overfitting_example_ita

overfitting_example_ita2.py

train_accs = []
test_accs = []

cols = [
    'fixed.acidity', 'volatile.acidity', 'citric.acid','residual.sugar', 'chlorides', 'free.sulfur.dioxide',
    'total.sulfur.dioxide', 'density', 'pH', 'sulphates', 'alcohol',
]

# inizializziamo un loop dove cambieremo il valore di max depth, partendo da 1 a 25
for depth in range(1, 25):
    clf = tree.DecisionTreeClassifier(max_depth=depth)
    clf.fit(df_train[cols], df_train.quality)
    train_predictions = clf.predict(df_train[cols])
    test_predictions = clf.predict(df_test[cols])
    
    train_acc = metrics.accuracy_score(df_train.quality, train_predictions)
    test_acc = metrics.accuracy_score(df_test.quality, test_predictions)
    
    # inseriamo in liste vuote le nostre accuracies
    train_accs.append(train_acc)
    test_accs.append(test_acc)
    
# visualizziamo i dati
plt.figure(figsize=(10, 5))
sns.set_style('whitegrid')
plt.plot(train_accs, label='train accuracy')
plt.plot(test_accs, label='test accuracy')
plt.legend(loc='upper left', prop={'size': 15})
plt.xticks(range(0, 26, 5))
plt.xlabel('max_depth', size=20)
plt.ylabel('accuracy', size=20)
plt.show()