python - Python中的基本决策树

Question

我不明白为什么我的算法没有分离样本“1”（蓝色），就好像算法忽略了它们。如果我错过添加任何参数，我不知道更新DecisionTreeClasiffier，算法如下。我有 3 个标签，即 3 种类型的样本（Import代码中缺少）

iris = datasets.load_iris()
X=iris.data[:,[2,3]]
y=iris.target

X_train, X_test, y_train, y_test= train_test_split(X, y, test_size=0.3, random_state=1, stratify=y)
sc= StandardScaler()
sc.fit(X_train)
X_train_std=sc.transform(X_train)
X_test_std= sc.transform(X_test)

def plot_decision_regions(X, y, classifier, test_idx=None, resolution = 0.02):
    #definir un generador de marcadores y un mapa de colores
    markers = ('s', 'x', 'o', '^','v')
    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
    cmap = ListedColormap(colors[:len(np.unique(y))])
    
    #representar la superficie de decision
    x1_min, x1_max = X[:, 0].min() -1, X[:,0].max() + 1
    x2_min, x2_max = X[:, 1].min() -1, X[:,1].max() + 1
    xx1, xx2= np.meshgrid (np.arange(x1_min, x1_max, resolution), np.arange(x2_min, x2_max, resolution))
    Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
    Z = Z.reshape(xx1.shape)
    plt.contourf(xx1, xx2, Z, alpha= 0.3, cmap = cmap)
    plt.xlim(xx1.min(), xx1.max())
    plt.ylim(xx2.min(), xx2.max())
    # print(Z)
     #Representar muestras de clase
    
    for idx, cl in enumerate (np.unique(y)):
       plt.scatter (x=X[y == cl, 0], y= X[y == cl, 1], alpha=0.8, c=colors[idx], marker= markers [idx], label = cl, edgecolor = 'black')
        
    if test_idx:
        #representa todas las muestras
        X_test, y_test= X[test_idx,:], y[test_idx]
        # print( X[test_idx,:])
   
        
        plt.scatter(X_test[:,0], X_test[:,1], c='', edgecolor= 'black', alpha= 0.9, linewidth=1, marker='o', s=100, label='test set' )
        

X_combined_std= np.vstack((X_train_std, X_test_std))
y_combined=np.hstack((y_train, y_test)) 

tree=DecisionTreeClassifier(criterion='gini', max_depth=4, random_state=1)
tree.fit(X_train, y_train)
plot_decision_regions(X= X_combined_std, y= y_combined, classifier=tree, test_idx=range(105,150))
plt.xlabel('sepal length[cm]')
plt.ylabel('petal width [cm]')
plt.legend(loc='upper left')
plt.show()

标签： pythonscikit-learndecision-tree

Answer 1

修改后的答案：

您只是忘记使用缩放特征训练模型X_train_std。所以，而不是

tree.fit(X_train, y_train)

它应该是

tree.fit(X_train_std, y_train)

现在，该模型能够区分所有三个类别：