volatility = pd.rolling_sum((x - x.shift(1)).abs(), n)
er = change / volatility
sc = (er * (2.0 / (pow1 + 1.0) - 2.0 / (pow2 + 1.0)) + 2.0 /
(pow2 + 1.0))**2.0
kama = [np.nan] * sc.size
first_value = True
for i in range(len(kama)):
if not pd.isnull(sc[i]):
if first_value:
kama[i] = x[i]
first_value = False
else:
kama[i] = kama[i - 1] + sc[i] * (x[i] - kama[i - 1])
return Series(data=[np.nan] * nan_count + kama,
name="KAMA_%d,%d,%d" % (n, pow1, pow2))
def test_kama(closes):
"""KAMA test function."""
kama10 = kama(closes, 10, 2, 30)
data = pd.concat([closes, kama10], axis=1)
# print(data)
data.plot(title="KAMA Chart")
plt.show()
if __name__ == "__main__":
test_kama(gen_closes())
wma = []
bar_count = len(arg)
nan_count = window - 1
if bar_count < nan_count:
nan_count = bar_count
for i in range(nan_count):
wma.append(np.nan)
div = (window + 1) * window / 2.0
for i in range(window-1, bar_count):
sum = 0
for j in range(window):
sum += arg[i - j] * (window - j)
wma.append(sum / div);
return Series(data = wma, name="wma" + str(window), index = arg.index)
def test_wma(closes):
"""WMA test function."""
wma5 = wma(closes, 5)
wma10 = wma(closes, 10)
data = pd.concat([closes, wma5, wma10], axis=1)
# print(data)
data.plot(title = "WMA Chart")
plt.show()
if __name__ == "__main__":
test_wma(gen_closes())
which will be used in calculating Bollinger Bands.
"""
sd = [np.nan] * min(closes.size, window - 1)
for i in range(window - 1, closes.size):
sum = 0.0
m = boll_mid[i]
for j in range(window):
sum += (closes[i - j] - m) ** 2;
sd.append(math.sqrt(sum / window))
return Series(data = sd, name = "sd")
boll_mid = sma(closes, window)
sd = calc_sd()
boll_up = boll_mid + sd * d
boll_low = boll_mid - sd * d
return DataFrame({"BOLL_UP":boll_up, "BOLL_MID":boll_mid, "BOLL_LOW":boll_low})
def test_bbands(closes):
"""BBANDS test function."""
bb = bbands(closes, 20, 2)
data = pd.concat([DataFrame(closes), bb], axis=1)
# print(data)
data.plot(title = "BBANDS Chart")
plt.show()
if __name__ == "__main__":
test_bbands(gen_closes(200))
def sma(arg, window):
"""SMA: Simple Moving Average.
Params:
arg (Series): Time series data such as close prices.
window (int): Moving average window size.
Returns:
Series: Simple moving average of arg.
"""
ma = pd.rolling_mean(arg, window)
return Series(data=ma, name="SMA" + str(window))
def test_sma(closes):
"""SMA test function."""
sma5 = sma(closes, 5)
sma10 = sma(closes, 10)
data = pd.concat([closes, sma5, sma10], axis=1)
# print(data)
data.plot(title="SMA Chart")
plt.show()
if __name__ == "__main__":
test_sma(gen_closes())
"""DEMA: Double Exponential Moving Average.
Params:
arg (Series): Time series data such as close prices.
window (int): Moving average window size.
Returns:
Series: Double exponential moving average of arg.
"""
ema1 = ema(arg, window)
ema2 = ema(ema1, window)
dema = ema1 * 2 - ema2
return Series(data = dema, name = "dema" + str(window))
def test_dema(closes):
"""DEMA test function."""
dema5 = dema(closes, 5)
dema10 = dema(closes, 10)
data = pd.concat([closes, dema5, dema10], axis=1)
# print(data)
data.plot(title = "DEMA Chart")
plt.show()
if __name__ == "__main__":
test_dema(gen_closes())
"divergence": divergence
})
def test_macd(closes):
"""MACD test function."""
macd_indicator = macd(closes)
data = macd_indicator
# print(data)
# Plot the price series.
ax1 = plt.subplot2grid((6, 4), (0, 0), rowspan=4, colspan=4)
ax1.grid(True)
ax1.plot(closes)
plt.ylabel("CLOSE")
plt.title("MACD Chart")
# Plot MACD.
ax2 = plt.subplot2grid((6, 4), (4, 0), sharex=ax1, rowspan=2, colspan=4)
ax2.grid(True)
ax2.plot(data["macd"])
ax2.plot(data["signal"])
ax2.fill_between(data.index, data["divergence"], 0, alpha=0.5)
plt.ylabel("MACD")
plt.setp(ax1.get_xticklabels(), visible=False)
plt.show()
if __name__ == "__main__":
test_macd(gen_closes())
def sma(arg, window):
"""SMA: Simple Moving Average.
