strategy

Technical Analysis using trix, ema¶

Predicting stocks using technical indicators (trix, ema)

You can clone and edit this example there (tab Examples).

This template shows you the basic steps for taking part to the NASDAQ-100 Stock Long-Short contest.

In [1]:

from IPython.display import display
import xarray as xr
import qnt.data as qndata
import qnt.output as qnout
import qnt.ta as qnta
import qnt.stats as qns


def multi_trix_v3(data, params):
    s_ = qnta.trix(data.sel(field='high'), params[0])
    w_1 = s_.shift(time=params[1]) > s_.shift(time=params[2])
    w_2 = s_.shift(time=params[3]) > s_.shift(time=params[4])
    weights = (w_1 * w_2) * data.sel(field="is_liquid")
    return weights.fillna(0)


def multi_ema_v3(data, params):
    s_ = qnta.ema(data.sel(field='high'), params[0])
    w_1 = s_.shift(time=params[1]) > s_.shift(time=params[2])
    w_2 = s_.shift(time=params[3]) > s_.shift(time=params[4])
    weights = (w_1 * w_2) * data.sel(field="is_liquid")
    return weights.fillna(0)


def multi_ema_v4(data, params):
    s_ = qnta.trix(data.sel(field='high'), 30)
    w_1 = s_.shift(time=params[0]) > s_.shift(time=params[1])
    s_ = qnta.ema(data.sel(field='high'), params[2])
    w_2 = s_.shift(time=params[3]) > s_.shift(time=params[4])
    weights = (w_1 * w_2) * data.sel(field="is_liquid")
    return weights.fillna(0)


data = qndata.stocks.load_ndx_data(min_date="2005-01-01")

weights_1 = multi_trix_v3(data, [87, 135, 108, 13, 114])
weights_2 = multi_trix_v3(data, [89, 8, 101, 148, 36])
weights_3 = multi_trix_v3(data, [196, 125, 76, 12, 192])
weights_4 = multi_ema_v3(data, [69, 47, 57, 7, 41])

weights_f = (weights_1 + weights_2) * weights_3 * weights_4

weights_5 = multi_trix_v3(data, [89, 139, 22, 8, 112])
weights_6 = multi_trix_v3(data, [92, 139, 20, 10, 110])
weights_7 = multi_ema_v4(data, [13, 134, 42, 66, 133])

weights_t = (weights_5 + weights_6) * weights_7 + weights_3

weights_all = 4 * weights_f + weights_t

100% (367973 of 367973) |################| Elapsed Time: 0:00:00 Time:  0:00:00
100% (39443 of 39443) |##################| Elapsed Time: 0:00:00 Time:  0:00:00
100% (14717216 of 14717216) |############| Elapsed Time: 0:00:00 Time:  0:00:00

fetched chunk 1/6 1s

100% (14720244 of 14720244) |############| Elapsed Time: 0:00:00 Time:  0:00:00

fetched chunk 2/6 2s

100% (14717184 of 14717184) |############| Elapsed Time: 0:00:00 Time:  0:00:00

fetched chunk 3/6 3s

100% (14717100 of 14717100) |############| Elapsed Time: 0:00:00 Time:  0:00:00

fetched chunk 4/6 5s

100% (14717100 of 14717100) |############| Elapsed Time: 0:00:00 Time:  0:00:00

fetched chunk 5/6 6s

100% (13667388 of 13667388) |############| Elapsed Time: 0:00:00 Time:  0:00:00

fetched chunk 6/6 7s
Data loaded 7s

In [2]:

def get_enough_bid_for(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_new = get_enough_bid_for(weights_all)
weights_new = weights_new.sel(time=slice("2006-01-01",None))

weights = qnout.clean(output=weights_new, data=data, kind="stocks_nasdaq100")

Output cleaning...
fix uniq
ffill if the current price is None...
Check liquidity...
Ok.
Check missed dates...
Ok.
Normalization...
Output cleaning is complete.

