class DecisionTree:
def __init__(self):
self.log = LoggerUtil(self.__class__.__name__).get()
self.config = ConfigUtil.get_config_instance()
self.helper = Helper()
self.metrics = Metrics()
@staticmethod
def train_model(x_train, y_train):
model = DecisionTreeClassifier()
model.fit(x_train, y_train)
return model
@staticmethod
def test_model(model, x_test):
return model.predict(x_test)
def main(self, x_train, x_test, y_train, y_test):
image_path = self.config["image_path"]
model = self.train_model(x_train, y_train)
self.log.info("{} Model performance on test data".format(self.__class__.__name__))
y_pred = self.test_model(model, x_test)
acc_score, cr_report, cnf_matrix = self.metrics.metrics(y_true=y_test, y_predicted=y_pred)
self.helper.plot_save_cnf_matrix(cnf_matrix, flag="test", model_name=self.__class__.__name__,
image_path=image_path)
return {
"model": model,
"metrics": {
"accuracy": acc_score,
"classification_report": cr_report,
"confusion_matrix": cnf_matrix
}
}
class TestModel:
def __init__(self):
self.log = LoggerUtil(self.__class__.__name__).get()
self.config = ConfigUtil.get_config_instance()
self.model = LinguisticModel()
self.read_data = ReadData()
self.metrics = Metrics()
self.helper = Helper()
self.logic = Logic()
def check_if_trained(self):
models_path = self.config["models_path"]
model = joblib.load(models_path + "/" + "mlp.mdl")
vectorizer = joblib.load(models_path + "/" + "vectorizer.mdl")
return vectorizer, model
def main(self, test=False):
if test:
nlp = load("en_core_web_sm")
vectorizer, model = self.check_if_trained()
self.log.info("Please enter the sentence")
sentence = str(input())
tokens = self.read_data.transform_sentence(sentence)
features = vectorizer.transform(tokens)
predictions = model.predict(features)
ling_pred = self.logic.apply_rules(text_tokens=tokens, nlp=nlp)
self.log.info("Given sentence : {}".format(sentence))
self.log.info(
"Prediction of Linguistic Model : {}".format(ling_pred))
self.log.info("Prediction of ML Model : {}".format(
any(predictions)))
self.log.info("Final Prediction : {}".format(ling_pred
or any(predictions)))
else:
model, vectorizer = self.model.main()
tagged_data_df = self.read_data.prepare_tagged_data()
features = vectorizer.transform(tagged_data_df["data"])
labels = tagged_data_df["labels"]
predictions = model.predict(features)
acc_score, cr_report, cnf_matrix = self.metrics.metrics(
y_true=labels, y_predicted=predictions)
self.helper.plot_save_cnf_matrix(
cnf_matrix=cnf_matrix,
model_name="satwik",
flag="test",
image_path=
"/home/satwik/Documents/Hiring/huddl_assignment/Images/")