def process_by_ml_name(ml):
from dataset_loader import DataSetLoader
from sklearn import cross_validation
print 'start ', ml
loader = DataSetLoader()
x, y = loader.loadData()[DataSetLoader.dataset_name[0]]
score_lst = []
for ml in ml:
print 'start cross val'
scores = cross_validation.cross_val_score(ml, x, y, cv=5)
print 'end cross val'
score_lst.append(scores.mean())
return score_lst
def load_dataset(self):
loader = DataSetLoader()
lst = loader.loadData()
return lst
y_pred = self.predict(X)
average_score = (accuracy_score(y, y_pred) + f1_score(y, y_pred)) / 2.0
return average_score
def predict(self, x):
f_result = open(self.path_test_data, 'w')
self.__write_data_file(f_result, x, [0] * len(x))
f_result.close()
create_predict = libsvm_path + '/svm-predict' + ' {} {} {}'.format(self.path_test_data,
self.path_model_result,
self.path_result)
print create_predict
os.system(create_predict)
return self.__read_result()
def get_params(self, deep=True):
return {"kernel": self.kernel}
def set_params(self, **parameters):
for parameter, value in parameters.items():
setattr(self, parameter, value)
if __name__ == '__main__':
from dataset_loader import DataSetLoader
from sklearn.cross_validation import train_test_split
loader = DataSetLoader()
x, y = loader.loadData()['heart']
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.75, random_state=42)
ml = LibSVMWrapper(kernel=0)
ml.fit(x_train, y_train)