def prepare_test_data():
test_data = []
log.write("Open test set")
with open(TESTING_FILE, "r") as csv_file:
csv_data = csv.DictReader(csv_file)
for row in csv_data:
test_data.append(row)
log.write("Preprocessed test set")
for data in test_data:
data["preprocessed_kalimat"] = Preprocess(data).preprocess()
log.write("Extract feature test set")
feature = Features(test_data)
feature.extract_feature()
# feature.get_trainable_dataset()
return test_data
def main():
log.write("Open dataset")
dataset = open_dataset([TRAINING_DIR + files for files in TRAINING_FILES])
merged_dataset = []
log.write("Resolve disagreement data")
for k, v in dataset.items():
if k == TRAINING_DIR + TRAINING_FILES[
2] or k == TRAINING_DIR + TRAINING_FILES[4]:
dataset[k] = disagreement_handling(v)
merged_dataset += dataset[k]
analyze_data(merged_dataset)
log.write("Analyzing sense")
sense_id = set()
for datum in merged_dataset:
sense_id.add(datum["sense"])
xml_root = ET.parse(SENSE_FILES).getroot()
for word in xml_root:
for sense in word.findall("senses/sense"):
if word.attrib["wid"].zfill(2) + sense.attrib["sid"].zfill(
2) not in sense_id:
log.write(
"Kata `{}` dengan sense `{}` tidak ditemukan di data training"
.format(word[0].text, sense.attrib))
log.write("Preprocessing")
for data in merged_dataset:
data["preprocessed_kalimat"] = Preprocess(data).preprocess()
# for datum in merged_dataset:
# datum["preprocessed_kalimat"] =
print(merged_dataset[0])
log.write("Feature extraction")
feature = Features(merged_dataset)
feature.extract_feature()
# feature.get_trainable_dataset()
# log.write(merged_dataset[0])
with open("feature.csv", "w") as csv_file:
csv_writer = csv.writer(csv_file)
# csv_writer.writerow(["kalimat_id", "sense", "features"])
for data in merged_dataset:
if "data_embedding" in data:
csv_writer.writerow(
[data["\ufeffkalimat_id"], data["kata"], data["sense"]] +
list(data["data_embedding"]))
log.write("Build Dataset")
word_feature_mat, dummy_train, dummy_test = build_dataset(merged_dataset)
classifier = {
"Random Forest":
RandomForestClassifier(n_estimators=1000),
"SVM":
SVC(C=10000, gamma=0.1, tol=1e-6, decision_function_shape='ovo'),
"Neural Net":
MLPClassifier(hidden_layer_sizes=2000,
activation='tanh',
solver='adam',
tol=1e-6,
learning_rate_init=0.001,
max_iter=1000,
early_stopping=True)
}
best_model = None
best_acc = 0.0000001
test_data = prepare_test_data()
for model_name, model_class in classifier.items():
log.write("Try {} :".format(model_name))
true_count = 0
n_data = 0
model = model_class
ansfile = "answers/{}_{}.csv".format(model_name, int(time.time()))
for word in sorted(list(word_feature_mat.keys())):
print("predicting {}".format(word))
model.fit(dummy_train[word][0], dummy_train[word][1])
prediction = model.predict(dummy_test[word][0])
n_data += len(prediction)
for pred, true in zip(prediction, dummy_test[word][1]):
if pred == true:
true_count += 1
model = model.fit(word_feature_mat[word][0],
word_feature_mat[word][1])
actual_test(test_data, model, word, ansfile)
accuracy = 100 * true_count / n_data
# if accuracy > best_acc:
# # best_model = model_class
log.write("Akurasi dari {} : {} %".format(model_name, accuracy))
