def get_model_accuracy_filter_feature_size(self,expression_file, ic50_file,feature_size,num_permutations,drug):
scikit_data,scikit_target = dfm.get_expression_scikit_data_target_for_drug(expression_file,ic50_file,drug,normalized=True,trimmed=True,threshold=None)
for i in range(0,num_permutations):
try:
shuffled_data,shuffled_target = dfm.shuffle_scikit_data_target(scikit_data,scikit_target)
accuracy = cv.cross_val_score_filter_feature_selection(self.model,cv.trim_X_num_features,feature_size,shuffled_data,shuffled_target,cv=5)
yield accuracy.mean()
except:
yield 0.0
def get_model_accuracy_RFE(self,expression_file,ic50_file,target_features,num_permutations,drug):
scikit_data,scikit_target = dfm.get_expression_scikit_data_target_for_drug(expression_file,ic50_file,drug,normalized=True,trimmed=True,threshold=None)
step_length = int(len(scikit_data.tolist()[0]) / 100) + 1
for i in xrange(0,num_permutations):
try:
shuffled_data,shuffled_target = dfm.shuffle_scikit_data_target(scikit_data,scikit_target)
selector = RFE(self.model,target_features,step=step_length)
yield cross_val_score(selector,shuffled_data,shuffled_target,cv=5).mean()
except:
yield 0.0
def get_cross_validation_time(self,expression_file, ic50_file,feature_size,num_permutations,drug):
scikit_data,scikit_target = dfm.get_expression_scikit_data_target_for_drug(expression_file,ic50_file,drug,normalized=True,trimmed=True,threshold=None)
for i in range(0,num_permutations):
try:
shuffled_data,shuffled_target = dfm.shuffle_scikit_data_target(scikit_data,scikit_target)
start_time = datetime.datetime.now()
cv.cross_val_score_filter_feature_selection(self.model,cv.trim_X_num_features,feature_size,shuffled_data,shuffled_target,cv=5)
end_time = datetime.datetime.now()
yield float((end_time - start_time).microseconds) / 100000
except:
yield 0.0
def acc_and_run(g,scikit_data,scikit_target,num_features,num_permutations):
results = []
for perm in xrange(0,num_permutations):
try:
start_time = datetime.datetime.now()
model = n.NeatClassifier(max_generations=g)
shuffled_data,shuffled_target = dfm.shuffle_scikit_data_target(scikit_data,scikit_target)
acc = cv.cross_val_score_filter_feature_selection(model,cv.trim_X_num_features,num_features,shuffled_data,shuffled_target,cv=5)
end_time = datetime.datetime.now()
results.append((acc.mean(),float((end_time - start_time).microseconds) / 100000))
except:
results.append((0.0, 1000.0))
print(sys.exc_info()[0])
return results
