def create_data(symbols: list[str]):
# np.random.seed(0)
# symbols = np.array(ALL)
# np.random.shuffle(symbols)
# symbols = symbols[0:1]
y = YahooData(symbols)
# window_sizes = [5, 10, 15, 20, 30, 40, 50, 60, 80, 100, 150, 200, 400]
window_sizes = [5, 10, 20, 50, 100, 400]
window_sizes = np.array(window_sizes)
max_window = np.max(window_sizes)
future_growth_window = 20
attrs = [
'exp_growth',
'rolling_avg',
]
df_dict = {}
for ii, symbol in enumerate(symbols):
print(f'Calculating symbol {symbol}')
df = y.get_symbol_all(symbol)
if len(df) == 0:
print(f'Symbol {symbol} data not available')
else:
series = df[DF_ADJ_CLOSE]
new = {}
for window in window_sizes:
# Get indicators
ts = TrailingStats(series, window)
for attr in attrs:
feature = getattr(ts, attr)
name = attr + f'({window})'
new[name] = feature[0:-future_growth_window]
# Get future growths
times = utils.dates2days(series.index.values)
dates = series.index[0:-future_growth_window]
_, growths = avg_future_growth(times,
series.values,
window=future_growth_window)
new['avg_future_growth'] = growths
new['date'] = dates
df_new = pd.DataFrame(new)
# Chop of NAN due to the largest window
df_new = df_new.iloc[max_window:]
df_dict[symbol] = df_new
return df_dict
def _jit_speed_test1():
# Test jit speed
from backtester.stockdata import YahooData
from backtester.definitions import DF_ADJ_CLOSE
from backtester import utils
import timeit
symbol = 'VOO'
y = YahooData([symbol])
df = y.get_symbol_all(symbol)
df = df.iloc[-100::2]
series = df[DF_ADJ_CLOSE]
times = utils.dates2days(series.index)
times = times.values.astype(np.float64)
prices = series.values
def test_no():
d = _buysell_nojit(
times,
prices,
min_hold_days=np.int64(1),
max_hold_days=np.int64(20),
skip=np.int64(1),
)
return d
def test_jit():
d = _buysell(
times,
prices,
min_hold_days=np.int64(1),
max_hold_days=np.int64(20),
skip=np.int64(1),
)
return d
t1 = timeit.timeit(test_no, number=10000)
t2 = timeit.timeit(test_jit, number=10000)
print('Time without jit', t1)
print('Time using jit', t2)
series = df[DF_ADJ_CLOSE]
ts = TrailingStats(series, 15)
stat1 = ts.return_ratio
mean = np.nanmean(stat1)
std = np.nanstd(stat1)
return (stat1 - mean) / std
yahoo.symbols = STOCKS
indicator = Indicators(yahoo)
indicator.create(post1)
df = indicator.get_column_from_all('post1()')
spy = yahoo.get_symbol_all('SPY')[DF_ADJ_CLOSE]
table = TableData(df)
# %%
ii = df.values < -1.5
stocknum = ii.shape[-1]
isum = np.sum(ii, axis=1)
imean = np.nanmean(df.values, axis=1)
# date1 = np.datetime64('2008-01-01')
# date2 = np.datetime64('2009-01-01')
date1 = None
date2 = None
plt.subplot(2, 2, 1)
plt.plot(df.index, imean)
plt.grid()
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from numba import njit
from backtester.indicators import TrailingStats
from backtester.smooth import TrailingSavGol
from backtester.stockdata import YahooData, Indicators, TableData
from backtester.definitions import DF_ADJ_CLOSE
yahoo = YahooData()
symbols = yahoo.get_symbol_names()
df = yahoo.get_symbol_all('SPY')
close = df[DF_ADJ_CLOSE]
@njit
def trough_volume(x: np.ndarray):
current_max = x[0]
current_max_loc = 0
xlen = len(x)
areas = np.zeros(xlen)
# Record some information about each trough
start_locs = np.zeros(xlen, dtype=np.int64)
end_locs = np.zeros(xlen, dtype=np.int64)
areas_final = np.zeros(xlen)
import matplotlib
import matplotlib.pyplot as plt
import backtester
from backtester.stockdata import YahooData
from backtester.definitions import (
DF_ADJ_CLOSE, DF_CLOSE, DF_OPEN, DF_HIGH, DF_LOW, DF_VOLUME)
from backtester.indicators import TrailingStats
from scipy.signal import savgol_filter
from scipy.ndimage import gaussian_filter1d, uniform_filter1d
symbol = 'APOL'
yd = YahooData()
df = yd.get_symbol_all(symbol)
def set_date_axes(dnum: int):
ax = plt.gca()
plt.xticks(rotation=60, ha='right')
plt.grid(which='major', color='k', lw=0.25, alpha=0.5)
plt.grid(which='minor', color='k', lw=0.25, alpha=0.2)
years = matplotlib.dates.YearLocator()
months = matplotlib.dates.MonthLocator()
days = matplotlib.dates.DayLocator()
if dnum / 12 > 20:
ax.xaxis.set_major_locator(years)
current_max = xi
pratios[ii] = 0
# Trough detected
else:
area += (current_max - xi)
pratios[ii] = (current_max - xi) / current_max
return pratios
yahoo = YahooData()
symbols = yahoo.get_symbol_names()
df = yahoo.get_symbol_all('GOOG')
close = df[DF_ADJ_CLOSE]
xlen = len(close)
iarr = np.arange(xlen)
# a, starts, ends, af = trough_volume(close.values)
# a2, starts2, ends2, af2 = trough_volume(-close.values[::-1])
# starts2 = iarr[::-1][starts2]
ratio = peak_ratio(close.values)
series = pd.Series(data=ratio, index=close.index)
ts = TrailingStats(series, 12)
slope = ts.linear_regression[0]
plt.subplot(2,2,1)