIONAL_INDEX in indicators:
Logger.console_log(message="Calculating " +
Indicators.AVERAGE_DIRECTIONAL_INDEX.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.AVERAGE_DIRECTIONAL_INDEX.value] = adx(high=df['high'],
low=df['low'],
close=df['close'],
n=adx_n)
if Indicators.MASS_INDEX in indicators:
Logger.console_log(message="Calculating " +
Indicators.MASS_INDEX.value + " for stock " +
ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.MASS_INDEX.value] = mass_index(high=df['high'],
low=df['low'],
n=mass_index_low,
n2=mass_index_high)
if Indicators.TRIPLE_EXPONENTIALLY_SMOOTHED_MOVING_AVERAGE in indicators:
Logger.console_log(
message="Calculating " +
Indicators.TRIPLE_EXPONENTIALLY_SMOOTHED_MOVING_AVERAGE.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.TRIPLE_EXPONENTIALLY_SMOOTHED_MOVING_AVERAGE.
value] = trix(close=df['close'], n=trix_n)
if Indicators.ICHIMOKU_A in indicators:
Logger.console_log(message="Calculating " +
Indicators.ICHIMOKU_A.value + " for stock " +
ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.ICHIMOKU_A.value] = ichimoku_a(high=df['high'],
low=df['low'],
n1=ichimoku_low_n,
n2=ichimoku_medium_n)
# Volume Indicator
if Indicators.CHAIKIN_MONEY_FLOW in indicators:
Logger.console_log(message="Calculating " +
Indicators.CHAIKIN_MONEY_FLOW.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.CHAIKIN_MONEY_FLOW.value] = chaikin_money_flow(
high=df['high'],
low=df['low'],
close=df['close'],
volume=df['volume'],
n=cmf_n)
if Indicators.ACCUMULATION_DISTRIBUTION_INDEX in indicators:
Logger.console_log(message="Calculating " +
Indicators.ACCUMULATION_DISTRIBUTION_INDEX.value +
" for stock " + ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.ACCUMULATION_DISTRIBUTION_INDEX.value] = acc_dist_index(
high=df['high'],
low=df['low'],
close=df['close'],
volume=df['volume'])
if Indicators.EASE_OF_MOVEMENT in indicators:
Logger.console_log(message="Calculating " +
Indicators.EASE_OF_MOVEMENT.value + " for stock " +
ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.EASE_OF_MOVEMENT.value] = ease_of_movement(
high=df['high'], low=df['low'], volume=df['volume'], n=eom_n)
if Indicators.FORCE_INDEX in indicators:
Logger.console_log(message="Calculating " +
Indicators.FORCE_INDEX.value + " for stock " +
ticker,
status=Logger.LogStatus.EMPHASIS)
df[Indicators.FORCE_INDEX.value] = force_index(close=df['close'],
volume=df['volume'],
n=force_index_n)
def __dataframe(self):
"""Create an comprehensive list of from data.
Args:
None
Returns:
result: dataframe for learning
"""
# Calculate the percentage and real differences between columns
difference = math.Difference(self._ohlcv)
num_difference = difference.actual()
pct_difference = difference.relative()
