def addTarget_1_minus(dataset, futureDays=30):
prices = dataset.price
m = futureDays
y_var = []
for t in range(0, len(prices) - m + 1):
p = prices.iloc[t:t + m]
_, var = future_mean_var(p, True)
y_var.append(var * 10000)
for t in range(len(y_var), len(prices)):
y_var.append(np.nan)
dataset['y'] = y_var
return dataset.dropna()
def addTarget_mean(dataset, futureDays=30):
prices = dataset.price
m = futureDays
y_m = []
for t in range(0, len(prices) - m + 1):
p = prices.iloc[t:t + m]
mean, _ = future_mean_var(p)
y_m.append(mean * 100)
for t in range(len(prices) - m + 1, len(prices)):
y_m.append(np.nan)
dataset['y'] = y_m
print(max(y_m), min(y_m))
return dataset.dropna()
def rpw_future(prices,
initial_weights=None,
risk_weights=None,
risk_parity_method='ccd',
maximum_iterations=100,
tolerance=1E-8,
min_assets_number=2,
max_assets_number=6):
r = prices.to_returns().dropna()
covar = ledoit_wolf(r)[0]
for i in range(len(r.columns)):
_, var = future_mean_var(prices[prices.columns[i]].values)
covar[i, i] = var * 100
return covar
def addTarget(dataset, futureDays=30):
prices = dataset.price
m = futureDays
y_var = []
for t in range(0, len(prices)-m+1):
p = prices.iloc[t:t+m]
_, var = future_mean_var(p)
y_var.append(var*10000)
y_min = min(y_var)
y_max = max(y_var)
y_distance = y_max-y_min
for t in range(len(y_var)):
y_var[t] = (y_var[t]-y_min)/y_distance
for t in range(len(prices)-m+1, len(prices)):
y_var.append(np.nan)
dataset['y'] = y_var
return dataset.dropna()
def addTarget_2(dataset, futureDays=30, sm=5):
prices = dataset.price
m = futureDays
y_var = []
for t in range(0, len(prices) - m + 1):
p = prices.iloc[t:t + m]
_, var = future_mean_var(p) #, True)
y_var.append(var * 10000)
ym_var = []
for t in range(sm, len(y_var)):
ym_var.append(sum(y_var[t - sm:t]) / sm)
for t in range(len(ym_var), len(prices)):
ym_var.append(np.nan)
dataset['y'] = ym_var
return dataset.dropna()
import pandas as pd
import numpy as np
# retrieve data from eod
etf_tickers = ['2800']
prices = ffn.get(tickers=etf_tickers,
market='HK',
provider=eod,
start='2005-01-01')
m = 30
mean = []
std = []
for t in range(0, len(prices) - m + 1):
p = prices[t:t + m].values
mean_t, var_t = future_mean_var(p, False)
mean.append(mean_t)
std.append(var_t**0.5)
p = prices['2800'][0:len(mean)].values
df = pd.DataFrame({
'2800': p,
'mean': mean,
'std': std
},
index=prices.index[0:len(mean)])
df['mal'] = MA(df['2800'], 120)
df['mas'] = MA(df['2800'], 10)
df['diff'] = (df['mas'] / df['mal'] - 1) / 10
df['slope'] = df['diff'].pct_change()
df['mean_std'] = 2 * df['std'] - df['mean']