def main():
# set path
iris_path = [
'DataAnalysisProjectDesign/Experiment1/iris_train.arff',
'DataAnalysisProjectDesign/Experiment1/iris_test.arff'
]
adult_path = [
'DataAnalysisProjectDesign/Experiment1/adult_train.arff',
'DataAnalysisProjectDesign/Experiment1/adult_test.arff'
]
# get choice
data_choice = input('Enter 1 for iris DT; Enter 2 for adult DT:')
tree_choice = input('Enter 1 for ID3; Enter 2 for CART:')
path = select_dataset(data_choice, iris_path, adult_path)
# create train data instance
train_data_obj = Data(path[0])
train_data_obj.load_data()
train_data_obj.fill_missing_data()
# create test data instance
test_data_obj = Data(path[1])
test_data_obj.clear_memory()
test_data_obj.load_data()
test_data_obj.fill_missing_data()
tree = dt_router(train_data_obj, test_data_obj, tree_choice)
tree.test()
conf_mat, judge = tree.get_conf_mat()
return tree, conf_mat, judge
def main():
# set path
iris_path = 'DataAnalysisProjectDesign/Experiment2/iris_train.arff'
adult_path = 'DataAnalysisProjectDesign/Experiment2/adult_train.arff'
# get choice
data_choice = input('Enter 1 for iris; Enter 2 for adult:')
dt_num = int(input('Enter your expected tree number:'))
path = select_dataset(data_choice,iris_path,adult_path)
# create data instance
data_obj = Data(path)
data_obj.load_data()
data_obj.fill_missing_data()
# create random forest
rf = RandomForest(
data=data_obj,
dt_num=dt_num
)
rf.bagging()
rf.train_rf()
correct_rate,conf_mat = rf.test_rf()
return dt_num,correct_rate,conf_mat
def main():
path = 'DM_Experiment4/iris.arff'
choice = input('Use KMeans Enter 1;Use DBSCAN Enter 2:')
# load data
data_obj = Data(path=path)
data_obj.load_data()
algorithm_router(choice, data_obj)
def run_model():
d = Data(LANG, DEVorTEST, GLOVE_FILE, ELMO_FILE, MODEL, DEP_ADJACENCY_GCN,
POSITION_EMBED)
d.load_data(
DATAPATH
) # This loads train, dev, and test if available, and also word2vec and ELMo where relevant
model = Tagger(d, d.max_length, d.input_dim, d.n_poses, d.n_classes,
initial_weight)
tagger = getattr(model, MODEL)() # choose the specified tagging model
T = Train_Test(POS, MODEL, tagger, d)
if DEVorTEST == "CROSS_VAL":
T.cross_validation(EPOCHS, BATCH_SIZE, DATAPATH)
else:
T.train(EPOCHS, BATCH_SIZE)
T.test(DATAPATH
) # We pass DATAPATH to this function to be used for evaluation
def run_model():
# args: lang, train, dev, test, word2vec_dir, elmo_dir, model_name
d = Data(LANG_TR, LANG_DEV, LANG_TS, DEVorTEST, WV_DIR, ELMO_PATH, MODEL,
DEP_ADJACENCY_GCN, DEP_INFO, POS)
d.load_data(
DATAPATH
) # This loads train, dev (if available), test (if available) and also word2vec and ELMo
# args: max_length, n_poses, n_classes, initial_weight=''
model = Tagger(d, initial_weight)
tagger = getattr(model, MODEL)() # choose the specified tagging model
print(tagger)
T = Train_Test(POS, W2V, MODEL, tagger, d, DEVorTEST)
if DEVorTEST == "CROSS_VAL":
T.cross_validation(EPOCHS, BATCH_SIZE, DATAPATH)
else:
T.train(EPOCHS, BATCH_SIZE)
T.test(
DATAPATH
) # We give the Data_path to this function, just for it to return the evaluation for us