def generate(self, seed=42):
if type(self.reader) == type(None):
s = None
if isinstance(self.classifier(), ClassifierMixin):
s = Splitter(train_fraction=[0.6, 10000000], valid_fraction=0.0, test_fraction=0.4, seed=seed)
elif isinstance(self.classifier(), RegressorMixin):
s = RandomSplitter(train_fraction=[0.6, 10000000], valid_fraction=0.0, test_fraction=0.4, seed=seed)
else:
pass
self.dataset = Reader(self.dataset_config[0], self.dataset_config[1], s)
else:
self.dataset = self.reader
self.raw_features = self.dataset.read()
print("training:" + str(len(self.dataset.splitted_target['train'])))
print("test:" + str(len(self.dataset.splitted_target['test'])))
if Config.get_default('instance.selection', 'False') == 'True':
self.train_X_all = copy.deepcopy(self.dataset.splitted_values['train'])
self.train_y_all = copy.deepcopy(self.dataset.splitted_target['train'])
self.dataset.splitted_values['train'], self.dataset.splitted_target['train'] = sample_data_by_cnn(self.dataset.splitted_values['train'], self.dataset.splitted_target['train'])
print("training:" + str(len(self.dataset.splitted_target['train'])))
else:
self.train_X_all = self.dataset.splitted_values['train']
self.train_y_all = self.dataset.splitted_target['train']
def generate(self):
s = Splitter(train_fraction=[0.6, 10000000], seed=42)
#s = Splitter(train_fraction=[0.1, 10000000], seed=42)
self.dataset = Reader(self.dataset_config[0], self.dataset_config[1], s)
raw_features = self.dataset.read()
def generate(self):
s = Splitter(train_fraction=[0.6, 10000000], seed=42)
#s = Splitter(train_fraction=[0.1, 10000000], seed=42)
self.dataset = Reader(self.dataset_config[0], self.dataset_config[1],
s)
raw_features = self.dataset.read()
g = Generator(raw_features)
self.candidates = g.generate_all_candidates()
print("Number candidates: " + str(len(self.candidates)))
all_data = pickle.load(open(file, "rb"))
feature_predictions = pickle.load(
open('/home/felix/phd/feature_predictions/all_data_predictions.p', "rb"))
name2result_predictions = {}
for result in feature_predictions:
name2result_predictions[str(result['candidate'])] = result
dataset_config = (Config.get('statlog_heart.csv'),
int(Config.get('statlog_heart.target')))
s = Splitter(train_fraction=[0.6, 10000000], seed=42)
dataset = Reader(dataset_config[0], dataset_config[1], s)
raw_features = dataset.read()
X = dataset.splitted_values['train']
#delta mean -> avg, min, max gain
def calculate_MSE(candidate: CandidateFeature, X):
ys = []
for p in candidate.parents:
p.fit(X)
y = p.transform(X)
ys.append(y)
#correlation
print(len(all_representations))
return all_representations
if __name__ == '__main__':
from fastsklearnfeature.splitting.Splitter import Splitter
import time
s = Splitter(train_fraction=[0.6, 10000000])
dataset = (Config.get('statlog_heart.csv'),
int(Config.get('statlog_heart.target')))
#dataset = ("/home/felix/datasets/ExploreKit/csv/dataset_27_colic_horse.csv", 22)
#dataset = ("/home/felix/datasets/ExploreKit/csv/phpAmSP4g_cancer.csv", 30)
#dataset = ("/home/felix/datasets/ExploreKit/csv/phpOJxGL9_indianliver.csv", 10)
#dataset = ("/home/felix/datasets/ExploreKit/csv/dataset_29_credit-a_credit.csv", 15)
#dataset = ("/home/felix/datasets/ExploreKit/csv/dataset_37_diabetes_diabetes.csv", 8)
#dataset = ("/home/felix/datasets/ExploreKit/csv/dataset_31_credit-g_german_credit.csv", 20)
#dataset = ("/home/felix/datasets/ExploreKit/csv/dataset_23_cmc_contraceptive.csv", 9)
#dataset = ("/home/felix/datasets/ExploreKit/csv/phpn1jVwe_mammography.csv", 6)
r = Reader(dataset[0], dataset[1], s)
raw_features = r.read()
g = TreeGenerator(raw_features)
start_time = time.time()
g.generate_candidates()