def alpha_44(self):
"""
formula: (-1 * ((rank((sum(delay(close, 5), 20) / 20)) * correlation(close, volume, 2))
*rank(correlation(sum(close, 5), sum(close, 20), 2))))
:return: dataframe, need more stock and long range
"""
df = _utils.correlation(self.close, self.volume, 2)
df = df.replace([-np.inf, np.inf], 0).fillna(value=0)
df = -1 * (_utils.rank(_utils.ts_ma(_utils.delay(self.close, 5), 20)) *
df * _utils.rank(
_utils.correlation(_utils.ts_sum(self.close, 5),
_utils.ts_sum(self.close, 20), 2)))
return df.fillna(method='backfill')
def alpha_39(self):
"""
formula: ((-1 * rank(stddev(high, 10))) * correlation(high, volume, 10))
:return:
"""
return -1 * _utils.rank(_utils.stddev(
self.high, 10)) * _utils.correlation(self.high, self.volume, 10)
def alpha_2(self):
"""
formula for alpha2: (-1*correlation(rank(delta(log(volume), 2)), rank(((close - open) / open)), 6))
:return: time series df of all stocks
"""
x1 = _utils.rank(_utils.delta(np.log(self.volume), period=2))
x2 = _utils.rank((self.close - self.open) / self.open)
return -1 * _utils.correlation(x1, x2, window=6)
def alpha_15(self):
"""
formula: (-1 * sum(rank(correlation(rank(high), rank(volume), 3)), 3))
"""
df = _utils.correlation(_utils.rank(self.high),
_utils.rank(self.volume), 3)
df = df.replace([-np.inf, np.inf], 0).fillna(method='backfill')
return (-1 * _utils.ts_sum(_utils.rank(df), 3)).fillna(method='ffill')
def alpha_22(self):
"""
formula: (-1 * (delta(correlation(high, volume, 5), 5) * rank(stddev(close, 20))))
"""
df = _utils.correlation(self.high, self.volume, 5)
df = df.replace([-np.inf, np.inf], 0).fillna(value=0)
return -1 * _utils.delta(df, 5) * _utils.rank(
_utils.stddev(self.close, 20))
def alpha_43(self):
"""
formula: (-1 * correlation(high, rank(volume), 5))
:return:
"""
df = _utils.correlation(self.high, _utils.rank(self.volume), 5)
df = df.replace([-np.inf, np.inf], 0).fillna(value=0)
return -1 * df
def alpha_14(self):
"""
formula:((-1 * rank(delta(returns, 3))) * correlation(open, volume, 10))
:return: dataframe need a lot stock to prevent inf
"""
df = _utils.correlation(self.open, self.volume, window=10)
df = df.replace([-np.inf, np.inf], 0).fillna(method='backfill')
return -1 * _utils.rank(_utils.delta(self.returns, period=3)) * df
def alpha_36(self):
"""
formula: (rank(correlation(delay((open - close), 1), close, 200)) + rank((open - close)))
:return:dataframe, need long range
"""
return (_utils.rank(
_utils.correlation(_utils.delay(self.open - self.close, 1),
self.close, 200)) +
_utils.rank(self.open - self.close)).fillna(method='backfill')
def alpha_28(self):
"""
formula: scale(((correlation(adv20, low, 5) + ((high + low) / 2)) - close))
:return: scaled df
"""
adv20 = _utils.ts_ma(self.volume, 20)
df = _utils.correlation(adv20, self.low, 5)
df = df.replace([-np.inf, np.inf], 0).fillna(value=0)
return _utils.scale(((df + ((self.high + self.low) / 2)) - self.close))
def alpha_3(self):
"""
data size should increse to see the difference
formula for alpha3: (-1*correlation(rank(open), rank(volume), 10))
:return:time series df of all stocks
"""
df = -1 * _utils.correlation(
_utils.rank(self.open), _utils.rank(self.volume), window=10)
return df.replace([-np.inf, np.inf], 0)
def alpha_25(self):
"""
formula: (-1 * ts_max(correlation(ts_rank(volume, 5), ts_rank(high, 5), 5), 3))
"""
return -1 * _utils.ts_max(_utils.correlation(
_utils.ts_rank(self.volume, window=5),
_utils.ts_rank(self.high, window=5),
window=5),
window=3).fillna(method='backfill')
def alpha_26(self):
"""
formula: (-1* ts_max(correlation(ts_rank(volume, 5), ts_rank(high, 5), 5), 3))
"""
df = _utils.correlation(_utils.ts_rank(self.volume, window=5),
_utils.ts_rank(self.high, window=5),
window=3)
df = df.replace([-np.inf, np.inf], 0)
df = -1 * _utils.ts_max(df.fillna(method='backfill'), window=3)
return df.fillna(0.5)
def alpha_18(self):
"""
formula: (-1 * rank(((stddev(abs((close - open)), 5) + (close - open)) + correlation(close, open,10))))
:return
"""
df = _utils.correlation(self.close, self.open, 10)
df = df.replace([-np.inf, np.inf], 0).fillna(value=0)
return -1 * _utils.rank(
_utils.stddev(abs(self.close - self.open), window=5) + self.close -
self.open) + df
def alpha_32(self):
"""
formula: (scale(((sum(close, 7) / 7) - close)) + (20* scale(correlation(vwap, delay(close, 5), 230))))
long time series
:return:
"""
return _utils.scale(
((_utils.ts_ma(self.close, 7) / 7) - self.close)
) + (20 * _utils.scale(
_utils.correlation(self.vwap, _utils.delay(self.close, 5), 230)))
def alpha_48(self):
"""
formula: (-1 * ts_max(rank(correlation(rank(volume), rank(vwap), 5)), 5))
:return:
"""
df = (-1 * _utils.ts_max(
_utils.rank(
_utils.correlation(_utils.rank(self.volume),
_utils.rank(self.vwap), 5)), 5))
return df.fillna(method='bfill')
def alpha_27(self):
"""
formula: ((0.5 < rank((sum(correlation(rank(volume), rank(vwap), 6), 2) / 2.0))) ? (-1* 1) : 1)
:return replaced nan to -1
"""
alpha = _utils.rank((_utils.ts_ma(
_utils.correlation(_utils.rank(self.volume),
_utils.rank(self.vwap), 6), 2)))
alpha[alpha > 0.5] = -1
alpha[alpha <= 0.5] = 1
return alpha.fillna(-1)
def alpha_31(self):
"""
formula: ((rank(rank(rank(decay_linear((-1* rank(rank(delta(close, 10)))), 10)))) +
rank((-1* delta(close, 3)))) + sign(scale(correlation(adv20, low, 12))))
:return:
"""
adv20 = _utils.ts_ma(self.volume, 20)
df = _utils.correlation(adv20, self.low, 12).replace([-np.inf, np.inf],
0).fillna(value=0)
p1 = _utils.rank(
_utils.rank(
_utils.rank(
_utils.decay_linear_pn((-1 * _utils.rank(
_utils.rank(_utils.delta(self.close, 10)))), 10))))
p2 = _utils.rank((-1 * _utils.delta(self.close, 3)))
p3 = np.sign(_utils.scale(df))
return p1 + p2 + p3
def alpha_6(self):
"""
formula for alpha6: (-1*correlation(open, volume, 10))
"""
df = -1 * _utils.correlation(self.open, self.volume, window=10)
return df.replace([-np.inf, np.inf], 0)
