51 lines
5.0 KiB
Plaintext
51 lines
5.0 KiB
Plaintext
|
§
|
|||
|
|
|
|||
|
|
3³g' ã óŠ — d dl Zd dlZd dlmZ d dlmZmZ ddej de
|
|||
|
|
fd„Z dd „Z dd „Z
|
|||
|
|
d
|
|||
|
|
efd„Zdefd„Zdefd„Zdd„ZdS )é N)ÚRandomForestRegressor)Úmean_squared_errorÚmean_absolute_errorçš™™™™™é?ÚdfÚ train_ratioc óÌ — t t | ¦ « |z ¦ « }| j d|… ¦ « }| j |d… ¦ « }||fS )z=
|
|||
|
|
Splits df into train and test sets chronologically.
|
|||
|
|
N)ÚintÚlenÚilocÚcopy)r r Ú split_indexÚdf_trainÚdf_tests ú?c:\Users\moham\OneDrive\ml_bot_trading\models\model_training.pyÚtime_based_splitr s_ € õ •c˜"‘g”g Ñ+Ñ,Ô,€KØŒw�|˜ �|Ô$×)Ò)Ñ+Ô+€HØŒg�k�l�lÔ#×(Ò(Ñ*Ô*€GØ �WÐ Ð ó é c óÚ — |€t dd¬¦ « }| | |¦ « |j }t j |¦ « ddd… }|d|… }| j dd…|f }||fS )z±
|
|||
|
|
Uses a random forest (or a user-provided estimator) to rank feature importances,
|
|||
|
|
then keeps the top 'max_features'.
|
|||
|
|
Returns (X_new, selected_features_indices).
|
|||
|
|
Néd é* ©Ú n_estimatorsÚ random_stateéÿÿÿÿ)r ÚfitÚfeature_importances_ÚnpÚargsortr )ÚXÚyÚ estimatorÚ max_featuresÚ importancesÚindicesÚ top_indicesÚX_news r Úselect_features_rf_regr( s € ð ÐÝ)°sÈÐLÑLÔLˆ à
|
|||
|
|
‡M‚M�!�QÑÔÐØÔ0€KåŒj˜Ñ%Ô% d d¨ dÔ+€Gؘ-˜<˜-Ô(€KØ
|
|||
|
|
ŒF�1�1�1�k�>Ô "€EØ �+Ð Ð r r r c óT — t ||¬¦ « }| | |¦ « |S )zF
|
|||
|
|
Trains a RandomForestRegressor and returns the fitted model.
|
|||
|
|
r )r r )ÚX_trainÚy_trainr r Úrfs r Útrain_random_forest_regr- # s/ € õ
|
|||
|
|
¨LÀ|Ð TÑ TÔ T€B؇F‚Fˆ7�GÑ Ô Ð Ø
|
|||
|
|
€Ir Úreturnc óv — | |¦ « }t ||¦ « }t ||¦ « }||dœS )zj
|
|||
|
|
Evaluates a regression model with MSE and MAE.
|
|||
|
|
Returns a dict with {'mse': ..., 'mae': ...}.
|
|||
|
|
)ÚmseÚmae)Úpredictr r )ÚmodelÚX_testÚy_testÚy_predr0 r1 s r Úevaluate_regressionr7 + sA € ð
|
|||
|
|
�]Š]˜6Ñ
|
|||
|
|
"Ô
|
|||
|
|
"€FÝ
|
|||
|
|
˜V VÑ
|
|||
|
|
,Ô
|
|||
|
|
,€CÝ
|
|||
|
|
˜f fÑ
|
|||
|
|
-Ô
|
|||
|
|
-€CؘsÐ #Ð #Ð#r Úmodelsc ó — ddl m} i }| ¦ « D ]A\ }}| | |¦ « | |¦ « } ||| ¦ « }
|
|||
|
|
|
|
|||
|
|
||< ŒB|S ©zm
|
|||
|
|
Trains and evaluates each model in 'models' dict.
|
|||
|
|
Returns a dict of MSE results for each model.
|
|||
|
|
r )r ©Úsklearn.metricsr Úitemsr r2 © r* r+ r4 r5 r8 r ÚresultsÚ
|
|||
|
|
model_namer3 r6 r0 s r Ú train_and_evaluate_reg_modelsrA 7 s€ € ð
|
|||
|
|
3Ð2Ð2Ð2Ð2Ð2à€GØ #Ÿ\š\™^œ^ð "ð "ш
|
|||
|
|
�EØ
|
|||
|
|
� Š �'˜7Ñ#Ô#Ð#Ø— ’ ˜vÑ&Ô&ˆØ Ð ¨Ñ0Ô0ˆØ !ˆ�
|
|||
|
|
ÑÐØ €Nr c óÂ — ddl m} i }| ¦ « D ]A\ }}| | |¦ « | |¦ « } ||| ¦ « }
|
|||
|
|
|
|
|||
|
|
||< ŒB|S r: r; r> s r rA rA F s€ € ð
|
|||
|
|
3Ð2Ð2Ð2Ð2Ð2Ø€GØ #Ÿ\š\™^œ^ð "ð "ш
|
|||
|
|
�EØ
|
|||
|
|
� Š �'˜7Ñ#Ô#Ð#Ø— ’ ˜vÑ&Ô&ˆØ Ð ¨Ñ0Ô0ˆØ !ˆ�
|
|||
|
|
ÑÐØ €Nr é c ó6 — t | ¦ « }||dz z }g }t |¦ « D ]o}|dz |z }|dz |z }||k r|}| j d|… } |j d|… }
|
|||
|
|
| j ||… } |j ||… } | | |
|
|||
|
|
| | f¦ « Œp|S )a�
|
|||
|
|
Splits the data X, y into multiple chronological folds.
|
|||
|
|
For example, with n_splits=3, we do:
|
|||
|
|
- Fold 1: Train [0 : fold1], Test [fold1 : fold2]
|