enron_dataset = dataset.get_dataset()
if CONFIG["dataset"]["output"]:
print("Exporting the dataset..")
dataset.to_csv(filepath=CONFIG["dataset"]["filepath"])
if CONFIG["preprocess"]["params"]["read_csv"]:
print("Reading the dataset..")
preprocessor = Preprocess(**CONFIG["preprocess"]["params"])
else:
preprocessor = Preprocess(dataset=enron_dataset, **CONFIG["preprocess"]["params"])
if CONFIG["preprocess"]["clean_dataset"]:
print("Cleaning the dataset..")
preprocessor.clean_data()
if CONFIG["preprocess"]["output_csv"]:
print("Exporting clean dataset..")
preprocessor.dataset.to_csv(CONFIG["preprocess"]["output_csv_filepath"])
print("Spliting the dataset..")
enron_dataset = preprocessor.dataset
enron_dataset = utils.split_dataset(x=enron_dataset["body"].values, y=enron_dataset["label"].values)
print("Transforming dataset into vectors and matrices..")
enron_dataset = preprocessor.transform(dataset=enron_dataset)
vocabulary = preprocessor.vocabulary
print("\n{}\n".format("-" * 50))
print("Building model..")
