def find_best_params(self,validation_data_x,validation_data_y,n_jobs=1,params=[]):
if not params:
params = self.get_default_param_grid()
merged_x = Data.merge_arrays(self.training_data_x, validation_data_x)
merged_y = Data.merge_arrays(self.training_data_y, validation_data_y)
test_fold = []
for i in range(0,len(self.training_data_y)):
test_fold.append(1)
for i in range(0,len(validation_data_y)):
test_fold.append(0)
cv = PredefinedSplit(test_fold)
gs = GridSearchCV(
estimator=GaussianNB(),
scoring='f1_micro',
param_grid=params,
n_jobs=n_jobs,
cv=cv
)
gs.fit(merged_x,merged_y)
best_params = gs.best_params_
results = gs.cv_results_
return best_params,results
def find_best_params(self,validation_data_x,validation_data_y,alpha_vals,n_jobs=1):
merged_x = Data.merge_arrays(self.training_data_x, validation_data_x)
merged_y = Data.merge_arrays(self.training_data_y, validation_data_y)
test_fold = []
for i in range(0,len(self.training_data_y)):
test_fold.append(1)
for i in range(0,len(validation_data_y)):
test_fold.append(0)
cv = PredefinedSplit(test_fold)
param = {"alpha": alpha_vals}
gs = GridSearchCV(
estimator=BernoulliNB(),
scoring='f1_micro',
param_grid=param,
n_jobs=n_jobs,
cv=cv
)
gs.fit(merged_x,merged_y)
best_params = gs.best_params_
results = gs.cv_results_
return best_params,results