# Create result to return.
result = pd.DataFrame()
# Add current value columns
result['open'] = self._ohlcv['open']
result['high'] = self._ohlcv['high']
result['low'] = self._ohlcv['low']
result['close'] = self._ohlcv['close']
result['volume'] = self._ohlcv['volume']
# Add columns of differences
result['num_diff_open'] = num_difference['open']
result['num_diff_high'] = num_difference['high']
result['num_diff_low'] = num_difference['low']
result['num_diff_close'] = num_difference['close']
result['pct_diff_open'] = pct_difference['open']
result['pct_diff_high'] = pct_difference['high']
result['pct_diff_low'] = pct_difference['low']
result['pct_diff_close'] = pct_difference['close']
result['pct_diff_volume'] = pct_difference['volume']
# Add date related columns
# result['day'] = self._dates.day
result['weekday'] = self._dates.weekday
# result['week'] = self._dates.week
result['month'] = self._dates.month
result['quarter'] = self._dates.quarter
# result['dayofyear'] = self._dates.dayofyear
# Moving averages
result['ma_open'] = result['open'].rolling(
self._globals['ma_window']).mean()
result['ma_high'] = result['high'].rolling(
self._globals['ma_window']).mean()
result['ma_low'] = result['low'].rolling(
self._globals['ma_window']).mean()
result['ma_close'] = result['close'].rolling(
self._globals['ma_window']).mean()
result['ma_volume'] = result['volume'].rolling(
self._globals['vma_window']).mean()
result['ma_volume_long'] = result['volume'].rolling(
self._globals['vma_window_long']).mean()
result[
'ma_volume_delta'] = result['ma_volume_long'] - result['ma_volume']
# Standard deviation related
result['ma_std_close'] = result['close'].rolling(
self._globals['ma_window']).std()
result['std_pct_diff_close'] = result['pct_diff_close'].rolling(
self._globals['ma_window']).std()
result['bollinger_lband'] = volatility.bollinger_lband(result['close'])
result['bollinger_hband'] = volatility.bollinger_lband(result['close'])
result[
'bollinger_lband_indicator'] = volatility.bollinger_lband_indicator(
result['close'])
result[
'bollinger_hband_indicator'] = volatility.bollinger_hband_indicator(
result['close'])
# Rolling ranges
result['amplitude'] = result['high'] - result['low']
_min = result['low'].rolling(self._globals['week']).min()
_max = result['high'].rolling(self._globals['week']).max()
result['amplitude_medium'] = abs(_min - _max)
_min = result['low'].rolling(2 * self._globals['week']).min()
_max = result['high'].rolling(2 * self._globals['week']).max()
result['amplitude_long'] = abs(_min - _max)
_min = result['volume'].rolling(self._globals['week']).min()
_max = result['volume'].rolling(self._globals['week']).max()
result['vol_amplitude'] = abs(_min - _max)
_min = result['volume'].rolling(2 * self._globals['week']).min()
_max = result['volume'].rolling(2 * self._globals['week']).max()
result['vol_amplitude_long'] = abs(_min - _max)
# Volume metrics
result['force_index'] = volume.force_index(result['close'],
result['volume'])
result['negative_volume_index'] = volume.negative_volume_index(
result['close'], result['volume'])
result['ease_of_movement'] = volume.ease_of_movement(
result['high'], result['low'], result['close'], result['volume'])
result['acc_dist_index'] = volume.acc_dist_index(
result['high'], result['low'], result['close'], result['volume'])
result['on_balance_volume'] = volume.on_balance_volume(
result['close'], result['volume'])
result['on_balance_volume_mean'] = volume.on_balance_volume(
result['close'], result['volume'])
result['volume_price_trend'] = volume.volume_price_trend(
result['close'], result['volume'])
# Calculate the Stochastic values
result['k'] = momentum.stoch(result['high'],
result['low'],
result['close'],
n=self._globals['kwindow'])
result['d'] = momentum.stoch_signal(result['high'],
result['low'],
result['close'],
n=self._globals['kwindow'],
d_n=self._globals['dwindow'])
# Calculate the Miscellaneous values
result['rsi'] = momentum.rsi(result['close'],
n=self._globals['rsiwindow'],
fillna=False)
miscellaneous = math.Misc(self._ohlcv)
result['proc'] = miscellaneous.proc(self._globals['proc_window'])
# Calculate ADX
result['adx'] = trend.adx(result['high'],
result['low'],
result['close'],
n=self._globals['adx_window'])
# Calculate MACD difference
result['macd_diff'] = trend.macd_diff(
result['close'],
n_fast=self._globals['macd_sign'],
n_slow=self._globals['macd_slow'],
n_sign=self._globals['macd_sign'])
# Create series for increasing / decreasing closes (Convert NaNs to 0)
_result = np.nan_to_num(result['pct_diff_close'].values)
_increasing = (_result >= 0).astype(int) * self._buy
_decreasing = (_result < 0).astype(int) * self._sell
