mirror of
https://github.com/Arianhgh/fx-quant-research.git
synced 2026-08-22 07:08:09 +00:00
36 lines
599 B
Plaintext
36 lines
599 B
Plaintext
|
# Core
|
||
|
|
numpy
|
||
|
|
pandas
|
||
|
|
scipy
|
||
|
|
scikit-learn
|
||
|
|
matplotlib
|
||
|
|
seaborn
|
||
|
|
joblib
|
||
|
|
|
||
|
|
# Gradient boosting / tree models
|
||
|
|
xgboost
|
||
|
|
lightgbm
|
||
|
|
catboost
|
||
|
|
|
||
|
|
# Regime detection
|
||
|
|
hmmlearn
|
||
|
|
|
||
|
|
# Feature selection / hyperparameter tuning / explainability
|
||
|
|
Boruta
|
||
|
|
optuna
|
||
|
|
scikit-optimize
|
||
|
|
shap
|
||
|
|
|
||
|
|
# Deep learning (neural ensemble)
|
||
|
|
torch
|
||
|
|
|
||
|
|
# Technical indicators
|
||
|
|
# NOTE: TA-Lib also needs the underlying C library installed on your system.
|
||
|
|
# macOS: brew install ta-lib
|
||
|
|
# Ubuntu: apt-get install ta-lib (or build from source)
|
||
|
|
# Windows: install a prebuilt wheel / the ta-lib binaries
|
||
|
|
TA-Lib
|
||
|
|
|
||
|
|
# Live data download (optional)
|
||
|
|
oandapyV20
|