gavindiaz/drift

mirror of https://github.com/webclinic017/drift.git synced 2026-07-27 18:57:55 +00:00

T

Mark Aron Szulyovszky a9b05dbd42 fix(Reporting): use weighted average (with no_of_samples as weights) and only report level-1 OR level-2 model performance (#91 )

* fix(Reporting): use weighted average (with no_of_samples as weights) and only report level-1 OR level-2 model performance

* chore(Config): updated sweep config

* fix(Reporting): missing import

* fix(Evaluation): get_first_valid_return_index can deal with zero valid indexes

* fix(Training): increase threshold for skipping assets

* fix(DataLoader): target asset should be always the first column

2021-12-26 12:15:11 +01:00

.github/workflows

refactor(Project): move out load_data to utils, rename fetch_data to run_fetch_data, got classifiers to work (#38 )

2021-12-17 17:41:50 +01:00

feat(Pipeline): save results, train on all assets

2021-12-14 22:59:44 +01:00

refactor(Project): move out load_data to utils, rename fetch_data to run_fetch_data, got classifiers to work (#38 )

2021-12-17 17:41:50 +01:00

refactor(Project): move out load_data to utils, rename fetch_data to run_fetch_data, got classifiers to work (#38 )

2021-12-17 17:41:50 +01:00

feature_extractors

feat(Config): feature extractors are enabled one-by-one with a bool, added previous model to model.fit() (#77 )

2021-12-23 10:35:20 +01:00

feat(Sweep): separated level-1 and level-2 sweep configs, skip assets with too few samples to train on, simplified model mapping (#84 )

2021-12-23 23:48:59 +01:00

fix(Reporting): use weighted average (with no_of_samples as weights) and only report level-1 OR level-2 model performance (#91 )

2021-12-26 12:15:11 +01:00

feat(Data): add option to predict 3 classes (#79 )

2021-12-23 13:24:56 +01:00

fix(Reporting): use weighted average (with no_of_samples as weights) and only report level-1 OR level-2 model performance (#91 )

2021-12-26 12:15:11 +01:00

fix(Reporting): use weighted average (with no_of_samples as weights) and only report level-1 OR level-2 model performance (#91 )

2021-12-26 12:15:11 +01:00

.gitignore

feature: Added Weights and Biases configuration to the repo. (#48 )

2021-12-20 14:01:14 +01:00

config.py

feat(Sweep): separated level-1 and level-2 sweep configs, skip assets with too few samples to train on, simplified model mapping (#84 )

2021-12-23 23:48:59 +01:00

conftest.py

feat(Tests): added basic unit tests for walk_forward_train_test() (#22 )

2021-12-15 17:54:03 +01:00

environment.yml

feat(Models): added debug_future_lookahead, sped up LogisticRegression & DecisionTreeClassifier (#74 )

2021-12-22 16:59:03 +01:00

exploration.ipynb

feat(Models): added model that predicts 10 days ahead

2021-11-12 16:10:55 +01:00

README.md

feat(Core): ensemble models, correct forward returns calculation, scaling, only train from when asset returns are available, major bug fixed in walk_forward_train_test (#35 )

2021-12-17 14:32:17 +01:00

run_fetch_data.py

refactor(Project): move out load_data to utils, rename fetch_data to run_fetch_data, got classifiers to work (#38 )

2021-12-17 17:41:50 +01:00

run_pipeline.py

fix(Reporting): use weighted average (with no_of_samples as weights) and only report level-1 OR level-2 model performance (#91 )

2021-12-26 12:15:11 +01:00

run_sweep.py

Feature: Added sweep functionality (#65 )

2021-12-21 17:28:36 +01:00

sweep_level_1.yaml

feat(Sweep): separated level-1 and level-2 sweep configs, skip assets with too few samples to train on, simplified model mapping (#84 )

2021-12-23 23:48:59 +01:00

sweep_level_2.yaml

fix(Reporting): use weighted average (with no_of_samples as weights) and only report level-1 OR level-2 model performance (#91 )

2021-12-26 12:15:11 +01:00

wandb_setup.py

feature: Added Weights and Biases configuration to the repo. (#48 )

2021-12-20 14:01:14 +01:00

README.md

Financial time series prediction models

Installation

Use the conda environment file attached!:)