Hello,

I'm testing combining crypto with stocks for Q21 but I'm getting an error. We hope to help.

Thank you.

Below is my code

# Import basic libraries.
import xarray as xr
import pandas as pd
import numpy as np
# Import Quantiacs libraries.
import qnt.data    as qndata  # load and manipulate data
import qnt.output as qnout   # manage output
import qnt.backtester as qnbt # backtester
import qnt.stats   as qnstats # statistical functions for analysis
import qnt.graph   as qngraph # graphical tools
import qnt.ta      as qnta    # indicators library
import qnt.xr_talib as xr_talib   # indicators library

def load_data(period):
    futures = qndata.futures.load_data(tail=period).isel(asset=0)
    stocks  = qndata.stocks.load_ndx_data(tail=period)
    crypto= qndata.crypto.load_data(tail=period)
    return {"futures": futures, "stocks": stocks, "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)),
        "stocks":  data["stocks"].sel(time=slice(min_date, max_date)),
        "crypto":  data["crypto"].sel(time=slice(min_date, max_date)),
    }


def strategy(data):
    close_futures = data["crypto"].sel(field="close")
    close_stocks  = data["stocks"].sel(field="close")
    sma20 = qnta.sma(close_futures, 20).isel(time=-1)
    sma20_stocks = qnta.sma(close_stocks, 20).isel(time=-1)
    is_liquid = data["stocks"].sel(field="is_liquid").isel(time=-1)
    weights = xr.where(sma20 < sma20_stocks, 1, -1)
    weights = weights * is_liquid 
    weights = weights / 100.0
    return weights

qnbt.backtest(
    competition_type= "stocks_nasdaq100",
    load_data= load_data,
    lookback_period= 90,
    start_date= "2006-01-01",
    strategy= strategy,
    window= window
)

Hello,

I'm trying to apply ticker filters from stocks to futures, but it doesn't work. Below is my code

For stock:

import qnt.stats as qnstats

# data = qndata.stocks.load_ndx_data(tail = 17*365, dims = ("time", "field", "asset"))
data = qndata.stocks.load_ndx_data(min_date="2005-01-01")
def get_best_instruments(data, weights, top_size):
    # compute statistics:
    stats_per_asset = qnstats.calc_stat(data, weights, per_asset=True)
    # calculate ranks of assets by "sharpe_ratio":
    ranks = (-stats_per_asset.sel(field="sharpe_ratio")).rank("asset")
    # select top assets by rank "top_period" days ago:
    top_period = 1
    rank = ranks.isel(time=-top_period)
    top = rank.where(rank <= top_size).dropna("asset").asset

    # select top stats:
    top_stats = stats_per_asset.sel(asset=top.values)

    # print results:
    print("SR tail of the top assets:")
    display(top_stats.sel(field="sharpe_ratio").to_pandas().tail())

    print("avg SR = ", top_stats[-top_period:].sel(field="sharpe_ratio").mean("asset")[-1].item())
    display(top_stats)
    return top_stats.coords["asset"].values

get_best_instruments(data, weight, 15)

For futures

import qnt.stats as qnstats

# data = qndata.stocks.load_ndx_data(tail = 17*365, dims = ("time", "field", "asset"))
data = qndata.futures_load_data(min_date="2005-01-01")
def get_best_instruments(data, weights, top_size):
    # compute statistics:
    stats_per_asset = qnstats.calc_stat(data, weights, per_asset=True)
    # calculate ranks of assets by "sharpe_ratio":
    ranks = (-stats_per_asset.sel(field="sharpe_ratio")).rank("asset")
    # select top assets by rank "top_period" days ago:
    top_period = 1
    rank = ranks.isel(time=-top_period)
    top = rank.where(rank <= top_size).dropna("asset").asset

    # select top stats:
    top_stats = stats_per_asset.sel(asset=top.values)

    # print results:
    print("SR tail of the top assets:")
    display(top_stats.sel(field="sharpe_ratio").to_pandas().tail())

    print("avg SR = ", top_stats[-top_period:].sel(field="sharpe_ratio").mean("asset")[-1].item())
    display(top_stats)
    return top_stats.coords["asset"].values

get_best_instruments(data, weight, 15)

Please help me. I hope you can provide an example on how to filter ticker futures by sharpe similar to the get_best_instruments function. Thank you

@support @Vyacheslav_B

Hello, I just found a new example about stateful long short. Link here:
https://github.com/quantiacs/strategy-stateful_long_short_with_exits/blob/master/strategy.ipynb
I would like to ask how to convert from multi backtest to single backtest and submit to the contest? Besides, if we keep the multi backtest, how to submit? Thank you.

@support @Vyacheslav_B

@eddiee Hi, Mr. Eddie.

I am new to building strategies using ML/DL on Quantiacs and am very impressed with the OS performance of your ML strategies. I hope you can give me your contact (mail, limkedin,...) so I can learn from your experience in building an ML/DL strategy.

Sincerely thank.

Hello, I am currently using the following backtest to develop a strategy using neural network

import qnt.data as qndata
import qnt.stats as qnstats
retrain_interval = 19*365 + 1
data = qndata.stocks.load_ndx_data(min_date ="2005-01-01")

models = train_model(data)
weights = predict(models, data)
is_liquid = data.sel(field="is_liquid")
weights   = weights * is_liquid

def get_enough_bid_for(data_, weights_):
    time_traded = weights_.time[abs(weights_).fillna(0).sum('asset') > 0]
    is_strategy_traded = len(time_traded)
    if is_strategy_traded:
        return xr.where(weights_.time < time_traded.min(), data_.sel(field="is_liquid"), weights_)
    return weights_


weights = get_enough_bid_for(data, weights)
weights = weights.fillna(0)
# Calculate stats
stats = qnstats.calc_stat(data, weights)
display(stats.to_pandas().tail())

# Graph
performance = stats.to_pandas()["equity"]
import qnt.graph as qngraph
#qngraph.make_plot_filled(performance.index, performance, name="PnL (Equity)", type="log")

The results of checking the strategy file are normal, however when I run precheck the following error occurs

And when I submit the strategy, it is put into the filter with the error that there is no weight. Please help me fix the error. Thank you.

My strategy ID is 16900804

@support @Vyacheslav_B

@vyacheslav_b Thank you so much.

I have one more question for you to answer. I ran the precheck and the result was nan value the first time, but I set the min_date to 2005 - 01 - 01. I would like to ask, why is there a nan value problem? Is it because the ticker I chose had some companies that weren't listed at that time? My strategy id code is # 16767242. Thank you so much

@vyacheslav_b said in How to filter ticker futures by sharpe:

data = qndata.futures_load_data(min_date="2005-01-01")

Here is my full code

# Import basic libraries.
import xarray as xr
import pandas as pd
import numpy as np
# Import Quantiacs libraries.
import qnt.data    as qndata  # load and manipulate data
import qnt.output as qnout   # manage output
import qnt.backtester as qnbt # backtester
import qnt.stats   as qnstats # statistical functions for analysis
import qnt.graph   as qngraph # graphical tools
import qnt.ta      as qnta    # indicators library
import qnt.xr_talib as xr_talib   # indicators library

def load_data(period):
    futures = qndata.futures_load_data(tail=period)
    crypto = qndata.cryptofutures_load_data(tail=period)
    stocks = qndata.stocks.load_ndx_data(tail=period)
    return {"futures": futures, "crypto": crypto, "stocks": stocks}, 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)),
        "stocks": data['stocks'].sel(time=slice(min_date, max_date)),
    }

def strategy(data):
    close = data['futures'].sel(field='close')
    close_prev = data['futures'].sel(field='close').shift(time=1)
    close_change = (close - close_prev)/close_prev

