def viterbi_test(test_path, features, weights, beam=10):
viterbi = Viterbi(features, weights, beam=beam)
list_of_sentences, real_list_of_tags = evaluation.prepare_test_data(
test_path)
pred_list_of_tags = viterbi.predict_tags(list_of_sentences)
# for i in range(len(pred_list_of_tags)):
# print("SENTENCE", i)
# print(list_of_sentences[i])
# for word, t1, t2 in zip(list_of_sentences[i].split(' '), real_list_of_tags[i], pred_list_of_tags[i]):
# if t1 != t2:
# print(word, t1, t2)
accuracy, accuracies, confusion_matrix = evaluation.calculate_accuracy(
real_list_of_tags, pred_list_of_tags)
return accuracy, accuracies, confusion_matrix
Xts = np.array([[1,4,5],[7,3,2]])
yts = np.array([1,2])
yts = np.reshape(yts,(2,1))
# Build Model
DTCmodel = DTC()
DTCmodel.fit(X_train = Xtr, y_train = ytr)
# Predict outputs
yh = DTCmodel.predict(X_test = Xts)
# calculate accuracy
acc = evaluation.calculate_accuracy(yts,yh)
print('Accuracy: ' + str(acc))
# Verify Nodes
node = DTCmodel.node_list[0]
print('Verify Node:')
print('Node Depth: ' + str(node.depth))
print('Node Data Indexes: ' + str(node.data_indexes))
print('Node sons: ' + str(node.sonList))
print('Node attribute: ' + str(node.attribute))
print('Node threshold: ' + str(node.threshold))
print('Node is leaf: ' + str(node.is_leaf))
print('Node Label: ' + str(node.label))
###################################################
if args['--output-dir'] is not None:
os.environ["OUT_DIR"] = args['--output-dir']
else:
assert "OUT_DIR" in os.environ
if args['--config'] is not None:
config = load_config_from_file(args['--config'])
else:
from seq2seq import config
print("Using configuration", config.__file__)
if args['--test'] is True:
test_file = config.filename_test
eval_type = 'test'
elif args['--dev'] is True:
test_file = config.filename_dev
eval_type = 'dev'
else:
raise ValueError('Specify --dev or --test.')
config_holder = ConfigHolder(config)
model = Model(config_holder)
df = evaluation.predict(model, config_holder, test_file)
acc_dict = evaluation.calculate_accuracy(df)
acc_verbose = evaluation.accuracy_to_string_verbose(acc_dict)
evaluation.save_results(df, acc_dict, acc_verbose, "Et-morf-yh", eval_type,
config.out_dir)
def evaluate(model, config_holder, test_file, lang_key, eval_type, out_dir):
df = evaluation.predict(model, config_holder, test_file)
acc_dict = evaluation.calculate_accuracy(df)
acc_verbose = evaluation.accuracy_to_string_verbose(acc_dict)
evaluation.save_results(df, acc_dict, acc_verbose, lang_key, eval_type, out_dir)
mean_acc_mdc = 0
for i in range(N):
# Split data between train and test
Xtr, Ytr, Xts, Yts = hold_out.leave_one_out(X, Y, i)
# Build Model
MDClassifier = MDC()
MDClassifier.fit(Xtr, Ytr)
# Predict outputs
Yh = MDClassifier.predict(Xts)
# Calculate and Accumulate accuracy
acc_mdc = evaluation.calculate_accuracy(Yts, Yh)
mean_acc_mdc = mean_acc_mdc + acc_mdc
# Mean Accuracy
mean_acc_mdc = mean_acc_mdc / N
print(
'Mean Accuracy of MD Classifier, with Iris Dataset and Leave-one-out Method:'
)
print(mean_acc_mdc)
# ########################## Experiment 2 - Wine, KNN, Random Subsampling
# Load DataSet
X, Y = data_loader.load_wine()