mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-13 10:58:06 +00:00
Mark Aron SzulyovszkyandGitHub
b1c04afb13
* refactor(Naming): use `primary_models` & `meta_labeling_models` * refactor(Naming): using primary * meta_labeling across config and in pipeline * feat(Pipeline): added back Ensemble models * fix(Pipeline): compiler error * fix(Config): typo * chore(Pipeline): removed unused averaging step * revert the changes in discretizing * chore(Pipeline): remove sharpe improvement logging * fix(Pipeline): ensemble predictions should be a pd.Series instead of a DataFrame * fix(Pipeline): discard unnecessary ensemble_probabilities * fix(Pipeline): fixes regarding various meta-labeling ensemble bugs * fix(Reporting): use the new naming convention * fix(Reporting): use the right variable * feat(Sweep): new sweep for ensemble models * fix(Sweep): config reference * fix(Config): simplified dev config * fix(Models): use the faster LR model * fix(Models): use LGBM in the meta-labeling model for speed * fix(Selection): always use the first model for feature selection, commented out caching from select_features() as it's close to redundant in terms of speed
44 KiB
44 KiB
In [1]:
import pandas as pd
import pandas_ta as ta
from config.config import get_default_ensemble_config
from config.preprocess import preprocess_config
from data_loader.load_data import load_data
import seaborn as sns
import numpy as np
model_config, training_config, data_config = get_default_ensemble_config()
model_config, training_config, data_config = preprocess_config(model_config, training_config, data_config)
data_config['target_asset'] = data_config['assets'][0]
X, y, target_returns = load_data(**data_config)[2m[36m(__load_df pid=52067)[0m /usr/local/anaconda3/envs/quant/lib/python3.9/site-packages/pandas/core/arraylike.py:364: RuntimeWarning: divide by zero encountered in log [2m[36m(__load_df pid=52067)[0m result = getattr(ufunc, method)(*inputs, **kwargs) [2m[36m(__load_df pid=52074)[0m /usr/local/anaconda3/envs/quant/lib/python3.9/site-packages/pandas/core/arraylike.py:364: RuntimeWarning: divide by zero encountered in log [2m[36m(__load_df pid=52074)[0m result = getattr(ufunc, method)(*inputs, **kwargs) [2m[36m(__load_df pid=52071)[0m /usr/local/anaconda3/envs/quant/lib/python3.9/site-packages/pandas/core/arraylike.py:364: RuntimeWarning: divide by zero encountered in log [2m[36m(__load_df pid=52071)[0m result = getattr(ufunc, method)(*inputs, **kwargs) [2m[36m(__load_df pid=52072)[0m /usr/local/anaconda3/envs/quant/lib/python3.9/site-packages/pandas/core/arraylike.py:364: RuntimeWarning: divide by zero encountered in log [2m[36m(__load_df pid=52072)[0m result = getattr(ufunc, method)(*inputs, **kwargs) [2m[36m(__load_df pid=52069)[0m /usr/local/anaconda3/envs/quant/lib/python3.9/site-packages/pandas/core/arraylike.py:364: RuntimeWarning: divide by zero encountered in log [2m[36m(__load_df pid=52069)[0m result = getattr(ufunc, method)(*inputs, **kwargs)
In [3]:
X.columnsOut [3]:
Index(['ADA_USD_returns', 'ADA_USD_mom_10', 'ADA_USD_mom_20', 'ADA_USD_mom_30',
'ADA_USD_mom_60', 'ADA_USD_mom_90', 'ADA_USD_vol_10', 'ADA_USD_vol_20',
'ADA_USD_vol_30', 'ADA_USD_vol_60',
...
'msol_standard_scaling_0', 'dormancy_standard_scaling_0',
'liveliness_standard_scaling_0',
'relative_unrealized_profit_standard_scaling_0',
'relative_unrealized_loss_standard_scaling_0',
'nupl_standard_scaling_0', 'sth_nupl_standard_scaling_0',
'lth_nupl_standard_scaling_0', 'ssr_standard_scaling_0',
'bvin_standard_scaling_0'],
dtype='object', length=542)In [6]:
X['liveliness_standard_scaling_0'].plot()Out [6]:
<AxesSubplot:>
In [7]:
X['BTC_USD_returns'].plot()Out [7]:
<AxesSubplot:>
In [7]:
# pd.plotting.scatter_matrix(X, figsize=(12, 12));In [ ]: