gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-16 12:28:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(Selection): added toggleable feature selection step into the pipeline (#83)

Browse Source 
* feat(Selection): added prototype feature selection python script

* feat(Utils): added some helpers for the future from Advances in Financial ML book

* feat(Selection): added RFECV

* feat(Selection): added configurable feature selection step into pipeline

* feat(Config): added level_1 & level_2 default config, PCA before feature selection process starts

* feat(Selection): added backup feature selector models if current one can't output feature importance, removed unnecessary array for level-2 models

* fix(Training): deal with zero first value coming out of static models

* feat(Sweep): added feature selection sweep

* fix(Sweep): config problem

* fix(Sweep): config

* chore(Utils): removed unnecessary purged k-fold crossval class

* feat(Config): added dimensionality_reduction as a separate flag

* fix(Sweep): config updated

* fix(Sweep): sweep name

* chore(Config): updated level_2 config to the best performing configuation
This commit is contained in:
Mark Aron Szulyovszky
2021-12-27 21:59:22 +01:00
committed by GitHub
parent a9b05dbd42
commit cc70d3f907
19 changed files with 442 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files
run_pipeline.py
+32 -12
View File
@@ -2,13 +2,15 @@ from utils.load_data import load_data
import pandas as pd
from training.training import run_single_asset_trainig
from reporting.wandb import launch_wandb, send_report_to_wandb, register_config_with_wandb
from models.model_map import map_model_name_to_function
from models.model_map import map_model_name_to_function, default_feature_selector_regression, default_feature_selector_classification
from feature_extractors.feature_extractor_presets import preprocess_feature_extractors_config
from config import get_default_config, validate_config, get_model_name
from utils.helpers import get_first_valid_return_index, weighted_average
from config import get_default_level_1_config, get_default_level_2_config, validate_config, get_model_name
from feature_selection.feature_selection import select_features
from feature_selection.dim_reduction import reduce_dimensionality
def setup_pipeline(project_name:str, with_wandb: bool, sweep: bool):
model_config, training_config, data_config = get_default_config()
model_config, training_config, data_config = get_default_level_2_config()
wandb = None
if with_wandb:
@@ -34,15 +36,30 @@ def pipeline(project_name:str, wandb, sweep:bool, model_config:dict, training_co
data_params['target_asset'] = asset
X, y, target_returns = load_data(**data_params)
original_X = X.copy()
first_valid_index = get_first_valid_return_index(X.iloc[:,0])
samples_to_train = len(y) - first_valid_index
if samples_to_train < training_config['sliding_window_size'] * 3:
print("Not enough samples to train")
continue
# 2. Train Level-1 models
# 2a. Dimensionality Reduction (optional)
if training_config['dimensionality_reduction']:
X = reduce_dimensionality(X, int(len(X.columns) / 2))
# 2b. Feature Selection (optional)
if training_config['feature_selection']:
print("Feature Selection started")
# TODO: this needs to be done per model!
backup_model = default_feature_selector_regression if data_config['method'] == 'regression' else default_feature_selector_classification
X = select_features(X, y, model_config['level_1_models'][0][1], min_features_to_select = 10, backup_model = backup_model)
print("Feature Selection ended")
# 3. Train Level-1 models
current_result, current_predictions = run_single_asset_trainig(
ticker_to_predict = asset,
original_X = original_X,
X = X,
y = y,
target_returns = target_returns,
@@ -56,20 +73,22 @@ def pipeline(project_name:str, wandb, sweep:bool, model_config:dict, training_co
level = 1
)
results = pd.concat([results, current_result], axis=1)
all_predictions = pd.concat([all_predictions, current_predictions], axis=1)
# With static models, because of the lag in the indicator, the first prediction is NA, so we fill it with zero.
all_predictions = pd.concat([all_predictions, current_predictions], axis=1).fillna(0.)
if len(model_config['level_2_models']) > 0:
# 3. Train Level-2 (Ensemble) model
# 3. Train Level-2 (Ensemble) model (Optional)
if model_config['level_2_model'] is not None:
ensemble_X = all_predictions
if training_config['include_original_data_in_ensemble']:
ensemble_X = pd.concat([ensemble_X, X], axis=1)
ensemble_result, ensemble_preds = run_single_asset_trainig(
ticker_to_predict = asset,
original_X = ensemble_X,
X = ensemble_X,
y = y,
target_returns = target_returns,
models = model_config['level_2_models'],
models = [model_config['level_2_model']],
method = data_config['method'],
expanding_window = training_config['expanding_window'],
sliding_window_size = training_config['sliding_window_size'],
@@ -82,7 +101,7 @@ def pipeline(project_name:str, wandb, sweep:bool, model_config:dict, training_co
results = pd.concat([results, ensemble_result], axis=1)
all_predictions = pd.concat([all_predictions, ensemble_preds], axis=1)
# 4. Save & report results
results.to_csv('results.csv')
level1_columns = results[[column for column in results.columns if 'lvl1' in column]]
@@ -99,9 +118,10 @@ def pipeline(project_name:str, wandb, sweep:bool, model_config:dict, training_co
print("Mean Sharpe ratio for Level-1 models: ", round(weighted_average(level1_columns, 'no_of_samples').loc['sharpe'], 3))
print("Mean Probabilistic Sharpe ratio for Level-1 models: ", round(weighted_average(level1_columns, 'no_of_samples').loc['prob_sharpe'].mean(), 3))
print("Level-2 (Ensemble): Number of samples evaluated: ", level2_columns.loc['no_of_samples'].sum())
print("Mean Sharpe ratio for Level-2 (Ensemble) models: ", round(weighted_average(level2_columns, 'no_of_samples').loc['sharpe'].mean(), 3))
print("Mean Probabilistic Sharpe ratio for Level-2 (Ensemble) models: ", round(weighted_average(level2_columns, 'no_of_samples').loc['prob_sharpe'].mean(), 3))
if model_config['level_2_model'] is not None:
print("Level-2 (Ensemble): Number of samples evaluated: ", level2_columns.loc['no_of_samples'].sum())
print("Mean Sharpe ratio for Level-2 (Ensemble) models: ", round(weighted_average(level2_columns, 'no_of_samples').loc['sharpe'].mean(), 3))
print("Mean Probabilistic Sharpe ratio for Level-2 (Ensemble) models: ", round(weighted_average(level2_columns, 'no_of_samples').loc['prob_sharpe'].mean(), 3))
if sweep:
if wandb.run is not None: