def tune_dart():
name = 'DartGBM'
dimension = 'winner'
stage, dart_clf, dart_checkpoint_score = stage_init(name,
dimension,
extension=EXTENSION)
if stage == 0:
dart_clf = lgb.LGBMClassifier(random_state=1108,
n_estimators=100,
subsample=.8,
verbose=-1,
is_unbalance=True)
dart_clf, dart_checkpoint_score = pipe_init(X, Y, dart_clf)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 1:
dart_clf, dart_checkpoint_score = test_scaler(dart_clf,
dart_checkpoint_score, X,
Y)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 2:
dart_clf, dart_checkpoint_score = feat_selection(
X, Y, dart_clf, dart_checkpoint_score)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 3:
dart_clf, dart_checkpoint_score = test_scaler(dart_clf,
dart_checkpoint_score, X,
Y)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 4:
dart_clf, dart_checkpoint_score = pca_tune(X, Y, dart_clf,
dart_checkpoint_score)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 5:
dart_clf, dart_checkpoint_score = feat_selection(
X, Y, dart_clf, dart_checkpoint_score)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 6:
dart_clf, dart_checkpoint_score = test_scaler(dart_clf,
dart_checkpoint_score, X,
Y)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 7:
dart_clf, dart_checkpoint_score = lgb_find_lr(dart_clf, X, Y,
dart_checkpoint_score)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 8:
dart_clf, dart_checkpoint_score = pca_tune(X,
Y,
dart_clf,
dart_checkpoint_score,
iter_=10)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 9:
dart_clf, dart_checkpoint_score = feat_selection(
X, Y, dart_clf, dart_checkpoint_score)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 10:
dart_clf, dart_checkpoint_score = test_scaler(dart_clf,
dart_checkpoint_score, X,
Y)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 11:
dart_clf, dart_checkpoint_score = lgb_tree_params(
X, Y, dart_clf, dart_checkpoint_score)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 12:
dart_clf, dart_checkpoint_score = pca_tune(X,
Y,
dart_clf,
dart_checkpoint_score,
iter_=10)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 13:
dart_clf, dart_checkpoint_score = feat_selection(
X, Y, dart_clf, dart_checkpoint_score)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 14:
dart_clf, dart_checkpoint_score = test_scaler(dart_clf,
dart_checkpoint_score, X,
Y)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 15:
dart_clf, dart_checkpoint_score = lgb_drop_lr(dart_clf, X, Y,
dart_checkpoint_score)
_save_model(stage,
'winner',
name,
dart_clf,
dart_checkpoint_score,
final=True,
extension=EXTENSION)
def tune_polysvc():
name = 'PolySVC'
dimension = 'winner'
stage, polysvc_clf, polysvc_checkpoint_score = stage_init(
name, dimension, extension=EXTENSION)
if stage == 0:
polysvc_clf = SVC(random_state=1108,
class_weight='balanced',
kernel='poly',
probability=True)
polysvc_clf, polysvc_checkpoint_score = pipe_init(X, Y, polysvc_clf)
_save_model(stage,
'winner',
name,
polysvc_clf,
polysvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 1:
polysvc_clf, polysvc_checkpoint_score = test_scaler(
polysvc_clf, polysvc_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
polysvc_clf,
polysvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 2:
polysvc_clf, polysvc_checkpoint_score = feat_selection_2(
X, Y, polysvc_clf, polysvc_checkpoint_score)
_save_model(stage,
'winner',
name,
polysvc_clf,
polysvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 3:
polysvc_clf, polysvc_checkpoint_score = test_scaler(
polysvc_clf, polysvc_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
polysvc_clf,
polysvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 4:
polysvc_clf, polysvc_checkpoint_score = pca_tune(
X, Y, polysvc_clf, polysvc_checkpoint_score)
_save_model(stage,
'winner',
name,
polysvc_clf,
polysvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 5:
polysvc_clf, polysvc_checkpoint_score = feat_selection_2(
X, Y, polysvc_clf, polysvc_checkpoint_score)
_save_model(stage,
'winner',
name,
polysvc_clf,
polysvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 6:
polysvc_clf, polysvc_checkpoint_score = test_scaler(
polysvc_clf, polysvc_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
polysvc_clf,
polysvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 7:
polysvc_clf, polysvc_checkpoint_score = svc_hyper_parameter_tuning(
X, Y, polysvc_clf, polysvc_checkpoint_score)
_save_model(stage,
'winner',
name,
polysvc_clf,
polysvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 8:
polysvc_clf, polysvc_checkpoint_score = pca_tune(