Params:
arg (Series): Time series data such as close prices.
window (int): Moving average window size.
Returns:
Series: Simple moving average of arg.
"""
ma = arg.rolling(window=window,center=False).mean()
return Series(data = ma, name = "sma" + str(window))
def test_sma(closes):
"""SMA test function."""
sma5 = sma(closes, 5)
sma10 = sma(closes, 10)
data = pd.concat([closes, sma5, sma10], axis=1)
# print(data)
data.plot(title = "SMA Chart")
plt.show()
if __name__ == "__main__":
test_sma(gen_closes())
Params:
arg (Series): Time series data such as close prices.
window (int): Moving average window size.
Returns:
Series: Triple exponential moving average of arg.
"""
ema1 = ema(arg, window)
ema2 = ema(ema1, window)
ema3 = ema(ema2, window)
tema = ema1 * 3 - ema2 * 3 + ema3
return Series(data = tema, name = "tema" + str(window))
def test_tema(closes):
"""TEMA test function."""
tema5 = tema(closes, 5)
tema10 = tema(closes, 10)
data = pd.concat([closes, tema5, tema10], axis=1)
# print(data)
data.plot(title = "TEMA Chart")
plt.show()
if __name__ == "__main__":
test_tema(gen_closes())
Params:
arg (Series): Time series data such as close prices.
window (int): Moving average window size.
Returns:
Series: Exponential moving average of arg.
"""
arg = Series(arg.dropna().values)
ema = []
w = 2.0 / (window + 1)
ema.append(arg[0])
for i in range(1, len(arg)):
ema.append(arg[i] * w + ema[-1] * (1.0 - w))
return Series(data=ema, name="EMA" + str(window))
def test_ema(closes):
"""EMA test function."""
ema5 = ema(closes, 5)
ema10 = ema(closes, 10)
data = pd.concat([closes, ema5, ema10], axis=1)
# print(data)
data.plot(title="EMA Chart")
plt.show()
if __name__ == "__main__":
test_ema(gen_closes())
"""DEMA: Double Exponential Moving Average.
Params:
arg (Series): Time series data such as close prices.
window (int): Moving average window size.
Returns:
Series: Double exponential moving average of arg.
"""
ema1 = ema(arg, window)
ema2 = ema(ema1, window)
dema = ema1 * 2 - ema2
return Series(data = dema, name = "dema" + str(window))
def test_dema(closes):
"""DEMA test function."""
dema5 = dema(closes, 5)
dema10 = dema(closes, 10)
data = pd.concat([closes, dema5, dema10], axis=1)
# print(data)
data.plot(title = "DEMA Chart")
plt.show()
if __name__ == "__main__":
test_dema(gen_closes())
Params:
arg (Series): Time series data such as close prices.
window (int): Moving average window size.
Returns:
Series: Exponential moving average of arg.
"""
arg = Series(arg.dropna().values, index = arg.index)
ema = []
w = 2.0 / (window + 1)
ema.append(arg[0])
for i in range(1, len(arg)):
ema.append(arg[i] * w + ema[-1] * (1.0 - w))
return Series(data = ema, name = "ema" + str(window), index = arg.index)
def test_ema(closes):
"""EMA test function."""
ema5 = ema(closes, 5)
ema10 = ema(closes, 10)
data = pd.concat([closes, ema5, ema10], axis=1)
# print(data)
data.plot(title = "EMA Chart")
plt.show()
if __name__ == "__main__":
test_ema(gen_closes())
change = (x - x.shift(n)).abs()
volatility = (x - x.shift(1)).abs().rolling(window=n).sum()
er = change / volatility
sc = (er * (2.0 /(pow1 + 1.0) - 2.0 / (pow2 + 1.0)) + 2.0 / (pow2 + 1.0)) ** 2.0
kama = [np.nan] * sc.size
first_value = True
for i in range(len(kama)):
if not pd.isnull(sc[i]):
if first_value:
kama[i] = x[i]
first_value = False
else:
kama[i] = kama[i-1] + sc[i] * (x[i] - kama[i-1])
return Series(data = [np.nan] * nan_count + kama, name = "kama(%d,%d,%d)" % (n, pow1, pow2), index = x.index)
def test_kama(closes):
"""KAMA test function."""
kama10 = kama(closes, 10, 2, 30)
data = pd.concat([closes, kama10], axis=1)
# print(data)
data.plot(title = "KAMA Chart")
plt.show()
if __name__ == "__main__":
test_kama(gen_closes())
