sub['Outlet_Identifier'] = test['Outlet_Identifier']
sub.to_csv('pseudo-labelling.csv', index='False')
model_factory = [
XGBRegressor(nthread=1),
PseudoLabeler(
XGBRegressor(nthread=1),
test,
features,
target,
sample_rate=0.2 #0.3
),
]
for model in model_factory:
model.seed = 42
num_folds = 2 #8
scores = cross_val_score(model,
X_train,
y_train,
cv=num_folds,
scoring='neg_mean_squared_error') #n_jobs=8
score_description = "MSE: %0.4f (+/- %0.4f)" % (np.sqrt(
scores.mean() * -1), scores.std() * 2)
print('{model:25} CV-{num_folds} {score_cv}'.format(
model=model.__class__.__name__,
num_folds=num_folds,
score_cv=score_description))
'''