result['increasing'] = _increasing + _decreasing
# Stochastic subtraciton
result['k_d'] = pd.Series(result['k'].values - result['d'].values)
# Other indicators
result['k_i'] = self._stochastic_indicator(result['k'], result['high'],
result['low'],
result['ma_close'])
result['d_i'] = self._stochastic_indicator(result['d'], result['high'],
result['low'],
result['ma_close'])
result['stoch_i'] = self._stochastic_indicator_2(
result['k'], result['d'], result['high'], result['low'],
result['ma_close'])
result['rsi_i'] = self._rsi_indicator(result['rsi'], result['high'],
result['low'],
result['ma_close'])
result['adx_i'] = self._adx_indicator(result['adx'])
result['macd_diff_i'] = self._macd_diff_indicator(result['macd_diff'])
result['volume_i'] = self._volume_indicator(result['ma_volume'],
result['ma_volume_long'])
# Create time shifted columns
for step in range(1, self._ignore_row_count + 1):
# result['t-{}'.format(step)] = result['close'].shift(step)
result['tpd-{}'.format(step)] = result['close'].pct_change(
periods=step)
# result['tad-{}'.format(step)] = result[
# 'close'].diff(periods=step)
# Mask increasing with
result['increasing_masked'] = _mask(result['increasing'].to_frame(),
result['stoch_i'],
as_integer=True).values
# Get class values for each vector
classes = pd.DataFrame(columns=self._shift_steps)
for step in self._shift_steps:
# Shift each column by the value of its label
classes[step] = result[self._label2predict].shift(-step)
# Remove all undesirable columns from the dataframe
undesired_columns = ['open', 'close', 'high', 'low', 'volume']
for column in undesired_columns:
result = result.drop(column, axis=1)
# Delete the firsts row of the dataframe as it has NaN values from the
# .diff() and .pct_change() operations
result = result.iloc[self._ignore_row_count:]
classes = classes.iloc[self._ignore_row_count:]
# Convert result to float32 to conserve memory
result = result.astype(np.float32)
# Return
return result, classes
def test_ease_of_movement(self):
target = "EMV"
result = ease_of_movement(**self._params)
pd.testing.assert_series_equal(self._df[target].tail(),
result.tail(),
check_names=False)
def __dataframe(self):
"""Create an comprehensive list of from data.
Args:
None
Returns:
result: dataframe for learning
"""
# Calculate the percentage and real differences between columns
difference = math.Difference(self._ohlcv)
num_difference = difference.actual()
pct_difference = difference.relative()
# Create result to return.
result = pd.DataFrame()
# Add current value columns
# NOTE Close must be first for correct correlation column dropping
result['close'] = self._ohlcv['close']
result['open'] = self._ohlcv['open']
result['high'] = self._ohlcv['high']
result['low'] = self._ohlcv['low']
result['volume'] = self._ohlcv['volume']
# Add columns of differences
# NOTE Close must be first for correct correlation column dropping
result['num_diff_close'] = num_difference['close']
result['pct_diff_close'] = pct_difference['close']
result['num_diff_open'] = num_difference['open']
result['pct_diff_open'] = pct_difference['open']
result['num_diff_high'] = num_difference['high']
result['pct_diff_high'] = pct_difference['high']
result['num_diff_low'] = num_difference['low']
result['pct_diff_low'] = pct_difference['low']
result['pct_diff_volume'] = pct_difference['volume']
# Add date related columns
# result['day'] = self._dates.day
result['weekday'] = self._dates.weekday
# result['week'] = self._dates.week
result['month'] = self._dates.month
result['quarter'] = self._dates.quarter
# result['dayofyear'] = self._dates.dayofyear
# Moving averages
result['ma_open'] = result['open'].rolling(
self._globals['ma_window']).mean()
result['ma_high'] = result['high'].rolling(
self._globals['ma_window']).mean()
result['ma_low'] = result['low'].rolling(
self._globals['ma_window']).mean()
result['ma_close'] = result['close'].rolling(
self._globals['ma_window']).mean()
result['ma_volume'] = result['volume'].rolling(
self._globals['vma_window']).mean()
result['ma_volume_long'] = result['volume'].rolling(
self._globals['vma_window_long']).mean()
result['ma_volume_delta'] = result[
'ma_volume_long'] - result['ma_volume']
# Standard deviation related
result['ma_std_close'] = result['close'].rolling(
self._globals['ma_window']).std()
result['std_pct_diff_close'] = result['pct_diff_close'].rolling(
self._globals['ma_window']).std()
result['bollinger_lband'] = volatility.bollinger_lband(result['close'])
result['bollinger_hband'] = volatility.bollinger_lband(result['close'])
result['bollinger_lband_indicator'] = volatility.bollinger_lband_indicator(result['close'])