    close_stocks = data['stocks'].sel(field='close')
    close_stocks_prev = data['stocks'].sel(field='close').shift(time=1)
    close_change_stocks = (close_stocks - close_stocks_prev)/close_stocks_prev

    sma200 = qnta.lwma(close_change, 20).fillna(0).mean('asset').isel(time=-1)
    sma200_crypto = qnta.dema(close_change_stocks, 20).isel(time=-1)
    return xr.where(sma200 < sma200_crypto, 1, 0)

weight = qnbt.backtest(
    competition_type="stocks_nasdaq100",
    load_data=load_data,
    lookback_period=90,
    start_date='2006-01-01',
    strategy=strategy,
    window=window
)

import qnt.stats as qnstats

# data = qndata.stocks.load_ndx_data(tail = 17*365, dims = ("time", "field", "asset"))
data = qndata.futures_load_data(min_date="2005-01-01")
def get_best_instruments(data, weights, top_size):
    # compute statistics:
    stats_per_asset = qnstats.calc_stat(data, weights, per_asset=True)
    # calculate ranks of assets by "sharpe_ratio":
    ranks = (-stats_per_asset.sel(field="sharpe_ratio")).rank("asset")
    # select top assets by rank "top_period" days ago:
    top_period = 1
    rank = ranks.isel(time=-top_period)
    top = rank.where(rank <= top_size).dropna("asset").asset

    # select top stats:
    top_stats = stats_per_asset.sel(asset=top.values)

    # print results:
    print("SR tail of the top assets:")
    display(top_stats.sel(field="sharpe_ratio").to_pandas().tail())

    print("avg SR = ", top_stats[-top_period:].sel(field="sharpe_ratio").mean("asset")[-1].item())
    display(top_stats)
    return top_stats.coords["asset"].values

get_best_instruments(data, weight, 15)

weights = weight.sel(time=slice("2006-01-01",None))

qnout.check(weights, data, "stocks_nasdaq100")
qnout.write(weights) # to participate in the competition

I can filter tickers by stocks, but I cannot filter tickers by futures. Please take a look and help me

@vyacheslav_b Thank you very much for your support.

I would like to ask, if I want to filter out the crypto codes with the highest sharpness, what should I do? Thank you. I tried using the get_best_instruments function but it didn't work

import qnt.stats as qnstats

# data = qndata.stocks.load_ndx_data(tail = 17*365, dims = ("time", "field", "asset"))
data = qndata.stocks.load_ndx_data(min_date="2005-01-01")
def get_best_instruments(data, weights, top_size):
    # compute statistics:
    stats_per_asset = qnstats.calc_stat(data, weights, per_asset=True)
    # calculate ranks of assets by "sharpe_ratio":
    ranks = (-stats_per_asset.sel(field="sharpe_ratio")).rank("asset")
    # select top assets by rank "top_period" days ago:
    top_period = 1
    rank = ranks.isel(time=-top_period)
    top = rank.where(rank <= top_size).dropna("asset").asset

    # select top stats:
    top_stats = stats_per_asset.sel(asset=top.values)

    # print results:
    print("SR tail of the top assets:")
    display(top_stats.sel(field="sharpe_ratio").to_pandas().tail())

    print("avg SR = ", top_stats[-top_period:].sel(field="sharpe_ratio").mean("asset")[-1].item())
    display(top_stats)
    return top_stats.coords["asset"].values

get_best_instruments(data, weights, 10)

Hello,

I'm testing combining crypto with stocks for Q21 but I'm getting an error. We hope to help.

Thank you.

