dataset = pd.read_csv(file)
training_samples = get_sample_number(dataset)
X_train = dataset.iloc[:training_samples, 5:9]
y_train = dataset.iloc[:training_samples, 9]
X_test = dataset.iloc[training_samples:, 5:9]

# Feature Scaling
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.fit_transform(X_test)

# Fitting classifier to the training set
classifier = KNeighborsClassifier(n_neighbors=5, metric='minkowski', p=2)
classifier.fit(X_train, y_train)

y_pred = classifier.predict(X_test)