X, Y, polysvc_clf, polysvc_checkpoint_score, iter_=10)
_save_model(stage,
'winner',
name,
polysvc_clf,
polysvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 9:
polysvc_clf, polysvc_checkpoint_score = feat_selection_2(
X, Y, polysvc_clf, polysvc_checkpoint_score)
_save_model(stage,
'winner',
name,
polysvc_clf,
polysvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 10:
polysvc_clf, polysvc_checkpoint_score = test_scaler(
polysvc_clf, polysvc_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
polysvc_clf,
polysvc_checkpoint_score,
final=True,
extension=EXTENSION)
def tune_log():
name = 'LogRegression'
dimension = 'winner'
stage, log_clf, log_checkpoint_score = stage_init(name,
dimension,
extension=EXTENSION)
if stage == 0:
log_clf = LogisticRegression(max_iter=1000,
random_state=1108,
class_weight='balanced',
solver='lbfgs')
log_clf, log_checkpoint_score = pipe_init(X, Y, log_clf)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 1:
log_clf, log_checkpoint_score = test_scaler(log_clf,
log_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 2:
log_clf, log_checkpoint_score = feat_selection(
X, Y, log_clf, log_checkpoint_score) #, _iter = 5)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 3:
log_clf, log_checkpoint_score = test_scaler(log_clf,
log_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 4:
log_clf, log_checkpoint_score = pca_tune(X, Y, log_clf,
log_checkpoint_score)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 5:
log_clf, log_checkpoint_score = feat_selection(
X, Y, log_clf, log_checkpoint_score) #, _iter = 5)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 6:
log_clf, log_checkpoint_score = test_scaler(log_clf,
log_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 7:
log_clf, log_checkpoint_score = C_parameter_tuning(
X, Y, log_clf, log_checkpoint_score)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 8:
log_clf, log_checkpoint_score = pca_tune(X,
Y,
log_clf,
log_checkpoint_score,
iter_=10)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 9:
log_clf, log_checkpoint_score = feat_selection(
X, Y, log_clf, log_checkpoint_score) #, _iter = 5)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 10:
log_clf, log_checkpoint_score = test_scaler(log_clf,
log_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 11:
log_clf, log_checkpoint_score = test_solver(X, Y, log_clf,
log_checkpoint_score)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 12:
log_clf, log_checkpoint_score = pca_tune(X,
Y,
log_clf,
log_checkpoint_score,
iter_=10)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 13:
log_clf, log_checkpoint_score = feat_selection(
X, Y, log_clf, log_checkpoint_score) #, _iter = 5)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 14:
log_clf, log_checkpoint_score = test_scaler(log_clf,
log_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
log_clf,
log_checkpoint_score,
final=True,
extension=EXTENSION)
def tune_linsvc():
name = 'LinSVC'
dimension = 'winner'
stage, linsvc_clf, linsvc_checkpoint_score = stage_init(
name, dimension, extension=EXTENSION)
if stage == 0:
linsvc_clf = SVC(random_state=1108,
class_weight='balanced',
kernel='linear',
probability=True)
linsvc_clf, linsvc_checkpoint_score = pipe_init(X, Y, linsvc_clf)
_save_model(stage,
'winner',
name,
linsvc_clf,
linsvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 1:
linsvc_clf, linsvc_checkpoint_score = test_scaler(
linsvc_clf, linsvc_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
linsvc_clf,
linsvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 2:
linsvc_clf, linsvc_checkpoint_score = feat_selection(
X, Y, linsvc_clf, linsvc_checkpoint_score)
_save_model(stage,
'winner',
name,
linsvc_clf,
linsvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 3:
linsvc_clf, linsvc_checkpoint_score = test_scaler(
linsvc_clf, linsvc_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
linsvc_clf,
linsvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 4:
linsvc_clf, linsvc_checkpoint_score = pca_tune(
X, Y, linsvc_clf, linsvc_checkpoint_score)
_save_model(stage,
'winner',
name,
linsvc_clf,
linsvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 5:
linsvc_clf, linsvc_checkpoint_score = feat_selection(
X, Y, linsvc_clf, linsvc_checkpoint_score)
_save_model(stage,
'winner',
name,
linsvc_clf,
linsvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 6:
linsvc_clf, linsvc_checkpoint_score = test_scaler(
linsvc_clf, linsvc_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
linsvc_clf,
linsvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 7:
linsvc_clf, linsvc_checkpoint_score = C_parameter_tuning(
X, Y, linsvc_clf, linsvc_checkpoint_score)
_save_model(stage,
'winner',
name,
linsvc_clf,
linsvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 8:
linsvc_clf, linsvc_checkpoint_score = pca_tune(X,
Y,
linsvc_clf,
linsvc_checkpoint_score,
iter_=10)
_save_model(stage,
'winner',
name,
linsvc_clf,
linsvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 9:
linsvc_clf, linsvc_checkpoint_score = feat_selection(
X, Y, linsvc_clf, linsvc_checkpoint_score)
_save_model(stage,
'winner',
name,
linsvc_clf,
linsvc_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 10:
linsvc_clf, linsvc_checkpoint_score = test_scaler(
linsvc_clf, linsvc_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
linsvc_clf,
linsvc_checkpoint_score,
final=True,
extension=EXTENSION)
def tune_knn():
name = 'KNN'
dimension = 'winner'
stage, knn_clf, knn_checkpoint_score = stage_init(name,
dimension,
extension=EXTENSION)
if stage == 0:
knn_clf = KNeighborsClassifier()
knn_clf, knn_checkpoint_score = pipe_init(X, Y, knn_clf)
_save_model(stage,
'winner',
name,
knn_clf,
knn_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 1:
knn_clf, knn_checkpoint_score = test_scaler(knn_clf,
knn_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
knn_clf,
knn_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 2:
knn_clf, knn_checkpoint_score = feat_selection_2(
X, Y, knn_clf, knn_checkpoint_score)
_save_model(stage,
'winner',
name,
knn_clf,
knn_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 3:
knn_clf, knn_checkpoint_score = test_scaler(knn_clf,
knn_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
knn_clf,
knn_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 4:
knn_clf, knn_checkpoint_score = pca_tune(X, Y, knn_clf,
knn_checkpoint_score)
_save_model(stage,
'winner',
name,
knn_clf,
knn_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 5:
knn_clf, knn_checkpoint_score = knn_hyper_parameter_tuning(
X, Y, knn_clf, knn_checkpoint_score)
_save_model(stage,
'winner',
name,
knn_clf,
knn_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 6:
knn_clf, knn_checkpoint_score = feat_selection_2(
X, Y, knn_clf, knn_checkpoint_score)
_save_model(stage,
'winner',
name,
knn_clf,
knn_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 7:
knn_clf, knn_checkpoint_score = test_scaler(knn_clf,
knn_checkpoint_score, X, Y)
_save_model(stage,
'winner',
name,
knn_clf,
knn_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 8:
knn_clf, knn_checkpoint_score = pca_tune(X,
Y,
knn_clf,
knn_checkpoint_score,
iter_=10)
_save_model(stage,
'winner',
name,
knn_clf,
knn_checkpoint_score,
final=True,
extension=EXTENSION)
def tune_rf():
name = 'RFclass'
dimension = 'winner'
stage, rf_clf, rf_checkpoint_score = stage_init(name,
dimension,
extension=EXTENSION)
if stage == 0:
rf_clf = RandomForestClassifier(random_state=1108, n_estimators=100)
rf_clf, rf_checkpoint_score = pipe_init(X, Y, rf_clf)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 1:
rf_clf, rf_checkpoint_score = test_scaler(rf_clf, rf_checkpoint_score,
X, Y)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 2:
rf_clf, rf_checkpoint_score = feat_selection(X, Y, rf_clf,
rf_checkpoint_score)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 3:
rf_clf, rf_checkpoint_score = test_scaler(rf_clf, rf_checkpoint_score,
X, Y)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 4:
rf_clf, rf_checkpoint_score = pca_tune(X, Y, rf_clf,
rf_checkpoint_score)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 5:
rf_clf, rf_checkpoint_score = feat_selection(X, Y, rf_clf,
rf_checkpoint_score)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 6:
rf_clf, rf_checkpoint_score = test_scaler(rf_clf, rf_checkpoint_score,
X, Y)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 7:
rf_clf, rf_checkpoint_score = forest_params(X, Y, rf_clf,
rf_checkpoint_score)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 8:
rf_clf, rf_checkpoint_score = pca_tune(X,
Y,
rf_clf,
rf_checkpoint_score,
iter_=10)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 9:
rf_clf, rf_checkpoint_score = feat_selection(X, Y, rf_clf,
rf_checkpoint_score)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 10:
rf_clf, rf_checkpoint_score = test_scaler(rf_clf, rf_checkpoint_score,
X, Y)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=False,
extension=EXTENSION)
elif stage == 11:
rf_clf, rf_checkpoint_score = rf_trees(X, Y, rf_clf,
rf_checkpoint_score)
_save_model(stage,
'winner',
name,
rf_clf,
rf_checkpoint_score,
final=True,
extension=EXTENSION)