Below is my code

# Import basic libraries.
import xarray as xr
import pandas as pd
import numpy as np
# Import Quantiacs libraries.
import qnt.data    as qndata  # load and manipulate data
import qnt.output as qnout   # manage output
import qnt.backtester as qnbt # backtester
import qnt.stats   as qnstats # statistical functions for analysis
import qnt.graph   as qngraph # graphical tools
import qnt.ta      as qnta    # indicators library
import qnt.xr_talib as xr_talib   # indicators library

def load_data(period):
    futures = qndata.futures.load_data(tail=period).isel(asset=0)
    stocks  = qndata.stocks.load_ndx_data(tail=period)
    crypto= qndata.crypto.load_data(tail=period)
    return {"futures": futures, "stocks": stocks, "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)),
        "stocks":  data["stocks"].sel(time=slice(min_date, max_date)),
        "crypto":  data["crypto"].sel(time=slice(min_date, max_date)),
    }


def strategy(data):
    close_futures = data["crypto"].sel(field="close")
    close_stocks  = data["stocks"].sel(field="close")
    sma20 = qnta.sma(close_futures, 20).isel(time=-1)
    sma20_stocks = qnta.sma(close_stocks, 20).isel(time=-1)
    is_liquid = data["stocks"].sel(field="is_liquid").isel(time=-1)
    weights = xr.where(sma20 < sma20_stocks, 1, -1)
    weights = weights * is_liquid 
    weights = weights / 100.0
    return weights

qnbt.backtest(
    competition_type= "stocks_nasdaq100",
    load_data= load_data,
    lookback_period= 90,
    start_date= "2006-01-01",
    strategy= strategy,
    window= window
)

Hello,

I'm trying to apply ticker filters from stocks to futures, but it doesn't work. Below is my code

For stock:

import qnt.stats as qnstats

# data = qndata.stocks.load_ndx_data(tail = 17*365, dims = ("time", "field", "asset"))
data = qndata.stocks.load_ndx_data(min_date="2005-01-01")
def get_best_instruments(data, weights, top_size):
    # compute statistics:
    stats_per_asset = qnstats.calc_stat(data, weights, per_asset=True)
    # calculate ranks of assets by "sharpe_ratio":
    ranks = (-stats_per_asset.sel(field="sharpe_ratio")).rank("asset")
    # select top assets by rank "top_period" days ago:
    top_period = 1
    rank = ranks.isel(time=-top_period)
    top = rank.where(rank <= top_size).dropna("asset").asset

    # select top stats:
    top_stats = stats_per_asset.sel(asset=top.values)

    # print results:
    print("SR tail of the top assets:")
    display(top_stats.sel(field="sharpe_ratio").to_pandas().tail())

    print("avg SR = ", top_stats[-top_period:].sel(field="sharpe_ratio").mean("asset")[-1].item())
    display(top_stats)
    return top_stats.coords["asset"].values

get_best_instruments(data, weight, 15)

For futures

import qnt.stats as qnstats

# data = qndata.stocks.load_ndx_data(tail = 17*365, dims = ("time", "field", "asset"))
data = qndata.futures_load_data(min_date="2005-01-01")
def get_best_instruments(data, weights, top_size):
    # compute statistics:
    stats_per_asset = qnstats.calc_stat(data, weights, per_asset=True)
    # calculate ranks of assets by "sharpe_ratio":
    ranks = (-stats_per_asset.sel(field="sharpe_ratio")).rank("asset")
    # select top assets by rank "top_period" days ago:
    top_period = 1
    rank = ranks.isel(time=-top_period)
    top = rank.where(rank <= top_size).dropna("asset").asset

    # select top stats:
    top_stats = stats_per_asset.sel(asset=top.values)

    # print results:
    print("SR tail of the top assets:")
    display(top_stats.sel(field="sharpe_ratio").to_pandas().tail())

    print("avg SR = ", top_stats[-top_period:].sel(field="sharpe_ratio").mean("asset")[-1].item())
    display(top_stats)
    return top_stats.coords["asset"].values

get_best_instruments(data, weight, 15)

Please help me. I hope you can provide an example on how to filter ticker futures by sharpe similar to the get_best_instruments function. Thank you

@support @Vyacheslav_B