In [3]:

def print_statistic(data, weights_all):
    import qnt.stats as qnstats

    stats = qnstats.calc_stat(data, weights_all)
    display(stats.to_pandas().tail(5))
    # graph
    performance = stats.to_pandas()["equity"]
    import qnt.graph as qngraph

    qngraph.make_plot_filled(performance.index, performance, name="PnL (Equity)", type="log")

print_statistic(data, weights)

field	equity	relative_return	volatility	underwater	max_drawdown	sharpe_ratio	mean_return	bias	instruments	avg_turnover	avg_holding_time
time
2024-04-18	55.790700	-0.004836	0.240905	-0.144033	-0.378033	1.021856	0.246170	1.0	217.0	0.170549	11.463648
2024-04-19	55.232784	-0.010000	0.240892	-0.152593	-0.378033	1.018818	0.245426	1.0	217.0	0.170571	11.463739
2024-04-22	56.006565	0.014009	0.240886	-0.140721	-0.378033	1.022536	0.246314	1.0	217.0	0.170553	11.463333
2024-04-23	56.916217	0.016242	0.240886	-0.126765	-0.378033	1.026848	0.247353	1.0	217.0	0.170517	11.463333
2024-04-24	57.188946	0.004792	0.240861	-0.122581	-0.378033	1.028058	0.247619	1.0	217.0	0.170578	11.466504

In [4]:

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

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

Check liquidity...
Ok.
Check missed dates...
Ok.
Check the sharpe ratio...
Period: 2006-01-01 - 2024-04-24
Sharpe Ratio = 1.0280582249229684
Ok.
Check correlation.

WARNING! Can't calculate correlation.
Correlation check failed.

Write output: /root/fractions.nc.gz

In [5]:

weights

Out[5]:

<xarray.DataArray (time: 4609, asset: 249)>
array([[0.        , 0.01123596, 0.        , ..., 0.        , 0.01123596,
        0.01123596],
       [0.        , 0.01190476, 0.        , ..., 0.        , 0.01190476,
        0.01190476],
       [0.        , 0.01190476, 0.        , ..., 0.        , 0.01190476,
        0.01190476],
       ...,
       [0.        , 0.        , 0.03571429, ..., 0.        , 0.        ,
        0.        ],
       [0.        , 0.        , 0.04545455, ..., 0.        , 0.        ,
        0.        ],
       [0.        , 0.        , 0.04255319, ..., 0.        , 0.        ,
        0.        ]])
Coordinates:
  * time     (time) datetime64[ns] 2006-01-03 2006-01-04 ... 2024-04-24
  * asset    (asset) <U10 'NAS:AAL' 'NAS:AAPL' ... 'NYS:RHT' 'NYS:TEVA'

In [6]:

data

Out[6]:

<xarray.DataArray 'stocks_nasdaq100' (field: 9, time: 4861, asset: 249)>
array([[[     nan,   1.1568,      nan, ...,  12.08  ,  13.41  ,
          29.81  ],
        [     nan,   1.1393,      nan, ...,  12.49  ,  13.05  ,
          29.2   ],
        [     nan,   1.1511,      nan, ...,  12.11  ,  12.6   ,
          27.97  ],
        ...,
        [ 14.28  , 165.515 , 156.19  , ...,  40.98  ,      nan,
          12.94  ],
        [ 13.962 , 165.35  , 157.24  , ...,  41.28  ,      nan,
          12.94  ],
        [ 14.22  , 166.54  , 164.475 , ...,  41.72  ,      nan,
          12.98  ]],

       [[     nan,   1.1179,      nan, ...,  11.9   ,  13.03  ,
          29.06  ],
        [     nan,   1.1245,      nan, ...,  11.97  ,  12.54  ,
          28.02  ],
        [     nan,   1.1438,      nan, ...,  11.97  ,  12.25  ,
          27.31  ],
...
        [  1.    ,   1.    ,   1.    , ...,   1.    ,      nan,
           1.    ],
        [  1.    ,   1.    ,   1.    , ...,   1.    ,      nan,
           1.    ],
        [  1.    ,   1.    ,   1.    , ...,   1.    ,      nan,
           1.    ]],

