def predict_t2(self, grid_search = True):
if self.docs == {}:
raise ValueError("docs have not been created. call set_prediction_docs first!")
# get features and target
X, Y, info = self.get_feature('t2')
# init svm classifier
svm = SVM(self._model_path, "trig-theme1-2", "linear", grid_search = grid_search, class_weight = 'auto')
svm.load()
return svm.predict(X), Y, info
def predict_tt(self, grid_search = True):
"""
return prediction of given docid_list
"""
if self.docs == {}:
raise ValueError("docs have not been created. call set_prediction_docs first!")
# get list of file
#doc_ids = self.get_docid_list(docid_list_fname)
# get features and target
X, Y, info = self.get_feature('tt')
# init svm classifier
svm = SVM(self._model_path, "trig-trig", "linear", grid_search = grid_search, class_weight = 'auto')
svm.load()
return svm.predict(X), Y, info
def learn_t2(self, docid_list_fname, grid_search):
# get list of file
doc_ids = self.get_docid_list(docid_list_fname)
# get features and target
X, Y = self.get_feature(doc_ids, 't2')
# init svm classifier
svm = SVM(self.path,
'trig-theme1-2',
'linear',
grid_search=grid_search,
class_weight='auto')
svm.create()
# fit training data
svm.learn(X, Y)
if __name__ == '__main__':
args = argument_parser()
method = args.method
train, labels, test, test_ids, classes = createDataSets()
classifiers = []
if method == 'MLP':
clf = MLP(train, labels, test, test_ids, classes)
classifiers.append(clf)
elif method == 'regression':
clf = Regression(train, labels, test, test_ids, classes)
classifiers.append(clf)
elif method == 'SVM':
clf = SVM(train, labels, test, test_ids, classes)
classifiers.append(clf)
elif method == 'randomforest':
clf = RF(train, labels, test, test_ids, classes)
classifiers.append(clf)
elif method == 'KNN':
clf = KNN(train, labels, test, test_ids, classes)
classifiers.append(clf)
elif method == 'naive_bayes':
clf = NB(train, labels, test, test_ids, classes)
classifiers.append(clf)
elif method == 'linear_discriminant_analysis':
clf = LDA(train, labels, test, test_ids, classes)
classifiers.append(clf)
elif method == 'all':
clfs = [MLP, SVM, RF, KNN, NB, LDA]