gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-07-27 18:57:55 +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
models/model_map.py
+7 -5
View File
@@ -22,12 +22,12 @@ model_map = {
KNN = SKLearnModel(KNeighborsRegressor(n_neighbors=25)),
AB = SKLearnModel(AdaBoostRegressor(random_state=1)),
MLP = SKLearnModel(MLPRegressor(hidden_layer_sizes=(100,20), max_iter=1000)),
RF = SKLearnModel(RandomForestRegressor(n_jobs=-1, random_state=1)),
RF = SKLearnModel(RandomForestRegressor(n_jobs=-1, max_depth=20, random_state=1)),
SVR = SKLearnModel(SVR(kernel='rbf', C=1e3, gamma=0.1)),
StaticNaive = StaticNaiveModel(),
),
"classification_models": dict(
LR= SKLearnModel(LogisticRegression(C=10, random_state=1, max_iter=1000)),
LR= SKLearnModel(LogisticRegression(C=10, random_state=1, max_iter=1000, n_jobs=-1)),
LDA= SKLearnModel(LinearDiscriminantAnalysis()),
KNN= SKLearnModel(KNeighborsClassifier()),
CART= SKLearnModel(DecisionTreeClassifier(max_depth=15, random_state=1)),
@@ -42,10 +42,12 @@ model_map = {
model_names_classification = list(model_map["classification_models"].keys())
model_names_regression = list(model_map["regression_models"].keys())
default_feature_selector_regression = model_map['regression_models']['RF']
default_feature_selector_classification = model_map['classification_models']['RF']
def map_model_name_to_function(model_config:dict, method:str) -> dict:
for level in ['level_1_models', 'level_2_models']:
model_category = method + '_models'
model_config[level] = [(model_name, model_map[model_category][model_name]) for model_name in model_config[level]]
model_config['level_1_models'] = [(model_name, model_map[method + '_models'][model_name]) for model_name in model_config['level_1_models']]
if model_config['level_2_model'] is not None:
model_config['level_2_model'] = (model_config['level_2_model'], model_map[method + '_models'][model_config['level_2_model']])
return model_config