       [[     nan,   1.    ,      nan, ...,   0.    ,   0.    ,
           1.    ],
        [     nan,   1.    ,      nan, ...,   0.    ,   0.    ,
           1.    ],
        [     nan,   1.    ,      nan, ...,   0.    ,   0.    ,
           1.    ],
        ...,
        [  0.    ,   1.    ,   1.    , ...,   0.    ,      nan,
           0.    ],
        [  0.    ,   1.    ,   1.    , ...,   0.    ,      nan,
           0.    ],
        [  0.    ,   1.    ,   1.    , ...,   0.    ,      nan,
           0.    ]]])
Coordinates:
  * time     (time) datetime64[ns] 2005-01-03 2005-01-04 ... 2024-04-24
  * asset    (asset) <U10 'NAS:AAL' 'NAS:AAPL' ... 'NYS:RHT' 'NYS:TEVA'
  * field    (field) object 'open' 'low' 'high' ... 'split_cumprod' 'is_liquid'

xarray.DataArray

'stocks_nasdaq100'

field: 9
time: 4861
asset: 249

nan 1.157 nan 31.5 37.02 38.86 38.4 ... nan 0.0 0.0 0.0 0.0 nan 0.0

array([[[     nan,   1.1568,      nan, ...,  12.08  ,  13.41  ,
          29.81  ],
        [     nan,   1.1393,      nan, ...,  12.49  ,  13.05  ,
          29.2   ],
        [     nan,   1.1511,      nan, ...,  12.11  ,  12.6   ,
          27.97  ],
        ...,
        [ 14.28  , 165.515 , 156.19  , ...,  40.98  ,      nan,
          12.94  ],
        [ 13.962 , 165.35  , 157.24  , ...,  41.28  ,      nan,
          12.94  ],
        [ 14.22  , 166.54  , 164.475 , ...,  41.72  ,      nan,
          12.98  ]],

       [[     nan,   1.1179,      nan, ...,  11.9   ,  13.03  ,
          29.06  ],
        [     nan,   1.1245,      nan, ...,  11.97  ,  12.54  ,
          28.02  ],
        [     nan,   1.1438,      nan, ...,  11.97  ,  12.25  ,
          27.31  ],
...
        [  1.    ,   1.    ,   1.    , ...,   1.    ,      nan,
           1.    ],
        [  1.    ,   1.    ,   1.    , ...,   1.    ,      nan,
           1.    ],
        [  1.    ,   1.    ,   1.    , ...,   1.    ,      nan,
           1.    ]],

       [[     nan,   1.    ,      nan, ...,   0.    ,   0.    ,
           1.    ],
        [     nan,   1.    ,      nan, ...,   0.    ,   0.    ,
           1.    ],
        [     nan,   1.    ,      nan, ...,   0.    ,   0.    ,
           1.    ],
        ...,
        [  0.    ,   1.    ,   1.    , ...,   0.    ,      nan,
           0.    ],
        [  0.    ,   1.    ,   1.    , ...,   0.    ,      nan,
           0.    ],
        [  0.    ,   1.    ,   1.    , ...,   0.    ,      nan,
           0.    ]]])

Coordinates: (3)

time

(time)

datetime64[ns]

2005-01-03 ... 2024-04-24

array(['2005-01-03T00:00:00.000000000', '2005-01-04T00:00:00.000000000',
       '2005-01-05T00:00:00.000000000', ..., '2024-04-22T00:00:00.000000000',
       '2024-04-23T00:00:00.000000000', '2024-04-24T00:00:00.000000000'],
      dtype='datetime64[ns]')

asset

(asset)

<U10

'NAS:AAL' 'NAS:AAPL' ... 'NYS:TEVA'

array(['NAS:AAL', 'NAS:AAPL', 'NAS:ABNB', ..., 'NYS:QGEN', 'NYS:RHT',
       'NYS:TEVA'], dtype='<U10')

field

(field)

object

'open' 'low' ... 'is_liquid'

array(['open', 'low', 'high', 'close', 'vol', 'divs', 'split', 'split_cumprod',
       'is_liquid'], dtype=object)

Attributes: (0)