result['bollinger_hband_indicator'] = volatility.bollinger_hband_indicator(result['close'])
# Rolling ranges
result['amplitude'] = result['high'] - result['low']
_min = result['low'].rolling(
self._globals['week']).min()
_max = result['high'].rolling(
self._globals['week']).max()
result['amplitude_medium'] = abs(_min - _max)
_min = result['low'].rolling(
2 * self._globals['week']).min()
_max = result['high'].rolling(
2 * self._globals['week']).max()
result['amplitude_long'] = abs(_min - _max)
_min = result['volume'].rolling(
self._globals['week']).min()
_max = result['volume'].rolling(
self._globals['week']).max()
result['vol_amplitude'] = abs(_min - _max)
_min = result['volume'].rolling(
2 * self._globals['week']).min()
_max = result['volume'].rolling(
2 * self._globals['week']).max()
result['vol_amplitude_long'] = abs(_min - _max)
# Volume metrics
result['force_index'] = volume.force_index(
result['close'], result['volume'])
result['negative_volume_index'] = volume.negative_volume_index(
result['close'], result['volume'])
result['ease_of_movement'] = volume.ease_of_movement(
result['high'], result['low'], result['close'], result['volume'])
result['acc_dist_index'] = volume.acc_dist_index(
result['high'], result['low'], result['close'], result['volume'])
result['on_balance_volume'] = volume.on_balance_volume(
result['close'], result['volume'])
result['on_balance_volume_mean'] = volume.on_balance_volume(
result['close'], result['volume'])
result['volume_price_trend'] = volume.volume_price_trend(
result['close'], result['volume'])
# Calculate the Stochastic values
result['k'] = momentum.stoch(
result['high'],
result['low'],
result['close'],
n=self._globals['kwindow'])
result['d'] = momentum.stoch_signal(
result['high'],
result['low'],
result['close'],
n=self._globals['kwindow'],
d_n=self._globals['dwindow'])
# Calculate the Miscellaneous values
result['rsi'] = momentum.rsi(
result['close'],
n=self._globals['rsiwindow'],
fillna=False)
miscellaneous = math.Misc(self._ohlcv)
result['proc'] = miscellaneous.proc(self._globals['proc_window'])
# Calculate ADX
result['adx'] = trend.adx(
result['high'],
result['low'],
result['close'],
n=self._globals['adx_window'])
# Calculate MACD difference
result['macd_diff'] = trend.macd_diff(
result['close'],
n_fast=self._globals['macd_sign'],
n_slow=self._globals['macd_slow'],
n_sign=self._globals['macd_sign'])
# Create series for increasing / decreasing closes (Convert NaNs to 0)
_result = np.nan_to_num(result['pct_diff_close'].values)
_increasing = (_result >= 0).astype(int) * self._buy
_decreasing = (_result < 0).astype(int) * self._sell
result['increasing'] = _increasing + _decreasing
# Stochastic subtraciton
result['k_d'] = pd.Series(result['k'].values - result['d'].values)
# Other indicators
result['k_i'] = self._stochastic_indicator(
result['k'], result['high'], result['low'], result['ma_close'])
result['d_i'] = self._stochastic_indicator(
result['d'], result['high'], result['low'], result['ma_close'])
result['stoch_i'] = self._stochastic_indicator_2(
result['k'], result['d'],
result['high'], result['low'], result['ma_close'])
result['rsi_i'] = self._rsi_indicator(
result['rsi'], result['high'], result['low'], result['ma_close'])
result['adx_i'] = self._adx_indicator(result['adx'])
result['macd_diff_i'] = self._macd_diff_indicator(result['macd_diff'])
result['volume_i'] = self._volume_indicator(
result['ma_volume'], result['ma_volume_long'])
# Create time shifted columns
for step in range(1, self._ignore_row_count + 1):
result['t-{}'.format(step)] = result['close'].shift(step)
result['tpd-{}'.format(step)] = result[
'close'].pct_change(periods=step)
result['tad-{}'.format(step)] = result[
'close'].diff(periods=step)
# Mask increasing with
result['increasing_masked'] = _mask(
result['increasing'].to_frame(),
result['stoch_i'],
as_integer=True).values
# Get class values for each vector
classes = pd.DataFrame(columns=self._shift_steps)
for step in self._shift_steps:
# Shift each column by the value of its label
if self._binary is True:
# Classes need to be 0 or 1 (One hot encoding)
classes[step] = (
result[self._label2predict].shift(-step) > 0).astype(int)
else:
classes[step] = result[self._label2predict].shift(-step)
# classes[step] = result[self._label2predict].shift(-step)
# Delete the firsts row of the dataframe as it has NaN values from the
# .diff() and .pct_change() operations
ignore = max(max(self._shift_steps), self._ignore_row_count)
result = result.iloc[ignore:]
classes = classes.iloc[ignore:]
# Convert result to float32 to conserve memory
result = result.astype(np.float32)
# Return
return result, classes
