from src.classification import CommonClassification
from src.preprocessing import CommonPreprocessing
from src.read_data import DataReader
SMOTE_K_NEIGHBOURS = 3
DATA_DIR = "../data"
data_reader = DataReader(DATA_DIR)
common_classifier = CommonClassification()
common_preprocessing = CommonPreprocessing()
keel_data = data_reader.read_keel_dat_directory()
for data in keel_data:
# initialize file names and params
print("Current dataset: " + str(data.file_name))
csv_export_file_name = "../results/smote_oversampling_k3/data-naive_bayes.csv"
output_csv = open(csv_export_file_name, "a")
confusion_matrix_plot_file_name = "../results/smote_oversampling_k3/confusion_matrix/%s-%s.%s" % (
data.file_name, "naive_bayes", "png")
class_distribution_plot_file_name = "../results/smote_oversampling_k3/class_distribution/%s-%s.%s" % (
data.file_name, "naive_bayes", "png")
# Split dataset and perform classification
testable = data.as_testable()
sampled_testable = common_preprocessing.smote_over_sampling(testable, SMOTE_K_NEIGHBOURS)
bayes_result = common_classifier.naive_bayes_gaussian_classification(sampled_testable)
# Print plots and data to files
print("%s;%s;%s;%s;%s" % (
bayes_result.file_name, bayes_result.accuracy, bayes_result.precision, bayes_result.recall, bayes_result.f1),
import random
from src.classification import CommonClassification
from src.preprocessing import CommonPreprocessing
from src.read_data import DataReader
DATA_DIR = "../data"
data_reader = DataReader(DATA_DIR)
common_classifier = CommonClassification()
common_preprocessing = CommonPreprocessing()
all_keel_data = data_reader.read_keel_dat_directory()
keel_data = random.choice(all_keel_data)
#keel_data = data_reader.read_keel_dat_file("winequality-white-3_vs_7.dat")
random_testable_keel_data = keel_data.as_testable()
print("Testable:")
random_testable_keel_data.print_info()
random_testable_keel_data.plot_train_class_distribution()
classification_result = common_classifier.naive_bayes_gaussian_classification(
random_testable_keel_data)
classification_result.print_info()
classification_result.plot_confusion_matrix()