def main(argv):
np.random.seed(1339)
np.seterr(all='ignore')
warnings.simplefilter(action='ignore', category=FutureWarning)
print()
print('Classification Experiment: Red Wine')
print()
data = imbalanced.oversample(
pd.read_csv('./data/csv/wine_red.csv', sep=';'), 'quality')
X = data.drop(['quality'], axis=1).values
Y = data.quality.values
X, X_t, Y, Y_true = model_selection.train_test_split(X, Y, train_size=0.5)
nb = NaiveBayes()
# nb = GaussianNaiveBayes()
nb.fit(X, Y)
Y_hat = nb.predict(X_t)
print()
print()
print()
print(' Result: {:.2f}% Correct'.format(
100 * (Y_true == Y_hat).sum() / float(len(Y_true))))
print()
print(' Classification Report:')
print()
print(metrics.classification_report(Y_true, Y_hat))
print()
print(' Confusion Matrix:')
print()
print(metrics.confusion_matrix(Y_true, Y_hat))
print()
def main(argv):
np.random.seed(1337)
np.seterr(all = 'ignore')
warnings.simplefilter(action = 'ignore', category = FutureWarning)
print()
print('Classification Experiment: White Wine')
print()
data = imbalanced.oversample(pd.read_csv('./data/csv/wine_white.csv', sep = ';'), 'quality')
X = data.iloc[:, :11]
Y = data.iloc[:, 11]
X, X_t, Y, Y_true = model_selection.train_test_split(X, Y, train_size = 0.5)
rf = RandomForest(cost = entropy, s_ratio = 0.75, dt_count = 9, f_count = 6)
# rf = RandomForest(cost = gini, s_ratio = 0.75, dt_count = 9, f_count = 6)
rf.fit(X, Y)
P = rf.predict(X_t)
print(rf)
print()
print()
print()
print(' Result: {:.2f}% Correct'.format(100 * (Y_true == P).sum() / float(len(Y_true))))
print()
print(' Classification Report:')
print()
print(metrics.classification_report(Y_true, P))
print()
print(' Confusion Matrix:')
print()
print(metrics.confusion_matrix(Y_true, P))
print()
def main(argv):
np.random.seed(2704)
np.seterr(all='ignore')
warnings.simplefilter(action='ignore', category=FutureWarning)
print()
print('Classification Experiment: Red Wine')
print()
data = imbalanced.oversample(
pd.read_csv('./data/csv/wine_red.csv', sep=';'), 'quality')
X = data.drop(['quality'], axis=1).values
Y = data.quality.values
sclr = preprocessing.StandardScaler().fit(X)
ohe = one_hot.OneHotEncoder(Y)
X, X_t, Y, Y_t = model_selection.train_test_split(X,
ohe.encode(Y),
train_size=0.5)
X = sclr.transform(X)
X_t = sclr.transform(X_t)
nn = Network()
nn.add(InputLayer(11, learning=0.25, regular=0.005, momentum=0.01))
nn.add(
HiddenLayer(100,
learning=0.25,
regular=0.005,
momentum=0,
function=LeakyReLU()))
nn.add(
HiddenLayer(100,
learning=0.25,
regular=0.005,
momentum=0,
function=LeakyReLU()))
nn.add(HiddenLayer(50, learning=0.25, regular=0.005, momentum=0.01))
nn.add(HiddenLayer(25, learning=0.25, regular=0.005, momentum=0.01))
nn.add(OutputLayer(6))
nn.fit(X, Y, batch=500, epochs=1000)
P = nn.predict(X_t)
P = ohe.decode(P)
Y_t = ohe.decode(Y_t)
print()
print()
print()
print(' Result: {:.2f}% Correct'.format(
100 * (Y_t == P).sum() / float(len(Y_t))))
print()
print(' Classification Report:')
print()
print(metrics.classification_report(Y_t, P))
print()
print(' Confusion Matrix:')
print()
print(metrics.confusion_matrix(Y_t, P))
print()