# List of all models to test
model_factory = [
RandomForestRegressor(n_jobs=1),
XGBRegressor(),
]
# Apply the PseudoLabeler class to each model
model_factory = map(pseudo_label_wrapper, model_factory)
# Train each model with different sample rates
results = {}
num_folds = 5
for model in model_factory:
model_name = model.get_model_name()
print('%s' % model_name)
results[model_name] = list()
for sample_rate in sample_rates:
model.sample_rate = sample_rate
# Calculate the CV-3 R2 score and store it
scores = cross_val_score(
model,
X_train,
y_train,
cv=num_folds,
scoring='neg_mean_squared_error') # n_jobs = 4
results[model_name].append(np.sqrt(scores.mean() * -1))
