def one_iteration(TR_set, labels, binary, ensemble_methods, weight, lb, test,
hamming):
TR_set_used = copy.deepcopy(TR_set)
first_predictions = None
second_predictions = None
#classifiers = measures.create_all(TR_set_used['TR1'], TR_set_used['TR1_outcome'], TR_set_used['TR2'], TR_set_used['TR2_outcome'], labels, binary, ensemble_methods, weight, lb)
#best_strings = measures.all_combinations(classifiers, TR_set_used['TR2_outcome'], labels, binary)
#print best_strings
#print "best strings length" + str(len(best_strings))
best_TR_models = None
best_strings = new_classifiers5.names_all_classifiers(ensemble_methods)
prev_distance = float("inf")
distance = float("inf")
#TR_models_used, second_predictions = create_all_expanded_sets(TR_set_used, best_strings, ensemble_methods, binary, weight, lb, labels)
#print distance_between(second_predictions, hamming)
i = 0
while i < 5:
if (prev_distance < distance):
best_TR_models = TR_models_used
break
print i
TR_models_used, second_predictions = create_all_expanded_sets(
TR_set_used, best_strings, ensemble_methods, binary, weight, lb,
labels)
#best_strings = get_new_best_strings(TR_models_used, TR_set_used, best_strings, labels, binary)
print("distance")
prev_distance = distance
holdi = distance_between(second_predictions, hamming)
distance = holdi[0]
largest = holdi[1]
print distance
print largest
#print best_strings
i = i + 1
print " "
if (test):
return best_classifiers_choice(best_TR_models['TR_model'],
TR_set_used['TS'],
TR_set_used['TS_outcome'], TR_set_used,
best_strings, binary, weight, lb,
labels)
else:
return best_classifiers_choice(best_TR_models['TR_model'],
TR_set_used['TR3'],
TR_set_used['TR3_outcome'], TR_set_used,
best_strings, binary, weight, lb,
labels)
def best_parameters(TR_set, ensemble_methods, binary):
keeper = []
for value in new_classifiers5.create_best_classifiers(
new_classifiers5.names_all_classifiers(ensemble_methods),
ensemble_methods):
keeper.append(
tuned_classifier_TR3(TR_set, value['model'],
value['tuned_parameters'], value['type'],
binary))
return keeper
def expand_all_combine_all(full_training_set, TR_set_used, TS, TS_outcome,
best_classifiers, labels, binary, new_features_only,
best_strings_first, ensemble_methods, weight, lb):
best_strings_second = new_classifiers5.names_all_classifiers(
ensemble_methods)
return mean_combine.combine(full_training_set, TR_set_used, TS, TS_outcome,
best_classifiers, labels, binary,
new_features_only, best_strings_first,
best_strings_second, ensemble_methods, weight,
lb)
def fit_expanded_set_all_models(TR2_expanded, TR2_outcome, ensemble_methods):
fitted_models = []
for each_classifier in new_classifiers5.create_best_classifiers(
new_classifiers5.names_all_classifiers(ensemble_methods),
ensemble_methods):
fitted_models.append(
tune_classifier_expanded(TR2_expanded, TR2_outcome,
each_classifier['model'],
each_classifier['tuned_parameters'],
each_classifier['type']))
return fitted_models
def expand_all(TR_set_used, labels, binary, new_features_only, training_set3,
ensemble_methods, lb, weight):
best_strings_first = new_classifiers5.names_all_classifiers(
ensemble_methods)
best_strings_second = best_strings_first
best_classifiers = new_classifiers5.one_iteration(
TR_set_used, training_set3, new_features_only, labels, binary,
best_strings_first, best_strings_second, ensemble_methods, lb, weight)
return (best_classifiers, best_strings_first)
def expand_best(TR_set_used, labels, binary, new_features_only, training_set3,
ensemble_methods, lb, weight):
#for each classifier train on tr and test on tR3
#
list_classifiers = []
for each_classifier in new_classifiers5.create_classifiers(
ensemble_methods):
model = None
if (each_classifier['tuned_parameters'] != []):
model = GridSearchCV(each_classifier['model'],
each_classifier['tuned_parameters'],
cv=10,
scoring="accuracy").fit(
TR_set_used['TR'],
TR_set_used['TR_outcome'])
else:
model = each_classifier['model'].fit(TR_set_used['TR'],
TR_set_used['TR_outcome'])
type_hold = each_classifier['type']
predictions = model.predict(TR_set_used['TR3'])
roc_score = None
if (binary):
roc_score = roc_auc_score(predictions, TR_set_used['TR3_outcome'])
else:
roc_score = new_classifiers5.multi_class_roc(
weight, lb, predictions, TR_set_used['TR3_outcome'], labels)
hold_tup = (type_hold, predictions, roc_score, model)
list_classifiers.append(hold_tup)
best_strings_first = greedy.find_best(list_classifiers, TR_set_used['TR3'],
TR_set_used['TR3_outcome'], labels,
TR_set_used['TR'],
TR_set_used['TR_outcome'], weight,
lb, binary)
best_strings_second = new_classifiers5.names_all_classifiers(
ensemble_methods)
best_classifiers = new_classifiers5.one_iteration(
TR_set_used, training_set3, new_features_only, labels, binary,
best_strings_first, best_strings_second, ensemble_methods, lb, weight)
return (best_classifiers, best_strings_first)
def linear_stacking(TR_set, ensemble_methods, weight, lb, binary, labels):
start_time = time.time()
TR2_predictions = []
TS_predictions = []
hold_sets = new_classifiers5.get_new_training(
np.column_stack((TR_set['TR_full'], TR_set["TR_full_outcome"])))
for each_classifier in new_classifiers5.create_best_classifiers(
new_classifiers5.names_all_classifiers(ensemble_methods),
ensemble_methods):
store = tuned_classifier(hold_sets['TR1'], hold_sets['TR1_outcome'],
each_classifier['model'],
each_classifier['tuned_parameters'],
each_classifier['type'])
if (len(TR2_predictions) == 0):
TR2_predictions = store['model'].predict(hold_sets['TR2'])
TS_predictions = store['model'].predict(TR_set['TS'])
else:
TR2_predictions = np.column_stack(
(TR2_predictions, store['model'].predict(hold_sets['TR2'])))
TS_predictions = np.column_stack(
(TS_predictions, store['model'].predict(TR_set['TS'])))
tuned_parameters_logistic = [{
'penalty': ['l1', 'l2'],
'C': [0.01, 0.1, 1, 5, 10]
}]
model = GridSearchCV(LogisticRegression(), tuned_parameters_logistic,
cv=5).fit(TR2_predictions, hold_sets['TR2_outcome'])
predictions = model.predict(TS_predictions)
if (binary):
print "linear stacking roc_auc_score: " + str(
roc_auc_score(
TR_set['TS_outcome'], predictions, average='weighted'))
print " f-score: " + str(
f1_score(TR_set['TS_outcome'], predictions, average='binary'))
else:
print " linear stacking roc_auc_score: " + str(
new_classifiers5.multi_class_roc(weight, lb, predictions,
TR_set['TS_outcome'], labels))
print " f-score: " + str(
f1_score(TR_set['TS_outcome'], predictions, average='weighted'))
print("--- %s seconds ---" % (time.time() - start_time))
print " "
