1: the lookback_period is 365 but you want a 400-day SMA. This will only produce NaNs, so the boolean array sma20 < sma20_crypto will be False everywhere resulting in -1 weights. 2*365 as lookback does the trick for these settings.

2: Bitcoin is trading 24/7, futures aren't. Better use crypto.time.values instead of futures.time.values for the output of load_data.

There might be something else that I didn't catch but the resulting sharpe is at least close to what would be expected (1.109 with 5 and 385)

then I run the backtest with the parameters I've found....and I get a totally different result!

How's that?

first block to find params:

import xarray as xr
import numpy as np

import qnt.backtester as qnbt
import qnt.data as qndata
import qnt.ta as qnta

import qnt.data as qndata
import qnt.ta as qnta
import qnt.output as qnout
import qnt.stats as qns
import qnt.log as qnlog
import qnt.optimizer as qnop
import qnt.backtester as qnbt

import xarray as xr


def align_data_by_time(data, data_for_align):
    data_for_outer = xr.align(data.time, data_for_align, join='outer')[1]
    ff = data_for_outer.ffill(dim='time')
    r = ff.sel(time=data.time)
    return r


min_date = '2014-01-01'
cryptofutures = qndata.cryptofutures.load_data(min_date=min_date)

futures = align_data_by_time(
    data=cryptofutures,
    data_for_align=qndata.futures.load_data(min_date=min_date, assets=["F_DX"]))

data = {"futures": futures, "cryptofutures": cryptofutures}


def strategy(data, param1=20, param2=20): #5 param1 , 385 param 2 best fit
    close_futures = data["futures"].sel(field="close").drop('asset')
    close_crypto = data["cryptofutures"].sel(field="close")
    sma20 = qnta.sma(close_futures, param1)
    sma20_crypto = qnta.sma(close_crypto, param2)
    a = xr.where(sma20 < sma20_crypto, 1, -1)
    return a


def stats_function(data, output):
    start_date = qns.get_default_is_start_date_for_type('cryptofutures')
    stat = qns.calc_stat(data['cryptofutures'], output.sel(time=slice(start_date, None)))
    return stat.isel(time=-1).to_pandas().to_dict()


result = qnop.optimize_strategy(
    data,
    strategy,
    qnop.full_range_args_generator(
        param1=range(5, 1500, 10),  # min, max, step
        param2=range(5, 1500, 10)  # min, max, step
    ),
    workers=1,  # you can set more workers on your PC
    stats_function=stats_function,
)

qnop.build_plot(result)

print("---")
print("Best iteration:")
print(result['best_iteration'])

then this cell:

import xarray as xr
import numpy as np

import qnt.backtester as qnbt
import qnt.data as qndata
import qnt.ta as qnta



def load_data(period):
    futures= qndata.futures.load_data(tail=period, assets=["F_DX"]).isel(asset=0)
    crypto=  qndata.cryptofutures.load_data(tail=period)
    return {"futures": futures, "crypto": crypto}, futures.time.values



def window(data, max_date: np.datetime64, lookback_period: int):
    min_date= max_date - np.timedelta64(lookback_period, "D")
    return {
        "futures": data["futures"].sel(time=slice(min_date, max_date)),
        "crypto":  data["crypto"].sel(time=slice(min_date, max_date)),
    }



def strategy(data):
    close_futures= data["futures"].sel(field="close")
    close_crypto=  data["crypto"].sel(field="close")
    sma20 = qnta.sma(close_futures, 400).isel(time=-1)
    sma20_crypto = qnta.sma(close_crypto, 400).isel(time=-1)
    return xr.where(sma20 < sma20_crypto, 1, -1)



qnbt.backtest(
    competition_type= "cryptofutures",
    load_data= load_data,
    lookback_period= 365,
    start_date= "2014-01-01",
    strategy= strategy,
    window= window
)

And I get a negative Sharpe!!! I tried with param1 5 and param2 385, too. Same bad results!
The optimizer says that for these values I should get Sharpe >1 !!!

Hello. Try this

import xarray as xr
import numpy as np

import qnt.backtester as qnbt
import qnt.data as qndata
import qnt.ta as qnta

import qnt.data as qndata
import qnt.ta as qnta
import qnt.output as qnout
import qnt.stats as qns
import qnt.log as qnlog
import qnt.optimizer as qnop
import qnt.backtester as qnbt

import xarray as xr


def align_data_by_time(data, data_for_align):
    data_for_outer = xr.align(data.time, data_for_align, join='outer')[1]
    ff = data_for_outer.ffill(dim='time')
    r = ff.sel(time=data.time)
    return r


min_date = '2014-01-01'
cryptofutures = qndata.cryptofutures.load_data(min_date=min_date)

futures = align_data_by_time(
    data=cryptofutures,
    data_for_align=qndata.futures.load_data(min_date=min_date, assets=["F_DX"]))

data = {"futures": futures, "cryptofutures": cryptofutures}


def strategy(data, param1=20, param2=20):
    close_futures = data["futures"].sel(field="close").drop('asset')
    close_crypto = data["cryptofutures"].sel(field="close")
    sma20 = qnta.sma(close_futures, param1)
    sma20_crypto = qnta.sma(close_crypto, param2)
    a = xr.where(sma20 < sma20_crypto, 1, -1)
    return a


def stats_function(data, output):
    start_date = qns.get_default_is_start_date_for_type('cryptofutures')
    stat = qns.calc_stat(data['cryptofutures'], output.sel(time=slice(start_date, None)))
    return stat.isel(time=-1).to_pandas().to_dict()


result = qnop.optimize_strategy(
    data,
    strategy,
    qnop.full_range_args_generator(
        param1=range(5, 150, 15),  # min, max, step
        param2=range(5, 100, 15)  # min, max, step
    ),
    workers=1,  # you can set more workers on your PC
    stats_function=stats_function,
)

qnop.build_plot(result)

print("---")
print("Best iteration:")
print(result['best_iteration'])